{"meta":{"query_hash":"e05165058cd2","filters":{"topic":"Generative Adversarial Networks and Image Synthesis"},"cohort_total":668,"direct_labels_cover":1,"predictions_cover":668,"exported":668,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/e05165058cd2","api":"https://metacan.xera.ac/api/v1/cohort?topic=Generative+Adversarial+Networks+and+Image+Synthesis"},"results":[{"id":"W1511867968","doi":"","title":"On the Convergence Properties of Contrastive Divergence","year":2010,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Regularization (linguistics); Markov chain; Counterintuitive; Mathematics; Boltzmann machine; Applied mathematics; Convergence (economics); Binary number; Fixed point; Markov process; Statistical physics; Discrete mathematics; Computer science; Mathematical optimization; Artificial intelligence; Mathematical analysis; Deep learning; Statistics; Physics","score_opus":0.01602882571888104,"score_gpt":0.19446784761454025,"score_spread":0.17843902189565922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1511867968","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22263967,0.00003505885,0.76662695,0.0024414333,0.0011554856,0.00021600086,0.0000015497644,0.00004597038,0.006837892],"genre_scores_gemma":[0.9957469,0.0000063796347,0.0034559695,0.00038574042,0.000036869595,0.000008549615,5.2855285e-8,0.0000022987404,0.00035722644],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993677,0.000050058727,0.00011788775,0.00017193436,0.00016194832,0.00013044378],"domain_scores_gemma":[0.99929047,0.00015135521,0.00005518752,0.0003434351,0.00012630432,0.00003326004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020218706,0.000078743404,0.00008959491,0.000017215458,0.00010879388,0.000034760676,0.00065902685,0.00002429289,0.00024699917],"category_scores_gemma":[0.00019777165,0.00003945187,0.000042001524,0.00014013758,0.00015949394,0.00017452794,0.0001259528,0.00011104421,0.0000521324],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010827888,0.000050506198,0.00037260514,0.0000027962883,0.00002220778,0.0000010988676,0.00045540513,0.00032516074,0.37608317,0.61609864,0.002602927,0.0039746477],"study_design_scores_gemma":[0.00008456179,0.0000709964,0.0020404516,0.000012893702,0.0000034935897,0.000001204661,0.000056858036,0.1036756,0.88989395,0.0034609493,0.00058463047,0.00011443071],"about_ca_topic_score_codex":0.000057750054,"about_ca_topic_score_gemma":0.000025449608,"teacher_disagreement_score":0.77310723,"about_ca_system_score_codex":0.0000027032584,"about_ca_system_score_gemma":0.00003177817,"threshold_uncertainty_score":0.27044678},"labels":[],"label_agreement":null},{"id":"W1524510684","doi":"","title":"Modeling pigeon behavior using a Conditional Restricted Boltzmann Machine.","year":2009,"lang":"en","type":"article","venue":"The European Symposium on Artificial Neural Networks","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Boltzmann machine; Computer science; Restricted Boltzmann machine; Artificial intelligence; Machine learning; Binary number; Deep learning; Mathematics","score_opus":0.03380569312864074,"score_gpt":0.2523828971768214,"score_spread":0.21857720404818065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1524510684","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.064767614,0.00012943082,0.9266872,0.0028555705,0.0011262156,0.00048656043,0.000008937342,0.0003452558,0.003593244],"genre_scores_gemma":[0.99446434,0.00002003444,0.0014714893,0.0021289901,0.0017833296,0.0000053859426,0.00002589818,0.000036380738,0.00006417565],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99661183,0.0011324183,0.0005431916,0.0006520075,0.00043130023,0.0006292447],"domain_scores_gemma":[0.9986333,0.00011453716,0.00016596734,0.0007964469,0.00011797331,0.00017175006],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005921846,0.00036938224,0.0002646966,0.00011546551,0.0009266027,0.000539739,0.0011573642,0.00006444596,0.000013462419],"category_scores_gemma":[0.00002877175,0.00027588385,0.0001954447,0.0005692042,0.000085598076,0.00044020207,0.00020941692,0.00052751263,0.000055577384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004724819,0.00011743315,0.000011505761,5.711356e-7,0.000010976859,0.00008354739,0.00008919363,0.9682292,0.008417041,0.0028965261,0.00031690163,0.019779878],"study_design_scores_gemma":[0.00018111971,0.00019945473,0.0007449801,0.000018149049,0.000037722464,0.000033434826,0.00000926007,0.99738264,0.00034355675,0.0005973819,0.00012794709,0.0003243479],"about_ca_topic_score_codex":0.000034105968,"about_ca_topic_score_gemma":0.000007646982,"teacher_disagreement_score":0.9296967,"about_ca_system_score_codex":0.000050265688,"about_ca_system_score_gemma":0.000023164612,"threshold_uncertainty_score":0.99996936},"labels":[],"label_agreement":null},{"id":"W1532251666","doi":"","title":"On autoencoder scoring","year":2013,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Autoencoder; Computer science; Artificial intelligence; Probabilistic logic; Machine learning; Restricted Boltzmann machine; Inference; Classifier (UML); Gradient descent; Pattern recognition (psychology); Deep learning; Artificial neural network","score_opus":0.00850723348046665,"score_gpt":0.1951846079573685,"score_spread":0.18667737447690186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1532251666","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001578435,0.000008029114,0.93082273,0.001274425,0.0002530308,0.00006433938,3.7067938e-8,0.0000964089,0.06590259],"genre_scores_gemma":[0.83627737,0.000001620445,0.15926826,0.0012694352,0.00006901098,0.000010874728,9.400043e-8,0.0000030657316,0.003100257],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994991,0.000020786982,0.000066245855,0.00017380138,0.00009469099,0.00014541973],"domain_scores_gemma":[0.99959385,0.00005282674,0.000014641411,0.00025637329,0.00003349975,0.000048807116],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0000514141,0.00005963007,0.0000544809,0.000028610179,0.0000647943,0.00016339163,0.0002851625,0.000015801139,0.00048777985],"category_scores_gemma":[0.000019266678,0.000042867832,0.000026969006,0.00010276392,0.000010023234,0.00043190236,0.00007838199,0.000040030536,0.0013796912],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012544812,0.00008385793,0.00021792745,0.000003023416,0.000024733019,0.0000056123263,0.0002543589,0.033087816,0.004638763,0.5095806,0.123125285,0.32897675],"study_design_scores_gemma":[0.000082379236,0.000042707805,0.0022346305,0.000005953531,7.4619413e-7,0.000001036885,0.0000071554337,0.9725143,0.006578905,0.01649355,0.0019238921,0.00011475775],"about_ca_topic_score_codex":0.00006935886,"about_ca_topic_score_gemma":0.0000021632286,"teacher_disagreement_score":0.9394265,"about_ca_system_score_codex":0.0000093542,"about_ca_system_score_gemma":0.000009203118,"threshold_uncertainty_score":0.9993979},"labels":[],"label_agreement":null},{"id":"W1536046558","doi":"10.1109/mva.2015.7153194","title":"Sparse image reconstruction by two phase RBM learning: Application to mine planning","year":2015,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Sample (material); Artificial intelligence; Restricted Boltzmann machine; Sampling (signal processing); Iterative reconstruction; Key (lock); Set (abstract data type); Image (mathematics); Computer vision; Machine learning; Data mining; Pattern recognition (psychology); Deep learning","score_opus":0.02596184403462985,"score_gpt":0.2940750747443805,"score_spread":0.2681132307097506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1536046558","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01973362,0.000036822068,0.9714099,0.0009638827,0.00023864873,0.00016267636,0.0000010535354,0.00014414024,0.0073092207],"genre_scores_gemma":[0.6890802,0.000001840395,0.3088558,0.00028938922,0.00022396949,0.000026531916,0.000010317124,0.000008927088,0.0015030546],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990433,0.00007589938,0.00016967539,0.00035445899,0.00015600273,0.0002006795],"domain_scores_gemma":[0.9993048,0.00003376441,0.00007141063,0.00025932564,0.00012814767,0.00020259549],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030600806,0.00011344015,0.00012136019,0.00006437838,0.0000984549,0.00015803524,0.00027395703,0.000029183948,0.000021689311],"category_scores_gemma":[0.000075505275,0.00010382862,0.000028791172,0.00029287048,0.000024010578,0.00056979584,0.000099761884,0.00008712791,0.00017725285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049577764,0.00015111292,0.00065816595,0.0000032004791,0.000024450084,0.0000064208257,0.0010152275,0.043763056,0.20872068,0.0013661546,0.09833547,0.64590645],"study_design_scores_gemma":[0.0011131789,0.00021835994,0.000030457879,0.000009119266,0.000006996718,0.00002173179,0.00019901503,0.88522506,0.05429868,0.00044167592,0.058184966,0.00025073395],"about_ca_topic_score_codex":0.00010404665,"about_ca_topic_score_gemma":0.0000061288265,"teacher_disagreement_score":0.841462,"about_ca_system_score_codex":0.000040944826,"about_ca_system_score_gemma":0.000029914054,"threshold_uncertainty_score":0.42340082},"labels":[],"label_agreement":null},{"id":"W154472438","doi":"","title":"Multimodal Learning with Deep Boltzmann Machines","year":2012,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":626,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Boltzmann machine; Artificial intelligence; Modalities; Modality (human–computer interaction); Generative model; Representation (politics); Kernel (algebra); Deep learning; Set (abstract data type); Machine learning; Pattern recognition (psychology); Data set; Restricted Boltzmann machine; Generative grammar; Mathematics","score_opus":0.008495873437115676,"score_gpt":0.21582754893814818,"score_spread":0.20733167550103251,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W154472438","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006161517,0.00014700257,0.97847813,0.00028706415,0.00017864205,0.000054876607,7.860809e-8,0.00012937073,0.014563342],"genre_scores_gemma":[0.77710485,0.0000032828289,0.22140963,0.00016459487,0.00020486426,0.0000042676793,6.535122e-7,0.0000058068554,0.0011020509],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925435,0.00006633271,0.0000800871,0.00016624619,0.00013186484,0.0003011502],"domain_scores_gemma":[0.9995787,0.000054436743,0.000034086082,0.00019094102,0.00003896011,0.00010287787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001611192,0.00010517877,0.0000967804,0.00003348763,0.00015313066,0.00009221609,0.00025224444,0.000024782274,0.00009616112],"category_scores_gemma":[0.000021313674,0.00006820854,0.000030564097,0.00014867325,0.00002427756,0.00079078897,0.00010910662,0.000094699724,0.00010575039],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003469404,0.00031687415,0.16792253,0.0000141106475,0.00014455561,0.000015583366,0.0042090095,0.08617451,0.0042433785,0.037993126,0.0024086705,0.69652295],"study_design_scores_gemma":[0.00025076707,0.00007546093,0.018943515,0.0000049534387,0.0000071169193,0.000014447583,0.00005517341,0.9656775,0.0028358346,0.000073047006,0.011828722,0.00023346495],"about_ca_topic_score_codex":0.00006315577,"about_ca_topic_score_gemma":0.000020698546,"teacher_disagreement_score":0.879503,"about_ca_system_score_codex":0.000009347677,"about_ca_system_score_gemma":0.000008927902,"threshold_uncertainty_score":0.27814636},"labels":[],"label_agreement":null},{"id":"W1544983288","doi":"10.48550/arxiv.1301.3568","title":"Joint Training Deep Boltzmann Machines for Classification","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Boltzmann machine; Inference; Computer science; Artificial intelligence; Train; Joint (building); Training (meteorology); Machine learning; Restricted Boltzmann machine; Generative grammar; Deep learning; Layer (electronics); Algorithm","score_opus":0.15549364605884414,"score_gpt":0.20347193269503988,"score_spread":0.047978286636195744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1544983288","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010239973,0.000076576325,0.98534423,0.0004035531,0.00094448787,0.00057773385,0.000012184971,0.00018245143,0.002218829],"genre_scores_gemma":[0.96325904,0.000065716835,0.0348755,0.00013702376,0.00031379168,0.000009980417,0.000033555145,0.000022311862,0.0012830667],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99807024,0.00013870884,0.00024319718,0.0010901286,0.00007441903,0.0003833142],"domain_scores_gemma":[0.99819005,0.00013028373,0.00031958224,0.00094541814,0.00026390012,0.00015079523],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000283355,0.00032539535,0.00037564532,0.00018990414,0.00025984907,0.00026316178,0.0012128315,0.00024678023,0.000036993675],"category_scores_gemma":[0.000072500916,0.00034463484,0.0003040082,0.0002652928,0.000082224156,0.0005203253,0.000764869,0.0003098759,0.00006166708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026610767,0.000119306824,0.00021018398,0.000118126096,0.00025296025,0.000029198347,0.0013368821,0.63490105,0.0014532114,0.31337178,0.0030438572,0.045136843],"study_design_scores_gemma":[0.00026428403,0.000034703844,0.00095892925,0.0000378916,0.00005034085,0.00000123698,0.00010003442,0.93262285,0.00017444126,0.064159825,0.0012302811,0.000365208],"about_ca_topic_score_codex":0.00009315883,"about_ca_topic_score_gemma":0.000037149108,"teacher_disagreement_score":0.9530191,"about_ca_system_score_codex":0.00012243044,"about_ca_system_score_gemma":0.0001256181,"threshold_uncertainty_score":0.9999006},"labels":[],"label_agreement":null},{"id":"W1554884521","doi":"","title":"Parallelizable Sampling of Markov Random Fields","year":2010,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Markov chain; Markov chain Monte Carlo; Variable-order Markov model; Computer science; Approximate inference; Graphical model; Algorithm; Inference; Markov random field; Random variable; Markov process; Artificial intelligence; Markov model; Mathematics; Machine learning; Bayesian probability; Statistics; Image segmentation","score_opus":0.01394052746388238,"score_gpt":0.23991398201181946,"score_spread":0.22597345454793707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1554884521","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047609317,0.000024163779,0.97426367,0.0005157463,0.00046942348,0.00005856156,3.0953638e-7,0.000033807064,0.019873362],"genre_scores_gemma":[0.66330963,0.000007788557,0.335779,0.00013678843,0.000070527814,0.0000023356888,2.964627e-7,0.0000020459408,0.00069154956],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994557,0.000023184775,0.00013910592,0.00015321634,0.00009406362,0.00013472441],"domain_scores_gemma":[0.9994,0.00013840554,0.000041438838,0.00032061513,0.000058000605,0.000041498988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022006371,0.00006301223,0.00012285761,0.000028594623,0.000052185285,0.00004649807,0.00037514258,0.00004668421,0.00027818148],"category_scores_gemma":[0.00006028555,0.000048306076,0.000057431404,0.00011249279,0.000024909668,0.00020138657,0.00010302147,0.00009186884,0.000012176193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011881683,0.0003084064,0.0030294762,0.000047268342,0.00016168115,0.00001127786,0.0010784836,0.024102347,0.23450264,0.21674666,0.03912266,0.4807703],"study_design_scores_gemma":[0.0020747725,0.000109464476,0.0020490254,0.00001751966,0.00001525407,0.000010280336,0.000036691104,0.792325,0.14308175,0.014300345,0.04553473,0.00044511826],"about_ca_topic_score_codex":0.0000722804,"about_ca_topic_score_gemma":0.00005719838,"teacher_disagreement_score":0.7682227,"about_ca_system_score_codex":0.00000154481,"about_ca_system_score_gemma":0.000021086978,"threshold_uncertainty_score":0.3045892},"labels":[],"label_agreement":null},{"id":"W1563292672","doi":"10.1007/3-540-47979-1_48","title":"Learning Montages of Transformed Latent Images as Representations of Objects That Change in Appearance","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Waterloo","funders":"","keywords":"Artificial intelligence; Computer science; Face (sociological concept); Computer vision; Object (grammar); Grid; Image (mathematics); Probabilistic logic; Transformation (genetics); Tree (set theory); Pattern recognition (psychology); Set (abstract data type); Mathematics","score_opus":0.028671184230646587,"score_gpt":0.25838737401608225,"score_spread":0.22971618978543568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1563292672","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00073615863,0.0014049083,0.9933896,0.00045504628,0.0004810668,0.0004983349,0.0000041040103,0.00003676205,0.0029939911],"genre_scores_gemma":[0.9407364,0.0006108813,0.05815108,0.00013492774,0.00011762703,0.000014253561,0.0000017453331,0.000017927663,0.00021515264],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99735725,0.000079240264,0.0005195034,0.0009020503,0.0007078121,0.00043415863],"domain_scores_gemma":[0.998413,0.0003011628,0.000378096,0.0006563037,0.00017407045,0.00007736251],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00052641705,0.0003451577,0.00060881884,0.00070636754,0.000102570855,0.000103587125,0.0014193624,0.00017536315,0.000022990447],"category_scores_gemma":[0.00008328543,0.0003170345,0.00015233814,0.0006535884,0.00052677427,0.0007432821,0.0003520907,0.00050775544,0.00000562383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018506933,0.00009832374,0.0028370467,0.00015955504,0.00003140397,0.00009382783,0.012419553,0.29103455,0.0021034046,0.0018763016,0.000009005155,0.68931854],"study_design_scores_gemma":[0.00084035855,0.00058144995,0.011016236,0.002160262,0.000022402166,0.000033149587,0.000005023588,0.8888291,0.07796827,0.017491387,0.00012979233,0.000922578],"about_ca_topic_score_codex":0.00029528324,"about_ca_topic_score_gemma":0.00018351643,"teacher_disagreement_score":0.94000024,"about_ca_system_score_codex":0.00008290917,"about_ca_system_score_gemma":0.000117260955,"threshold_uncertainty_score":0.9999282},"labels":[],"label_agreement":null},{"id":"W16016350","doi":"10.1007/978-3-642-23783-6_41","title":"Higher Order Contractive Auto-Encoder","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":380,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Hessian matrix; Jacobian matrix and determinant; Initialization; Computer science; Robustness (evolution); Manifold (fluid mechanics); Encoder; Norm (philosophy); Autoencoder; Artificial intelligence; Regularization (linguistics); Feature vector; Algorithm; Mathematical optimization; Mathematics; Applied mathematics; Deep learning","score_opus":0.020430625937921373,"score_gpt":0.23109404550762624,"score_spread":0.21066341956970486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W16016350","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000028381446,0.00046401046,0.96235347,0.0008604963,0.0037352904,0.00037415203,0.000004664941,0.00015676256,0.032048296],"genre_scores_gemma":[0.16339083,0.000092154034,0.82507324,0.00396862,0.0016767962,0.000022265971,0.0000050145554,0.000079984624,0.005691066],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99598885,0.00006745187,0.0005047468,0.0017970037,0.0008207951,0.00082117255],"domain_scores_gemma":[0.99698067,0.0004479724,0.0003410828,0.0014592211,0.00054957584,0.00022145553],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006492536,0.00067109615,0.00066950487,0.0005279063,0.00031400516,0.0005473844,0.0031141993,0.00041318955,0.00031295503],"category_scores_gemma":[0.000083060906,0.0005711089,0.00014153091,0.00061610364,0.00088000775,0.001115461,0.001201955,0.0008750449,0.00018006677],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013907428,0.00006488459,0.00001987636,0.000015471656,0.000052164585,0.0001647147,0.0009096684,0.025006518,0.0004319724,0.051948033,0.0003584925,0.9210143],"study_design_scores_gemma":[0.00066493574,0.00038592276,0.00046194473,0.00036124868,0.00003816434,0.00005811987,1.783428e-7,0.49984285,0.0071127885,0.4497325,0.03935193,0.001989397],"about_ca_topic_score_codex":0.000057161906,"about_ca_topic_score_gemma":0.000058631656,"teacher_disagreement_score":0.9190249,"about_ca_system_score_codex":0.0002365949,"about_ca_system_score_gemma":0.00060234143,"threshold_uncertainty_score":0.999674},"labels":[],"label_agreement":null},{"id":"W1654947107","doi":"10.48550/arxiv.1406.2751","title":"Reweighted Wake-Sleep","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Inference; Estimator; Latent variable; Computer science; Artificial intelligence; Generative model; Wake; Interpretation (philosophy); Machine learning; Deep belief network; Pattern recognition (psychology); Generative grammar; Deep learning; Mathematics; Statistics","score_opus":0.048230166332688264,"score_gpt":0.16732111517517625,"score_spread":0.119090948842488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1654947107","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017171139,0.00006905164,0.97252774,0.0002471675,0.0012902762,0.00021242946,0.000006936818,0.00029101485,0.008184233],"genre_scores_gemma":[0.9880876,0.00009973468,0.009014392,0.00026009665,0.0003381348,9.4347774e-7,0.000014538672,0.000021898484,0.00216265],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99757457,0.00030647495,0.00021969122,0.001343312,0.00010841189,0.00044753434],"domain_scores_gemma":[0.9974429,0.00013329659,0.00026359584,0.0017316424,0.00021241423,0.00021616835],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030240093,0.00039110423,0.00043499688,0.00020285403,0.0002195574,0.00021018604,0.002296186,0.00033391974,0.00008087145],"category_scores_gemma":[0.000049263333,0.00041848127,0.0002996272,0.000483167,0.000111926754,0.0003650628,0.002243767,0.0005443619,0.0002857643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018737843,0.00008114172,0.0004113014,0.000038817667,0.0001685897,0.00020673257,0.00012673669,0.8937835,0.00008112036,0.097039804,0.0043630865,0.0036804285],"study_design_scores_gemma":[0.00028520188,0.00003770507,0.00038736942,0.000046199246,0.00005739621,0.0000022033933,0.000008489906,0.96131444,0.00053319824,0.030420663,0.006405771,0.00050136354],"about_ca_topic_score_codex":0.0001042943,"about_ca_topic_score_gemma":0.000027103584,"teacher_disagreement_score":0.97091645,"about_ca_system_score_codex":0.00013116069,"about_ca_system_score_gemma":0.00010702555,"threshold_uncertainty_score":0.9998267},"labels":[],"label_agreement":null},{"id":"W1659448245","doi":"10.1109/ijcnn.2015.7280568","title":"An empirical analysis of different sparse penalties for autoencoder in unsupervised feature learning","year":2015,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Autoencoder; MNIST database; Computer science; Feature learning; Sparse approximation; Artificial intelligence; Machine learning; Pattern recognition (psychology); Representation (politics); Feature (linguistics); Feature vector; Norm (philosophy); Matrix norm; Deep learning","score_opus":0.052909457775207606,"score_gpt":0.31237006232963993,"score_spread":0.2594606045544323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1659448245","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.110588536,0.000048012393,0.88808423,0.00073850463,0.00007721783,0.00011240219,0.0000015514671,0.000036181977,0.0003133875],"genre_scores_gemma":[0.9082458,0.0000037568132,0.091181435,0.00012972832,0.00003719602,0.00001136237,0.000010217214,0.0000048294805,0.00037565816],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989291,0.00018078777,0.00019058949,0.0003017359,0.00019388387,0.00020390503],"domain_scores_gemma":[0.99926376,0.00012499042,0.000060604805,0.00029023763,0.00014663077,0.00011379256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032171083,0.00011987758,0.00034400995,0.00025721567,0.000042345444,0.0000757436,0.00038117397,0.000059167167,0.000020650532],"category_scores_gemma":[0.000083061765,0.00008563333,0.00012913108,0.00071835046,0.000028677665,0.00031237738,0.00007730137,0.000093598246,0.000001098466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006819358,0.00036886655,0.15618646,0.000011578631,0.00037590385,0.0000042111,0.00602906,0.8182407,0.0013751213,0.0020499404,0.002724574,0.012565409],"study_design_scores_gemma":[0.00032780334,0.00015768682,0.041491196,0.0000038741555,0.000066979504,2.0780034e-7,0.00032653767,0.95589805,0.00096791884,0.00029632368,0.00035427618,0.00010912831],"about_ca_topic_score_codex":0.0000751653,"about_ca_topic_score_gemma":0.000403131,"teacher_disagreement_score":0.7976573,"about_ca_system_score_codex":0.000030365738,"about_ca_system_score_gemma":0.00004771187,"threshold_uncertainty_score":0.34920257},"labels":[],"label_agreement":null},{"id":"W166282841","doi":"10.1007/978-3-642-41218-9_42","title":"An Unsupervised Deep-Learning Architecture That Can Reconstruct Paired Images","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"","keywords":"MNIST database; Computer science; Artificial intelligence; Associative property; Unsupervised learning; Pattern recognition (psychology); Restricted Boltzmann machine; Image (mathematics); Set (abstract data type); Deep learning; Digit recognition; Content-addressable memory; Channel (broadcasting); Matching (statistics); Layer (electronics); Artificial neural network; Mathematics","score_opus":0.014536088730198682,"score_gpt":0.21383681591845377,"score_spread":0.1993007271882551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W166282841","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022210562,0.00047329682,0.99353015,0.0009502206,0.0014936127,0.00048164555,0.00000591551,0.00027935236,0.0025637185],"genre_scores_gemma":[0.41267723,0.00007382334,0.5851575,0.0009105625,0.00074745633,0.000015037547,0.000012717106,0.000058816084,0.0003468282],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950634,0.00021042318,0.00051165634,0.002273099,0.00093046477,0.0010109046],"domain_scores_gemma":[0.9966333,0.00052952056,0.00035538038,0.0017865994,0.00030774693,0.00038746482],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007773907,0.00083844236,0.00077057007,0.00075660343,0.0005914469,0.0015374937,0.0040010265,0.0004070126,0.0001787129],"category_scores_gemma":[0.00010922046,0.0007199876,0.00021604722,0.00054972456,0.000946943,0.0010555028,0.0009397347,0.001366378,0.000047592956],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035128458,0.000014423878,0.00023458629,0.000015948324,0.000017529363,0.000049363087,0.0007540501,0.14002027,0.0005408049,0.00062800845,0.000023913903,0.8576976],"study_design_scores_gemma":[0.0003652176,0.0003299437,0.00091127877,0.0003125865,0.000019064159,0.00012397321,0.0000016190025,0.9328416,0.0059099672,0.05639378,0.0013987771,0.0013922127],"about_ca_topic_score_codex":0.00013389805,"about_ca_topic_score_gemma":0.00027895105,"teacher_disagreement_score":0.85630536,"about_ca_system_score_codex":0.0002284365,"about_ca_system_score_gemma":0.000414531,"threshold_uncertainty_score":0.9995251},"labels":[],"label_agreement":null},{"id":"W1665214252","doi":"","title":"Rectified Linear Units Improve Restricted Boltzmann Machines","year":2010,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":13244,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Boltzmann machine; Binary number; Sigmoid function; Computer science; Object (grammar); Restricted Boltzmann machine; Artificial intelligence; Inference; Pattern recognition (psychology); Feature (linguistics); Cognitive neuroscience of visual object recognition; Algorithm; Mathematics; Computer vision; Deep learning; Arithmetic; Artificial neural network","score_opus":0.030533236294757893,"score_gpt":0.2802265611432088,"score_spread":0.24969332484845091,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1665214252","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10440882,0.000044288812,0.7450849,0.015189621,0.009762648,0.00042329723,0.000039293125,0.0008622767,0.124184854],"genre_scores_gemma":[0.97803795,0.00002627783,0.016512038,0.00033972718,0.00059237494,0.000013599578,0.000044118613,0.000017379267,0.0044165053],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99842155,0.00015838347,0.00026699845,0.00050016714,0.00039541378,0.00025746354],"domain_scores_gemma":[0.9986144,0.00018710236,0.00018516486,0.0003522319,0.0005506591,0.000110465066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002740815,0.00022271085,0.00017597836,0.00020673791,0.00024472238,0.0003454382,0.001088244,0.00009961436,0.00042081857],"category_scores_gemma":[0.0009773418,0.00019422048,0.000062610794,0.00035811414,0.00005108504,0.00043651185,0.00025742993,0.001087475,0.00015122343],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015175609,0.00017945268,0.005260977,0.000008153805,0.00016905165,0.00007258736,0.00069586537,0.012411369,0.32190645,0.31747374,0.00095649785,0.3407141],"study_design_scores_gemma":[0.00037227027,0.00013386956,0.0021948107,0.00001802524,0.00000494069,0.0000103993225,0.000015074661,0.97019696,0.005083253,0.0017974592,0.01992706,0.00024584675],"about_ca_topic_score_codex":0.0003264335,"about_ca_topic_score_gemma":0.00013868164,"teacher_disagreement_score":0.9577856,"about_ca_system_score_codex":0.000023607301,"about_ca_system_score_gemma":0.00010137367,"threshold_uncertainty_score":0.79200816},"labels":[],"label_agreement":null},{"id":"W1697053819","doi":"10.48550/arxiv.1202.3748","title":"Conditional Restricted Boltzmann Machines for Structured Output Prediction","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; University of Toronto","funders":"","keywords":"Computer science; Boltzmann machine; Range (aeronautics); Divergence (linguistics); Probabilistic logic; Artificial intelligence; Algorithm; Structured prediction; Machine learning; Space (punctuation); Set (abstract data type); Deep learning","score_opus":0.049063878663810435,"score_gpt":0.18280883507585963,"score_spread":0.1337449564120492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1697053819","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041888364,0.000038430542,0.956276,0.00009315163,0.00063491357,0.00018971908,0.000058744656,0.00011873708,0.0007019262],"genre_scores_gemma":[0.9918306,0.0000090485155,0.006653874,0.00010009371,0.00038645926,0.0000013941899,0.0000502897,0.000007665553,0.0009605685],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991464,0.00007197979,0.000107127285,0.00031865298,0.000059738784,0.00029610124],"domain_scores_gemma":[0.9992776,0.00010631622,0.00008374838,0.0002810744,0.000117089316,0.00013416552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000103815044,0.00013137766,0.00012108193,0.0001041759,0.0002489618,0.000048191654,0.00036377806,0.00007301464,0.00002681592],"category_scores_gemma":[0.000047239413,0.00013258542,0.00009485595,0.00035971505,0.000050087965,0.0010129727,0.00009854926,0.000077346864,0.0000191316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015116594,0.0002569186,0.030402662,0.000027354608,0.0002466414,0.000020659343,0.00041539883,0.26834494,0.0029868698,0.66734123,0.02430773,0.005498417],"study_design_scores_gemma":[0.0007603863,0.000074904725,0.057411738,0.0000058810806,0.000043992914,0.000005369398,0.000026951868,0.91323316,0.0008954353,0.019885095,0.007439236,0.00021785487],"about_ca_topic_score_codex":0.000017063032,"about_ca_topic_score_gemma":0.0000058307605,"teacher_disagreement_score":0.94994223,"about_ca_system_score_codex":0.000055019747,"about_ca_system_score_gemma":0.00003257732,"threshold_uncertainty_score":0.54066765},"labels":[],"label_agreement":null},{"id":"W1738389294","doi":"10.48550/arxiv.1412.6617","title":"Understanding Minimum Probability Flow for RBMs Under Various Kinds of Dynamics","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Boltzmann machine; Divergence (linguistics); Computer science; Importance sampling; Partition function (quantum field theory); Artificial intelligence; Sampling (signal processing); Function (biology); Dynamics (music); Restricted Boltzmann machine; Gibbs sampling; Flow (mathematics); Monte Carlo method; Artificial neural network; Machine learning; Statistical physics; Mathematics; Statistics; Physics; Bayesian probability","score_opus":0.14770479353702415,"score_gpt":0.19762062670710018,"score_spread":0.04991583317007603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1738389294","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006634796,0.000021426378,0.9903371,0.00019809914,0.0009038683,0.0006011245,0.000048705075,0.00009711525,0.0011577861],"genre_scores_gemma":[0.9570973,0.00002786873,0.042341333,0.0000677324,0.00010176888,0.000002270613,0.000028779528,0.000021688073,0.0003112966],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99778193,0.00021422602,0.0003187986,0.0011541337,0.00011424187,0.0004166533],"domain_scores_gemma":[0.9975455,0.00039513255,0.00040919037,0.0012492146,0.00026067448,0.00014032488],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000550974,0.00036003077,0.00055317825,0.00018802572,0.0001972365,0.00011016021,0.0014416811,0.00036059206,0.000011974854],"category_scores_gemma":[0.00007557845,0.00039542725,0.00038676226,0.00038356293,0.00021363058,0.00025981336,0.0012033085,0.00032593904,0.0000042549727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003164998,0.000073233576,0.00019526255,0.00011133677,0.00011268096,0.0000051246284,0.000096601805,0.75234586,0.000018366234,0.24661666,0.00017029406,0.00022291117],"study_design_scores_gemma":[0.00034952085,0.00007257436,0.000088449786,0.00005178837,0.0000739259,7.04468e-7,0.00005006211,0.70036227,0.000068301866,0.2985608,0.00004030197,0.00028131212],"about_ca_topic_score_codex":0.000074887,"about_ca_topic_score_gemma":0.00021123835,"teacher_disagreement_score":0.95046246,"about_ca_system_score_codex":0.00069247617,"about_ca_system_score_gemma":0.0002584999,"threshold_uncertainty_score":0.99984974},"labels":[],"label_agreement":null},{"id":"W1745681373","doi":"10.1162/neco_a_00848","title":"An Infinite Restricted Boltzmann Machine","year":2016,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Restricted Boltzmann machine; Boltzmann machine; Limit (mathematics); Computer science; Boltzmann constant; Function (biology); Artificial intelligence; Layer (electronics); Energy (signal processing); Artificial neural network; Algorithm; Mathematics; Pattern recognition (psychology); Statistics; Physics; Mathematical analysis","score_opus":0.01818591154454845,"score_gpt":0.2571290816638627,"score_spread":0.23894317011931426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1745681373","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059385534,0.000028935348,0.9380362,0.0015915897,0.00036187776,0.000089627436,0.0000029628598,0.00019529408,0.00030795243],"genre_scores_gemma":[0.97345996,0.0000062927634,0.025950024,0.00035923268,0.00014846082,0.0000040219093,0.0000074624545,0.0000073209503,0.000057219695],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901044,0.00017047251,0.00016933396,0.00029691862,0.00017314577,0.00017968705],"domain_scores_gemma":[0.99935734,0.00013127981,0.00007943513,0.0002432382,0.00010525826,0.00008343363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000083610656,0.0001094121,0.000099704,0.00008616302,0.00011906301,0.00012944653,0.00032681145,0.00003499454,0.000012126954],"category_scores_gemma":[0.000040531067,0.00007312746,0.00003628353,0.00029145536,0.000025267496,0.0009971514,0.00006426146,0.000052500625,0.00004894513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002086107,0.000061582854,0.0010446431,0.0000027567562,0.00001121872,0.000016302187,0.0001632953,0.031263564,0.04507947,0.0027048006,0.0014052766,0.91822624],"study_design_scores_gemma":[0.0003840645,0.00019912308,0.028311502,0.000007986897,0.0000035326766,0.000006532239,0.000002215765,0.9647788,0.0029083963,0.002376749,0.0008730153,0.00014810804],"about_ca_topic_score_codex":0.000026155065,"about_ca_topic_score_gemma":0.000008714865,"teacher_disagreement_score":0.9335152,"about_ca_system_score_codex":0.000020629595,"about_ca_system_score_gemma":0.000017439981,"threshold_uncertainty_score":0.29820514},"labels":[],"label_agreement":null},{"id":"W177847060","doi":"","title":"Efficient Learning of Deep Boltzmann Machines","year":2010,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":335,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"MNIST database; Boltzmann machine; Inference; Discriminative model; Computer science; Deep belief network; Artificial intelligence; Restricted Boltzmann machine; Deep learning; Generative model; Machine learning; Pattern recognition (psychology); Cognitive neuroscience of visual object recognition; Hidden variable theory; Generative grammar; Object (grammar)","score_opus":0.005926535575176141,"score_gpt":0.21648160607120615,"score_spread":0.21055507049603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W177847060","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050821982,0.000024899382,0.93587583,0.00022995484,0.00040215728,0.000040153194,1.1270989e-7,0.000053899148,0.012551022],"genre_scores_gemma":[0.8837889,9.3620156e-7,0.11569189,0.000048883638,0.000072189396,0.0000014595678,2.5626628e-7,0.0000032304893,0.00039226367],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994199,0.00003535442,0.000120816825,0.00016849632,0.00012201679,0.0001333863],"domain_scores_gemma":[0.9995376,0.00006763827,0.0000515973,0.00023219903,0.0000673733,0.0000435793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019480262,0.00006932163,0.00009788269,0.000042783657,0.00007761095,0.000041164396,0.00034259967,0.000028964983,0.00013560634],"category_scores_gemma":[0.00007377097,0.000051827275,0.0000497669,0.00015463839,0.000035978042,0.00006133176,0.00013848812,0.00013000106,0.000029208877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005674486,0.0001390321,0.0033520698,0.000010269594,0.000029844687,0.000005176941,0.00087452686,0.29651153,0.20523062,0.1432849,0.00045032255,0.35010603],"study_design_scores_gemma":[0.000072593946,0.000023866225,0.0020887286,0.0000014537252,0.0000020021403,0.0000020641382,0.000009843579,0.9800488,0.016036572,0.00019820075,0.001448413,0.000067488465],"about_ca_topic_score_codex":0.00003930624,"about_ca_topic_score_gemma":0.000019460616,"teacher_disagreement_score":0.8329669,"about_ca_system_score_codex":0.0000021940502,"about_ca_system_score_gemma":0.000010602016,"threshold_uncertainty_score":0.2113455},"labels":[],"label_agreement":null},{"id":"W1779483307","doi":"10.48550/arxiv.1509.00519","title":"Importance Weighted Autoencoders","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":251,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Autoencoder; Inference; Posterior probability; Computer science; Weighting; Artificial intelligence; Generative grammar; Pattern recognition (psychology); Generative model; Flexibility (engineering); Machine learning; Algorithm; Artificial neural network; Mathematics; Statistics; Bayesian probability","score_opus":0.07168787938815764,"score_gpt":0.18660334109591692,"score_spread":0.11491546170775928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1779483307","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020989152,0.0001543306,0.96768594,0.0002684942,0.0011596797,0.00024309444,0.0000138525975,0.00033082912,0.009154609],"genre_scores_gemma":[0.97835994,0.00013441357,0.018641105,0.00019146231,0.00020077107,0.0000010923761,0.000018626117,0.00002110577,0.0024315058],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976849,0.00019860864,0.00023027936,0.0013067436,0.00013066619,0.00044879512],"domain_scores_gemma":[0.9974789,0.00006395,0.00029968453,0.0015423289,0.00032229983,0.0002928603],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003501855,0.0003847224,0.00041074114,0.00017875968,0.00015540863,0.00018453067,0.0021903338,0.00025425217,0.000048923393],"category_scores_gemma":[0.000041154264,0.00041651932,0.00023246005,0.0006013861,0.00012663486,0.00055593747,0.0019368938,0.00052020553,0.00014514361],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023708693,0.000095579824,0.001896494,0.000029906767,0.0001802781,0.00057080574,0.00028876433,0.93215096,0.000018691864,0.044867545,0.018431742,0.0014455148],"study_design_scores_gemma":[0.00028958076,0.00003133921,0.00038116067,0.000034311863,0.000045393223,0.0000028243164,0.000032325526,0.93605864,0.00007985066,0.059704114,0.0028663774,0.00047407858],"about_ca_topic_score_codex":0.00015541888,"about_ca_topic_score_gemma":0.00008142638,"teacher_disagreement_score":0.95737076,"about_ca_system_score_codex":0.00027252242,"about_ca_system_score_gemma":0.00043941115,"threshold_uncertainty_score":0.99982864},"labels":[],"label_agreement":null},{"id":"W1811734137","doi":"10.48550/arxiv.1211.4246","title":"What Regularized Auto-Encoders Learn from the Data Generating Distribution","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":101,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Encoder; Algorithm; Computer science; Autoencoder; Parametrization (atmospheric modeling); Function (biology); Probability density function; Mathematics; Pattern recognition (psychology); Artificial intelligence; Applied mathematics; Statistics; Deep learning","score_opus":0.11217046916588065,"score_gpt":0.20349423320740612,"score_spread":0.09132376404152547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1811734137","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013619189,0.0006868323,0.98110044,0.0009654269,0.0028856741,0.00029708148,0.0001694664,0.00016546677,0.00011040507],"genre_scores_gemma":[0.98524576,0.0008234141,0.01094353,0.00025277285,0.000872681,0.0000011894679,0.0011412215,0.000020376841,0.0006990226],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996988,0.00067104853,0.00025457895,0.0014354229,0.00016302885,0.0004879373],"domain_scores_gemma":[0.9953064,0.00035363648,0.00036475022,0.003660667,0.00015291401,0.00016165755],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00076145143,0.00037786085,0.0003565756,0.000039545645,0.00057697314,0.0010416965,0.004693281,0.0002972976,0.000055080138],"category_scores_gemma":[0.00013752432,0.00032814944,0.00018025433,0.0003920831,0.00017345937,0.0026640848,0.0069891866,0.0007160942,0.00007456922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004717315,0.00015334891,0.0010757186,0.000024274728,0.0005809175,0.0000982729,0.0013445418,0.93718714,0.0009347564,0.019942204,0.016121112,0.022490516],"study_design_scores_gemma":[0.00026846066,0.000008584654,0.00052129966,0.000088008,0.00014317744,0.000001198736,0.000233033,0.98732746,0.00015576456,0.0046231933,0.006234491,0.00039535874],"about_ca_topic_score_codex":0.0007704429,"about_ca_topic_score_gemma":0.00013406317,"teacher_disagreement_score":0.9716266,"about_ca_system_score_codex":0.00016982126,"about_ca_system_score_gemma":0.0002068284,"threshold_uncertainty_score":0.9999953},"labels":[],"label_agreement":null},{"id":"W1814923578","doi":"10.48550/arxiv.1312.5578","title":"Multimodal Transitions for Generative Stochastic Networks","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Markov chain; Estimator; Autoregressive model; Computer science; Consistency (knowledge bases); Hidden Markov model; Operator (biology); Probabilistic logic; Distribution (mathematics); Artificial intelligence; Algorithm; Mathematics; Machine learning; Statistics","score_opus":0.05444185490410923,"score_gpt":0.18740520412848982,"score_spread":0.13296334922438058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1814923578","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031139534,0.00009746144,0.9938761,0.00032418594,0.0011224688,0.0010065313,0.00005441728,0.00018054165,0.00022432697],"genre_scores_gemma":[0.9617132,0.00003758917,0.036615353,0.00019203023,0.00047023816,0.00002149569,0.0000603791,0.000027633401,0.00086208794],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99776554,0.00018358599,0.00023641581,0.0012354879,0.000067863664,0.0005110918],"domain_scores_gemma":[0.9980756,0.00022493437,0.00020965353,0.0009079588,0.00036320015,0.00021863471],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017283743,0.00042622548,0.00044056683,0.00016470709,0.00039804782,0.00025588705,0.0012742714,0.0003441042,0.000049316586],"category_scores_gemma":[0.000033138367,0.00046556155,0.0003996587,0.00033492525,0.00013533134,0.0005034719,0.0006358506,0.00045684716,0.000038697806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000152584935,0.00006503673,0.000006198087,0.000011171331,0.00013412313,0.000013750968,0.00019296804,0.9559125,0.000042534266,0.04123385,0.0012949436,0.0010776746],"study_design_scores_gemma":[0.0005207243,0.000064822045,0.00005311336,0.000044168104,0.000104046725,0.0000015022081,0.000042284053,0.9767055,0.00007683417,0.021769367,0.000117461444,0.0005002018],"about_ca_topic_score_codex":0.00010051061,"about_ca_topic_score_gemma":0.00005269763,"teacher_disagreement_score":0.95859927,"about_ca_system_score_codex":0.00014166514,"about_ca_system_score_gemma":0.00016116955,"threshold_uncertainty_score":0.9997796},"labels":[],"label_agreement":null},{"id":"W1817457711","doi":"","title":"Products of Hidden Markov Models: It Takes N>1 to Tango","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Hidden Markov model; Artificial intelligence; Markov chain; Graphical model; Machine learning; Generative model; Divergence (linguistics); Partition (number theory); Markov process; Maximum-entropy Markov model; Markov model; Generative grammar; Class (philosophy); Theoretical computer science; Variable-order Markov model; Algorithm; Mathematics; Statistics","score_opus":0.08303800281857779,"score_gpt":0.17894278681204492,"score_spread":0.09590478399346714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1817457711","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051433336,0.00007902061,0.9378243,0.0005224794,0.0003158551,0.00017812647,0.000003595927,0.000057312787,0.009585962],"genre_scores_gemma":[0.9648686,0.000018001108,0.032719992,0.00019904152,0.00013517942,4.6418987e-7,8.993961e-7,0.000008044728,0.0020497926],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989681,0.00009385544,0.00012372828,0.00038675664,0.000079021214,0.0003485242],"domain_scores_gemma":[0.9989239,0.000056335288,0.000082227656,0.00059877255,0.00016164222,0.00017712144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024294404,0.00013763417,0.00017641547,0.00012105948,0.00008755597,0.000027968093,0.000730384,0.000047997273,0.000032472803],"category_scores_gemma":[0.000049331935,0.00014012607,0.00006736103,0.00084111886,0.000048725455,0.0011984534,0.00023034595,0.00006817404,0.00007135957],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017215803,0.00089732243,0.0077739437,0.00009951612,0.000324992,0.00009064982,0.0069296565,0.36427072,0.014060944,0.51157844,0.049424034,0.044377647],"study_design_scores_gemma":[0.0006599193,0.00020042992,0.0035836473,0.00006209249,0.00008019891,0.0000074376835,0.0005793044,0.9508788,0.025578355,0.005589978,0.011974741,0.0008051228],"about_ca_topic_score_codex":0.00005876837,"about_ca_topic_score_gemma":0.0000119885,"teacher_disagreement_score":0.9134352,"about_ca_system_score_codex":0.000045033696,"about_ca_system_score_gemma":0.000042770796,"threshold_uncertainty_score":0.5714175},"labels":[],"label_agreement":null},{"id":"W182494199","doi":"10.1111/j.1467-8640.2012.00419.x","title":"DETONATION CLASSIFICATION FROM ACOUSTIC SIGNATURE WITH THE RESTRICTED BOLTZMANN MACHINE","year":2012,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Université de Montréal","funders":"","keywords":"Discriminative model; Signature (topology); Preprocessor; Task (project management); Pattern recognition (psychology); Support vector machine; Property (philosophy); Boltzmann machine","score_opus":0.027353602024745155,"score_gpt":0.2552475120779182,"score_spread":0.22789391005317303,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W182494199","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022979553,0.0007099029,0.9937143,0.0023645104,0.00028042382,0.00017329247,0.0000095205805,0.00007872901,0.0003713849],"genre_scores_gemma":[0.9220841,0.000013580294,0.076947525,0.00053656904,0.0002575741,0.000019732228,0.000063920816,0.00000837387,0.00006865049],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879515,0.00014226927,0.0001860579,0.0002717006,0.00038234488,0.00022248965],"domain_scores_gemma":[0.9985,0.0007250437,0.00014031604,0.00028192776,0.00027222428,0.00008052687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017960063,0.0001460392,0.00010033172,0.000060341485,0.0002694268,0.00015380314,0.0005896174,0.000056132638,0.000040679755],"category_scores_gemma":[0.00007527775,0.00009469335,0.0000367749,0.0005387837,0.00008337083,0.00065503456,0.00008713319,0.0001918849,0.000082338185],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020920806,0.00009742855,0.0006810582,0.0000029094401,0.00004901224,0.0000022096738,0.0009018144,0.9087896,0.0012943607,0.03321815,0.0024128587,0.052529715],"study_design_scores_gemma":[0.00005029598,0.000031249503,0.03869052,0.000010723237,0.000015156093,0.0000055861597,0.000072550785,0.9534104,0.0012124676,0.005105472,0.0012492754,0.0001463064],"about_ca_topic_score_codex":0.00003701719,"about_ca_topic_score_gemma":0.000017890097,"teacher_disagreement_score":0.9197861,"about_ca_system_score_codex":0.00005093529,"about_ca_system_score_gemma":0.000060387174,"threshold_uncertainty_score":0.38614827},"labels":[],"label_agreement":null},{"id":"W1853745982","doi":"","title":"Modeling documents with a Deep Boltzmann Machine","year":2013,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Softmax function; Computer science; Boltzmann machine; Initialization; Restricted Boltzmann machine; Artificial intelligence; Inference; Tying; Machine learning; Natural language processing; Pattern recognition (psychology); Deep learning","score_opus":0.007847439632798367,"score_gpt":0.20149788407532424,"score_spread":0.19365044444252588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1853745982","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004387997,0.00007456719,0.9842154,0.000880813,0.00007379167,0.00013807522,1.20107e-7,0.00008869386,0.010140576],"genre_scores_gemma":[0.7623497,0.0000060176985,0.23622532,0.00048321736,0.000039072107,0.000017542778,6.811142e-7,0.0000052099435,0.0008731888],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992342,0.000028479431,0.00010810822,0.00025270862,0.00015660073,0.00021990854],"domain_scores_gemma":[0.99949116,0.000014315818,0.000020193522,0.0003135971,0.00007883285,0.000081880615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006688456,0.0001072302,0.000099526376,0.00003592302,0.000097680415,0.0002662618,0.00038060223,0.000020504034,0.00024990216],"category_scores_gemma":[0.0000054415964,0.00006846392,0.00002726704,0.00014526788,0.000013137287,0.0009579897,0.00013119967,0.000055155368,0.0002458729],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012002872,0.00015904577,0.0011333551,0.000010014277,0.00014306747,0.000017870198,0.0007555429,0.76784843,0.0016403416,0.018721266,0.004470801,0.20508824],"study_design_scores_gemma":[0.0001684007,0.000040321604,0.00008640165,0.0000043947575,0.0000028381526,0.0000035959865,0.000014973289,0.9974625,0.00044421127,0.0013657368,0.0002909226,0.00011567557],"about_ca_topic_score_codex":0.00090062973,"about_ca_topic_score_gemma":0.00009772213,"teacher_disagreement_score":0.75796175,"about_ca_system_score_codex":0.00001292612,"about_ca_system_score_gemma":0.000013529271,"threshold_uncertainty_score":0.3160281},"labels":[],"label_agreement":null},{"id":"W1859551169","doi":"10.48550/arxiv.1708.00805","title":"Variational Generative Stochastic Networks with Collaborative Shaping","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"MNIST database; Computer science; Generative grammar; Generative model; Artificial intelligence; Regularization (linguistics); Reinforcement learning; Machine learning; Autoencoder; Markov chain; Bayesian probability; Mathematical optimization; Artificial neural network; Mathematics","score_opus":0.053265284979675094,"score_gpt":0.1830332014202123,"score_spread":0.1297679164405372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1859551169","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004487595,0.000029376084,0.99225205,0.00029331856,0.00025688758,0.00018159245,0.0000052643663,0.00006457887,0.0024293377],"genre_scores_gemma":[0.981976,0.00001336149,0.01700025,0.00014369447,0.00020279431,0.0000014254338,0.000003504376,0.000010408743,0.00064861396],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987495,0.000117107986,0.00010753916,0.00062577124,0.00009073307,0.000309378],"domain_scores_gemma":[0.9984,0.00012013378,0.0002524355,0.000759154,0.00033403552,0.00013426275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017443114,0.00020167576,0.00020077855,0.00007021487,0.0012545636,0.00043720735,0.0010612988,0.00007046019,0.00003387897],"category_scores_gemma":[0.000059949285,0.00018741873,0.000054861932,0.00033203288,0.00019733228,0.0014642754,0.00031487618,0.00015019927,0.000025661111],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003119907,0.000026355212,0.0004570687,8.3531444e-7,0.000075024735,0.00006160009,0.00013819835,0.86288464,0.000031015115,0.13568439,0.00018054782,0.0004291194],"study_design_scores_gemma":[0.0006071076,0.00009309341,0.0036178206,0.00002055661,0.000028193932,0.0000033338795,0.00006176395,0.9922488,0.00008009177,0.0028641855,0.00011320859,0.0002618487],"about_ca_topic_score_codex":0.00004776801,"about_ca_topic_score_gemma":0.000101323676,"teacher_disagreement_score":0.97748834,"about_ca_system_score_codex":0.00008151791,"about_ca_system_score_gemma":0.00015622297,"threshold_uncertainty_score":0.96492153},"labels":[],"label_agreement":null},{"id":"W1867591718","doi":"10.1007/978-3-319-23528-8_33","title":"Scoring and Classifying with Gated Auto-Encoders","year":2015,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Artificial intelligence; Autoencoder; Encoder; Representation (politics); Probabilistic logic; Set (abstract data type); Machine learning; Extension (predicate logic); Simple (philosophy); Pattern recognition (psychology); Encoding (memory); Function (biology); Theoretical computer science; Deep learning","score_opus":0.02827276685641825,"score_gpt":0.2546110047077628,"score_spread":0.22633823785134458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1867591718","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009405013,0.00043796745,0.98699814,0.0011184574,0.0014959336,0.00031302465,0.0000013722122,0.00016716428,0.00006290824],"genre_scores_gemma":[0.5523499,0.0000150610385,0.44717193,0.00026522708,0.00018010821,0.0000063253397,9.1349017e-7,0.000009835613,6.9824034e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99643344,0.00014328367,0.00032391475,0.0016809788,0.0007228128,0.00069558347],"domain_scores_gemma":[0.9978885,0.00024717892,0.00021162083,0.001074824,0.00032679655,0.00025109889],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012173896,0.00044282805,0.0004667885,0.00045750252,0.0002836047,0.001445569,0.0021341213,0.00019221564,0.0000021722317],"category_scores_gemma":[0.00014941717,0.00034941864,0.000047318208,0.0013968772,0.00064739276,0.00081478135,0.003492508,0.00084334076,0.0000031756979],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005621966,0.000018778534,0.0011145439,0.000028307984,0.000010757368,0.00004311305,0.0011709799,0.7277103,0.00026168462,0.000060091417,0.000017179444,0.26955867],"study_design_scores_gemma":[0.00025470468,0.000097878605,0.0009795344,0.00036303417,0.0000072532807,0.000033724536,0.0000015840944,0.9873117,0.002900779,0.007540146,0.000040253606,0.0004694007],"about_ca_topic_score_codex":0.00012168756,"about_ca_topic_score_gemma":0.00010000409,"teacher_disagreement_score":0.5429449,"about_ca_system_score_codex":0.00023226127,"about_ca_system_score_gemma":0.000918381,"threshold_uncertainty_score":0.99989575},"labels":[],"label_agreement":null},{"id":"W1876224860","doi":"10.48550/arxiv.1203.4416","title":"On Training Deep Boltzmann Machines","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Boltzmann machine; Regularization (linguistics); Boltzmann constant; Computer science; Artificial intelligence; Probabilistic logic; Restricted Boltzmann machine; Machine learning; Deep learning; Training (meteorology); Physics","score_opus":0.08224779654064972,"score_gpt":0.18990349661233516,"score_spread":0.10765570007168544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1876224860","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022066496,0.00016293957,0.9656881,0.00014672853,0.0015409673,0.00019009119,0.000007648346,0.00021218797,0.009984837],"genre_scores_gemma":[0.992454,0.00007838944,0.0056066248,0.00027390232,0.0003918439,0.000001030104,0.0000110602705,0.000022461922,0.0011606755],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99801195,0.00021936368,0.00017502575,0.0009788162,0.00010421505,0.00051064644],"domain_scores_gemma":[0.9981867,0.0001824584,0.00020858346,0.0011039558,0.00009248904,0.00022581684],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028381826,0.0003878309,0.00037648503,0.00019979656,0.00020080149,0.00016067167,0.001609595,0.0002487143,0.00009368773],"category_scores_gemma":[0.000050396935,0.00040303383,0.00026840428,0.0003466858,0.00008317339,0.00044730233,0.0013070385,0.00056552247,0.00019736034],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023378961,0.00010123255,0.00030549782,0.000023711867,0.00013053879,0.00013059589,0.00082299864,0.8127497,0.000039417904,0.16826278,0.0007558269,0.01665432],"study_design_scores_gemma":[0.00026663186,0.000039904287,0.00073093217,0.000059114725,0.000058477224,0.000003002905,0.000041706317,0.95630646,0.0001015952,0.040634207,0.0012271517,0.0005307908],"about_ca_topic_score_codex":0.00007210922,"about_ca_topic_score_gemma":0.000034882618,"teacher_disagreement_score":0.9703875,"about_ca_system_score_codex":0.00011233274,"about_ca_system_score_gemma":0.00008770107,"threshold_uncertainty_score":0.99984217},"labels":[],"label_agreement":null},{"id":"W1886634424","doi":"10.48550/arxiv.1206.6445","title":"Deep Lambertian Networks","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Albedo (alchemy); Artificial intelligence; Computer science; Invariant (physics); Generative model; Computer vision; Prior probability; Surface (topology); Latent variable; Representation (politics); Photometric stereo; Object (grammar); Pattern recognition (psychology); Image (mathematics); Generative grammar; Mathematics; Geometry; Bayesian probability","score_opus":0.05038077141648527,"score_gpt":0.17132817862376395,"score_spread":0.12094740720727869,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1886634424","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020668202,0.00044297543,0.9894802,0.00012924873,0.0018325631,0.00021839012,0.0000023832517,0.00023029144,0.0055971504],"genre_scores_gemma":[0.9911591,0.00024478615,0.0064528575,0.00021179499,0.0006010691,0.0000011439025,0.000013501682,0.000024499583,0.0012912357],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99779993,0.0002569847,0.00020484536,0.0010156253,0.00008149434,0.0006410937],"domain_scores_gemma":[0.9977707,0.00010750217,0.00023477954,0.0014433403,0.00013992468,0.00030374416],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028084125,0.00039736828,0.00038124353,0.00013839197,0.00021942728,0.00019583387,0.0019012041,0.00038330222,0.00010514556],"category_scores_gemma":[0.000022806316,0.0004348955,0.0002946706,0.0004821008,0.000103754624,0.0005934837,0.0025028475,0.0006414374,0.00016463548],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009190114,0.00005904894,0.0009286041,0.000012413337,0.00009644553,0.00008251058,0.00012227219,0.9629233,0.000006688498,0.03172954,0.00082716206,0.0032028097],"study_design_scores_gemma":[0.00019126006,0.000016038672,0.0008963757,0.000032915068,0.00007326081,0.0000032334135,0.00001855929,0.99101436,0.000051685307,0.005499255,0.0017061791,0.0004968563],"about_ca_topic_score_codex":0.00014150598,"about_ca_topic_score_gemma":0.000090784415,"teacher_disagreement_score":0.9890923,"about_ca_system_score_codex":0.00014303921,"about_ca_system_score_gemma":0.000082872866,"threshold_uncertainty_score":0.9998103},"labels":[],"label_agreement":null},{"id":"W189596042","doi":"","title":"Deep Boltzmann machines","year":2009,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1778,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Boltzmann machine; MNIST database; Restricted Boltzmann machine; Focus (optics); Computer science; Inference; Artificial intelligence; Boltzmann constant; Hidden Markov model; Hidden variable theory; Markov chain; Object (grammar); Generative model; Deep learning; Boltzmann distribution; Layer (electronics); Algorithm; Pattern recognition (psychology); Machine learning; Generative grammar; Statistical physics; Physics","score_opus":0.008837415005454985,"score_gpt":0.22445313261263705,"score_spread":0.21561571760718207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W189596042","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020404726,0.00011243283,0.9446248,0.0034899148,0.00016386254,0.000036543992,5.990948e-8,0.00011593,0.05125244],"genre_scores_gemma":[0.7978938,0.000008911165,0.19804654,0.0024873877,0.00014562614,9.737957e-7,4.1848625e-7,0.0000018801527,0.0014144237],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994676,0.000025445615,0.00008256534,0.00018087766,0.00009181116,0.00015170535],"domain_scores_gemma":[0.9996194,0.000019922716,0.000018660256,0.00026143424,0.00002968318,0.000050856182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007442317,0.000072443436,0.000074994365,0.000029547737,0.000076747456,0.00011159396,0.0003773601,0.000019905969,0.00007608039],"category_scores_gemma":[0.00001447385,0.000053579704,0.000041183805,0.00014809784,0.000009186461,0.00034089942,0.000044715016,0.00003730603,0.000105887935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021148692,0.000052550266,0.00011187024,6.7350044e-7,0.000008181611,0.000010846402,0.00014932449,0.0040535904,0.0021168566,0.10866479,0.012744484,0.87208474],"study_design_scores_gemma":[0.000110914276,0.00006585087,0.005412849,0.0000018944764,0.000002101692,0.000005249643,0.0000040858413,0.96617794,0.0029865138,0.014526562,0.010566085,0.00013994932],"about_ca_topic_score_codex":0.000010295962,"about_ca_topic_score_gemma":0.000007680269,"teacher_disagreement_score":0.96212435,"about_ca_system_score_codex":0.0000057794973,"about_ca_system_score_gemma":0.0000075384723,"threshold_uncertainty_score":0.21849169},"labels":[],"label_agreement":null},{"id":"W1901467827","doi":"10.1007/978-3-319-23528-8_30","title":"An Empirical Investigation of Minimum Probability Flow Learning Under Different Connectivity Patterns","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Boltzmann machine; Divergence (linguistics); Partition function (quantum field theory); Artificial intelligence; Importance sampling; Gibbs sampling; Artificial neural network; Function (biology); Sampling (signal processing); Restricted Boltzmann machine; Machine learning; Partition (number theory); Focus (optics); Theoretical computer science; Monte Carlo method; Mathematics; Statistics; Bayesian probability","score_opus":0.04715265720020493,"score_gpt":0.2759495844214585,"score_spread":0.22879692722125358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1901467827","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019468071,0.00007959059,0.9785073,0.00052583596,0.00083058595,0.00035470419,0.0000057598454,0.00008439331,0.00014379648],"genre_scores_gemma":[0.8581547,0.0000053410704,0.14122558,0.000250781,0.00030238737,0.0000059907475,0.000009042136,0.000018465667,0.000027715949],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963684,0.00029469092,0.000522803,0.0014221885,0.0009332215,0.00045871292],"domain_scores_gemma":[0.9972103,0.0005751424,0.00036651548,0.0010858395,0.0004948017,0.0002673557],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013308913,0.00046823447,0.0006415753,0.00033033272,0.00018214367,0.0002802509,0.0016721064,0.00029222612,0.000017951123],"category_scores_gemma":[0.00018008432,0.00038761625,0.00012340354,0.00034152507,0.00070872693,0.00072144,0.0007436172,0.00071184564,0.0000041586154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013179622,0.000080731064,0.010767033,0.00005362262,0.000020442207,0.000010183206,0.0018392717,0.7902129,0.00095407845,0.001148812,0.000020986738,0.1948787],"study_design_scores_gemma":[0.00019014705,0.00037711518,0.0062013287,0.0001491949,0.000009472268,0.0000064769815,5.270334e-7,0.86207086,0.0034687845,0.12709042,0.000032347518,0.00040333634],"about_ca_topic_score_codex":0.000030789663,"about_ca_topic_score_gemma":0.00019316527,"teacher_disagreement_score":0.83868665,"about_ca_system_score_codex":0.0003157256,"about_ca_system_score_gemma":0.00051028933,"threshold_uncertainty_score":0.99985754},"labels":[],"label_agreement":null},{"id":"W1904567485","doi":"10.48550/arxiv.1301.3529","title":"Discrete Restricted Boltzmann Machines","year":2013,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Defense Advanced Research Projects Agency; Max-Planck-Institut für Mathematik in den Naturwissenschaften; Institute for Catastrophic Loss Reduction; Pennsylvania State University","keywords":"Boltzmann machine; Graphical model; Bipartite graph; Hidden variable theory; Probabilistic logic; Dimension (graph theory); Probability distribution; Inference; Binary number; Computer science; Theoretical computer science; Boltzmann constant; Simplex; Mathematics; Algorithm; Combinatorics; Artificial intelligence; Deep learning; Graph","score_opus":0.03094119658479569,"score_gpt":0.16403762214020595,"score_spread":0.13309642555541026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1904567485","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.080715284,0.00003717391,0.9123174,0.00041451902,0.0002344679,0.000157754,0.0000018245797,0.00017069996,0.0059509124],"genre_scores_gemma":[0.99178,0.000042788302,0.004238402,0.0001722677,0.00008394572,7.700244e-7,0.0000025809302,0.000008065954,0.0036711837],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894685,0.000108139895,0.000107967564,0.0004836151,0.000057002722,0.00029641512],"domain_scores_gemma":[0.99903667,0.000076530734,0.00007142408,0.0005616803,0.00010865622,0.00014503367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000058532987,0.00015419238,0.00014302465,0.00010262038,0.00019542388,0.00014576998,0.00081928005,0.000057084148,0.0001499398],"category_scores_gemma":[0.00003340682,0.00014405226,0.00009095919,0.0007149265,0.00006631456,0.0011664153,0.000293665,0.00011116017,0.00046453893],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005228865,0.0003043807,0.023683298,0.000029328781,0.0003056234,0.0005120158,0.000564236,0.4146376,0.008131031,0.46326473,0.046594568,0.04192089],"study_design_scores_gemma":[0.00028754034,0.00004679094,0.014222765,0.0000073783212,0.000012714192,0.0000025911588,0.00002322177,0.9703867,0.0003757986,0.012052466,0.0023437166,0.00023832032],"about_ca_topic_score_codex":0.00038948323,"about_ca_topic_score_gemma":0.00002244701,"teacher_disagreement_score":0.91106474,"about_ca_system_score_codex":0.000034770233,"about_ca_system_score_gemma":0.000028268867,"threshold_uncertainty_score":0.5970863},"labels":[],"label_agreement":null},{"id":"W193255932","doi":"10.1007/978-3-642-42054-2_41","title":"Semi Supervised Autoencoders: Better Focusing Model Capacity during Feature Extraction","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Autoencoder; Artificial intelligence; Pattern recognition (psychology); Machine learning; Feature extraction; Task (project management); Unsupervised learning; Deep learning; Data mining","score_opus":0.02212003609481173,"score_gpt":0.22627803316221387,"score_spread":0.20415799706740215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W193255932","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008307414,0.00021010482,0.9927414,0.0020468787,0.0014986859,0.00044544192,0.0000054372317,0.00020116559,0.0020201392],"genre_scores_gemma":[0.16303739,0.000035359753,0.8335765,0.0012582178,0.0011083083,0.000013720663,0.0000040679474,0.000050375857,0.00091607607],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957175,0.000063457184,0.0004744855,0.0018603085,0.000982563,0.0009016569],"domain_scores_gemma":[0.9975045,0.00022612858,0.00030558478,0.0013919526,0.0003432498,0.0002286373],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005137195,0.0007309941,0.00062060193,0.00062929647,0.00059404253,0.0011976918,0.0022688468,0.00052983226,0.00005054632],"category_scores_gemma":[0.000061631305,0.00066121155,0.00022509601,0.0004635475,0.0004839363,0.0022892586,0.0009643081,0.0012775293,0.000057304984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005083651,0.000025922558,0.00002207614,0.000042932566,0.000022553231,0.000041978936,0.0008781062,0.82829875,0.0064119846,0.000812517,0.00021754377,0.16322057],"study_design_scores_gemma":[0.00022118556,0.000037961396,0.000093436705,0.00028225707,0.000012573255,0.0000531991,2.1626906e-7,0.9570409,0.008613462,0.032694772,0.00022868664,0.00072133983],"about_ca_topic_score_codex":0.000045723613,"about_ca_topic_score_gemma":0.00006387235,"teacher_disagreement_score":0.16249923,"about_ca_system_score_codex":0.00046535087,"about_ca_system_score_gemma":0.0003144812,"threshold_uncertainty_score":0.9998392},"labels":[],"label_agreement":null},{"id":"W193851967","doi":"","title":"Tempered Markov Chain Monte Carlo for training of Restricted Boltzmann Machines","year":2010,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Markov chain Monte Carlo; Boltzmann machine; Monte Carlo method; Computer science; Statistical physics; Markov chain; Markov chain mixing time; Parallel tempering; Boltzmann constant; Direct simulation Monte Carlo; Monte Carlo molecular modeling; Markov model; Markov property; Artificial intelligence; Dynamic Monte Carlo method; Mathematics; Physics; Machine learning; Artificial neural network; Statistics; Thermodynamics","score_opus":0.0921970941412643,"score_gpt":0.3253742672901905,"score_spread":0.23317717314892616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W193851967","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007162992,0.000009414968,0.9887243,0.0012310679,0.001134171,0.00019052644,0.00028949504,0.000025877443,0.0012321612],"genre_scores_gemma":[0.82714665,0.00004065939,0.17235461,0.00009320805,0.00016306285,0.00001883371,0.000014644182,0.0000070622773,0.00016126674],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987757,0.000051809002,0.00040629855,0.00032770095,0.0002462465,0.00019220349],"domain_scores_gemma":[0.9984714,0.00054167496,0.00017207587,0.0002031046,0.00053169276,0.00008004659],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027656328,0.00015339679,0.00019890234,0.00013191169,0.000118666496,0.00019045247,0.0005074232,0.00006807501,0.000072440576],"category_scores_gemma":[0.0007862357,0.00013984124,0.0000453419,0.00011565081,0.0001496784,0.0001767307,0.00007343703,0.00016401727,0.0000046488735],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006749313,0.00004484468,0.00002979235,0.000005369207,0.000024928837,0.0000035609228,0.0006487055,0.00043256267,0.013915536,0.61577743,0.00021023721,0.3688395],"study_design_scores_gemma":[0.00005242021,0.00017379185,0.00031809122,0.00002424936,0.00000754367,0.0000039448532,0.0002682314,0.9033294,0.007051245,0.088175945,0.00043588007,0.00015926856],"about_ca_topic_score_codex":0.00011378768,"about_ca_topic_score_gemma":0.00035479714,"teacher_disagreement_score":0.9028968,"about_ca_system_score_codex":0.000009849319,"about_ca_system_score_gemma":0.00009242984,"threshold_uncertainty_score":0.570256},"labels":[],"label_agreement":null},{"id":"W1963079441","doi":"","title":"Deep networks for robust visual recognition","year":2010,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Deep belief network; Computer science; Robustness (evolution); Artificial intelligence; Pattern recognition (psychology); Probabilistic logic; Classifier (UML); Noise reduction; Deep learning; Machine learning","score_opus":0.019670266540156,"score_gpt":0.23953346990804972,"score_spread":0.21986320336789372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963079441","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000565454,0.000013172207,0.99484444,0.00042078638,0.0012363449,0.00017281351,4.542673e-7,0.00010187362,0.0026446388],"genre_scores_gemma":[0.3728896,0.000004932349,0.6255588,0.0005085307,0.0007205329,0.00003289898,0.00000795224,0.0000076213228,0.00026916136],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930185,0.000022950122,0.000121653415,0.00025646604,0.000073277624,0.0002237725],"domain_scores_gemma":[0.99944407,0.00013439881,0.000040213996,0.00019082511,0.00011994187,0.00007052487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021515993,0.00009075076,0.000091381386,0.000033193068,0.00014597797,0.0001639221,0.0002688169,0.000071389964,0.00011542764],"category_scores_gemma":[0.000057701516,0.00007617449,0.00006730232,0.00013597861,0.000023450224,0.0003916943,0.00006782062,0.00010536342,0.000033479413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010454847,0.00006898967,0.000051394498,0.0000029223734,0.00001965475,0.0000013315105,0.0000500447,0.031140504,0.0025185533,0.0051027983,0.006426275,0.95460707],"study_design_scores_gemma":[0.0001758615,0.00005287188,0.00015820988,0.0000018116276,0.0000046798086,0.0000027057517,0.00000678283,0.9925296,0.0025691225,0.0014202854,0.0029528078,0.00012531661],"about_ca_topic_score_codex":0.000011050654,"about_ca_topic_score_gemma":0.00012684378,"teacher_disagreement_score":0.96138906,"about_ca_system_score_codex":0.000005191854,"about_ca_system_score_gemma":0.000014624364,"threshold_uncertainty_score":0.31063056},"labels":[],"label_agreement":null},{"id":"W1964155876","doi":"10.1145/1390156.1390224","title":"Classification using discriminative restricted Boltzmann machines","year":2008,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":665,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Discriminative model; Boltzmann machine; Computer science; Restricted Boltzmann machine; Artificial intelligence; Pattern recognition (psychology); Machine learning; Artificial neural network","score_opus":0.06793276002285821,"score_gpt":0.27554448800590137,"score_spread":0.20761172798304317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964155876","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024777817,0.000043291628,0.96642834,0.00061852514,0.00020408073,0.00008854918,8.7828477e-7,0.000104043545,0.007734477],"genre_scores_gemma":[0.8435884,0.000020915766,0.15542567,0.00012639252,0.00009834085,0.0000036673734,0.0000022680813,0.0000049415944,0.00072939525],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916047,0.00009143034,0.00014820448,0.00027440093,0.00015865918,0.00016681771],"domain_scores_gemma":[0.99941176,0.00005842659,0.000066005545,0.00030172226,0.00010693125,0.00005515132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000059368864,0.00010326405,0.00010522084,0.000076193246,0.00028614176,0.000056703953,0.00033918914,0.00003325555,0.000023779],"category_scores_gemma":[0.00005425694,0.000080284466,0.000044669752,0.00038748604,0.000060521783,0.00060788984,0.00010133839,0.00006285042,0.00001773468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007009329,0.0010300407,0.023076132,0.000032629596,0.00026365716,0.0002470596,0.010868804,0.03352394,0.29569373,0.3332265,0.053730305,0.24823713],"study_design_scores_gemma":[0.00011558571,0.000023443805,0.04549881,0.000003948393,0.0000046308023,0.00001761835,0.000034448403,0.9493444,0.0033576514,0.00072221836,0.00074472814,0.00013252816],"about_ca_topic_score_codex":0.00012900063,"about_ca_topic_score_gemma":0.000008479763,"teacher_disagreement_score":0.9158205,"about_ca_system_score_codex":0.00003131854,"about_ca_system_score_gemma":0.000044327644,"threshold_uncertainty_score":0.32739055},"labels":[],"label_agreement":null},{"id":"W196761320","doi":"","title":"Deep learning via Hessian-free optimization","year":2010,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":716,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Hessian matrix; Artificial intelligence; Computer science; Deep learning; Autoencoder; Class (philosophy); Encoder; Curvature; Machine learning; Optimization problem; Deep neural networks; Mathematical optimization; Pattern recognition (psychology); Algorithm; Mathematics; Applied mathematics","score_opus":0.005286602652571105,"score_gpt":0.19858033194310332,"score_spread":0.1932937292905322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W196761320","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012857575,0.000013752091,0.9776438,0.0008075523,0.00053936517,0.00004738039,4.2879464e-8,0.00014159248,0.020677928],"genre_scores_gemma":[0.40840742,0.0000042594597,0.59044623,0.00015945839,0.00014046865,0.0000031427817,9.86149e-7,0.0000048336533,0.0008331783],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993546,0.000040666302,0.00010344142,0.00021379329,0.000120160796,0.00016735338],"domain_scores_gemma":[0.9993931,0.000044934375,0.00004235039,0.00039434977,0.000062118095,0.000063166684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015662384,0.0000808415,0.00007623006,0.000040254665,0.0001692913,0.00016662775,0.0005681986,0.00004930188,0.00034548226],"category_scores_gemma":[0.000090752175,0.000066480614,0.000035857993,0.00018453659,0.000023725726,0.00054903555,0.00019559605,0.00016929512,0.000054090742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016943932,0.000026616257,0.00026888028,0.000001660656,0.000010323243,0.0000036729955,0.00016910792,0.81509805,0.0059288368,0.013078862,0.0008606356,0.16455165],"study_design_scores_gemma":[0.000110366505,0.000018164648,0.0002509984,0.000001104029,0.0000019519161,0.0000039222386,0.0000066494667,0.99252015,0.0032371178,0.00080066774,0.0029504045,0.00009851385],"about_ca_topic_score_codex":0.000022613747,"about_ca_topic_score_gemma":0.000053571533,"teacher_disagreement_score":0.40827885,"about_ca_system_score_codex":0.000005322991,"about_ca_system_score_gemma":0.000012008464,"threshold_uncertainty_score":0.37827885},"labels":[],"label_agreement":null},{"id":"W1972120712","doi":"10.1109/fpl.2009.5272516","title":"A multi-FPGA architecture for stochastic Restricted Boltzmann Machines","year":2009,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Field-programmable gate array; Pipeline (software); Emulation; Artificial neural network; Parallel computing; Node (physics); Embedded system; Artificial intelligence; Operating system","score_opus":0.017399748695398832,"score_gpt":0.2541633033148319,"score_spread":0.23676355461943305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972120712","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00037443815,0.00010105755,0.994849,0.0035489681,0.00021405112,0.00033681965,0.0000041502376,0.0001802802,0.00039122],"genre_scores_gemma":[0.4452645,0.0000018802463,0.5524944,0.0010884436,0.00019356576,0.000016893166,0.00000403353,0.000006225553,0.0009300521],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990142,0.0000428034,0.00016352787,0.00036142694,0.00012228065,0.00029578232],"domain_scores_gemma":[0.9992796,0.00013307677,0.00005122632,0.0003595217,0.00008537631,0.00009118674],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008482086,0.00015822102,0.00016391149,0.00008922794,0.00016024554,0.000138782,0.0005154082,0.000050395673,0.000011382605],"category_scores_gemma":[0.0001374001,0.000117400414,0.00009726096,0.00027831874,0.000019606121,0.00018781441,0.00005779954,0.00008635388,0.00000918944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006820692,0.00031962746,0.000014554863,0.000009844281,0.00005558061,0.000010925556,0.00065299065,0.16391207,0.020438826,0.009611417,0.02022784,0.7846781],"study_design_scores_gemma":[0.00063279446,0.00021561047,0.0024814208,0.000009584446,0.000009500522,0.0000068405693,0.0000054464285,0.98762304,0.0011268554,0.0050161714,0.002649591,0.00022317053],"about_ca_topic_score_codex":0.000021434722,"about_ca_topic_score_gemma":0.000027980228,"teacher_disagreement_score":0.8237109,"about_ca_system_score_codex":0.000012808797,"about_ca_system_score_gemma":0.000030289704,"threshold_uncertainty_score":0.47874498},"labels":[],"label_agreement":null},{"id":"W1977469241","doi":"10.1109/icsmc.2006.384749","title":"A Hardware-Accelerated Patch Search Engine for Image Completion","year":2006,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Inpainting; Texture synthesis; Image (mathematics); Artificial intelligence; Pixel; Search engine; Matching (statistics); Computer vision; Scale (ratio); Texture (cosmology); Image texture; Image processing; Mathematics; Information retrieval","score_opus":0.026364529981431337,"score_gpt":0.25262021580150573,"score_spread":0.22625568582007438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977469241","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028570415,0.000027671626,0.9914283,0.0014362019,0.00016916792,0.0002780109,0.00000800012,0.00015612475,0.003639448],"genre_scores_gemma":[0.6306313,0.0000029426515,0.3673508,0.00016432493,0.0002452094,0.000029619783,0.00002954618,0.000009081998,0.0015371486],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901354,0.00005152096,0.00017235479,0.00030627183,0.00015673187,0.00029957114],"domain_scores_gemma":[0.99932563,0.00008563883,0.000028847848,0.000260691,0.000252072,0.000047139583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023705709,0.00011657322,0.00014467684,0.000057237274,0.00016349395,0.00026354697,0.0003295964,0.000035942743,0.00009765288],"category_scores_gemma":[0.000015225586,0.00009876052,0.00007057825,0.00026878147,0.000026642532,0.00040683208,0.00008656392,0.000054391556,0.00005030259],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008732805,0.0006931776,0.00090217177,0.00008423617,0.00011086505,0.000040316347,0.0003981147,0.054530963,0.33870646,0.113233164,0.3384575,0.15275574],"study_design_scores_gemma":[0.00041590963,0.00006789501,0.0017138369,0.0000046870005,0.0000036421006,0.000002877941,0.000009253691,0.91783625,0.06406357,0.0009792516,0.014737538,0.0001652697],"about_ca_topic_score_codex":0.0005489935,"about_ca_topic_score_gemma":0.00006160987,"teacher_disagreement_score":0.8633053,"about_ca_system_score_codex":0.000027163358,"about_ca_system_score_gemma":0.000029951685,"threshold_uncertainty_score":0.4027337},"labels":[],"label_agreement":null},{"id":"W1981124010","doi":"10.1007/s00138-006-0028-0","title":"On the Use of Hash Functions as Preprocessing Algorithms to Detect Defects on Repeating Definite Textures","year":2006,"lang":"en","type":"article","venue":"Machine Vision and Applications","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hash function; Feature hashing; Preprocessor; Computer science; Image (mathematics); Cryptographic hash function; Algorithm; Texture (cosmology); Pattern recognition (psychology); Rolling hash; Theoretical computer science; Artificial intelligence; Double hashing","score_opus":0.02066308187240268,"score_gpt":0.26047430442935954,"score_spread":0.23981122255695686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981124010","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010815417,0.000071460534,0.9858464,0.0013720016,0.000031467967,0.0003191566,0.000007638009,0.000075970514,0.00146051],"genre_scores_gemma":[0.9609397,0.000006122924,0.037555773,0.00093333685,0.00007546458,0.00010597661,0.000003802213,0.000010555541,0.00036927286],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991798,0.00006290684,0.00016965617,0.00032553784,0.0001470335,0.000115077186],"domain_scores_gemma":[0.99887687,0.00049708755,0.000086608765,0.00043276622,0.00006091079,0.00004574749],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015322375,0.0001093139,0.000097791926,0.00008086214,0.00050709024,0.0002021664,0.00018410812,0.000027655864,0.000008729745],"category_scores_gemma":[0.00011246045,0.00006949537,0.000043988406,0.00041316287,0.00003447846,0.00010617699,0.0001003267,0.00009212394,0.0000318165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020047988,0.00018816043,0.00018554028,0.0000117353875,0.000016140404,8.459539e-7,0.00013907117,0.09167844,0.016898451,0.07030326,0.008589387,0.8119689],"study_design_scores_gemma":[0.00050471444,0.000734603,0.013367872,0.00021120379,0.000044360724,0.0000123571335,0.00003928321,0.78851163,0.030322526,0.029598176,0.1361073,0.00054599374],"about_ca_topic_score_codex":0.00013678105,"about_ca_topic_score_gemma":0.00003584808,"teacher_disagreement_score":0.95012426,"about_ca_system_score_codex":0.000009086152,"about_ca_system_score_gemma":0.0000131530915,"threshold_uncertainty_score":0.39001793},"labels":[],"label_agreement":null},{"id":"W1981364124","doi":"10.1109/reconfig.2011.79","title":"Resource Efficient Arithmetic Effects on RBM Neural Network Solution Quality Using MNIST","year":2011,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"MNIST database; Computer science; Field-programmable gate array; Artificial neural network; Digital signal processing; Floating point; Computer engineering; Parallel computing; Deep learning; Computer hardware; Algorithm; Artificial intelligence","score_opus":0.05547931979710371,"score_gpt":0.26416344310761397,"score_spread":0.20868412331051026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981364124","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043919813,0.000086032946,0.9468544,0.00018274596,0.0007605555,0.00021514788,4.278889e-7,0.00014879504,0.0078320755],"genre_scores_gemma":[0.902284,0.000001051954,0.09646602,0.0007462956,0.00035232503,0.00000526574,8.6455407e-7,0.000010141275,0.00013398434],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979796,0.0005117797,0.0002624396,0.0004896664,0.00028297812,0.00047354674],"domain_scores_gemma":[0.9988906,0.00023915539,0.00011568693,0.0005750706,0.000056348334,0.00012313899],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000696774,0.00019443885,0.00021854282,0.00005444018,0.00038238318,0.00012715618,0.00046956004,0.0000662402,0.000023616058],"category_scores_gemma":[0.000071105016,0.00015900037,0.0001123653,0.00038015415,0.000051873845,0.00014287302,0.00023573809,0.00014399468,0.000040953735],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014651091,0.0005227057,0.0011251129,0.000053534706,0.00009326002,0.000060145132,0.0014819739,0.75247675,0.005891883,0.06402529,0.005386687,0.16873617],"study_design_scores_gemma":[0.00023974835,0.00015578969,0.006385993,0.000029337294,0.000012779474,0.000004674963,0.000010927155,0.9837501,0.008061412,0.0004945774,0.00060906966,0.00024561],"about_ca_topic_score_codex":0.00025907086,"about_ca_topic_score_gemma":0.0000156461,"teacher_disagreement_score":0.8583642,"about_ca_system_score_codex":0.000061058236,"about_ca_system_score_gemma":0.000023990353,"threshold_uncertainty_score":0.64838463},"labels":[],"label_agreement":null},{"id":"W1990980378","doi":"10.1145/1143844.1143940","title":"Combining discriminative features to infer complex trajectories","year":2006,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Discriminative model; Computer science; Artificial intelligence; Probabilistic logic; Relevance (law); Sequence (biology); Pattern recognition (psychology); Generative model; Range (aeronautics); Statistical model; Generative grammar; Machine learning; Data mining","score_opus":0.01850378410623475,"score_gpt":0.24634407847526077,"score_spread":0.22784029436902603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990980378","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003805546,0.000024966945,0.93778914,0.0023638862,0.00027272193,0.0001243515,0.0000021588676,0.00013127936,0.05548595],"genre_scores_gemma":[0.87437016,5.869531e-7,0.12256157,0.0006549511,0.00015055566,0.000010149432,0.000003847899,0.0000059406516,0.0022422182],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99909186,0.00006233855,0.00013865525,0.0002852003,0.00017385678,0.00024806187],"domain_scores_gemma":[0.99945825,0.000103006154,0.000031510568,0.00025146143,0.00009139683,0.00006436052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000096744116,0.00013541043,0.00015316534,0.00006679887,0.00017796305,0.0002450874,0.0004050261,0.000028279012,0.000058595582],"category_scores_gemma":[0.000028967646,0.00010488036,0.000051191288,0.00030822383,0.000039872768,0.00036840793,0.00017981206,0.00006430753,0.000038351132],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012272094,0.00015119072,0.0011825652,0.00000630628,0.00003486126,0.000014739127,0.002655386,0.010136305,0.022861486,0.76991034,0.16349687,0.029537706],"study_design_scores_gemma":[0.001278252,0.00059464975,0.6148183,0.00005415431,0.00003501244,0.000021333473,0.0010323826,0.07486291,0.18123615,0.045190144,0.07914771,0.0017290448],"about_ca_topic_score_codex":0.0005739291,"about_ca_topic_score_gemma":0.00034152405,"teacher_disagreement_score":0.87056464,"about_ca_system_score_codex":0.000023167906,"about_ca_system_score_gemma":0.000018983672,"threshold_uncertainty_score":0.4276897},"labels":[],"label_agreement":null},{"id":"W1994197834","doi":"10.1145/1273496.1273556","title":"An empirical evaluation of deep architectures on problems with many factors of variation","year":2007,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1030,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Variation (astronomy); Deep learning; Artificial intelligence; Machine learning; Artificial neural network; Series (stratigraphy); Simple (philosophy); Support vector machine","score_opus":0.03353096239121345,"score_gpt":0.2989716356777909,"score_spread":0.26544067328657744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994197834","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32690388,0.0000054300635,0.67176193,0.000040249513,0.000034763045,0.00013304953,3.1474238e-7,0.00001300699,0.001107399],"genre_scores_gemma":[0.9424301,2.7068415e-7,0.057493187,0.00003545961,0.000027783499,0.0000020979833,0.0000017692273,0.0000036054382,0.00000575057],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886215,0.00013740786,0.00018923558,0.00019588662,0.00049951556,0.00011578447],"domain_scores_gemma":[0.9992151,0.00011222881,0.00012358959,0.00026758417,0.0002396394,0.000041810876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094506104,0.000081439815,0.00011432183,0.00010063005,0.000033365173,0.000017561402,0.00020455148,0.000034541015,0.000031887943],"category_scores_gemma":[0.000041165786,0.000051404455,0.000027605383,0.00023647505,0.000029791647,0.00012273795,0.000018516375,0.000045110883,6.9929865e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058667436,0.00038079175,0.013195963,0.00001267354,0.000056092158,4.814183e-7,0.0055019474,0.7699989,0.021036355,0.0044587925,0.000020355088,0.18527897],"study_design_scores_gemma":[0.00022334332,0.00051414676,0.2442944,0.000008308315,0.00001566335,4.7091694e-7,0.00003946731,0.6921998,0.06127134,0.0013544974,0.000007198092,0.00007130897],"about_ca_topic_score_codex":0.00006524801,"about_ca_topic_score_gemma":0.00014339657,"teacher_disagreement_score":0.6155262,"about_ca_system_score_codex":0.000020740617,"about_ca_system_score_gemma":0.000035516994,"threshold_uncertainty_score":0.20962128},"labels":[],"label_agreement":null},{"id":"W1995997122","doi":"10.1109/cvpr.2011.5995710","title":"On deep generative models with applications to recognition","year":2011,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":235,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Artificial intelligence; Discriminative model; Computer science; Probabilistic logic; Generative model; Pattern recognition (psychology); Generative grammar; Deep belief network; Statistical model; Pixel; Deep learning; Machine learning; Representation (politics); Computer vision","score_opus":0.05773346823870358,"score_gpt":0.22840695992910487,"score_spread":0.1706734916904013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995997122","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023791411,0.00000516704,0.92381054,0.00022006182,0.00003133537,0.00026977097,0.0000012631358,0.00007192718,0.07535199],"genre_scores_gemma":[0.3724949,0.0000020708853,0.6258875,0.0012033739,0.000041275904,0.0001493821,0.0000017123633,0.000004714013,0.00021507741],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993457,0.00003424341,0.00008326011,0.0002941595,0.00010371794,0.00013887468],"domain_scores_gemma":[0.9994528,0.000028149721,0.00002611415,0.00029273477,0.00011201335,0.00008816002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006267994,0.00009117603,0.00007444795,0.000056011377,0.00011004529,0.000050923547,0.0002483824,0.00002167163,0.00008488201],"category_scores_gemma":[0.000003898324,0.00006499796,0.000020599042,0.0002528122,0.000015167622,0.00034481473,0.000047749472,0.00004076238,0.00025193059],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004280754,0.00022459716,0.000008460348,0.0000020872135,0.0000461305,0.0000041585095,0.0024537628,0.040788602,0.00074632984,0.61381316,0.0020676868,0.3398022],"study_design_scores_gemma":[0.00031833188,0.00066703744,0.00015551194,0.000014727587,0.0000135493,0.000005158435,0.0000978958,0.71673524,0.06264504,0.21796858,0.00092231366,0.00045659175],"about_ca_topic_score_codex":0.000031775067,"about_ca_topic_score_gemma":0.000059525253,"teacher_disagreement_score":0.67594665,"about_ca_system_score_codex":0.000015510961,"about_ca_system_score_gemma":0.00001622404,"threshold_uncertainty_score":0.32381418},"labels":[],"label_agreement":null},{"id":"W2005013039","doi":"10.1145/1101389.1101443","title":"Integrating procedural textures with replicated image editing","year":2005,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Image editing; Automation; Context (archaeology); Image (mathematics); Computer graphics (images); Texture (cosmology); Texture synthesis; Workload; Software; Image manipulation; Computer vision; Image texture; Artificial intelligence; Human–computer interaction; Image processing; Programming language; Engineering; Operating system","score_opus":0.007074178616795615,"score_gpt":0.22209865820816982,"score_spread":0.21502447959137422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005013039","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002250554,0.00003202088,0.96547204,0.0060862848,0.00005549799,0.00011714254,3.642086e-7,0.00025348103,0.0257326],"genre_scores_gemma":[0.5690466,8.113468e-7,0.4291524,0.00081592344,0.00035969994,0.000009153888,9.3093917e-7,0.0000058079913,0.0006086398],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904895,0.00003234834,0.00015959467,0.00035308613,0.00015254781,0.00025345964],"domain_scores_gemma":[0.99936557,0.000046223544,0.00007519466,0.00031656484,0.00013170665,0.00006474123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015587383,0.00013159007,0.00011622573,0.000039637627,0.00016697799,0.00027267452,0.00040466015,0.000028523222,0.00004720953],"category_scores_gemma":[0.0000795862,0.00008292721,0.000032994005,0.00027399263,0.000042078093,0.0008974404,0.00010611857,0.000116650524,0.000041133262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030883493,0.00019116348,0.00076074613,0.000024794512,0.0001053977,0.000034179397,0.0023928913,0.005698477,0.12691593,0.04900553,0.116244465,0.6985955],"study_design_scores_gemma":[0.00034227682,0.00011419404,0.000647992,0.00004624344,0.000008159181,0.000053804335,0.00025471445,0.7691595,0.21503063,0.00029926057,0.013696586,0.0003466565],"about_ca_topic_score_codex":0.00003336198,"about_ca_topic_score_gemma":0.000083572246,"teacher_disagreement_score":0.763461,"about_ca_system_score_codex":0.000022644741,"about_ca_system_score_gemma":0.000035479177,"threshold_uncertainty_score":0.33816734},"labels":[],"label_agreement":null},{"id":"W2013035813","doi":"10.1162/neco_a_00142","title":"A Connection Between Score Matching and Denoising Autoencoders","year":2011,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":980,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Autoencoder; Restricted Boltzmann machine; Artificial intelligence; Noise reduction; Pattern recognition (psychology); Estimator; Computer science; Matching (statistics); Probabilistic logic; Unsupervised learning; Nonparametric statistics; Energy (signal processing); Rank (graph theory); Artificial neural network; Machine learning; Mathematics; Statistics","score_opus":0.06044979363662861,"score_gpt":0.24992128469515484,"score_spread":0.18947149105852623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013035813","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36752105,0.000021397742,0.6318885,0.000101163365,0.00014692104,0.00005920463,2.598728e-7,0.00007646799,0.00018505132],"genre_scores_gemma":[0.9343232,0.0000020091313,0.06545926,0.00011506094,0.000084924905,0.0000018973726,0.0000023697448,0.000005681586,0.000005584167],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992864,0.00009212625,0.00013661948,0.00024242119,0.000104989274,0.00013744048],"domain_scores_gemma":[0.99966395,0.00007570913,0.000074113006,0.00008634574,0.000048199217,0.000051710747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012752676,0.00009158936,0.00010121049,0.0000675512,0.00019229633,0.00012855708,0.00011886645,0.00003174547,0.0000030585634],"category_scores_gemma":[0.000014538567,0.00008704609,0.000025778383,0.00015581246,0.000026543581,0.00069351995,0.000074557,0.00007822394,0.0000052633923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002562349,0.0000517959,0.023267511,0.000042040127,0.00007012031,0.00002879417,0.013478029,0.09588788,0.006404745,0.0072509963,0.00023762166,0.85325485],"study_design_scores_gemma":[0.00024992827,0.00012252931,0.15469025,0.000022556262,0.000015214573,0.000017195582,0.00009327009,0.818454,0.002803896,0.023318034,0.000017769538,0.00019530617],"about_ca_topic_score_codex":0.00011556026,"about_ca_topic_score_gemma":0.0000086103055,"teacher_disagreement_score":0.85305953,"about_ca_system_score_codex":0.000016269407,"about_ca_system_score_gemma":0.000010288691,"threshold_uncertainty_score":0.35496366},"labels":[],"label_agreement":null},{"id":"W2025768430","doi":"10.1145/1390156.1390294","title":"Extracting and composing robust features with denoising autoencoders","year":2008,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":7343,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Artificial intelligence; Discriminative model; Benchmark (surveying); Generative grammar; Perspective (graphical); Unsupervised learning; Deep learning; Representation (politics); Suite; Feature learning; Pattern recognition (psychology); Machine learning; Noise reduction","score_opus":0.02008602172927967,"score_gpt":0.19497921799193751,"score_spread":0.17489319626265784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025768430","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023387091,0.00021564381,0.97052604,0.0005810917,0.00007231785,0.000057130845,8.946358e-8,0.00010238669,0.0050582113],"genre_scores_gemma":[0.5865664,0.000014371073,0.41300878,0.00016663122,0.00004216246,7.4763e-7,1.92508e-7,0.000004429533,0.00019630541],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992583,0.000041153737,0.000090840585,0.00027021574,0.00013803442,0.00020148976],"domain_scores_gemma":[0.9995793,0.00010386909,0.000047311845,0.00017023343,0.00003159777,0.00006766007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000095823096,0.00010926676,0.000113269365,0.000044387587,0.0004697117,0.0001738365,0.00016791916,0.000027493585,0.0000048602424],"category_scores_gemma":[0.000014487434,0.00007960737,0.000018928433,0.00015566514,0.00007686235,0.0006689628,0.000077719094,0.000098069104,0.0000020367436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000080109305,0.00022445344,0.022366714,0.000036769114,0.0002462273,0.0008087842,0.012042323,0.6771725,0.030521674,0.011475948,0.010756474,0.23426805],"study_design_scores_gemma":[0.0005996556,0.00014116337,0.024945546,0.00007521617,0.0000168665,0.0012409198,0.00038338208,0.95387876,0.016537169,0.00014548072,0.0014847715,0.00055106304],"about_ca_topic_score_codex":0.00009891674,"about_ca_topic_score_gemma":0.000037724083,"teacher_disagreement_score":0.56317925,"about_ca_system_score_codex":0.0000135263335,"about_ca_system_score_gemma":0.0000300035,"threshold_uncertainty_score":0.36126903},"labels":[],"label_agreement":null},{"id":"W2040562177","doi":"10.1145/1950413.1950452","title":"Building a multi-FPGA virtualized restricted boltzmann machine architecture using embedded MPI","year":2011,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Field-programmable gate array; Emulation; Embedded system; Computer architecture; Context (archaeology); FPGA prototype; Architecture; Parallel computing","score_opus":0.052968138588593165,"score_gpt":0.2735298800079917,"score_spread":0.22056174141939855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040562177","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011400365,0.00013960844,0.98572344,0.00009922978,0.0003847563,0.00023092848,0.0000034161772,0.00028586056,0.001732408],"genre_scores_gemma":[0.38063592,0.00000556858,0.61874014,0.0002782763,0.000081895225,0.000005415048,0.0000012376203,0.000015276735,0.00023625192],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981295,0.00023700444,0.0003328535,0.00058848556,0.00024318862,0.00046896414],"domain_scores_gemma":[0.99883413,0.00008672491,0.00013497735,0.00066804385,0.00010453883,0.00017156539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021338205,0.00027680193,0.0003004546,0.00019949857,0.0002540066,0.00015134065,0.00087171805,0.00009882297,0.00015437233],"category_scores_gemma":[0.00012131475,0.00021971503,0.000138823,0.0006457519,0.00006238056,0.0004415036,0.00040962358,0.00021713055,0.00001810315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003703422,0.0013770533,0.0009982963,0.000059020942,0.00069765584,0.00045117995,0.014877623,0.048227273,0.53990483,0.053134046,0.0028808094,0.33702183],"study_design_scores_gemma":[0.0010059214,0.00008530936,0.0010069917,0.000027277028,0.000026022704,0.00003236083,0.00003743037,0.9413703,0.053065382,0.0017259481,0.0011771396,0.0004398887],"about_ca_topic_score_codex":0.00061489776,"about_ca_topic_score_gemma":0.00005848603,"teacher_disagreement_score":0.89314306,"about_ca_system_score_codex":0.000036323916,"about_ca_system_score_gemma":0.000059109323,"threshold_uncertainty_score":0.8959719},"labels":[],"label_agreement":null},{"id":"W2051717488","doi":"10.1162/neco_a_00014","title":"Tractable Multivariate Binary Density Estimation and the Restricted Boltzmann Forest","year":2010,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of Toronto","funders":"","keywords":"Restricted Boltzmann machine; Multivariate statistics; Boltzmann machine; Density estimation; Binary tree; Binary number; Boltzmann constant; Focus (optics); Mathematics; Tree (set theory); Extension (predicate logic); Computer science; Applied mathematics; Algorithm; Artificial intelligence; Statistics; Artificial neural network; Combinatorics; Physics","score_opus":0.011530800144518677,"score_gpt":0.24013102566113526,"score_spread":0.22860022551661657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051717488","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43062413,0.000013941754,0.56711483,0.001532915,0.00039351993,0.00017066467,4.6469574e-7,0.00006425905,0.000085274776],"genre_scores_gemma":[0.94017303,0.0000027396936,0.059507173,0.00018142562,0.000091972375,0.000007778502,0.000007831795,0.000005250554,0.000022775459],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913657,0.00015958112,0.00016361116,0.00024423216,0.0001490255,0.00014700831],"domain_scores_gemma":[0.99919575,0.00036091247,0.00010810017,0.00018319316,0.000104717255,0.000047341153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023035666,0.00010622899,0.00011808704,0.00004980485,0.00033867446,0.0002626377,0.00019595929,0.000048530736,0.0000018309267],"category_scores_gemma":[0.00016066754,0.000073255054,0.000034695513,0.00023654773,0.0000872202,0.00067165896,0.000104306884,0.0002013302,0.000007098953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018461909,0.00010558866,0.001194318,0.000016855856,0.00003538154,0.000020796437,0.0014420099,0.46199054,0.035744812,0.023776757,0.0013365452,0.4741518],"study_design_scores_gemma":[0.00062512583,0.0000308766,0.1057878,0.00000278316,0.000008293106,0.000013190875,0.0000055068017,0.8879417,0.00043061998,0.005034258,0.00004259,0.000077231314],"about_ca_topic_score_codex":0.00019480225,"about_ca_topic_score_gemma":0.00006184071,"teacher_disagreement_score":0.5095489,"about_ca_system_score_codex":0.000007762707,"about_ca_system_score_gemma":0.000018156628,"threshold_uncertainty_score":0.29872546},"labels":[],"label_agreement":null},{"id":"W2051859319","doi":"10.1109/icip.2014.7025557","title":"Scalable learning for restricted Boltzmann machines","year":2014,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Boltzmann machine; Restricted Boltzmann machine; Scalability; Computer science; Artificial intelligence; Locality; Set (abstract data type); Pattern recognition (psychology); Exploit; Image (mathematics); Translation (biology); Deep learning","score_opus":0.01222544693284059,"score_gpt":0.2300644788109967,"score_spread":0.21783903187815612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051859319","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008096553,0.00002717622,0.98386955,0.00097438676,0.00023251306,0.00010141035,1.91216e-7,0.00015806584,0.013827066],"genre_scores_gemma":[0.7164776,0.000005448611,0.27482298,0.000365198,0.00027095125,0.000017690127,0.0000028325776,0.000008229202,0.008029089],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925655,0.00007673659,0.00011496087,0.00024740532,0.0000904171,0.00021390912],"domain_scores_gemma":[0.9993866,0.00021573433,0.000041235933,0.00021879151,0.00008195974,0.000055690267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020488477,0.00008669345,0.00011179229,0.00004521927,0.00021034597,0.00015594662,0.0003368484,0.00003237438,0.000026444939],"category_scores_gemma":[0.00024220218,0.00006772956,0.000053274867,0.00019209787,0.000014965242,0.0002780016,0.00009471027,0.000059453418,0.000036009813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000234282,0.000089257104,0.0024635594,0.000023662227,0.000051421546,0.0000014598145,0.00021994843,0.083117865,0.013905467,0.14702687,0.06953216,0.6835449],"study_design_scores_gemma":[0.000188254,0.00007717115,0.0010339605,0.0000034339523,0.0000029958214,7.851284e-7,0.0000031769448,0.8977041,0.002639247,0.0023749354,0.09587238,0.00009950836],"about_ca_topic_score_codex":0.00004380237,"about_ca_topic_score_gemma":0.000009263355,"teacher_disagreement_score":0.8145863,"about_ca_system_score_codex":0.0000074515383,"about_ca_system_score_gemma":0.000012891663,"threshold_uncertainty_score":0.2761931},"labels":[],"label_agreement":null},{"id":"W2054814877","doi":"10.1109/cvpr.2012.6247936","title":"Robust Boltzmann Machines for recognition and denoising","year":2012,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":172,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Restricted Boltzmann machine; Artificial intelligence; Computer science; Noise reduction; Boltzmann machine; Pattern recognition (psychology); Noise (video); Unsupervised learning; Pixel; Mixture model; Inference; Image (mathematics); Computer vision; Machine learning; Deep learning","score_opus":0.06998329453687235,"score_gpt":0.24436771098258014,"score_spread":0.1743844164457078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054814877","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008063163,0.00027411964,0.9894739,0.00039770585,0.00025274963,0.00009820164,0.000001656996,0.000043874243,0.0013946538],"genre_scores_gemma":[0.61237514,0.000011897173,0.38663888,0.0003391109,0.00035866094,0.000010333209,0.0000034353495,0.000004737306,0.00025778962],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99956834,0.000023296985,0.00007168335,0.00012297851,0.000044578497,0.00016914337],"domain_scores_gemma":[0.99970883,0.0000785354,0.000023833958,0.00009324502,0.000038118586,0.000057436922],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001980737,0.000060996088,0.000064407235,0.00002690476,0.00011500807,0.00009710292,0.00008364118,0.000022031416,0.000015065429],"category_scores_gemma":[0.000034672277,0.00004831212,0.00002332514,0.000058441627,0.000012745563,0.00070944644,0.000054140968,0.000021855343,0.000013241159],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009859644,0.0000685595,0.0015624829,0.00001972509,0.00002990156,4.4091712e-7,0.00063349,0.00036295803,0.008198063,0.008264557,0.0072576306,0.97359234],"study_design_scores_gemma":[0.0011729622,0.00019712768,0.013543704,0.00004972724,0.00006091779,0.000047162604,0.00013320861,0.85752046,0.07321258,0.027895639,0.025254978,0.0009115311],"about_ca_topic_score_codex":0.000018904346,"about_ca_topic_score_gemma":0.000007241873,"teacher_disagreement_score":0.9726808,"about_ca_system_score_codex":0.0000055184487,"about_ca_system_score_gemma":0.0000042698443,"threshold_uncertainty_score":0.1970111},"labels":[],"label_agreement":null},{"id":"W2064630666","doi":"10.1162/neco.2008.04-07-510","title":"Representational Power of Restricted Boltzmann Machines and Deep Belief Networks","year":2008,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":839,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Boltzmann machine; Deep belief network; Restricted Boltzmann machine; Artificial intelligence; Block (permutation group theory); Artificial neural network; Inference; Probabilistic logic; Computer science; Deep learning; Generative model; Boltzmann constant; Power (physics); Machine learning; Generative grammar; Theoretical computer science; Mathematics","score_opus":0.0162958313026846,"score_gpt":0.2431024191057949,"score_spread":0.22680658780311028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064630666","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2396715,0.00026332508,0.7591361,0.00032280007,0.00023392968,0.00009664597,9.231556e-7,0.00004491628,0.00022988427],"genre_scores_gemma":[0.9735461,0.000036382313,0.026140915,0.00014701908,0.0000803973,0.0000031775905,0.00001239307,0.0000055780165,0.000028043454],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990759,0.00011373251,0.00022565355,0.0002578928,0.00019666665,0.00013013896],"domain_scores_gemma":[0.9993596,0.00017737056,0.00012562537,0.0001374484,0.00014930603,0.00005063664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006019807,0.00010062192,0.00013486376,0.00007649858,0.00016057595,0.000038011403,0.00015634905,0.00003832666,0.0000060944567],"category_scores_gemma":[0.000046214125,0.00009190133,0.000039662787,0.00031441805,0.00006975038,0.0004028658,0.00009933245,0.000079335936,0.0000016287778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003837966,0.00007458568,0.009501885,0.0000071085055,0.00003150289,0.000029117085,0.00096522353,0.9329822,0.0020466084,0.0016167054,0.0017907269,0.05091596],"study_design_scores_gemma":[0.00021543377,0.00007185451,0.17109816,0.0000034105942,0.0000033057388,0.000029985327,0.0000061897986,0.82774734,0.0001975779,0.00052348286,0.000028379003,0.0000748677],"about_ca_topic_score_codex":0.000038739236,"about_ca_topic_score_gemma":0.000004021493,"teacher_disagreement_score":0.7338746,"about_ca_system_score_codex":0.00000798166,"about_ca_system_score_gemma":0.000015108245,"threshold_uncertainty_score":0.37476277},"labels":[],"label_agreement":null},{"id":"W2071709160","doi":"10.1162/neco_a_00311","title":"An Efficient Learning Procedure for Deep Boltzmann Machines","year":2012,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":490,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Boltzmann machine; Restricted Boltzmann machine; MNIST database; Computer science; Artificial neural network; Artificial intelligence; Boltzmann constant; Deep belief network; Deep learning; Focus (optics); Inference; Algorithm; Hidden Markov model; Pattern recognition (psychology); Machine learning; Physics","score_opus":0.016284688758106135,"score_gpt":0.2747265167593389,"score_spread":0.2584418280012328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071709160","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1248474,0.000113148315,0.87388813,0.00023329952,0.00049309304,0.00021240911,4.971167e-7,0.00013091846,0.00008111919],"genre_scores_gemma":[0.929613,6.7135437e-7,0.06973023,0.00017678847,0.00041271903,0.000019428691,0.000015552521,0.000009661762,0.000021966076],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991345,0.00010395205,0.00013500352,0.00022378674,0.00013691692,0.00026587115],"domain_scores_gemma":[0.99952954,0.000092815586,0.0000800865,0.00010572677,0.00010094447,0.00009089013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020776443,0.00011206176,0.000101372105,0.00005211944,0.0002659867,0.00014203998,0.00019758218,0.00003371453,0.000002765527],"category_scores_gemma":[0.000050870054,0.00009701189,0.000049853632,0.00016140698,0.000014026861,0.0005731478,0.00004073152,0.000080585385,0.000009486265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000746728,0.00005387026,0.000895877,0.000009485133,0.0000043766267,2.573107e-7,0.0007592924,0.8982161,0.0014509248,0.0010986866,0.00011257426,0.09739105],"study_design_scores_gemma":[0.00017075075,0.00012688142,0.007942328,0.0000034899592,0.000006104165,0.000005026759,0.000025773066,0.9902909,0.00083659386,0.00019090051,0.00028074277,0.00012050217],"about_ca_topic_score_codex":0.0000050764525,"about_ca_topic_score_gemma":0.0000017267932,"teacher_disagreement_score":0.8047656,"about_ca_system_score_codex":0.00001779127,"about_ca_system_score_gemma":0.0000104112505,"threshold_uncertainty_score":0.39560303},"labels":[],"label_agreement":null},{"id":"W2073591796","doi":"10.1109/crv.2013.32","title":"A Dynamic Bayesian Framework for Motion Segmentation","year":2013,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Segmentation; Artificial intelligence; Bayesian probability; Dynamic Bayesian network; Image segmentation; Mixture model; Flexibility (engineering); Expectation–maximization algorithm; Pattern recognition (psychology); Computer vision; Noise (video); Image (mathematics); Mathematics; Maximum likelihood","score_opus":0.009816354623365836,"score_gpt":0.24815866737329462,"score_spread":0.2383423127499288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073591796","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005482348,0.000014196158,0.99596703,0.0022758387,0.00027038352,0.0003692322,5.5886755e-7,0.00007790236,0.00047663323],"genre_scores_gemma":[0.4326559,0.0000021004212,0.5666962,0.0003070903,0.000029214718,0.00006375166,0.0000021618614,0.0000030874696,0.00024046787],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994513,0.00002671769,0.00010285168,0.00019559535,0.000076931545,0.00014663315],"domain_scores_gemma":[0.99957126,0.00008775175,0.00003792592,0.0001908181,0.000069538524,0.000042730186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007555804,0.00006889607,0.00006523252,0.000033287695,0.000094141455,0.00018439305,0.00019347384,0.000038844064,0.00014033714],"category_scores_gemma":[0.000033573822,0.00005699977,0.00004378927,0.00011923745,0.000010208913,0.000615916,0.00003506499,0.000032860895,0.000077037264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024077674,0.000055530247,0.0001268831,0.000010034881,0.00002532938,3.025385e-7,0.00036491692,0.0036482993,0.009670559,0.121473,0.0037724169,0.86085033],"study_design_scores_gemma":[0.000089221816,0.000033944274,0.0010272277,0.0000045636225,0.0000024907322,5.071601e-7,0.000036723042,0.9021793,0.003207214,0.09318769,0.00015150214,0.00007962462],"about_ca_topic_score_codex":0.000029361485,"about_ca_topic_score_gemma":0.0000065489257,"teacher_disagreement_score":0.89853096,"about_ca_system_score_codex":0.000023614433,"about_ca_system_score_gemma":0.000008770206,"threshold_uncertainty_score":0.23243831},"labels":[],"label_agreement":null},{"id":"W2076423492","doi":"10.1109/iscslp.2014.6936696","title":"Acoustic emotion recognition based on fusion of multiple feature-dependent deep Boltzmann machines","year":2014,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Boltzmann machine; Support vector machine; Computer science; Artificial intelligence; Restricted Boltzmann machine; Pattern recognition (psychology); Binary classification; Feature (linguistics); Feature extraction; Task (project management); Set (abstract data type); Data set; Speech recognition; Deep learning; Engineering","score_opus":0.011689335513117072,"score_gpt":0.2125541630571329,"score_spread":0.20086482754401583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076423492","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00797654,0.000010412139,0.98810077,0.0005237165,0.00041464868,0.00014839869,0.0000025988825,0.000082379454,0.0027405568],"genre_scores_gemma":[0.9216764,0.000004523209,0.07757729,0.00040205728,0.00013924089,0.0000059288354,0.000014073341,0.000007932564,0.00017254063],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891245,0.00018196258,0.0001643031,0.0003131873,0.000264383,0.00016373742],"domain_scores_gemma":[0.99911845,0.0002424113,0.00010563854,0.00034423856,0.00013106433,0.000058188012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003317719,0.00013513761,0.00015549539,0.00010466968,0.000107246495,0.000057100613,0.00025341575,0.000068278016,0.00006341099],"category_scores_gemma":[0.0002101763,0.000105012165,0.00007532015,0.00016622143,0.00002040704,0.00021982176,0.00006491593,0.0000871526,0.000047718273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007689363,0.00033311915,0.0007949609,0.000039668634,0.000017611354,0.0000026633368,0.00015038687,0.27062243,0.070850745,0.00029839078,0.0016263714,0.6551868],"study_design_scores_gemma":[0.00043562675,0.00019030173,0.0036404843,0.000031030668,0.000009517692,9.872641e-7,0.000007747221,0.9637084,0.031278994,0.00046178442,0.000108659326,0.00012649133],"about_ca_topic_score_codex":0.0000633006,"about_ca_topic_score_gemma":0.0001144099,"teacher_disagreement_score":0.91369987,"about_ca_system_score_codex":0.00002045465,"about_ca_system_score_gemma":0.000012300666,"threshold_uncertainty_score":0.4282272},"labels":[],"label_agreement":null},{"id":"W2084336274","doi":"10.1111/cogs.12049","title":"Where Do Features Come From?","year":2013,"lang":"en","type":"article","venue":"Cognitive Science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Boltzmann machine; Computer science; Backpropagation; Artificial intelligence; Restricted Boltzmann machine; Artificial neural network; Initialization; Feed forward; Generalization; Deep learning; Deep belief network; Machine learning; Feedforward neural network; Generative model; Set (abstract data type); Inference; Generative grammar; Pattern recognition (psychology); Mathematics","score_opus":0.010501653854667654,"score_gpt":0.23694192017474933,"score_spread":0.22644026632008168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084336274","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054321643,0.0016772253,0.90241826,0.00190807,0.0011618575,0.00045840864,0.000014018242,0.00017708287,0.037863437],"genre_scores_gemma":[0.97789353,0.00003357428,0.020863255,0.000607472,0.0001526604,0.000026902677,9.1487186e-7,0.000005299279,0.0004164185],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.998271,0.000070263464,0.00013246504,0.0006513422,0.00044970674,0.0004252191],"domain_scores_gemma":[0.99857587,0.00024497067,0.0000690337,0.0003613437,0.00055342296,0.00019534769],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00027426603,0.00014676874,0.00014376981,0.00010418749,0.0004380842,0.0010257554,0.0012918037,0.000037184072,0.00038528992],"category_scores_gemma":[0.00029045055,0.0001202481,0.000050838014,0.000919637,0.00065540354,0.0022230097,0.00048629555,0.00013418379,0.00095350156],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009427611,0.00017867856,0.0075088376,0.000009643745,0.000049594633,0.00003372332,0.0030419861,0.00014048933,0.09910583,0.01722842,0.03180607,0.8408873],"study_design_scores_gemma":[0.001377597,0.00032074034,0.6475587,0.00039778603,0.000035018056,0.000025769827,0.0016193741,0.07898244,0.20837747,0.053774383,0.0058884127,0.0016423167],"about_ca_topic_score_codex":0.0001542372,"about_ca_topic_score_gemma":0.000013901673,"teacher_disagreement_score":0.9235719,"about_ca_system_score_codex":0.000030471521,"about_ca_system_score_gemma":0.000119651995,"threshold_uncertainty_score":0.99982435},"labels":[],"label_agreement":null},{"id":"W2091944568","doi":"10.1167/11.11.1160","title":"Segmentation mechanisms are sensitive to and can segment by higher-order statistics in naturalistic textures","year":2011,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Texture (cosmology); Orientation (vector space); Segmentation; Boundary (topology); Pattern recognition (psychology); Phase (matter); Artificial intelligence; Computer science; Mathematics; Geometry; Physics; Image (mathematics); Mathematical analysis","score_opus":0.012560711974032246,"score_gpt":0.2515151070197386,"score_spread":0.23895439504570637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091944568","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017348867,0.000084424,0.9810642,0.00096497923,0.00039783833,0.00009242365,0.000013192299,0.000004264928,0.000029807343],"genre_scores_gemma":[0.701018,0.0000288987,0.29831174,0.00056283234,0.000033168646,6.045819e-7,0.0000011127241,0.0000039177858,0.00003973784],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99919826,0.00010442625,0.00023121765,0.00013004437,0.00021863932,0.000117425225],"domain_scores_gemma":[0.9993656,0.00006230489,0.00020447477,0.00007748292,0.00019925517,0.000090825044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022740947,0.00009030344,0.00014935943,0.000097170945,0.000048957707,0.00006442168,0.00011986911,0.00003279486,0.000011067966],"category_scores_gemma":[0.00004356926,0.000068805624,0.000017219447,0.0001506723,0.000013799622,0.00022671305,0.00006547828,0.000105245344,0.0000014352808],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004368217,0.00067599275,0.0008733813,0.000059197708,0.00018472243,0.000850949,0.01632816,0.005881827,0.58903676,0.013973796,0.080710046,0.29098836],"study_design_scores_gemma":[0.005466598,0.0066935914,0.44782758,0.0012787008,0.0001735696,0.00027716032,0.0031722842,0.13216889,0.35340258,0.045643624,0.0021924537,0.0017029907],"about_ca_topic_score_codex":0.000054019278,"about_ca_topic_score_gemma":0.000047255322,"teacher_disagreement_score":0.68366915,"about_ca_system_score_codex":0.00005763817,"about_ca_system_score_gemma":0.000021002588,"threshold_uncertainty_score":0.2805812},"labels":[],"label_agreement":null},{"id":"W2096192494","doi":"10.1145/1390156.1390266","title":"On the quantitative analysis of deep belief networks","year":2008,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":432,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Computer science; Inference; Boltzmann machine; Artificial intelligence; Graphical model; Deep belief network; Deep learning; Estimator; Generative model; Belief propagation; Partition (number theory); Machine learning; Hidden variable theory; Theoretical computer science; Algorithm; Generative grammar; Mathematics; Statistics","score_opus":0.025398655419327634,"score_gpt":0.23775206171733126,"score_spread":0.21235340629800364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096192494","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0072278115,0.000091838396,0.9834032,0.00065705465,0.00008866107,0.00006448,6.4044957e-7,0.00002383144,0.008442496],"genre_scores_gemma":[0.9714012,0.000038955855,0.027621532,0.0007059567,0.00002091595,0.000004452216,0.0000010875159,0.0000029581677,0.00020292212],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99914044,0.00013966463,0.00017121805,0.00021118356,0.00018430791,0.00015317232],"domain_scores_gemma":[0.9985656,0.00076712546,0.00008529657,0.00044612173,0.00010140138,0.000034434768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022392013,0.000091390175,0.00020021661,0.00011286418,0.00018008087,0.00002387485,0.0005073103,0.000028217453,0.00015441197],"category_scores_gemma":[0.00007867698,0.000052099727,0.00016713169,0.0014316806,0.000097439115,0.00013127647,0.000089917885,0.00007109076,0.000014339719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006757614,0.000056397996,0.00034303605,3.4988005e-7,0.00054499955,0.00000386627,0.00062181096,0.636733,0.00007452495,0.35639483,0.002242726,0.0029776997],"study_design_scores_gemma":[0.000046940917,0.00007505771,0.0061494373,0.0000016015294,0.000055175682,4.7639003e-7,0.000038054884,0.9923226,0.0005104567,0.0006210424,0.00010926105,0.00006985508],"about_ca_topic_score_codex":0.00006003478,"about_ca_topic_score_gemma":0.000067848814,"teacher_disagreement_score":0.96417344,"about_ca_system_score_codex":0.000008801822,"about_ca_system_score_gemma":0.000012369949,"threshold_uncertainty_score":0.21245652},"labels":[],"label_agreement":null},{"id":"W2098617596","doi":"","title":"Multi-Prediction Deep Boltzmann Machines","year":2013,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":116,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Boltzmann machine; dBm; Restricted Boltzmann machine; Computer science; Train; Artificial intelligence; Inference; Probabilistic logic; Machine learning; Field (mathematics); Deep learning; Layer (electronics); Algorithm; Mathematics","score_opus":0.014587863853125178,"score_gpt":0.22425470366639977,"score_spread":0.20966683981327458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098617596","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028999613,0.00024377625,0.9934216,0.0004444055,0.0011892151,0.00032841152,0.0000022631477,0.00032347834,0.0011468921],"genre_scores_gemma":[0.98270875,0.0000045708325,0.016388342,0.00038670024,0.00019729346,0.00008628227,0.000016273665,0.000005718877,0.00020604767],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887824,0.000060909922,0.00044204795,0.00014702129,0.00024877742,0.00022300985],"domain_scores_gemma":[0.9991047,0.000020179546,0.00024587577,0.000221408,0.00032807793,0.00007975916],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0001635978,0.00014455477,0.00014024286,0.00011886451,0.00030558254,0.0015462348,0.0003685717,0.00006366338,0.000012016296],"category_scores_gemma":[0.000044422042,0.00011385715,0.00004085852,0.00029249402,0.00002694879,0.010430579,0.000075060976,0.000102470665,0.00026553278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042555057,0.00004303278,0.001313376,0.00026979973,0.000021923599,0.0000011063065,0.0036672044,0.16198123,0.002679079,0.000642927,0.008293755,0.8210823],"study_design_scores_gemma":[0.00018973435,0.000021036167,0.0027802947,0.000029520752,0.0000029904563,0.00001772703,0.0001304405,0.99336165,0.00015721687,0.00002598077,0.0031635026,0.00011990901],"about_ca_topic_score_codex":0.00015810874,"about_ca_topic_score_gemma":0.0000022598467,"teacher_disagreement_score":0.9798088,"about_ca_system_score_codex":0.000033550547,"about_ca_system_score_gemma":0.000024602274,"threshold_uncertainty_score":0.99949026},"labels":[],"label_agreement":null},{"id":"W2098779819","doi":"10.1111/cgf.12307","title":"Analogy‐driven 3D style transfer","year":2014,"lang":"en","type":"article","venue":"Computer Graphics Forum","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Analogy; Computer science; Set (abstract data type); Process (computing); Simple (philosophy); Transfer of learning; Artificial intelligence; Transformation (genetics); Programming language","score_opus":0.009397812953508665,"score_gpt":0.20348474148352577,"score_spread":0.1940869285300171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098779819","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015603391,0.0000648285,0.9943477,0.0016504878,0.0010593497,0.00012892972,0.0000025824354,0.00018552286,0.0010002769],"genre_scores_gemma":[0.8947055,0.000026022184,0.10168784,0.0031083478,0.0003894148,0.000009383047,0.000006170192,0.0000170936,0.0000502681],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982795,0.00017681583,0.0002553942,0.0005384813,0.00024383841,0.0005059715],"domain_scores_gemma":[0.9988384,0.00013262135,0.000040168954,0.00071879255,0.00011389407,0.00015607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027527066,0.00022728107,0.0002689308,0.00018436377,0.00026677366,0.00022229497,0.0010523018,0.00010341069,0.000015153256],"category_scores_gemma":[0.000009571748,0.00020504328,0.00018893465,0.0005195458,0.00010261292,0.00045001088,0.0002643986,0.00019787997,0.000052442658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008748477,0.00015235353,0.0028234913,0.000017150269,0.00013562596,0.000015271167,0.0005124273,0.0074566067,0.0003539838,0.77217835,0.020007214,0.19633879],"study_design_scores_gemma":[0.00034953104,0.00018087741,0.0020237018,0.0000141479495,0.000010482376,0.000008158587,0.0000034489449,0.9301721,0.00034259152,0.00562916,0.0609863,0.00027953487],"about_ca_topic_score_codex":0.000018319073,"about_ca_topic_score_gemma":0.000045273002,"teacher_disagreement_score":0.9227155,"about_ca_system_score_codex":0.000012167895,"about_ca_system_score_gemma":0.000024396219,"threshold_uncertainty_score":0.83614224},"labels":[],"label_agreement":null},{"id":"W2100717332","doi":"10.1109/tnn.2010.2073481","title":"High-Performance Reconfigurable Hardware Architecture for Restricted Boltzmann Machines","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Field-programmable gate array; Speedup; Modular design; Exploit; Parallel computing; Virtex; Embedded system; Artificial neural network; Reconfigurable computing; Computer architecture; Hardware acceleration; Hardware architecture; Computer hardware; Software; Operating system; Artificial intelligence","score_opus":0.01109397436070237,"score_gpt":0.21800306020283178,"score_spread":0.20690908584212941,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100717332","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025955498,0.000032023298,0.96615744,0.0014818787,0.005419212,0.00047649114,0.000026152778,0.0002869631,0.00016436838],"genre_scores_gemma":[0.96986705,0.000046106452,0.027930053,0.0006141602,0.00062919245,0.00013921679,0.000008884874,0.000033814744,0.00073152786],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99827075,0.00007848629,0.00031739508,0.0005947618,0.00019207229,0.00054651196],"domain_scores_gemma":[0.99860597,0.00030704172,0.00011050664,0.00068024034,0.0001342364,0.0001620273],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00013709706,0.00032079854,0.00028955823,0.0001463476,0.0006476154,0.00022893392,0.00073258654,0.00019441222,0.00006225833],"category_scores_gemma":[0.000010772474,0.00027176976,0.00018020922,0.00051215425,0.00007149666,0.00049912167,0.0000033702352,0.0008419091,0.000011754137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006174138,0.000049674687,0.000004383847,0.0000068353957,0.000025557854,0.0000024977292,0.000027630142,0.72907656,0.0031879959,0.000080562146,0.0013876385,0.2660889],"study_design_scores_gemma":[0.0005257236,0.00026051432,0.00020917205,0.000018171071,0.000024558754,0.000021496398,0.0000020105608,0.9737272,0.02139449,0.00018906772,0.0033012312,0.00032633005],"about_ca_topic_score_codex":0.000060781247,"about_ca_topic_score_gemma":0.00019458003,"teacher_disagreement_score":0.94391155,"about_ca_system_score_codex":0.000018047627,"about_ca_system_score_gemma":0.000030184432,"threshold_uncertainty_score":0.9999735},"labels":[],"label_agreement":null},{"id":"W2102166778","doi":"","title":"A Rate Distortion Approach for Semi-Supervised Conditional Random Fields","year":2009,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Discriminative model; Conditional entropy; Conditional random field; Entropy (arrow of time); Regularization (linguistics); Artificial intelligence; Mathematics; Mutual information; Maxima and minima; Information theory; Pattern recognition (psychology); Machine learning; Computer science; Principle of maximum entropy; Statistics","score_opus":0.01637336448854162,"score_gpt":0.2297908730047532,"score_spread":0.21341750851621158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102166778","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032503848,0.000033844677,0.991996,0.0015068197,0.00012228667,0.00026099608,0.0000038144628,0.000072097915,0.005679082],"genre_scores_gemma":[0.8364102,0.0000039982906,0.16084975,0.0015460624,0.00018603586,0.000032062428,0.000040572875,0.0000025585125,0.00092870876],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99929297,0.000055261076,0.00014215811,0.00025105744,0.00009402764,0.00016453785],"domain_scores_gemma":[0.9995543,0.00009574511,0.00003579014,0.00018697945,0.0000734437,0.00005378391],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022903747,0.00009246798,0.00012806611,0.000031147145,0.00013978171,0.000098736935,0.00023306803,0.00004734953,0.00003980811],"category_scores_gemma":[0.00003878806,0.00007378657,0.0000980171,0.000104839986,0.000015604784,0.00034956,0.000020122872,0.000044182303,0.000005538303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059018616,0.001029212,0.00012841605,0.00004470147,0.00019463788,0.0000093652725,0.0013324708,0.18401852,0.02371086,0.27129173,0.25105378,0.26659608],"study_design_scores_gemma":[0.0013649677,0.000099085955,0.00055787293,0.0000022617628,0.0000075019293,0.0000019644185,0.000010480683,0.9800909,0.004969902,0.010586883,0.002168495,0.00013965981],"about_ca_topic_score_codex":0.0000042366896,"about_ca_topic_score_gemma":0.0000012217487,"teacher_disagreement_score":0.8360852,"about_ca_system_score_codex":0.000015475225,"about_ca_system_score_gemma":0.00002408123,"threshold_uncertainty_score":0.3008929},"labels":[],"label_agreement":null},{"id":"W2105486361","doi":"","title":"Learning to Learn with Compound HD Models","year":2011,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Hierarchical Dirichlet process; Computer science; Artificial intelligence; Inference; Deep learning; Hierarchy; Machine learning; Prior probability; Boltzmann machine; Restricted Boltzmann machine; Hierarchical database model; Bayesian inference; Topic model; Process (computing); Bayesian probability; Bayesian network; Latent Dirichlet allocation; Data mining","score_opus":0.039020469088080816,"score_gpt":0.21039332941568145,"score_spread":0.17137286032760063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105486361","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056013437,0.000009104333,0.89907545,0.00020896891,0.00006556351,0.00007675817,6.507578e-8,0.000115567855,0.09484716],"genre_scores_gemma":[0.72777134,0.0000016622141,0.2689387,0.00033561728,0.000032917473,0.000004506265,1.9062212e-7,0.0000058853593,0.00290917],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921554,0.000054716453,0.00009199307,0.00027598004,0.00014268703,0.0002190874],"domain_scores_gemma":[0.9995126,0.000027158396,0.000027499285,0.00025299995,0.0000718931,0.00010782241],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013393731,0.000099632525,0.000112821304,0.000047695197,0.00013219821,0.0000970441,0.00039267697,0.000021517217,0.00008411173],"category_scores_gemma":[0.00000787457,0.00007115343,0.000025509255,0.00021954968,0.000021738784,0.0005113134,0.00015469364,0.00008829173,0.00013565092],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008726048,0.00020787308,0.001278204,0.000008439862,0.00012345529,0.00008700245,0.020128086,0.5973819,0.0022890596,0.15010624,0.0056560277,0.22264645],"study_design_scores_gemma":[0.0002388143,0.00054234604,0.0009982628,0.000014698811,0.000006618446,0.000013457393,0.0003176456,0.9820488,0.0061834566,0.003798504,0.005504192,0.0003331774],"about_ca_topic_score_codex":0.00020177057,"about_ca_topic_score_gemma":0.000052730556,"teacher_disagreement_score":0.72217,"about_ca_system_score_codex":0.000011140547,"about_ca_system_score_gemma":0.000021754799,"threshold_uncertainty_score":0.29015526},"labels":[],"label_agreement":null},{"id":"W2106439909","doi":"10.1162/neco_a_00158","title":"Quickly Generating Representative Samples from an RBM-Derived Process","year":2011,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Gibbs sampling; Herding; Sampling (signal processing); Exploit; Markov chain; Computer science; Algorithm; Markov process; Mixing (physics); Process (computing); Divergence (linguistics); Mathematics; Artificial intelligence; Machine learning; Statistics; Bayesian probability","score_opus":0.07464532759247174,"score_gpt":0.30442490654509974,"score_spread":0.22977957895262802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106439909","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39699107,0.000020776502,0.60223085,0.000091673544,0.00025482598,0.0001133716,0.0000034976329,0.0001160354,0.00017791433],"genre_scores_gemma":[0.78617454,0.0000016461883,0.21321368,0.0003341569,0.0002137687,0.000012617211,0.000032288244,0.000010351805,0.0000069533853],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984452,0.0002957783,0.00026034354,0.00054863974,0.000225818,0.00022423347],"domain_scores_gemma":[0.9991523,0.00011391675,0.00017365682,0.00025842397,0.00020310924,0.00009858802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012027736,0.0001683334,0.00017103115,0.00005907003,0.00025356023,0.00020318579,0.00042473493,0.00004608326,0.000032228294],"category_scores_gemma":[0.00005472661,0.00015499601,0.000049565253,0.0002456398,0.00004686804,0.0014454995,0.00010033034,0.000108300395,0.000015753847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009304521,0.00037246538,0.0057539367,0.000021278698,0.00013017387,0.00006028235,0.06410374,0.44703194,0.13370533,0.001885829,0.0008826722,0.3459593],"study_design_scores_gemma":[0.0002258361,0.00013039539,0.018590461,0.0000071755544,0.000008465119,0.0000027673643,0.00033740833,0.9380725,0.037291445,0.0051394156,0.0000053594954,0.00018873683],"about_ca_topic_score_codex":0.0006419101,"about_ca_topic_score_gemma":0.00006927308,"teacher_disagreement_score":0.4910406,"about_ca_system_score_codex":0.000018872073,"about_ca_system_score_gemma":0.00003497525,"threshold_uncertainty_score":0.6320554},"labels":[],"label_agreement":null},{"id":"W2107215445","doi":"10.1109/ita.2010.5454138","title":"A tutorial on stochastic approximation algorithms for training Restricted Boltzmann Machines and Deep Belief Nets","year":2010,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Boltzmann machine; MNIST database; Restricted Boltzmann machine; Deep belief network; Computer science; Boltzmann constant; Artificial intelligence; Divergence (linguistics); Classifier (UML); Algorithm; Belief propagation; Training set; Machine learning; Artificial neural network; Mathematical optimization; Mathematics","score_opus":0.02284832176213295,"score_gpt":0.25437778742591133,"score_spread":0.23152946566377838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107215445","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004434772,0.00001763211,0.99216205,0.0006636623,0.0016998987,0.00035748203,0.000003312494,0.000102832,0.00055834564],"genre_scores_gemma":[0.6051745,0.0000019352908,0.39312884,0.00022640597,0.0012458937,0.000060182345,0.000009366951,0.000012051235,0.00014086095],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903315,0.00003472446,0.00017387618,0.00036477012,0.00015537921,0.00023810934],"domain_scores_gemma":[0.99923104,0.0002919303,0.00006944119,0.00023167637,0.00008609335,0.000089847585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020118957,0.00014638217,0.00015610938,0.000083006824,0.00022454001,0.00022541248,0.00024043424,0.00007709049,0.000009165841],"category_scores_gemma":[0.00025321773,0.00011743762,0.00004294326,0.00016258459,0.00003621744,0.00033428398,0.00006439382,0.00013144795,0.0000033883277],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057133806,0.00009468196,0.00000874578,0.000009454304,0.00003754857,0.0000022470658,0.001766623,0.007002284,0.015318248,0.06146774,0.0011018186,0.9131335],"study_design_scores_gemma":[0.0005972272,0.0001831472,0.00039287945,0.0000059083377,0.000008135721,0.0000047881285,0.00001953719,0.9919466,0.00051967154,0.0051306207,0.001033931,0.00015760366],"about_ca_topic_score_codex":0.000030682262,"about_ca_topic_score_gemma":0.000046458856,"teacher_disagreement_score":0.9849443,"about_ca_system_score_codex":0.000008174917,"about_ca_system_score_gemma":0.00003191045,"threshold_uncertainty_score":0.47889674},"labels":[],"label_agreement":null},{"id":"W2110750681","doi":"","title":"Marginalized Denoising Auto-encoders for Nonlinear Representations","year":2014,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":111,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research","funders":"","keywords":"Computer science; Speedup; Regularization (linguistics); Artificial intelligence; Noise reduction; Encoder; Representation (politics); Machine learning; Noise (video); Process (computing); Range (aeronautics); Training (meteorology); Algorithm; Pattern recognition (psychology); Engineering; Law; Parallel computing","score_opus":0.023164919105381,"score_gpt":0.27235591848448554,"score_spread":0.24919099937910455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110750681","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002174959,0.000016360438,0.9895923,0.0026521333,0.00027433303,0.0001610249,0.0000014396273,0.000113499555,0.006971372],"genre_scores_gemma":[0.10577043,0.0000037594398,0.8910873,0.00071187,0.00022815647,0.00003818162,0.0000046407445,0.000007941273,0.0021477214],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991768,0.00007068586,0.00014887143,0.0002890878,0.000112869886,0.00020171386],"domain_scores_gemma":[0.9991591,0.0002685607,0.000049233044,0.00035725854,0.00010347329,0.00006239864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029611064,0.00008609916,0.00011618018,0.00004837562,0.00020688625,0.0001842505,0.00034981317,0.000029027316,0.000045946104],"category_scores_gemma":[0.00017176628,0.000073476214,0.00008002556,0.00016499776,0.000027972399,0.0003737447,0.00007682792,0.00003657177,0.000027395825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005621937,0.00024921942,0.00068014924,0.000047151847,0.00018018726,0.000004857003,0.0016650463,0.06354173,0.023751013,0.37541512,0.12750839,0.4069009],"study_design_scores_gemma":[0.0003181987,0.00003403625,0.00013987486,0.000004474771,0.0000070786705,0.0000015263356,0.000024730154,0.92780167,0.0052825045,0.004339231,0.0619388,0.00010787145],"about_ca_topic_score_codex":0.000040360894,"about_ca_topic_score_gemma":0.000017951577,"teacher_disagreement_score":0.86425996,"about_ca_system_score_codex":0.000012949538,"about_ca_system_score_gemma":0.000028207825,"threshold_uncertainty_score":0.2996273},"labels":[],"label_agreement":null},{"id":"W2110798204","doi":"10.7551/mitpress/7503.003.0024","title":"Greedy Layer-Wise Training of Deep Networks","year":2007,"lang":"en","type":"book-chapter","venue":"The MIT Press eBooks","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4704,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Training (meteorology); Layer (electronics); Computer science; Artificial intelligence; Geography; Materials science; Composite material; Meteorology","score_opus":0.08055135584822232,"score_gpt":0.2532535131225538,"score_spread":0.17270215727433147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110798204","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000015091418,0.0012660341,0.46819443,0.000020542131,0.0004007906,0.00024056443,0.0000036889462,0.0000526501,0.5298198],"genre_scores_gemma":[0.1223101,0.00021247094,0.025466138,0.00087892206,0.0028346577,0.00004223757,0.0000112591,0.00018684224,0.8480574],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980053,0.00008389567,0.0005262198,0.000509606,0.00041726266,0.00045772243],"domain_scores_gemma":[0.9976982,0.00034996952,0.00045726605,0.0012231378,0.00015793441,0.000113534115],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006693861,0.00042959425,0.0005556962,0.00008978524,0.0001830086,0.00011703749,0.0018162332,0.00031324071,0.000036266792],"category_scores_gemma":[0.000016729366,0.00031451526,0.00030418986,0.000017253065,0.00028594775,0.00010009645,0.0005901618,0.00054465624,0.000009603277],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028741322,0.000010539726,3.2943834e-7,0.000024179366,0.00033718097,0.00003991565,0.0023383207,0.009020125,0.00009271381,0.43674597,0.0012571772,0.5501048],"study_design_scores_gemma":[0.00073085877,0.0002391676,0.000015400114,0.00046937983,0.00042470236,0.00004885419,0.00003621306,0.30397898,0.0029705642,0.027403813,0.66228074,0.0014013047],"about_ca_topic_score_codex":0.00010008398,"about_ca_topic_score_gemma":0.00008846364,"teacher_disagreement_score":0.6610236,"about_ca_system_score_codex":0.000027005182,"about_ca_system_score_gemma":0.00004670768,"threshold_uncertainty_score":0.9999307},"labels":[],"label_agreement":null},{"id":"W2111838090","doi":"10.1162/neco.2010.08-09-1081","title":"Deep Belief Networks Are Compact Universal Approximators","year":2010,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":173,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Deep belief network; Artificial intelligence; Sigmoid function; Generative grammar; Deep neural networks; Deep learning; Computer science; Artificial neural network; Generative model; Expression (computer science); Mathematics; Theoretical computer science","score_opus":0.010136306833914668,"score_gpt":0.2242362151020559,"score_spread":0.21409990826814124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111838090","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04706401,0.000030226096,0.94959265,0.00078408036,0.0014936988,0.00015176223,8.6312076e-7,0.00020555804,0.0006771339],"genre_scores_gemma":[0.97758174,0.0000024479002,0.021703165,0.00032260708,0.0003340961,0.000001847165,0.000012666803,0.000012251863,0.000029183728],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884593,0.000092684466,0.00019121035,0.0003676266,0.00021422587,0.00028829926],"domain_scores_gemma":[0.99918866,0.00013230255,0.00016035931,0.00026260142,0.00012964942,0.00012643893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013992417,0.00017648199,0.00017967235,0.000086685955,0.0002531545,0.00024803856,0.00045207315,0.00008460143,0.000015613992],"category_scores_gemma":[0.000029522796,0.00016415624,0.0000840563,0.00038200256,0.00006031002,0.00069427944,0.00009955374,0.00032375322,0.00002380042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000097498305,0.000054385942,0.0017537277,0.0000043208706,0.000016710186,0.000018384168,0.0001857687,0.93898195,0.0014087632,0.0029823426,0.0016191462,0.052964732],"study_design_scores_gemma":[0.00025320117,0.000047105234,0.013407817,0.000004641822,0.0000065432687,0.000013424498,0.000025876363,0.9846346,0.00029739412,0.0006034981,0.0005243281,0.00018161502],"about_ca_topic_score_codex":0.000030376203,"about_ca_topic_score_gemma":0.000049844355,"teacher_disagreement_score":0.93051773,"about_ca_system_score_codex":0.000022720742,"about_ca_system_score_gemma":0.000019805657,"threshold_uncertainty_score":0.66940975},"labels":[],"label_agreement":null},{"id":"W2114153178","doi":"","title":"Rate-coded Restricted Boltzmann Machines for Face Recognition","year":2000,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":135,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Feature (linguistics); Pattern recognition (psychology); Artificial intelligence; Boltzmann machine; Computer science; Generative model; Facial recognition system; Face (sociological concept); Restricted Boltzmann machine; Feature vector; Detector; Support vector machine; Generative grammar; Artificial neural network","score_opus":0.022983319582882543,"score_gpt":0.2413044029940622,"score_spread":0.21832108341117965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114153178","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00805162,0.000043483233,0.9759828,0.0016178759,0.00020535699,0.00029952425,0.000010063804,0.000185324,0.013603981],"genre_scores_gemma":[0.5872632,0.00009342202,0.38989663,0.0018647368,0.00045648037,0.00010590942,0.00006240198,0.000022292938,0.020234907],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991334,0.00008401546,0.00016452097,0.00031337285,0.00008320064,0.00022147752],"domain_scores_gemma":[0.9994179,0.00014489958,0.00003553312,0.00025482193,0.000086010055,0.000060861392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014011696,0.0001174505,0.00012310181,0.000044347307,0.00015966328,0.00015621017,0.00031291874,0.000047231504,0.0003870159],"category_scores_gemma":[0.000054527332,0.000095238036,0.00006928241,0.00026164437,0.000017285765,0.00046701776,0.000030074945,0.000048236674,0.0001856417],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049606107,0.0000652732,0.000014593599,0.0000055777227,0.000026266905,0.00000270201,0.0001488931,0.0026898482,0.0059850793,0.0009992983,0.029674605,0.96033823],"study_design_scores_gemma":[0.00076400745,0.0001406805,0.001283778,0.000011699743,0.0000135736,0.000003792997,0.000013267227,0.92107147,0.028095055,0.012122436,0.036157813,0.00032241445],"about_ca_topic_score_codex":0.000061020233,"about_ca_topic_score_gemma":0.00002045194,"teacher_disagreement_score":0.96001583,"about_ca_system_score_codex":0.00001191659,"about_ca_system_score_gemma":0.00002117623,"threshold_uncertainty_score":0.42375526},"labels":[],"label_agreement":null},{"id":"W2115096495","doi":"10.1145/1553374.1553505","title":"Factored conditional restricted Boltzmann Machines for modeling motion style","year":2009,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":361,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Boltzmann machine; Computer science; Motion (physics); Style (visual arts); Artificial intelligence; Artificial neural network; Geography","score_opus":0.024916068292754192,"score_gpt":0.25572879288103917,"score_spread":0.23081272458828497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115096495","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031228669,0.000027805221,0.9937799,0.0014630343,0.00014684058,0.00017313963,0.000009911768,0.00012433683,0.0011521868],"genre_scores_gemma":[0.86282504,0.000002890671,0.13629095,0.00040403655,0.00017147585,0.000007853111,0.000042376323,0.0000033818644,0.00025200937],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924433,0.00003060387,0.00015572253,0.00025507208,0.00013479835,0.00017946633],"domain_scores_gemma":[0.9995391,0.000052145304,0.000040040315,0.00018196994,0.00013241376,0.000054348202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007689799,0.00010078749,0.00010560403,0.000062171865,0.00016515591,0.0001288306,0.00024534343,0.00004093171,0.00002454874],"category_scores_gemma":[0.000050723,0.00008353059,0.00006871538,0.00014584837,0.000008601617,0.00051513914,0.000025866315,0.000043883967,0.000007791578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004324908,0.00023381581,0.00006901691,0.000006975685,0.000049357022,0.000003762465,0.00026725186,0.622377,0.025693873,0.19701028,0.014570083,0.13967533],"study_design_scores_gemma":[0.00026187705,0.00006507448,0.0010226128,0.0000026031385,0.000003830783,0.0000011843038,0.000005866197,0.9672909,0.0015818046,0.029355943,0.0003012419,0.00010711071],"about_ca_topic_score_codex":0.000019168467,"about_ca_topic_score_gemma":0.000004085821,"teacher_disagreement_score":0.85970217,"about_ca_system_score_codex":0.000018656105,"about_ca_system_score_gemma":0.000020298568,"threshold_uncertainty_score":0.34062785},"labels":[],"label_agreement":null},{"id":"W2115595010","doi":"10.48550/arxiv.1312.6110","title":"Learning Generative Models with Visual Attention","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":86,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Generative model; Computer science; Generative grammar; Artificial intelligence; Inference; Machine learning","score_opus":0.05209607952777962,"score_gpt":0.1778900880922505,"score_spread":0.12579400856447087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115595010","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13561644,0.000035563873,0.86147296,0.00008239714,0.00025738837,0.00027204782,0.000001965878,0.00017218637,0.0020890166],"genre_scores_gemma":[0.9792134,0.00010571234,0.01678433,0.00006390011,0.00016265373,0.000003040646,0.000019421681,0.000022783126,0.0036247289],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99784887,0.00032423157,0.00016556513,0.0011649841,0.00012124689,0.00037511313],"domain_scores_gemma":[0.9986102,0.00006088377,0.0002731377,0.0005788831,0.0003216516,0.00015524996],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016706082,0.00037002203,0.0003445787,0.00017531826,0.00030762696,0.00032559657,0.00089670287,0.00021806658,0.00003856607],"category_scores_gemma":[0.000011275519,0.00035257553,0.00016455658,0.0003963925,0.000106881074,0.0010865093,0.0012072441,0.00062546314,0.00009618897],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013581108,0.000046360772,0.0003045462,0.000012443804,0.00011702778,0.00006265967,0.00019590043,0.9661555,0.00013462275,0.031567734,0.00016879878,0.00122079],"study_design_scores_gemma":[0.00030450587,0.00014474514,0.00027431682,0.00006246215,0.00005541123,0.0000025399283,0.000103139755,0.98346555,0.00022775639,0.014820768,0.00009308581,0.00044571984],"about_ca_topic_score_codex":0.00021506635,"about_ca_topic_score_gemma":0.000030954114,"teacher_disagreement_score":0.84468865,"about_ca_system_score_codex":0.00014052617,"about_ca_system_score_gemma":0.0001424039,"threshold_uncertainty_score":0.99989265},"labels":[],"label_agreement":null},{"id":"W2117499988","doi":"","title":"The Difficulty of Training Deep Architectures and the Effect of Unsupervised Pre-Training","year":2009,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":323,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Artificial intelligence; Computer science; Initialization; Robustness (evolution); Deep learning; Training (meteorology); Machine learning; Deep neural networks; Unsupervised learning; Training set","score_opus":0.051975758152895186,"score_gpt":0.3078173894272081,"score_spread":0.2558416312743129,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117499988","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02852775,0.0000779141,0.9686359,0.0016015804,0.00019374759,0.00016077604,0.000020570702,0.000009007502,0.00077276526],"genre_scores_gemma":[0.9907714,0.00012861313,0.008945464,0.00007481471,0.000052375817,0.0000052892583,0.0000024558826,0.0000025427348,0.000017038768],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887705,0.00021496441,0.00033090368,0.00018473009,0.0002554294,0.0001369002],"domain_scores_gemma":[0.99743176,0.0020752088,0.00015208121,0.00015087731,0.00015241951,0.00003765902],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059365045,0.00011891731,0.00019588236,0.000041664476,0.00016896806,0.00015665287,0.0004354919,0.000028919061,0.000009269998],"category_scores_gemma":[0.0007153387,0.00006370814,0.00003697781,0.00008065949,0.00045948505,0.000053908738,0.000055695335,0.000117940755,6.4817647e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001662374,0.0000071258796,0.000011166026,0.0000022125826,0.000019331093,8.856098e-7,0.0036807284,0.0013723038,0.0008520117,0.43898973,0.0000048090947,0.5548935],"study_design_scores_gemma":[0.00011211324,0.00045723448,0.0011427732,0.00004265944,0.000012887913,0.000004723776,0.00065351115,0.80071,0.008951396,0.1878019,0.00002558819,0.000085186926],"about_ca_topic_score_codex":0.000025941235,"about_ca_topic_score_gemma":0.000056119577,"teacher_disagreement_score":0.9622437,"about_ca_system_score_codex":0.000005448499,"about_ca_system_score_gemma":0.000028466102,"threshold_uncertainty_score":0.25979424},"labels":[],"label_agreement":null},{"id":"W2120001410","doi":"10.1109/icip.2008.4712326","title":"A nonlocal-means approach to exemplar-based inpainting","year":2008,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":184,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inpainting; Artificial intelligence; Image (mathematics); Similarity (geometry); Computer science; Sample (material); Pixel; Computer vision; Pattern recognition (psychology); Function (biology)","score_opus":0.027624160402231097,"score_gpt":0.2148781973603699,"score_spread":0.1872540369581388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120001410","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00093857927,0.000011295887,0.94492483,0.0011494786,0.00012450242,0.00014902512,3.9777018e-7,0.00016410627,0.052537806],"genre_scores_gemma":[0.51487625,5.983322e-7,0.48269615,0.0018449269,0.000086240405,0.000012927401,6.9557393e-7,0.00000592294,0.00047627892],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987956,0.00007752056,0.00016815698,0.00040981188,0.00022234772,0.00032651657],"domain_scores_gemma":[0.9992227,0.00006354305,0.000032287346,0.00045312927,0.00007779669,0.000150576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024212763,0.00013618331,0.00015428546,0.00009057579,0.00025400784,0.000082681465,0.00058561657,0.0000402642,0.000021269607],"category_scores_gemma":[0.00006196495,0.00011317326,0.00007495664,0.0005181522,0.000027477847,0.00024887896,0.00015769109,0.00008123367,0.00011153181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000415598,0.0012550605,0.0026050352,0.000043177304,0.00010451115,0.00012354864,0.005390985,0.6349936,0.019014198,0.043188624,0.14101677,0.1522229],"study_design_scores_gemma":[0.00018624577,0.000045141733,0.00034802212,0.0000058741894,0.0000020351006,0.00001077346,0.000029763361,0.9765035,0.009508025,0.000042504143,0.013116705,0.0002014332],"about_ca_topic_score_codex":0.000054614422,"about_ca_topic_score_gemma":0.000005561803,"teacher_disagreement_score":0.51393765,"about_ca_system_score_codex":0.00002417842,"about_ca_system_score_gemma":0.00006648376,"threshold_uncertainty_score":0.46150714},"labels":[],"label_agreement":null},{"id":"W2120190345","doi":"10.1109/cvpr.2007.383036","title":"Unsupervised Learning of Image Transformations","year":2007,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":184,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Conditional random field; Computer science; Affine transformation; Artificial intelligence; Transformation (genetics); Invariant (physics); Transformation geometry; Inference; Pattern recognition (psychology); Probabilistic logic; Factorial; Field (mathematics); Set (abstract data type); Image (mathematics); Mathematics","score_opus":0.009036694890710533,"score_gpt":0.22830365980622622,"score_spread":0.21926696491551567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120190345","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030315046,0.000022772181,0.9466741,0.00023738909,0.000058681042,0.000045272656,2.1401489e-7,0.00005110379,0.049878966],"genre_scores_gemma":[0.8038132,0.0000068239983,0.19585551,0.000052997635,0.000020967775,5.872908e-7,6.2947447e-7,0.0000020392267,0.0002472325],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99948543,0.000025445452,0.00016296287,0.000089915935,0.00010193479,0.00013432719],"domain_scores_gemma":[0.9996571,0.00007331066,0.000029049585,0.00012807368,0.00007366203,0.000038827024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033918986,0.000050018374,0.00007496779,0.000057442066,0.00007087628,0.00002923292,0.00021668531,0.000019506137,0.000076306926],"category_scores_gemma":[0.000021749805,0.00004141643,0.00004726001,0.00024159533,0.000023699144,0.0004702454,0.000026316886,0.000053404077,0.000020116848],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001651466,0.00016645972,0.0008700136,0.00003092131,0.00006263952,0.00000975569,0.005814887,0.010152359,0.31860995,0.17516601,0.0018499559,0.4872505],"study_design_scores_gemma":[0.0004723415,0.00011090996,0.006010205,0.000012339302,0.000008306862,0.000004493049,0.00040037223,0.516143,0.46653968,0.0011834768,0.008895874,0.00021900222],"about_ca_topic_score_codex":0.00002217827,"about_ca_topic_score_gemma":0.0000084163385,"teacher_disagreement_score":0.8007817,"about_ca_system_score_codex":0.000005838306,"about_ca_system_score_gemma":0.0000136667795,"threshold_uncertainty_score":0.16889131},"labels":[],"label_agreement":null},{"id":"W2120536363","doi":"10.1109/icsmc.2009.5346016","title":"On video textures generation: A comparison between different dimensionality reduction techniques","year":2009,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Isomap; Computer science; Artificial intelligence; Principal component analysis; Dimensionality reduction; Pattern recognition (psychology); Computer vision; Video quality; Texture synthesis; Kernel principal component analysis; Nonlinear dimensionality reduction; Image texture; Image processing; Kernel method; Support vector machine; Image (mathematics)","score_opus":0.0337194387480269,"score_gpt":0.28842046059354254,"score_spread":0.25470102184551563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120536363","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032652516,0.000055195087,0.9580167,0.0053560976,0.0002450267,0.00019721333,0.0000012382451,0.0002669927,0.0032090025],"genre_scores_gemma":[0.95159787,0.0000056001827,0.046871178,0.00053669256,0.00068424793,0.0000076942915,0.00001136391,0.000003687452,0.0002816809],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987453,0.00013235694,0.00025490287,0.0004051581,0.0002779068,0.00018433956],"domain_scores_gemma":[0.9992918,0.000060148082,0.00008119235,0.00040982655,0.00007780293,0.000079245314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017521053,0.00016651937,0.00021943584,0.00006732537,0.00023927684,0.00016499148,0.00028869306,0.000069624126,0.00004058158],"category_scores_gemma":[0.000024610325,0.00012015929,0.00007622576,0.00016076448,0.000025852429,0.00028963556,0.000055559765,0.00012341487,0.000013496854],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018780329,0.00042095216,0.00034534553,0.0000025980678,0.000045620447,0.0000028223612,0.00018194086,0.002092036,0.116019905,0.12706947,0.1375089,0.61629164],"study_design_scores_gemma":[0.00020926718,0.0006505697,0.021422215,0.000025400292,0.000018069186,0.0000043899695,0.000010131116,0.054167524,0.8946725,0.024732536,0.0036704834,0.0004168784],"about_ca_topic_score_codex":0.000015753889,"about_ca_topic_score_gemma":0.0000037033622,"teacher_disagreement_score":0.9189453,"about_ca_system_score_codex":0.00004836574,"about_ca_system_score_gemma":0.000014821611,"threshold_uncertainty_score":0.48999536},"labels":[],"label_agreement":null},{"id":"W2121331909","doi":"","title":"Generating more realistic images using gated MRF's","year":2010,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Computer science; Inpainting; Pixel; Probabilistic logic; Pattern recognition (psychology); Set (abstract data type); Statistical model; Latent variable; Image (mathematics); Computer vision; Generative model; Image resolution; Generative grammar","score_opus":0.01859920218874686,"score_gpt":0.26075077497891375,"score_spread":0.24215157279016689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121331909","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040064506,0.00008330918,0.956621,0.00029690802,0.0016411731,0.0002251445,0.0000062572794,0.00028085455,0.0007808462],"genre_scores_gemma":[0.9540377,0.000001302426,0.045154132,0.00032718142,0.00037990318,0.000010374482,0.000017576891,0.000009048377,0.00006273183],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985948,0.00006383815,0.00053409394,0.00019171185,0.0003209272,0.0002945889],"domain_scores_gemma":[0.9987279,0.000037604612,0.00040292778,0.00030918975,0.00042717438,0.000095160525],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00035024816,0.00018447179,0.0001912383,0.00013457949,0.0005229588,0.0018753775,0.00043954307,0.00009049612,0.0000049934274],"category_scores_gemma":[0.00014236945,0.0001557925,0.00004416139,0.00042425998,0.00005490374,0.005645065,0.000096998825,0.00023682171,0.00001670272],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008625717,0.000027446436,0.00027351588,0.00034551605,0.00002261335,0.000009298166,0.0032923848,0.6970004,0.13040076,0.002118555,0.0027735056,0.16372736],"study_design_scores_gemma":[0.00013793737,0.000012209554,0.0000857714,0.000046494242,0.0000066454695,0.00007323861,0.00011879038,0.9941469,0.003357136,0.000017992581,0.0018072603,0.00018966124],"about_ca_topic_score_codex":0.00018366093,"about_ca_topic_score_gemma":0.0000036754616,"teacher_disagreement_score":0.9139732,"about_ca_system_score_codex":0.000030024476,"about_ca_system_score_gemma":0.000097519995,"threshold_uncertainty_score":0.99916077},"labels":[],"label_agreement":null},{"id":"W2123284177","doi":"10.48550/arxiv.1206.6434","title":"A Generative Process for Sampling Contractive Auto-Encoders","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Jacobian matrix and determinant; Representation (politics); Encoder; Manifold (fluid mechanics); Generative model; Computer science; Generative grammar; Algorithm; Invariant (physics); Boltzmann machine; Mathematics; Transformation (genetics); Artificial intelligence; Pattern recognition (psychology); Applied mathematics; Artificial neural network; Statistics","score_opus":0.11733918508137181,"score_gpt":0.22639306920465493,"score_spread":0.10905388412328312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123284177","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030349704,0.00006137935,0.96755916,0.0001434059,0.0003752675,0.0003134212,0.000007619225,0.000093818795,0.0010962377],"genre_scores_gemma":[0.9826856,0.000012973943,0.016418053,0.00022565568,0.00023718014,0.000004006075,0.0000032618243,0.000011327311,0.00040193644],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880177,0.00008621114,0.00011733634,0.00045326928,0.000058719364,0.0004826859],"domain_scores_gemma":[0.9989394,0.00024812925,0.000121295365,0.0003008095,0.00020892665,0.00018145076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002569414,0.0001798568,0.0001946278,0.00008524493,0.00033124638,0.0000711096,0.0004954754,0.000075860335,0.000016919113],"category_scores_gemma":[0.00008345365,0.0001827989,0.000119316945,0.00041476553,0.00007218738,0.0017065924,0.00009363514,0.000108997585,0.000024465038],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013853096,0.00035346075,0.0027601412,0.00003060929,0.00029232606,0.000017433418,0.003855325,0.6044669,0.0029710392,0.37928358,0.00074636587,0.005084293],"study_design_scores_gemma":[0.00067039503,0.00007626666,0.0005978066,0.000013079781,0.00004595423,0.0000029879704,0.0005209532,0.97879606,0.005874196,0.011262535,0.0018010548,0.0003387304],"about_ca_topic_score_codex":0.000017822986,"about_ca_topic_score_gemma":0.000009037763,"teacher_disagreement_score":0.9523359,"about_ca_system_score_codex":0.000090592664,"about_ca_system_score_gemma":0.00008030417,"threshold_uncertainty_score":0.7454323},"labels":[],"label_agreement":null},{"id":"W2125113755","doi":"","title":"A Better Way to Pretrain Deep Boltzmann Machines","year":2012,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":106,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"MNIST database; Boltzmann machine; Computer science; Restricted Boltzmann machine; Artificial intelligence; Deep belief network; Deep learning; Layer (electronics); Boltzmann constant; Generative grammar; Generative model; Pattern recognition (psychology); Machine learning; Algorithm","score_opus":0.014542773663114903,"score_gpt":0.2387916199599926,"score_spread":0.2242488462968777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125113755","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009534892,0.00029973892,0.9837146,0.0011517529,0.0017896191,0.00030286636,0.0000024105273,0.0001976318,0.0030065128],"genre_scores_gemma":[0.9853023,8.1801505e-7,0.011998014,0.0018945002,0.0006150115,0.000052573097,0.000007027254,0.000006757988,0.000122967],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872935,0.00007484727,0.00039586253,0.0001245014,0.00029924323,0.00037617254],"domain_scores_gemma":[0.9992371,0.00002872373,0.00017813523,0.00023633057,0.0001563525,0.0001633443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038752635,0.00015848258,0.00016028056,0.00013845353,0.00023952224,0.00088611216,0.00040360395,0.000057178662,0.000007168807],"category_scores_gemma":[0.000059281698,0.0001243911,0.000042259704,0.0003874329,0.000017099268,0.007782174,0.00010356838,0.00009913683,0.00018977019],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001080536,0.00003572588,0.0019331068,0.00024603197,0.000018601397,8.6387894e-7,0.014695158,0.026740404,0.000852829,0.0018676148,0.011546652,0.9420522],"study_design_scores_gemma":[0.0001294324,0.000032001346,0.0025516779,0.000048069447,0.0000047163303,0.00002585297,0.00012334963,0.9598376,0.0005000659,0.000023893068,0.03650178,0.00022152212],"about_ca_topic_score_codex":0.000025468986,"about_ca_topic_score_gemma":0.0000015808284,"teacher_disagreement_score":0.97576743,"about_ca_system_score_codex":0.000037879534,"about_ca_system_score_gemma":0.000014829809,"threshold_uncertainty_score":0.85448},"labels":[],"label_agreement":null},{"id":"W2126229007","doi":"","title":"On the Representational Efficiency of Restricted Boltzmann Machines","year":2013,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Boltzmann machine; Restricted Boltzmann machine; Computer science; Type (biology); Function (biology); Generative model; Simple (philosophy); Series (stratigraphy); Upper and lower bounds; Exponential function; Theoretical computer science; Artificial neural network; Probability density function; Generative grammar; Artificial intelligence; Algorithm; Mathematics","score_opus":0.013529553574904997,"score_gpt":0.22884517678926608,"score_spread":0.2153156232143611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126229007","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06349205,0.000022032089,0.9025402,0.0061138994,0.00018172544,0.00021137674,8.325103e-7,0.00004202117,0.027395833],"genre_scores_gemma":[0.9788517,0.0000027541066,0.019678708,0.0004529106,0.00004357663,0.000013715256,5.4483763e-7,0.000002339428,0.0009537592],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931145,0.00008314162,0.00014069032,0.00016302856,0.0001972125,0.00010448684],"domain_scores_gemma":[0.9990172,0.00044275043,0.000057228473,0.00034989635,0.000107667074,0.000025277506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007497951,0.00006160008,0.00006653768,0.000037763322,0.000088912224,0.000067699075,0.00047598104,0.000015963064,0.0004172862],"category_scores_gemma":[0.00017012551,0.000032568234,0.00004100932,0.00028988806,0.00004430416,0.00018720857,0.00009127789,0.000046291847,0.000096843774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008580101,0.00025544246,0.0017289614,0.0000047512945,0.000047082485,0.000003270598,0.0004616942,0.020910503,0.0152727,0.7206179,0.20127504,0.03941409],"study_design_scores_gemma":[0.00014863788,0.00008690773,0.072154775,0.0000070185442,0.0000027707542,0.0000019013816,0.000028185654,0.88771963,0.0103979,0.029037893,0.00030539872,0.000108985136],"about_ca_topic_score_codex":0.00027758736,"about_ca_topic_score_gemma":0.000002914247,"teacher_disagreement_score":0.9153596,"about_ca_system_score_codex":0.000004420851,"about_ca_system_score_gemma":0.00001801844,"threshold_uncertainty_score":0.45689917},"labels":[],"label_agreement":null},{"id":"W2134653808","doi":"","title":"Modeling image patches with a directed hierarchy of Markov random fields","year":2007,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":103,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Inference; Markov random field; Hierarchy; Generative model; Markov chain; Generative grammar; Artificial intelligence; Hidden Markov model; Markov process; Layer (electronics); Image (mathematics); Variable-order Markov model; Markov model; Algorithm; Pattern recognition (psychology); Machine learning; Mathematics; Image segmentation; Statistics","score_opus":0.009046311200374649,"score_gpt":0.21600189472252662,"score_spread":0.206955583522152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134653808","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028347027,0.0000544639,0.96218467,0.0002700705,0.000069655376,0.000108775275,5.41443e-7,0.00009673963,0.008868055],"genre_scores_gemma":[0.6608891,0.0000084241,0.33877122,0.000085990025,0.000039234594,0.0000020215803,5.438086e-7,0.0000042801958,0.00019920229],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990836,0.000049708764,0.00021350449,0.00023363509,0.00018446837,0.0002351221],"domain_scores_gemma":[0.9992665,0.00017002593,0.00004492174,0.00030343037,0.00014847546,0.00006663392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045090515,0.000111158304,0.00019314472,0.00007333476,0.00006334714,0.000050926723,0.00031641204,0.000042723994,0.000036159625],"category_scores_gemma":[0.00004088905,0.000075748976,0.000057901667,0.00030081486,0.0000416511,0.0003239934,0.00009061368,0.00008045561,0.0000026862476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019575714,0.0006267833,0.0020991468,0.000108825756,0.00052874093,0.00020366271,0.0064117783,0.112285696,0.06374425,0.006346107,0.0037605774,0.80192685],"study_design_scores_gemma":[0.0008134255,0.000076031036,0.00019180677,0.000018935907,0.000008063794,0.0000035433814,0.0000562888,0.9548652,0.043310657,0.00045601878,0.00006353197,0.00013645212],"about_ca_topic_score_codex":0.0002531636,"about_ca_topic_score_gemma":0.0001763459,"teacher_disagreement_score":0.84257954,"about_ca_system_score_codex":0.0000091409565,"about_ca_system_score_gemma":0.000032539076,"threshold_uncertainty_score":0.30889535},"labels":[],"label_agreement":null},{"id":"W2135181320","doi":"","title":"The Neural Autoregressive Distribution Estimator","year":2011,"lang":"en","type":"article","venue":"Edinburgh Research Explorer (University of Edinburgh)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":431,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Autoregressive model; Conditional probability distribution; Joint probability distribution; Autoencoder; Restricted Boltzmann machine; Computer science; Boltzmann machine; Marginal distribution; Probability distribution; Mathematics; Applied mathematics; Algorithm; Artificial intelligence; Artificial neural network; Statistics; Random variable","score_opus":0.10162534281393382,"score_gpt":0.2832050384575156,"score_spread":0.18157969564358178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135181320","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02463253,0.0007947284,0.9553958,0.0058428827,0.00274602,0.0007825105,0.000033766177,0.00025473518,0.009517014],"genre_scores_gemma":[0.9899911,0.00027220754,0.0075523094,0.000016700054,0.00038218882,0.000005137595,0.000011560699,0.000010827693,0.0017579678],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971005,0.00027389676,0.0002143132,0.0005607517,0.0010284457,0.0008221051],"domain_scores_gemma":[0.99699086,0.0006716175,0.00016682336,0.00089994515,0.000959914,0.00031086142],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001837412,0.00020202858,0.00026158188,0.00017830681,0.0017369194,0.00013341055,0.0024221372,0.000117644355,0.0007118123],"category_scores_gemma":[0.0004762464,0.00016670264,0.000189929,0.0008760798,0.0010395461,0.0013617165,0.0011612084,0.00051257556,0.000015928894],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030876076,0.00031136535,0.0010655564,0.000008609577,0.00022093975,0.0002616891,0.01723382,0.00032329783,0.0014132996,0.017737161,0.8658361,0.09527941],"study_design_scores_gemma":[0.0022071262,0.0013821741,0.010348818,0.00020159087,0.00007871784,0.000034511446,0.02338242,0.692209,0.009234337,0.045707323,0.21402562,0.0011883319],"about_ca_topic_score_codex":0.00030732405,"about_ca_topic_score_gemma":0.000021650436,"teacher_disagreement_score":0.96535856,"about_ca_system_score_codex":0.00012576078,"about_ca_system_score_gemma":0.00018789775,"threshold_uncertainty_score":0.9995627},"labels":[],"label_agreement":null},{"id":"W2135341757","doi":"","title":"The Recurrent Temporal Restricted Boltzmann Machine","year":2008,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":373,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Inference; Computer science; Heuristic; Probabilistic logic; Artificial intelligence; Boltzmann machine; Algorithm; Pixel; Motion (physics); Machine learning; Deep learning","score_opus":0.020788431152509057,"score_gpt":0.22700613922084484,"score_spread":0.20621770806833578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135341757","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026483268,0.000978696,0.97583735,0.005483546,0.00089205796,0.00015779419,0.0000013182832,0.0001811234,0.013819793],"genre_scores_gemma":[0.96153253,0.0003491994,0.033386737,0.0003085297,0.0001818378,0.000009746563,0.0000024877604,0.000005856789,0.0042230845],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990957,0.0000985973,0.00016253779,0.00022176119,0.00019371815,0.00022770869],"domain_scores_gemma":[0.9992486,0.000118617485,0.000050035786,0.0004470686,0.0000666791,0.00006896127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001290782,0.00009888025,0.000087792796,0.000027022676,0.00059854606,0.00009759265,0.0006429033,0.0000246899,0.000020034973],"category_scores_gemma":[0.000057852118,0.000055554356,0.00005762176,0.00031167746,0.000067502006,0.0002255146,0.00018033096,0.00009794127,0.00007043498],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054387896,0.00024003754,0.006071665,0.000003782238,0.000096207375,0.0001294674,0.0007261033,0.00092711137,0.0007582046,0.05953896,0.5423437,0.3891104],"study_design_scores_gemma":[0.00042487076,0.00018997342,0.022068476,0.000006543092,0.0000050713115,0.000052095293,0.000019063214,0.4821384,0.0023543744,0.0017350735,0.4906813,0.00032476327],"about_ca_topic_score_codex":0.00013961658,"about_ca_topic_score_gemma":0.00007259943,"teacher_disagreement_score":0.9588842,"about_ca_system_score_codex":0.00001555488,"about_ca_system_score_gemma":0.00004622095,"threshold_uncertainty_score":0.4603593},"labels":[],"label_agreement":null},{"id":"W2135354436","doi":"","title":"Learning Stochastic Feedforward Neural Networks","year":2013,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":100,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Boltzmann machine; Artificial intelligence; Conditional probability distribution; Artificial neural network; Perceptron; Sigmoid function; Hidden variable theory; Feed forward; Machine learning; Feedforward neural network; Algorithm; Pattern recognition (psychology); Mathematics; Statistics","score_opus":0.008129313795125234,"score_gpt":0.19831206509765822,"score_spread":0.19018275130253298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135354436","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022480723,0.0000534925,0.99172324,0.00090811163,0.0003798573,0.00013355572,3.7382854e-8,0.00019109469,0.0043625217],"genre_scores_gemma":[0.97464085,0.00000246383,0.022729974,0.0004932599,0.00022345451,0.000018915309,8.2109443e-7,0.0000079999845,0.001882283],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990354,0.00007695754,0.0001441989,0.00027505553,0.00013231853,0.0003360327],"domain_scores_gemma":[0.99940544,0.00010529555,0.000046000525,0.0002494388,0.000082538914,0.0001112803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010873859,0.00012511315,0.00012807005,0.000041650128,0.00017869468,0.00035522148,0.00044744698,0.000042187505,0.00031627942],"category_scores_gemma":[0.000042998603,0.00009787054,0.000064644766,0.00022575364,0.000029545781,0.00072520145,0.00020874829,0.00016726243,0.0002508439],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.217611e-7,0.0000086908385,0.00009887052,6.163586e-7,0.000009557559,0.0000011579132,0.00006730745,0.8846368,0.00011914628,0.0019737638,0.0028838115,0.11019961],"study_design_scores_gemma":[0.000091130234,0.000056995636,0.0011369247,0.000002461232,0.0000026276591,0.00000396779,0.000027764932,0.99778616,0.000053365107,0.0003371805,0.00036706618,0.00013432447],"about_ca_topic_score_codex":0.000101899976,"about_ca_topic_score_gemma":0.0000039838637,"teacher_disagreement_score":0.97239274,"about_ca_system_score_codex":0.0000133213525,"about_ca_system_score_gemma":0.0000091562815,"threshold_uncertainty_score":0.3991045},"labels":[],"label_agreement":null},{"id":"W2135624716","doi":"10.1109/icdm.2009.27","title":"A Deep Non-linear Feature Mapping for Large-Margin kNN Classification","year":2009,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":87,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Margin (machine learning); Pattern recognition (psychology); k-nearest neighbors algorithm; Autoencoder; Benchmark (surveying); Dimensionality reduction; Feature (linguistics); Deep learning; Metric (unit); Feature extraction; Machine learning","score_opus":0.023442518297408697,"score_gpt":0.25905084412238333,"score_spread":0.23560832582497462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135624716","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010699679,0.000052700274,0.9868355,0.008329456,0.00021664948,0.0002787352,0.000001309548,0.000089992565,0.004088666],"genre_scores_gemma":[0.47514248,0.00000956177,0.5211441,0.0015911566,0.00031477277,0.00001667931,0.0000087838525,0.000005031108,0.0017674841],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909395,0.000029404771,0.00013292761,0.00033831495,0.000118597985,0.00028681164],"domain_scores_gemma":[0.9993499,0.00005992361,0.00006095393,0.00034681198,0.000115771756,0.000066669105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023928139,0.00011949687,0.00013411853,0.0000615035,0.00018787477,0.00012408943,0.0003917062,0.00007312298,0.000015978658],"category_scores_gemma":[0.000044954497,0.00009864835,0.000087524284,0.00027553635,0.000007725984,0.0003831629,0.000040565552,0.00007703126,0.000030208907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000466685,0.0004519074,0.00024131368,0.00003213678,0.0000879854,0.0000090473095,0.001968311,0.006899839,0.054430865,0.24805595,0.14446256,0.54331344],"study_design_scores_gemma":[0.00030327687,0.00005397167,0.003094825,0.0000080117225,0.0000038332755,0.0000013895229,0.000054151726,0.9524405,0.0019484354,0.0012491244,0.040704343,0.0001381406],"about_ca_topic_score_codex":0.000002317363,"about_ca_topic_score_gemma":0.0000073075935,"teacher_disagreement_score":0.94554067,"about_ca_system_score_codex":0.00002436505,"about_ca_system_score_gemma":0.000026559388,"threshold_uncertainty_score":0.4022763},"labels":[],"label_agreement":null},{"id":"W2136163184","doi":"10.1162/neco.2010.01-09-953","title":"Learning to Represent Spatial Transformations with Factored Higher-Order Boltzmann Machines","year":2010,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":231,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Transformation (genetics); Multiplicative function; Boltzmann machine; Mathematics; Artificial intelligence; Filter (signal processing); Image (mathematics); Pixel; Tensor (intrinsic definition); Computer science; Algorithm; Pattern recognition (psychology); Artificial neural network; Computer vision; Geometry; Mathematical analysis","score_opus":0.011382037352796385,"score_gpt":0.24592227413558276,"score_spread":0.23454023678278638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136163184","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.198576,0.0000033476263,0.7972455,0.002713038,0.000555994,0.00019480642,0.0000012575831,0.00014070178,0.0005693512],"genre_scores_gemma":[0.94316643,5.8357557e-7,0.056254,0.00021881725,0.00020302676,0.000014238724,0.00001644446,0.000009695031,0.00011676895],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999007,0.00008708637,0.00017713514,0.00029239405,0.0002411794,0.0001952226],"domain_scores_gemma":[0.9994029,0.000080677775,0.00006731716,0.00017266767,0.00017790409,0.00009855635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008933407,0.00013790549,0.0001236723,0.00008810145,0.0002642628,0.00024169013,0.00023901573,0.000039216975,0.000026013819],"category_scores_gemma":[0.000030502775,0.0001087146,0.000037414262,0.00035292277,0.000024395325,0.0005996063,0.000052456006,0.00023940345,0.000027078044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002467547,0.000034937075,0.0009784206,0.0000051681623,0.000014903593,0.0000049712858,0.001430101,0.74081016,0.011228941,0.00045402744,0.0004136613,0.24460004],"study_design_scores_gemma":[0.0002718154,0.00020345737,0.03584676,0.000004812913,0.00000645156,0.000006694607,0.000013746943,0.9595754,0.0018602632,0.00022602949,0.001818265,0.000166262],"about_ca_topic_score_codex":0.00021248231,"about_ca_topic_score_gemma":0.00022191672,"teacher_disagreement_score":0.7445904,"about_ca_system_score_codex":0.000010821869,"about_ca_system_score_gemma":0.000023686243,"threshold_uncertainty_score":0.44332528},"labels":[],"label_agreement":null},{"id":"W2141122175","doi":"10.1109/tpami.2012.273","title":"Scaling Up Spike-and-Slab Models for Unsupervised Feature Learning","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal; Université de Montréal","funders":"Defense Advanced Research Projects Agency; Canadian Institute for Advanced Research","keywords":"Computer science; Inference; Artificial intelligence; Pattern recognition (psychology); Cognitive neuroscience of visual object recognition; Scaling; Spike (software development); Feature (linguistics); Boltzmann machine; Deep learning; Feature extraction; Algorithm; Machine learning; Mathematics","score_opus":0.022080934654375134,"score_gpt":0.24802817248773112,"score_spread":0.225947237833356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141122175","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025462918,0.00022430316,0.995782,0.0009497844,0.00016517902,0.00022468425,0.000010926811,0.000060904138,0.00003592374],"genre_scores_gemma":[0.9849686,0.0004502659,0.013503299,0.0003701635,0.000033292938,0.000059060578,0.000003997087,0.000012572452,0.00059875887],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986852,0.000089548426,0.0002477916,0.00054900686,0.00016390685,0.0002645608],"domain_scores_gemma":[0.99914443,0.0002307321,0.000074194555,0.0002857457,0.00012931634,0.00013560393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020221176,0.0002260757,0.0003208963,0.00026997086,0.00039064747,0.00033726788,0.0002763212,0.000077437995,0.00007527521],"category_scores_gemma":[0.0000073577357,0.00018621872,0.00022793036,0.00053831545,0.000050521863,0.0005155797,0.000007891636,0.00024881455,0.000010269238],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004393201,0.000025825726,0.000068712936,0.00000938267,0.00022203774,5.613233e-7,0.00034328454,0.30874148,0.0004894818,0.00004771262,0.000015730004,0.6900314],"study_design_scores_gemma":[0.00009753473,0.00006656814,0.0001739008,0.000016220998,0.00022821236,0.0000027287965,0.00008311318,0.9583619,0.040008187,0.0006726849,0.00007679294,0.00021214233],"about_ca_topic_score_codex":0.0009362322,"about_ca_topic_score_gemma":0.00019831685,"teacher_disagreement_score":0.9824223,"about_ca_system_score_codex":0.000015504167,"about_ca_system_score_gemma":0.000010979012,"threshold_uncertainty_score":0.7593779},"labels":[],"label_agreement":null},{"id":"W2145836866","doi":"10.1109/ccece.2008.4564577","title":"Reconstruction of handwritten digit images using autoencoder neural networks","year":2008,"lang":"en","type":"article","venue":"Conference proceedings - Canadian Conference on Electrical and Computer Engineering","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Autoencoder; Restricted Boltzmann machine; Artificial intelligence; Computer science; Pattern recognition (psychology); Artificial neural network; Numerical digit; Deep learning; Iterative reconstruction; Mathematics; Arithmetic","score_opus":0.019454013604217668,"score_gpt":0.19033444779977118,"score_spread":0.17088043419555352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145836866","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06103972,0.00010628929,0.9375201,0.0003104797,0.00027988153,0.0001628849,0.0000030562073,0.00010044852,0.00047715008],"genre_scores_gemma":[0.97246164,0.000098824115,0.027059523,0.0001310763,0.00019636686,0.000008639348,0.0000014426638,0.000014765108,0.000027707409],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830294,0.00001488149,0.0003270971,0.00054204586,0.00019745159,0.00061557273],"domain_scores_gemma":[0.99888134,0.00004880562,0.00011126137,0.00015276427,0.0003697568,0.00043610032],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000089936686,0.00030603498,0.00039047364,0.0003416259,0.00022689017,0.00028908212,0.00047330515,0.00013278473,0.000013451745],"category_scores_gemma":[0.00003147732,0.00029651317,0.0000705424,0.0005377859,0.00010669804,0.0006786355,0.00009117726,0.00033552712,0.0000013578506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046995552,0.00011911939,0.01066172,0.00011208964,0.0002286432,0.00012519596,0.0014307541,0.12480892,0.0065751704,0.097848184,0.0010054772,0.75703776],"study_design_scores_gemma":[0.00019011562,0.00016784212,0.0033995905,0.00007744678,0.00000954304,0.00020349905,0.000006116327,0.9942685,0.0010170279,0.00026102972,0.00006923988,0.00033010126],"about_ca_topic_score_codex":0.0012273693,"about_ca_topic_score_gemma":0.00008590393,"teacher_disagreement_score":0.91142195,"about_ca_system_score_codex":0.00008683683,"about_ca_system_score_gemma":0.00025643007,"threshold_uncertainty_score":0.9999487},"labels":[],"label_agreement":null},{"id":"W2149117060","doi":"10.1109/tip.2006.877410","title":"A global approach for solving evolutive heat transfer for image denoising and inpainting","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Inpainting; Partial differential equation; Discretization; Mathematical optimization; Domain (mathematical analysis); Computer science; Noise reduction; Applied mathematics; Heat equation; Algorithm; Block (permutation group theory); Mathematics; Image (mathematics); Artificial intelligence; Mathematical analysis","score_opus":0.012014017516776068,"score_gpt":0.24050397318524586,"score_spread":0.2284899556684698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149117060","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017790591,0.0003110412,0.99621326,0.0002557631,0.00015865675,0.0006971005,0.000038726736,0.00017733638,0.00036906035],"genre_scores_gemma":[0.5430654,0.0000034533589,0.4565819,0.00007088901,0.00010989863,0.000115953626,0.000002173244,0.000018563102,0.00003173822],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99819666,0.000046620997,0.00033890238,0.00069459,0.00018299211,0.00054023176],"domain_scores_gemma":[0.9992264,0.0001722987,0.000037652007,0.00019905408,0.00028227072,0.000082319166],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00038857554,0.00028763196,0.0002877777,0.00011524799,0.0011369693,0.0007991113,0.0002683795,0.00009138396,0.0000017221553],"category_scores_gemma":[0.000017072116,0.0002833159,0.00017129858,0.00040831664,0.00013552136,0.0016018708,0.0000040726095,0.00012576094,6.2983963e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030859245,0.00081998215,0.000037089954,0.0010107781,0.00014975436,0.000008828439,0.0020770698,0.13648342,0.3143536,0.00076586433,0.0005076756,0.54347736],"study_design_scores_gemma":[0.0009270662,0.00009312062,0.000044626584,0.000088514455,0.000069511436,0.000022638025,0.0001723076,0.9146229,0.08244251,0.0011046748,0.00006300751,0.00034909588],"about_ca_topic_score_codex":0.00007150665,"about_ca_topic_score_gemma":0.000029689709,"teacher_disagreement_score":0.77813953,"about_ca_system_score_codex":0.00011954271,"about_ca_system_score_gemma":0.00010039054,"threshold_uncertainty_score":0.9999619},"labels":[],"label_agreement":null},{"id":"W2149508559","doi":"10.1109/crv.2006.41","title":"Image Inpainting and Segmentation using Hierarchical Level Set Method","year":2006,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Inpainting; Artificial intelligence; Image (mathematics); Image segmentation; Computer vision; Set (abstract data type); Computer science; Segmentation; Level set (data structures); Pattern recognition (psychology)","score_opus":0.04128480416652987,"score_gpt":0.3028574363973616,"score_spread":0.26157263223083177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149508559","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0125402035,0.000019037796,0.9854934,0.0004398078,0.000068038695,0.000067976514,0.0000013428253,0.000038375252,0.0013318178],"genre_scores_gemma":[0.20217048,0.0000011370203,0.7974236,0.00016334755,0.000111212816,0.000001378815,0.0000018714886,0.0000039844545,0.0001229711],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992009,0.00014997875,0.00013666993,0.00024293496,0.00011057377,0.00015899059],"domain_scores_gemma":[0.99966204,0.00009741657,0.0000414081,0.00012601954,0.000038679722,0.00003445913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038817184,0.00008254695,0.00008884816,0.000049679693,0.00014673038,0.00023404462,0.00012210797,0.000026378175,0.000012354544],"category_scores_gemma":[0.000023330198,0.00007126387,0.000025314443,0.00014670433,0.00002929974,0.00040318255,0.00014323389,0.00006186784,0.000002699566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000823988,0.00006174435,0.0026963486,0.000019484185,0.00003411548,0.00001749602,0.0006314405,0.01307499,0.7137436,0.029641176,0.0031417029,0.23692964],"study_design_scores_gemma":[0.00015222093,0.0000129441,0.0032265063,0.00000444629,0.0000046973537,0.0000120946825,0.000029490671,0.96886706,0.024159225,0.0032429865,0.00017918763,0.00010912534],"about_ca_topic_score_codex":0.00038147013,"about_ca_topic_score_gemma":0.000027165255,"teacher_disagreement_score":0.95579207,"about_ca_system_score_codex":0.000015072219,"about_ca_system_score_gemma":0.000016855332,"threshold_uncertainty_score":0.29060563},"labels":[],"label_agreement":null},{"id":"W2149845449","doi":"","title":"Implicit Mixtures of Restricted Boltzmann Machines","year":2008,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Boltzmann machine; MNIST database; Mixture model; Parameterized complexity; Computer science; Restricted Boltzmann machine; Function (biology); Partition function (quantum field theory); Boltzmann constant; Mixing (physics); Feature (linguistics); Artificial intelligence; Statistical physics; Theoretical computer science; Algorithm; Deep learning; Physics","score_opus":0.015154704209542702,"score_gpt":0.22872283202998378,"score_spread":0.21356812782044107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149845449","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039260756,0.00022713501,0.9439576,0.00060136867,0.00020157531,0.000084977684,0.0000018550301,0.00009648819,0.015568196],"genre_scores_gemma":[0.92423904,0.0000475971,0.0744868,0.00020532553,0.00008207416,0.0000025826691,0.0000010235945,0.000004048528,0.0009314856],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993018,0.000045243458,0.00016659357,0.00019394151,0.00014164356,0.00015078089],"domain_scores_gemma":[0.99940014,0.000068931506,0.000058497317,0.0003404019,0.0000840867,0.00004794491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004659882,0.00008883201,0.00014221489,0.00006339319,0.000094614195,0.000017805081,0.0004401556,0.00003319232,0.000043425687],"category_scores_gemma":[0.00004117576,0.000065333814,0.0000621192,0.00032044656,0.000045941506,0.00021321702,0.00012447896,0.000047670248,0.000013836473],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059591002,0.0005484154,0.01817419,0.000036191264,0.00024673354,0.00015087792,0.00207766,0.00958386,0.44884834,0.101656675,0.28219625,0.13642123],"study_design_scores_gemma":[0.0010923125,0.0003807341,0.20519038,0.000024894976,0.000021167323,0.00013878678,0.000022385457,0.38755572,0.37970537,0.0074642785,0.017630657,0.00077332614],"about_ca_topic_score_codex":0.00022245655,"about_ca_topic_score_gemma":0.000008985041,"teacher_disagreement_score":0.8849783,"about_ca_system_score_codex":0.0000051731035,"about_ca_system_score_gemma":0.000029317653,"threshold_uncertainty_score":0.26642355},"labels":[],"label_agreement":null},{"id":"W2150529939","doi":"10.1145/1553374.1553506","title":"Using fast weights to improve persistent contrastive divergence","year":2009,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":281,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Markov chain; Computer science; Variance (accounting); Algorithm; Set (abstract data type); Divergence (linguistics); Markov chain Monte Carlo; Statistical physics; Artificial intelligence; Machine learning; Physics","score_opus":0.021919743668629987,"score_gpt":0.24568680120823722,"score_spread":0.22376705753960724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150529939","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060932008,0.000057125293,0.98693246,0.0011179406,0.0004765966,0.0001771528,0.00000193288,0.00006249454,0.0050810934],"genre_scores_gemma":[0.7989488,0.0000029067348,0.1992152,0.0011754574,0.00013565474,0.0000017969991,2.4808173e-7,0.0000026815371,0.00051721104],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893606,0.000040595456,0.00014385252,0.0003977274,0.00017903454,0.00030272573],"domain_scores_gemma":[0.9993592,0.000029413904,0.00003959975,0.0002815886,0.00012241809,0.00016780598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009597028,0.00013660923,0.00014615628,0.00005524118,0.00018652313,0.00014057681,0.0004551686,0.000031422143,0.00004782154],"category_scores_gemma":[0.000023971754,0.000107555155,0.00010779526,0.0002542568,0.000019129639,0.0004015881,0.00012657582,0.000055620905,0.000062076484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000061764666,0.000368709,0.0004024851,0.0000057521975,0.00020031017,0.000060820992,0.0039661834,0.052448347,0.31783608,0.077406995,0.004974374,0.54226816],"study_design_scores_gemma":[0.00028854716,0.0004629795,0.0030489746,0.000020167045,0.000026104815,0.00000709545,0.00014927391,0.938066,0.054624695,0.001283121,0.0016036496,0.00041940872],"about_ca_topic_score_codex":0.000051865845,"about_ca_topic_score_gemma":0.000005494151,"teacher_disagreement_score":0.8856176,"about_ca_system_score_codex":0.00004342757,"about_ca_system_score_gemma":0.000032887292,"threshold_uncertainty_score":0.4385972},"labels":[],"label_agreement":null},{"id":"W2153125595","doi":"10.1109/tpami.2012.269","title":"Learning with Hierarchical-Deep Models","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":235,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Computer science; Deep learning; Machine learning","score_opus":0.015050925652501376,"score_gpt":0.22827013586340825,"score_spread":0.21321921021090687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153125595","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016625448,0.000050020823,0.9971478,0.0006037092,0.000055783054,0.00012246422,0.0000025266438,0.00007565452,0.00027948644],"genre_scores_gemma":[0.9872453,0.00019717067,0.01177269,0.0003537767,0.000018349205,0.000037570167,0.000001692728,0.000010317047,0.00036309467],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864125,0.00012469631,0.00024018653,0.00050234585,0.0002368745,0.00025467324],"domain_scores_gemma":[0.99918497,0.0001343434,0.00007216656,0.00035689987,0.00010114121,0.0001504535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001292177,0.00020842325,0.0002739677,0.0002983977,0.00028634007,0.00027300077,0.00033631074,0.000046393172,0.0002554929],"category_scores_gemma":[0.0000022840206,0.00015051813,0.00015129971,0.00085198914,0.00007567125,0.00054221944,0.000005910034,0.00032030072,0.000048371716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027078431,0.000040299732,0.000080029255,0.0000021031594,0.0002082258,0.0000021884687,0.00023546781,0.48722672,0.000112874994,0.00004574181,0.0000022984068,0.51204133],"study_design_scores_gemma":[0.000055964836,0.00016836457,0.00027231046,0.000009562658,0.00015151521,0.0000048621555,0.000050693652,0.9777511,0.020682232,0.00062775175,0.000022542616,0.00020315172],"about_ca_topic_score_codex":0.0013960548,"about_ca_topic_score_gemma":0.0005575841,"teacher_disagreement_score":0.98558277,"about_ca_system_score_codex":0.000015510146,"about_ca_system_score_gemma":0.00001097684,"threshold_uncertainty_score":0.6137951},"labels":[],"label_agreement":null},{"id":"W2153346333","doi":"10.1609/aaai.v28i1.8924","title":"On the Challenges of Physical Implementations of RBMs","year":2014,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Implementation; Markov chain Monte Carlo; Physical system; Boltzmann machine; Computation; Software; Sampling (signal processing); Inference; Computer engineering; Focus (optics); Variety (cybernetics); Stochastic computing; Range (aeronautics); Theoretical computer science; Distributed computing; Machine learning; Computational science; Artificial intelligence; Deep learning; Algorithm; Software engineering; Bayesian probability","score_opus":0.08616196602842285,"score_gpt":0.30097166722354385,"score_spread":0.214809701195121,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153346333","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56044734,0.000074861484,0.32236436,0.03812897,0.0008746421,0.0014641734,0.000025371044,0.00008830362,0.076532006],"genre_scores_gemma":[0.99869263,0.000023657778,0.0010887055,0.00009112404,0.000062760344,0.0000143583,9.539351e-8,0.0000054400934,0.000021223708],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987975,0.000043224474,0.00035901877,0.0002555108,0.0003690287,0.00017575717],"domain_scores_gemma":[0.99831504,0.00047400958,0.00040296908,0.00029510196,0.00048014836,0.000032725744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050765084,0.00013567948,0.0002298438,0.00005760159,0.00011508251,0.0000438901,0.0013620354,0.000030653315,0.000029612438],"category_scores_gemma":[0.00049429416,0.00007823442,0.00012895769,0.000298808,0.0002865085,0.00015538836,0.00021116834,0.00012874245,0.000012827239],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013964584,0.00011544129,0.000013327684,0.0000140482525,0.0000139469275,1.2053937e-8,0.0015445558,0.00026909055,0.04173192,0.90744364,0.00007313907,0.048766937],"study_design_scores_gemma":[0.000013581955,0.0002901874,0.0001610405,0.00008857259,0.0000084385965,1.6942369e-7,0.00052238896,0.090334855,0.6349689,0.27352062,0.000024450856,0.000066820896],"about_ca_topic_score_codex":0.000026998327,"about_ca_topic_score_gemma":0.0000091822285,"teacher_disagreement_score":0.633923,"about_ca_system_score_codex":0.000009553716,"about_ca_system_score_gemma":0.00003343612,"threshold_uncertainty_score":0.3190307},"labels":[],"label_agreement":null},{"id":"W2155217764","doi":"10.1162/neco_a_00682","title":"Efficient Training of Convolutional Deep Belief Networks in the Frequency Domain for Application to High-Resolution 2D and 3D Images","year":2014,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Mental Health; National Institute on Aging; National Center for Research Resources; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Benchmark (surveying); Deep learning; Artificial intelligence; Convolutional neural network; Domain (mathematical analysis); Image (mathematics); Frequency domain; Deep belief network; Training (meteorology); Pattern recognition (psychology); Voxel; Machine learning; Algorithm; Computer vision; Mathematics","score_opus":0.012361938694241941,"score_gpt":0.2370243755422255,"score_spread":0.22466243684798357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155217764","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08872653,0.00006233593,0.90958166,0.0009843853,0.00013408362,0.0004444774,0.00000236383,0.00001907642,0.00004510478],"genre_scores_gemma":[0.81697494,9.397734e-7,0.18259078,0.00024504706,0.00011560249,0.000054410306,0.0000136401995,0.000003999767,6.2258147e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989644,0.00019735322,0.00023699974,0.00026616806,0.00016208184,0.00017297806],"domain_scores_gemma":[0.9992149,0.0004125355,0.00011252459,0.00012704698,0.00009991148,0.00003307468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060587033,0.000095966636,0.00013013878,0.0000758681,0.00014535194,0.00005737927,0.00020051679,0.000037715276,4.409369e-7],"category_scores_gemma":[0.00005303251,0.000077968965,0.000030262549,0.00025722387,0.000044997392,0.00010317135,0.00004169375,0.00006485038,7.3671043e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009070637,0.000020734633,0.0000684113,0.000005251755,0.000002534865,1.1170346e-7,0.0007218,0.9137423,0.0014656639,0.01878866,0.00003345874,0.065141976],"study_design_scores_gemma":[0.00031837623,0.00013618349,0.022777949,0.000009063281,0.0000046484156,0.0000023668986,0.000053419026,0.9684321,0.00006177415,0.00809984,0.000024479195,0.000079787205],"about_ca_topic_score_codex":0.00005549143,"about_ca_topic_score_gemma":0.00003073336,"teacher_disagreement_score":0.7282484,"about_ca_system_score_codex":0.000025032186,"about_ca_system_score_gemma":0.000012070766,"threshold_uncertainty_score":0.3179482},"labels":[],"label_agreement":null},{"id":"W2156740722","doi":"10.1162/neco.2008.11-07-647","title":"Justifying and Generalizing Contrastive Divergence","year":2008,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":211,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Mathematics; Estimator; Gibbs sampling; Applied mathematics; Convergence (economics); Boltzmann machine; Gradient descent; Statistics; Bayesian probability; Computer science; Artificial intelligence; Artificial neural network","score_opus":0.03970591529768274,"score_gpt":0.24661055085706,"score_spread":0.20690463555937724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156740722","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23116006,0.0001701287,0.76782167,0.00028313414,0.00028926463,0.00006712271,5.521413e-7,0.0000638231,0.00014425474],"genre_scores_gemma":[0.95244974,0.000038447608,0.04708449,0.0002899935,0.00010226049,0.0000030435956,0.0000019093472,0.0000040955506,0.000026016049],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925053,0.000075827425,0.00012385004,0.00025564164,0.00013204128,0.0001621069],"domain_scores_gemma":[0.9996394,0.000088703826,0.00005801809,0.000077437224,0.00007839514,0.000058054546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000068741436,0.000093886236,0.000101482314,0.000042935993,0.00033725018,0.00006598199,0.00012925922,0.000023879804,0.0000027525762],"category_scores_gemma":[0.000028533137,0.000087316526,0.000025552175,0.00016297483,0.00005099574,0.00052066596,0.000102972175,0.000065421045,0.000006611187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002904485,0.00006810875,0.014122655,0.000026961972,0.000055925942,0.0001827794,0.0052258563,0.5209548,0.034960087,0.00691797,0.0033706299,0.41408518],"study_design_scores_gemma":[0.00017021401,0.00004006536,0.033474445,0.000005165821,0.000003955754,0.000043385502,0.000014554449,0.96395904,0.001689345,0.0004015424,0.00008767897,0.00011063481],"about_ca_topic_score_codex":0.00003395037,"about_ca_topic_score_gemma":0.000002616931,"teacher_disagreement_score":0.7212897,"about_ca_system_score_codex":0.000013573635,"about_ca_system_score_gemma":0.00001333222,"threshold_uncertainty_score":0.35606647},"labels":[],"label_agreement":null},{"id":"W2158097779","doi":"10.1109/cvpr.2013.14","title":"Exploring Compositional High Order Pattern Potentials for Structured Output Learning","year":2013,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Image (mathematics); Structured prediction; Boltzmann machine; Equivalence (formal languages); Machine learning; Variation (astronomy); Deep learning; Mathematics","score_opus":0.05019302572815967,"score_gpt":0.22216143838523897,"score_spread":0.1719684126570793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158097779","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02197956,0.000012558206,0.9753061,0.0015382741,0.0005733364,0.0002462475,0.0000019617828,0.00010352927,0.00023845828],"genre_scores_gemma":[0.8045727,0.000004029913,0.1942416,0.00034111255,0.000267382,0.00008961961,0.000011201038,0.000008658595,0.00046370673],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904776,0.000060758855,0.00017403782,0.00029872186,0.00016134456,0.00025739137],"domain_scores_gemma":[0.99935925,0.000106953776,0.0000598178,0.0001799068,0.00022435494,0.00006973663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000096345044,0.00012526228,0.00014520016,0.00005070129,0.00024015646,0.00031490414,0.0003131929,0.000029305278,0.00025884365],"category_scores_gemma":[0.000026045875,0.000102630074,0.0000647069,0.000115248964,0.000018704322,0.001019715,0.00013174597,0.00007482762,0.000072598836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006643391,0.00006959475,0.000646534,0.000022178552,0.00016002434,0.0000037099946,0.0005836358,0.114301234,0.05669711,0.013692481,0.007206461,0.8066104],"study_design_scores_gemma":[0.00092463096,0.00017543758,0.02804296,0.000024532046,0.000018746932,0.000007000037,0.00012747194,0.9080926,0.04957346,0.0067201974,0.0057204724,0.0005724724],"about_ca_topic_score_codex":0.00021474503,"about_ca_topic_score_gemma":0.0000065340305,"teacher_disagreement_score":0.8060379,"about_ca_system_score_codex":0.000015547477,"about_ca_system_score_gemma":0.000017013906,"threshold_uncertainty_score":0.4185133},"labels":[],"label_agreement":null},{"id":"W2160142299","doi":"","title":"Unsupervised Models of Images by Spike-and-Slab RBMs","year":2011,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Spike (software development); Slab; Computer science; Feature (linguistics); Pattern recognition (psychology); Variable (mathematics); Artificial intelligence; Binary number; Boltzmann machine; Latent variable; Algorithm; Mathematics; Artificial neural network; Physics; Mathematical analysis; Arithmetic","score_opus":0.05242372225847681,"score_gpt":0.2522785329033527,"score_spread":0.19985481064487592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160142299","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011673698,0.00014304237,0.92363876,0.0009805403,0.00023450304,0.000079758036,0.000013941892,0.000066498185,0.06316923],"genre_scores_gemma":[0.97993004,0.00013050086,0.018868644,0.00013664321,0.000032021664,0.000005127274,0.00000963408,0.000007972974,0.00087939936],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901503,0.00010142666,0.00020134871,0.00029453135,0.0002471265,0.00014054617],"domain_scores_gemma":[0.9994254,0.00005777407,0.00012196654,0.00016089622,0.00017761826,0.00005631435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019463105,0.0001342887,0.00015328219,0.000091454545,0.00006972663,0.00008252784,0.0005786429,0.000038381837,0.00031132082],"category_scores_gemma":[0.000060204653,0.00011758075,0.000047259084,0.0000800624,0.000060413524,0.00046354407,0.00018624293,0.00020402613,0.000015407999],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014568286,0.00031009523,0.00931099,0.000021241109,0.00023140808,0.00002309845,0.0039989688,0.011914638,0.07563404,0.68205816,0.00092596066,0.2154257],"study_design_scores_gemma":[0.0003151338,0.00015310086,0.0010091081,0.000036061872,0.000005206787,0.00000354299,0.00004738686,0.9725039,0.014893559,0.010380817,0.00049378956,0.00015837648],"about_ca_topic_score_codex":0.00034217662,"about_ca_topic_score_gemma":0.0000059572612,"teacher_disagreement_score":0.96825635,"about_ca_system_score_codex":0.000012524991,"about_ca_system_score_gemma":0.000023650846,"threshold_uncertainty_score":0.47948036},"labels":[],"label_agreement":null},{"id":"W2161000554","doi":"","title":"Factored 3-Way Restricted Boltzmann Machines For Modeling Natural Images","year":2010,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":194,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Boltzmann machine; Restricted Boltzmann machine; Computer science; Artificial intelligence; Covariance; Deep belief network; Binary number; Pattern recognition (psychology); Probabilistic logic; Set (abstract data type); Deep learning; Simple (philosophy); Object (grammar); Image (mathematics); Data modeling; Binary Independence Model; Statistical model; Mathematics","score_opus":0.014499267645369018,"score_gpt":0.24645180649573084,"score_spread":0.23195253885036182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161000554","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027921256,0.000055277236,0.96806,0.0010573133,0.0014313281,0.00022000282,0.0000057749717,0.00018536842,0.0010636873],"genre_scores_gemma":[0.7408001,0.000002880992,0.258157,0.00014440043,0.00027337574,0.000014006204,0.0000061336227,0.000008422753,0.0005937076],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989914,0.000027959517,0.00018133236,0.00036397678,0.00014204258,0.00029329263],"domain_scores_gemma":[0.9991708,0.0001274151,0.00004771954,0.0003901427,0.00018528216,0.00007867706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011650102,0.00015689357,0.00015361972,0.00007330289,0.00020726662,0.0002663331,0.00059950707,0.00006246556,0.000021328318],"category_scores_gemma":[0.00016816531,0.00011523134,0.00010112763,0.00018052095,0.00002529804,0.0006406485,0.00013951975,0.00017629706,0.000010051875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005000874,0.00012389383,0.0003630129,0.000020518137,0.00009422239,0.000008377828,0.0003763852,0.021924743,0.7461624,0.02841356,0.018606938,0.18385594],"study_design_scores_gemma":[0.0002382593,0.000022558777,0.00045954913,0.0000023767436,0.0000048933243,0.0000024697597,0.000008080414,0.97488534,0.020265486,0.0030808502,0.00085782696,0.0001722913],"about_ca_topic_score_codex":0.00014569082,"about_ca_topic_score_gemma":0.000113336304,"teacher_disagreement_score":0.9529606,"about_ca_system_score_codex":0.000007406752,"about_ca_system_score_gemma":0.000028849061,"threshold_uncertainty_score":0.46989977},"labels":[],"label_agreement":null},{"id":"W2162747531","doi":"","title":"Generative versus discriminative training of RBMs for classification of fMRI images","year":2008,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Baycrest Hospital; University of Toronto","funders":"","keywords":"Discriminative model; Overfitting; Artificial intelligence; Computer science; Pattern recognition (psychology); Generative model; Voxel; Machine learning; Set (abstract data type); Training set; Data set; Task (project management); Generative grammar; Artificial neural network","score_opus":0.1259106268912469,"score_gpt":0.29798518063031604,"score_spread":0.17207455373906913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162747531","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007063915,0.0000460612,0.9870961,0.0005647089,0.00022943573,0.00020493698,0.000011552954,0.000019715266,0.004763628],"genre_scores_gemma":[0.745669,0.0000151645945,0.2540242,0.00001594998,0.000052983993,0.000019408932,0.0000038893363,0.0000043174064,0.00019508539],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99914336,0.00006801205,0.00025388802,0.00023959654,0.00014887605,0.00014626233],"domain_scores_gemma":[0.99891496,0.00033680827,0.00018443161,0.0002313832,0.00029672636,0.000035712652],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016518,0.00010235262,0.00021677741,0.00006634507,0.00010350847,0.000011871492,0.0003019024,0.000034234963,0.000012414926],"category_scores_gemma":[0.00013503624,0.000082628576,0.00009809782,0.0001936158,0.00016445547,0.00037962032,0.00005247963,0.00003637869,0.0000010832617],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028494684,0.00034622877,0.00018152168,0.000053148073,0.0002900774,0.0000032419339,0.031054864,0.004180367,0.54655546,0.22867492,0.00911055,0.17926465],"study_design_scores_gemma":[0.0012160122,0.0005299998,0.005120534,0.00001495993,0.000024271116,0.0000018652189,0.0025847503,0.28224185,0.706122,0.0016467051,0.00029323614,0.00020382844],"about_ca_topic_score_codex":0.000026182604,"about_ca_topic_score_gemma":0.00001162623,"teacher_disagreement_score":0.7386051,"about_ca_system_score_codex":0.000016845952,"about_ca_system_score_gemma":0.00007585647,"threshold_uncertainty_score":0.33694956},"labels":[],"label_agreement":null},{"id":"W2167348665","doi":"10.48550/arxiv.1406.1485","title":"Iterative Neural Autoregressive Distribution Estimator (NADE-k)","year":2014,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Inference; Autoregressive model; Estimator; Computer science; Artificial intelligence; Artificial neural network; Machine learning; Pattern recognition (psychology); Adaptive neuro fuzzy inference system; Block (permutation group theory); Algorithm; Mathematics; Statistics","score_opus":0.029222498880668694,"score_gpt":0.16797665070522771,"score_spread":0.13875415182455902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167348665","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026582945,0.00001460265,0.9710835,0.00031295637,0.00034801653,0.00009722525,0.000009391508,0.00013992193,0.0014114258],"genre_scores_gemma":[0.9967538,0.0000043434698,0.002386081,0.00012596263,0.000120638506,5.800412e-7,0.000014602726,0.0000070336746,0.00058694114],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987641,0.00020684474,0.00011482928,0.0005453373,0.00006839464,0.00030049434],"domain_scores_gemma":[0.9990046,0.00013808723,0.00011401762,0.00045662283,0.00013721015,0.00014947697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014139985,0.00017943479,0.0001753712,0.000052850315,0.00031809247,0.00013614568,0.0006198658,0.00006712294,0.000026312322],"category_scores_gemma":[0.00009073154,0.00017454568,0.00009957875,0.00037086286,0.00010639973,0.0009044754,0.00021301334,0.00013041796,0.00008504914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002918069,0.00008076424,0.0017505527,0.000007601663,0.000051726805,0.00010889318,0.00024207975,0.3589082,0.00035406463,0.6275104,0.00271261,0.008243851],"study_design_scores_gemma":[0.00032859744,0.0000766003,0.0025213028,0.000012016159,0.000015887385,0.000004214159,0.000020362604,0.98823464,0.00094830897,0.0045330403,0.0030915332,0.0002135173],"about_ca_topic_score_codex":0.00003965214,"about_ca_topic_score_gemma":0.000013620515,"teacher_disagreement_score":0.97017086,"about_ca_system_score_codex":0.00008093069,"about_ca_system_score_gemma":0.000036919,"threshold_uncertainty_score":0.7117766},"labels":[],"label_agreement":null},{"id":"W2171282218","doi":"","title":"Inductive Principles for Restricted Boltzmann Machine Learning","year":2010,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":143,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Boltzmann machine; Computer science; Artificial intelligence; Restricted Boltzmann machine; Machine learning; Matching (statistics); Divergence (linguistics); Partition (number theory); Range (aeronautics); Binary number; Deep learning; Mathematics; Statistics","score_opus":0.024342392485161107,"score_gpt":0.2429792260977759,"score_spread":0.2186368336126148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171282218","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013524427,0.000018575194,0.97868854,0.001001871,0.0005383946,0.00021141085,0.0000017329687,0.00015801273,0.005857053],"genre_scores_gemma":[0.6640906,0.0000044089866,0.3328711,0.00010834704,0.00023234461,0.000023828447,0.0000039200013,0.000007632802,0.002657811],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991893,0.0000425395,0.0001430753,0.00030047112,0.00010552187,0.00021909038],"domain_scores_gemma":[0.9992988,0.00016578283,0.00006896494,0.0002697454,0.00012767434,0.00006899181],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018188015,0.0001055544,0.00011470547,0.00006149014,0.00022132097,0.00013381518,0.00042485,0.00005993873,0.000036740512],"category_scores_gemma":[0.00031702066,0.00008285101,0.000057342837,0.00020893093,0.000032030508,0.00036484405,0.00016294044,0.00022961613,0.000016334801],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053478136,0.00022997225,0.0058824443,0.000016333115,0.00013881594,0.000010402037,0.0012188142,0.008523922,0.27059406,0.47347978,0.0049863993,0.23486559],"study_design_scores_gemma":[0.00036297986,0.00013025787,0.0047414294,0.0000032077085,0.000006988318,0.000003857038,0.000023781313,0.7817306,0.030711174,0.00218175,0.17987722,0.00022679356],"about_ca_topic_score_codex":0.000076741846,"about_ca_topic_score_gemma":0.00012365726,"teacher_disagreement_score":0.77320665,"about_ca_system_score_codex":0.000007924921,"about_ca_system_score_gemma":0.00003823839,"threshold_uncertainty_score":0.33785662},"labels":[],"label_agreement":null},{"id":"W2177899970","doi":"10.1609/aaai.v31i1.10777","title":"Denoising Criterion for Variational Auto-Encoding Framework","year":2017,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":142,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Autoencoder; MNIST database; Noise reduction; Noise (video); Upper and lower bounds; Pattern recognition (psychology); Encoding (memory); Encoder; Artificial intelligence; Computer science; Algorithm; Mathematics; Deep learning","score_opus":0.10276992054147606,"score_gpt":0.3279392752590403,"score_spread":0.22516935471756427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2177899970","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009427655,0.0000123950085,0.9781022,0.007517604,0.00093647285,0.00036047577,0.0000055391006,0.000045992307,0.0035916686],"genre_scores_gemma":[0.92373276,0.000011987575,0.07561787,0.00018879262,0.00029389342,0.00002847463,2.7477245e-7,0.000009928401,0.00011602166],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984725,0.000014591904,0.0003952846,0.00045721565,0.0003481465,0.0003122274],"domain_scores_gemma":[0.99794906,0.00021587686,0.00057727384,0.00044556835,0.0007447237,0.00006747194],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006398885,0.00018692444,0.00022650391,0.00006876798,0.0011684143,0.0011388717,0.002522137,0.000101323756,0.000029660183],"category_scores_gemma":[0.0020379722,0.0001449406,0.00014480912,0.00014400328,0.0002145857,0.0009336298,0.00044961637,0.00020131918,0.000018729594],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030508596,0.00004687389,0.000099039054,0.000017913993,0.000014673392,1.4373823e-7,0.0005956834,0.00036869737,0.04318574,0.9098545,0.000121574914,0.04566469],"study_design_scores_gemma":[0.000018820225,0.00007788167,0.0005471616,0.000229043,0.000010699838,0.0000011586126,0.00007238362,0.32885462,0.27812862,0.39175564,0.00014889397,0.00015505224],"about_ca_topic_score_codex":0.000026730271,"about_ca_topic_score_gemma":0.000003848509,"teacher_disagreement_score":0.9143051,"about_ca_system_score_codex":0.000039946677,"about_ca_system_score_gemma":0.00008584064,"threshold_uncertainty_score":0.999898},"labels":[],"label_agreement":null},{"id":"W2184456254","doi":"","title":"Fast Inference and Learning for Modeling Documents with a Deep Boltzmann Machine","year":2013,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Softmax function; Boltzmann machine; Restricted Boltzmann machine; Inference; Computer science; Artificial intelligence; Machine learning; Deep learning; Layer (electronics); Boltzmann constant; Natural language processing; Pattern recognition (psychology)","score_opus":0.011344222520975871,"score_gpt":0.22772643201367626,"score_spread":0.2163822094927004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2184456254","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012572152,0.000072709896,0.98547447,0.000381101,0.000032935077,0.00021604252,1.5421355e-7,0.000054056283,0.001196371],"genre_scores_gemma":[0.7414037,0.00001062074,0.2578331,0.00013939124,0.000024540557,0.000035674082,0.0000010463531,0.00000490877,0.0005470382],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993096,0.000033318185,0.00010166816,0.00026044447,0.00009302263,0.0002019554],"domain_scores_gemma":[0.9995796,0.00007851396,0.000033511307,0.00013858169,0.00009939887,0.00007040498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000107409534,0.000105475025,0.000109195025,0.00003437758,0.00019962317,0.00032803343,0.00018887564,0.000022034938,0.000030744362],"category_scores_gemma":[0.00003309422,0.000072161616,0.000018174991,0.00008307246,0.00001787529,0.00080259715,0.00012312092,0.000079076824,0.000011640572],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013913154,0.00003829273,0.0029100939,0.000018882836,0.000059429105,0.000001452964,0.0010757865,0.66028947,0.0010971244,0.0056076585,0.00018637662,0.32870153],"study_design_scores_gemma":[0.00025659485,0.0001034011,0.00018138204,0.000009551219,0.0000040914506,0.0000017922425,0.00005547775,0.9978416,0.00019360257,0.00105329,0.00018311187,0.000116134346],"about_ca_topic_score_codex":0.00037995735,"about_ca_topic_score_gemma":0.000067211186,"teacher_disagreement_score":0.7288315,"about_ca_system_score_codex":0.000007707871,"about_ca_system_score_gemma":0.000012795517,"threshold_uncertainty_score":0.3163234},"labels":[],"label_agreement":null},{"id":"W2187294194","doi":"10.14288/1.0051916","title":"Deep learning of invariant spatio-temporal features from video","year":2010,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Deep belief network; Artificial intelligence; Discriminative model; Computer science; Deep learning; Pattern recognition (psychology); Generative model; Feature learning; Boltzmann machine; Restricted Boltzmann machine; Invariant (physics); Generative grammar; Mathematics","score_opus":0.005741611207891186,"score_gpt":0.16541011664924385,"score_spread":0.15966850544135266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2187294194","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71540314,0.00008572201,0.28313154,0.000117689604,0.00029189995,0.00009521869,0.000019295347,0.000047469388,0.00080804934],"genre_scores_gemma":[0.95583147,0.000026267324,0.043787107,0.000025152007,0.000060695696,1.7566168e-7,0.000016662992,0.000006420832,0.0002460503],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990276,0.00009524436,0.000121253004,0.00035576476,0.0002222418,0.00017789469],"domain_scores_gemma":[0.9990841,0.00009743972,0.00019563029,0.00033690862,0.00019294808,0.00009294539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018870646,0.000045324272,0.0002442407,0.000037148766,0.00020734656,0.0001361068,0.0006955629,0.00010549022,0.00016533618],"category_scores_gemma":[0.000075754986,0.00014201149,0.00011255815,0.00025138404,0.00018084527,0.00058589136,0.00028242354,0.0002446175,0.000009305658],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011624939,0.000117385076,0.030822042,0.000018654026,0.000081237136,0.00011015608,0.00085973175,0.00080215797,0.007722388,0.000059179794,0.0026888996,0.9567065],"study_design_scores_gemma":[0.00045430093,0.000057457575,0.96507066,0.000040476094,0.000018680461,0.000010540338,0.0002617594,0.032460608,0.00006479279,0.0006963579,0.0007049913,0.00015937962],"about_ca_topic_score_codex":0.18560398,"about_ca_topic_score_gemma":0.42745033,"teacher_disagreement_score":0.95654714,"about_ca_system_score_codex":0.00001316493,"about_ca_system_score_gemma":0.000059979004,"threshold_uncertainty_score":0.81981915},"labels":[],"label_agreement":null},{"id":"W2187650160","doi":"","title":"Discussion of \\The Neural Autoregressive Distribution Estimator\"","year":2011,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"MNIST database; Boltzmann machine; Latent variable; Estimator; Restricted Boltzmann machine; Graphical model; Computer science; Inference; Block (permutation group theory); Gibbs sampling; Artificial intelligence; Autoregressive model; Algorithm; Mathematics; Applied mathematics; Machine learning; Artificial neural network; Statistics; Combinatorics","score_opus":0.107768844503171,"score_gpt":0.30808845568070176,"score_spread":0.20031961117753078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2187650160","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007719834,0.0000061463716,0.9954892,0.0011502823,0.0008699491,0.00008239046,0.00013029411,0.000014708059,0.0014850438],"genre_scores_gemma":[0.9750043,0.000018031074,0.024751011,0.00006065106,0.000043263703,0.000004950076,0.000011542957,0.000003288037,0.00010297337],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990613,0.00007972882,0.00027032028,0.00021465417,0.00025164834,0.00012234661],"domain_scores_gemma":[0.99923325,0.00008898712,0.0001638177,0.00019754858,0.00026666524,0.000049754934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012469139,0.00010750912,0.000105935054,0.00003174331,0.00012735065,0.00008368474,0.00052493374,0.00003659326,0.00010808521],"category_scores_gemma":[0.00025458704,0.000062551204,0.000034823686,0.00008442772,0.00020700139,0.00018343136,0.00015267005,0.000100002435,0.0000119163105],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024526233,0.00005199709,0.00013415843,0.000002111059,0.000010074818,0.0000034442007,0.00045634934,0.00023123143,0.0004528033,0.82318366,0.00017704122,0.17527258],"study_design_scores_gemma":[0.000018326591,0.00009152132,0.002870646,0.000041725085,0.000006475264,0.0000042129623,0.00016148391,0.77546275,0.018090287,0.20306134,0.00008946783,0.00010179065],"about_ca_topic_score_codex":0.00004957494,"about_ca_topic_score_gemma":0.000030962205,"teacher_disagreement_score":0.9742323,"about_ca_system_score_codex":0.000018704503,"about_ca_system_score_gemma":0.000045262885,"threshold_uncertainty_score":0.2550764},"labels":[],"label_agreement":null},{"id":"W2187720631","doi":"10.1109/idaacs.2015.7340725","title":"A new technique for restricted Boltzmann machine learning","year":2015,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"MNIST database; Boltzmann machine; Restricted Boltzmann machine; Artificial intelligence; Computer science; Deep belief network; Perceptron; Artificial neural network; Deep learning; Machine learning; Visualization; Multilayer perceptron; Representation (politics); Pattern recognition (psychology)","score_opus":0.03087663653453267,"score_gpt":0.2543824357478542,"score_spread":0.2235057992133215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2187720631","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013223468,0.00011063519,0.99303555,0.0013120036,0.00015613023,0.0002744467,5.703402e-7,0.00018753746,0.0049098865],"genre_scores_gemma":[0.09049634,0.0000059523036,0.8997198,0.00020847535,0.00020652272,0.000038053484,0.0000039396427,0.00000926507,0.009311706],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992682,0.00005616044,0.00012373805,0.00023692648,0.000119019554,0.00019600187],"domain_scores_gemma":[0.99938554,0.00007371925,0.000045522735,0.00022540294,0.00011038605,0.00015943355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021997879,0.00009484502,0.00011331822,0.000061075996,0.000079508834,0.00010968673,0.00037995868,0.000044857494,0.000014712842],"category_scores_gemma":[0.00020933234,0.00007621122,0.000048171165,0.00027625606,0.000008461486,0.00028879402,0.0001306248,0.00008439845,0.000019260353],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012903418,0.00015061653,0.001055572,0.000019258065,0.00011462701,0.000027787393,0.001216383,0.020545546,0.08578387,0.10691541,0.5106604,0.27338147],"study_design_scores_gemma":[0.000720933,0.00036714922,0.00010071329,0.000009676331,0.000007851023,0.00001036596,0.000020852822,0.694237,0.039168842,0.009255119,0.25583452,0.00026701746],"about_ca_topic_score_codex":0.00023716733,"about_ca_topic_score_gemma":0.000022452368,"teacher_disagreement_score":0.6736914,"about_ca_system_score_codex":0.000022979239,"about_ca_system_score_gemma":0.000114229464,"threshold_uncertainty_score":0.31078032},"labels":[],"label_agreement":null},{"id":"W2191540403","doi":"","title":"On Autoencoders and Score Matching for Energy Based Models","year":2011,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of British Columbia","funders":"","keywords":"Autoencoder; Artificial intelligence; Pattern recognition (psychology); Matching (statistics); Gaussian; Estimator; Regularization (linguistics); Computer science; Feature extraction; Mathematics; Statistics; Deep learning","score_opus":0.05270944082733099,"score_gpt":0.21232315439005842,"score_spread":0.1596137135627274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2191540403","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005444507,0.00001780733,0.98902047,0.00020705066,0.000116399584,0.0000634273,9.571557e-7,0.00006224142,0.009967172],"genre_scores_gemma":[0.6246624,0.0000021975025,0.37409008,0.0010565176,0.000018513749,0.00001121092,4.6196593e-7,0.000004480503,0.00015411942],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994114,0.000024968775,0.00008445348,0.0002488698,0.000072439485,0.00015787555],"domain_scores_gemma":[0.99959147,0.0000945012,0.000027150274,0.0001978416,0.00003149252,0.000057570087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010443729,0.00008863244,0.00008810615,0.000044555673,0.00010387631,0.000060496164,0.0002098397,0.000027962125,0.000019774621],"category_scores_gemma":[0.000007604722,0.000069087684,0.000037946756,0.000059146336,0.0000202947,0.00032233572,0.00004765071,0.000024538209,0.0000013509472],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021715681,0.00004588054,0.000008867365,0.0000056184945,0.000014682986,0.000002168935,0.000482953,0.08534435,0.000265603,0.8779348,0.0019298447,0.0339435],"study_design_scores_gemma":[0.00015749791,0.00007361668,0.000036503272,0.000007644366,0.0000024518567,3.9876744e-7,0.000010172403,0.85430825,0.0034378052,0.14176655,0.000112756476,0.0000863349],"about_ca_topic_score_codex":0.00015222387,"about_ca_topic_score_gemma":0.00002761938,"teacher_disagreement_score":0.76896393,"about_ca_system_score_codex":0.0000075075727,"about_ca_system_score_gemma":0.000021952323,"threshold_uncertainty_score":0.2817314},"labels":[],"label_agreement":null},{"id":"W2235935298","doi":"","title":"On the Expressive Power of Restricted Boltzmann Machines.","year":2013,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Boltzmann machine; Restricted Boltzmann machine; Computer science; Generative model; Upper and lower bounds; Function (biology); Type (biology); Artificial neural network; Exponential function; Theoretical computer science; Simple (philosophy); Algorithm; Generative grammar; Artificial intelligence; Mathematics","score_opus":0.011548361567214038,"score_gpt":0.2130703337697511,"score_spread":0.20152197220253706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2235935298","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13604067,0.0003604831,0.835541,0.004262639,0.0017107626,0.0014926746,0.00000896712,0.00029694894,0.020285849],"genre_scores_gemma":[0.9987501,0.0000015242678,0.0005308737,0.00050059916,0.00003981883,0.000057954214,0.0000031445413,0.0000037935022,0.00011222969],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892104,0.00009581432,0.00040914808,0.0001033683,0.000310454,0.0001601583],"domain_scores_gemma":[0.99873924,0.00012550477,0.00041846128,0.000300842,0.00037572155,0.000040214272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001343046,0.000118897835,0.00013697983,0.000088995715,0.00019411313,0.0006060746,0.0005031289,0.00004477956,0.000020506915],"category_scores_gemma":[0.0001435255,0.00006857131,0.00003982925,0.00035396373,0.00004242827,0.0032355394,0.000071291586,0.00010912109,0.000076030185],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006716176,0.00020282337,0.00048301535,0.0006418982,0.000119250835,0.000004328499,0.027213413,0.28954172,0.016075654,0.099556796,0.24871941,0.31737453],"study_design_scores_gemma":[0.00014279378,0.000061081766,0.0011345041,0.00009104517,0.0000024503722,0.0000056165068,0.0002551169,0.9949406,0.0015855414,0.00032063722,0.0013477105,0.000112913265],"about_ca_topic_score_codex":0.00009229906,"about_ca_topic_score_gemma":2.3086596e-7,"teacher_disagreement_score":0.8627094,"about_ca_system_score_codex":0.000016631342,"about_ca_system_score_gemma":0.000034115837,"threshold_uncertainty_score":0.5844391},"labels":[],"label_agreement":null},{"id":"W2247537918","doi":"10.1109/cvpr.2016.271","title":"Automatic Content-Aware Color and Tone Stylization","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Tone (literature); Ranking (information retrieval); Matching (statistics); Selection (genetic algorithm); Artificial intelligence; Artifact (error); Style (visual arts); Transfer (computing); Computer vision; Natural language processing; Mathematics; Linguistics","score_opus":0.035476560700733774,"score_gpt":0.26302420164086365,"score_spread":0.22754764094012989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2247537918","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00539872,0.00016751306,0.9882574,0.0031441518,0.0006794525,0.00032832177,0.000007901694,0.00020535321,0.0018111704],"genre_scores_gemma":[0.9376534,0.000096577634,0.059037004,0.00061311905,0.00019765257,0.000049078786,0.000008815442,0.000014255458,0.0023300736],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987997,0.00009715002,0.00023682877,0.0005028515,0.0001694192,0.00019404113],"domain_scores_gemma":[0.9990198,0.00010683974,0.0001451142,0.0004917765,0.00015003124,0.00008644183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017366663,0.0002027023,0.0002738495,0.00006800823,0.000093895236,0.0002943365,0.0004577754,0.0001454914,0.00011612296],"category_scores_gemma":[0.00005057999,0.00013906507,0.00005650497,0.00006822398,0.000055323453,0.00026761205,0.0011507107,0.000100899175,0.00003251632],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019837285,0.00024235346,0.0015848045,0.00049569306,0.00060194236,0.000051469662,0.0023066013,0.0025960323,0.0075752353,0.15829,0.022760838,0.8034752],"study_design_scores_gemma":[0.00033443005,0.000049340044,0.0026242484,0.00019298689,0.00002373887,0.0000046415566,0.000027962167,0.9851996,0.0031918697,0.0065370803,0.0014393984,0.00037474747],"about_ca_topic_score_codex":0.0000363738,"about_ca_topic_score_gemma":0.000012775498,"teacher_disagreement_score":0.98260355,"about_ca_system_score_codex":0.000037660957,"about_ca_system_score_gemma":0.00007306865,"threshold_uncertainty_score":0.5670909},"labels":[],"label_agreement":null},{"id":"W2249616250","doi":"","title":"Regularized Auto-Encoders Estimate Local Statistics","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Encoder; Algorithm; Computer science; Probability density function; Autoencoder; Parametrization (atmospheric modeling); Pattern recognition (psychology); Mathematics; Artificial intelligence; Statistics; Deep learning","score_opus":0.04334108668390863,"score_gpt":0.18404595641889418,"score_spread":0.14070486973498555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2249616250","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049895886,0.000033879784,0.9925742,0.000080566315,0.00044480665,0.00009057502,0.000007613748,0.00014344722,0.0016353158],"genre_scores_gemma":[0.9179189,0.000017112316,0.08065688,0.00012349378,0.00007520744,2.970171e-7,0.0000042864854,0.00001000897,0.0011937675],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987869,0.00013944296,0.0001255552,0.00037946,0.000081380014,0.0004872633],"domain_scores_gemma":[0.9989391,0.00012134619,0.0000883194,0.00051662826,0.000089978435,0.00024464534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025054166,0.00017214041,0.00017905186,0.00008489139,0.00021712447,0.00007020471,0.00060766615,0.0000746716,0.000076144366],"category_scores_gemma":[0.000040056155,0.00018010015,0.000072147224,0.00047120388,0.0001533842,0.001030419,0.00025361625,0.00012749783,0.00022160135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040236293,0.00017020025,0.0030209434,0.0000141546625,0.00009779237,0.00013670123,0.00039590147,0.34915024,0.0004815336,0.6293949,0.0057060327,0.011391343],"study_design_scores_gemma":[0.00049081893,0.000033901073,0.0015377663,0.0000075557805,0.000031783515,0.0000052326845,0.00005485184,0.9877018,0.00054259767,0.007256472,0.0020951992,0.00024205145],"about_ca_topic_score_codex":0.00006204278,"about_ca_topic_score_gemma":0.000013217078,"teacher_disagreement_score":0.91292936,"about_ca_system_score_codex":0.00009054273,"about_ca_system_score_gemma":0.000058873095,"threshold_uncertainty_score":0.7344271},"labels":[],"label_agreement":null},{"id":"W2274603360","doi":"10.71781/10876","title":"Improving sampling, optimization and feature extraction in Boltzmann machines","year":2013,"lang":"en","type":"dissertation","venue":"Open MIND","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Boltzmann machine; Sampling (signal processing); Computer science; Extraction (chemistry); Feature (linguistics); Restricted Boltzmann machine; Artificial intelligence; Data mining; Pattern recognition (psychology); Statistics; Machine learning; Mathematics; Chromatography; Chemistry; Artificial neural network","score_opus":0.021034169314759682,"score_gpt":0.29619403430179914,"score_spread":0.2751598649870395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2274603360","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037210457,0.0014228484,0.94477755,0.00040174183,0.002100053,0.0016512685,0.000011625474,0.0000102786225,0.012414169],"genre_scores_gemma":[0.040467665,0.00017482105,0.93699634,0.000040996205,0.00027252143,0.00006789052,0.00046409032,0.00003240142,0.021483293],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890393,0.00006497493,0.00020035786,0.00053512026,0.00012314519,0.0001724481],"domain_scores_gemma":[0.9993298,0.00004774379,0.00023406192,0.0002520004,0.00008643119,0.000049959413],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00020781439,0.00020424876,0.00023074671,0.00012903706,0.00012645991,0.0011763268,0.0005073796,0.00021468921,0.00020597388],"category_scores_gemma":[0.000056373046,0.00018926228,0.000030309231,0.0001818345,0.000009482991,0.0013612153,0.00013143581,0.00024053204,0.00002353764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015123041,0.0000325062,0.00006191246,0.00001940141,0.00001462126,0.0000044623102,0.0009304855,0.021370258,0.0035074726,0.000023898858,0.0004302789,0.9735896],"study_design_scores_gemma":[0.00032000893,0.00004178331,0.002492287,0.00015184471,0.000023073537,0.000005796485,0.00022098319,0.98867303,0.0031921223,0.00008138814,0.004393368,0.00040428425],"about_ca_topic_score_codex":0.00048804178,"about_ca_topic_score_gemma":0.0008321587,"teacher_disagreement_score":0.9731853,"about_ca_system_score_codex":0.00003247401,"about_ca_system_score_gemma":0.00007090521,"threshold_uncertainty_score":0.9998605},"labels":[],"label_agreement":null},{"id":"W2287859846","doi":"","title":"Transfert de couleurs et colorisation guidés par la texture","year":2015,"lang":"fr","type":"preprint","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Humanities; Art; Philosophy","score_opus":0.024753495393592555,"score_gpt":0.2594355843323161,"score_spread":0.23468208893872355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2287859846","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007073069,0.003917706,0.9354014,0.0438173,0.0013562217,0.0016600603,0.00021912507,0.00080519426,0.0057499614],"genre_scores_gemma":[0.6540722,0.0025701972,0.33199668,0.0062799104,0.0010215937,0.00094546494,0.00015230796,0.00017746419,0.0027841441],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9916518,0.0026516318,0.0012254735,0.0017260588,0.0010206571,0.0017244092],"domain_scores_gemma":[0.99471986,0.00060585357,0.00046443287,0.002227803,0.00089908374,0.0010829902],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.005122244,0.0012618408,0.0012433912,0.0004584095,0.00052938994,0.001662272,0.002599003,0.0020027957,0.0000895128],"category_scores_gemma":[0.00073551666,0.0013409954,0.00066722103,0.0009200347,0.00045164293,0.0011827095,0.0012100778,0.002367619,0.000076001634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033951135,0.0011457936,0.00771443,0.00023286739,0.00057195337,0.00045893158,0.007862678,0.47607744,0.0128140785,0.2588999,0.1397497,0.09413272],"study_design_scores_gemma":[0.00086257624,0.00032180955,0.017252497,0.00037139625,0.00022242233,0.00029142832,0.00014102638,0.8335748,0.007841807,0.021607244,0.11610413,0.0014089058],"about_ca_topic_score_codex":0.02161485,"about_ca_topic_score_gemma":0.005497399,"teacher_disagreement_score":0.6469992,"about_ca_system_score_codex":0.0017576001,"about_ca_system_score_gemma":0.0037240642,"threshold_uncertainty_score":0.99993396},"labels":[],"label_agreement":null},{"id":"W2289330286","doi":"","title":"A Spike and Slab Restricted Boltzmann Machine","year":2011,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Boltzmann machine; Spike (software development); Slab; Restricted Boltzmann machine; Computer science; Block (permutation group theory); Boltzmann equation; Boltzmann constant; Lattice Boltzmann methods; Support vector machine; Artificial intelligence; Pattern recognition (psychology); Algorithm; Mathematics; Physics; Artificial neural network; Geometry; Mechanics; Thermodynamics","score_opus":0.12679983297307296,"score_gpt":0.3056727456217436,"score_spread":0.17887291264867067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2289330286","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011334809,0.000038193444,0.987921,0.0006483101,0.0004627723,0.00009211621,0.00007481554,0.000037869602,0.009591462],"genre_scores_gemma":[0.88334286,0.00034013853,0.11574403,0.00027154488,0.00007086504,0.000007126473,0.000011198335,0.000006025498,0.00020617885],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988884,0.00006846244,0.00028272028,0.00035944622,0.00022126657,0.0001797162],"domain_scores_gemma":[0.9992199,0.0001544573,0.000093996496,0.00018063777,0.00024464878,0.00010637897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014751479,0.00015271857,0.00013769846,0.000115993585,0.0001256163,0.00023944139,0.00037757677,0.00004909129,0.00021982737],"category_scores_gemma":[0.00021411563,0.00013724339,0.000018738901,0.000114927905,0.00015398521,0.00024454843,0.00014827398,0.00013338882,0.000051047035],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038889237,0.00004752314,0.00007938935,0.0000018859516,0.000016382126,0.000023639881,0.0005764265,0.000016932549,0.00047833705,0.77403253,0.00014468814,0.22454338],"study_design_scores_gemma":[0.000043944237,0.00027702318,0.0016386484,0.00002740237,0.000009180082,0.000016095002,0.00018272694,0.6229757,0.0049384576,0.3690056,0.00064934307,0.00023587703],"about_ca_topic_score_codex":0.00020507562,"about_ca_topic_score_gemma":0.0001246891,"teacher_disagreement_score":0.8822094,"about_ca_system_score_codex":0.000014236024,"about_ca_system_score_gemma":0.00004055802,"threshold_uncertainty_score":0.5596623},"labels":[],"label_agreement":null},{"id":"W2296973526","doi":"10.1145/2890104","title":"Enhanced Reweighted MRFs for Efficient Fashion Image Parsing","year":2016,"lang":"en","type":"article","venue":"ACM Transactions on Multimedia Computing Communications and Applications","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Markov random field; Parsing; Conditional random field; Artificial intelligence; Smoothing; Random forest; Pattern recognition (psychology); Markov chain; Image (mathematics); Set (abstract data type); Machine learning; Computer vision; Image segmentation","score_opus":0.02184744000109047,"score_gpt":0.278291196220301,"score_spread":0.25644375621921056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2296973526","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010793855,0.000094076626,0.9904411,0.0069205114,0.00010483251,0.0008859067,0.000033572367,0.00024145751,0.00019915056],"genre_scores_gemma":[0.55423,0.00018732314,0.44510522,0.0000877311,0.000046074812,0.00028048604,0.0000079802485,0.000012272986,0.00004294524],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985425,0.00013056275,0.0003742439,0.000507413,0.000139828,0.00030545943],"domain_scores_gemma":[0.99475837,0.0022638026,0.00015574948,0.0024288557,0.0002582857,0.00013491129],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00031406825,0.00020212185,0.00020174198,0.00015447538,0.0013851842,0.000141339,0.0014807936,0.000078822886,0.00000779234],"category_scores_gemma":[0.000069742295,0.0001620119,0.0001110688,0.00043865255,0.00023912756,0.00020744694,0.00011142311,0.00014729076,0.000031666277],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005946502,0.000262565,0.0000042402107,0.000007250271,0.000034675853,6.273967e-8,0.00033793118,0.00094780495,0.043649107,0.0043874,0.000047761456,0.95031524],"study_design_scores_gemma":[0.0013942836,0.00012086188,0.0003464546,0.00012424329,0.00006158598,0.0000054986813,0.00015784398,0.9532024,0.028903272,0.0024720943,0.012700375,0.0005110568],"about_ca_topic_score_codex":0.00000810254,"about_ca_topic_score_gemma":0.000010223512,"teacher_disagreement_score":0.95225465,"about_ca_system_score_codex":0.00006381299,"about_ca_system_score_gemma":0.00004876327,"threshold_uncertainty_score":0.9999149},"labels":[],"label_agreement":null},{"id":"W2404912485","doi":"","title":"An Augmented Efficient Backpropagation Training Strategy for Deep Autoassociative Neural Networks","year":2010,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Backpropagation; Initialization; Computer science; Boltzmann machine; Artificial neural network; Artificial intelligence; Training (meteorology); Extension (predicate logic); Deep neural networks; Deep learning; Algorithm","score_opus":0.0241782087594648,"score_gpt":0.2677236558870207,"score_spread":0.24354544712755588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2404912485","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022790276,0.000009638564,0.97457844,0.0003275077,0.000897762,0.00037094607,0.0000023918258,0.00016443376,0.0008586116],"genre_scores_gemma":[0.9149429,5.544323e-7,0.08430278,0.0002324991,0.00037146776,0.000039952927,0.000015598249,0.00001154261,0.00008266179],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865913,0.000102472644,0.00022977694,0.00042997996,0.00016921136,0.00040945387],"domain_scores_gemma":[0.99905837,0.00017112274,0.00012690612,0.00031224664,0.00019855218,0.000132777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049758574,0.00016627359,0.00017423002,0.00005077382,0.00030293368,0.00032517663,0.00046307355,0.00009541648,0.0000456485],"category_scores_gemma":[0.000060280356,0.00013970838,0.00008584315,0.0002416303,0.00004210317,0.00046812426,0.000049490576,0.00018571994,0.000003630041],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009530671,0.00007407578,0.000041872932,0.0000015281252,0.000022124512,0.0000010799596,0.0007623806,0.79308444,0.0064149247,0.013614245,0.00014398839,0.18582982],"study_design_scores_gemma":[0.0003633014,0.00017886722,0.0014699999,0.0000020022894,0.0000086294895,0.0000014723147,0.00019369973,0.9953384,0.00173301,0.00043022798,0.00009606095,0.00018432268],"about_ca_topic_score_codex":0.000020330444,"about_ca_topic_score_gemma":0.00015290946,"teacher_disagreement_score":0.89215267,"about_ca_system_score_codex":0.00002781821,"about_ca_system_score_gemma":0.000045028704,"threshold_uncertainty_score":0.56971425},"labels":[],"label_agreement":null},{"id":"W2421157170","doi":"10.48550/arxiv.1506.03877","title":"Bidirectional Helmholtz Machines","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Inference; Generative model; Computer science; Generative grammar; Bhattacharyya distance; Fiducial inference; Frequentist inference; Artificial intelligence; Helmholtz free energy; Algorithm; Machine learning; Bayesian inference; Bayesian probability","score_opus":0.08125603442208122,"score_gpt":0.19082608724919653,"score_spread":0.10957005282711531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2421157170","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016280105,0.00022850561,0.9720502,0.0002466965,0.0020490084,0.00016860366,0.000021003245,0.00027276168,0.008683156],"genre_scores_gemma":[0.9873996,0.000118506796,0.0064076665,0.0001265413,0.00041943512,9.3275224e-7,0.0000175494,0.00001620518,0.005493574],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99825156,0.00019932215,0.00015568934,0.0009816104,0.00011262056,0.00029920132],"domain_scores_gemma":[0.9983668,0.00007126668,0.00017051965,0.00089187076,0.00029401938,0.00020557064],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002960805,0.00030239517,0.0003026889,0.00019394721,0.00016518812,0.00017576739,0.0014041944,0.00021852081,0.00006404082],"category_scores_gemma":[0.0000500938,0.00032154194,0.00020880748,0.00047250284,0.00009369041,0.00041431832,0.001852462,0.0004127728,0.00016988201],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002079691,0.00009093957,0.0011903587,0.00001981903,0.00013577072,0.00017917315,0.00011197257,0.9511129,0.000053675834,0.030918384,0.012307943,0.0038582708],"study_design_scores_gemma":[0.0002490049,0.00002964046,0.00049336493,0.00002965649,0.00003726667,0.0000056059803,0.000011333855,0.94485354,0.00014514934,0.04637421,0.0073673576,0.0004038391],"about_ca_topic_score_codex":0.0002457331,"about_ca_topic_score_gemma":0.000059026694,"teacher_disagreement_score":0.97111946,"about_ca_system_score_codex":0.00017091089,"about_ca_system_score_gemma":0.00027391678,"threshold_uncertainty_score":0.99992365},"labels":[],"label_agreement":null},{"id":"W2463733835","doi":"10.1007/978-3-319-34111-8_6","title":"Gaussian Neuron in Deep Belief Network for Sentiment Prediction","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Artificial intelligence; Gaussian; Gaussian process; Sentiment analysis; Deep belief network; Artificial neural network; Machine learning","score_opus":0.011674106813574982,"score_gpt":0.22216150511168256,"score_spread":0.2104873982981076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2463733835","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009014199,0.0003781173,0.9917629,0.0015534043,0.0035863016,0.0007345119,0.000009848869,0.000083215826,0.0018827174],"genre_scores_gemma":[0.10339436,0.00016231007,0.888031,0.002617415,0.004492194,0.000082572944,0.000013773882,0.00007945627,0.0011269168],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99642384,0.000059634633,0.0005560928,0.0015362068,0.00058183935,0.00084241276],"domain_scores_gemma":[0.9980269,0.00047077725,0.0002568469,0.0009523904,0.00014575444,0.00014732823],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009046951,0.00047681318,0.00048194246,0.0004502065,0.00026337072,0.00035936,0.001758612,0.00035288848,0.000017836788],"category_scores_gemma":[0.000057057372,0.00038752228,0.00015239467,0.00043022135,0.00030299975,0.00061503856,0.0007180717,0.0005034019,0.000018266795],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013723072,0.00002913292,0.0001214745,0.000018643042,0.000012345384,0.000025850362,0.00022934207,0.3069809,0.00012255558,0.010636304,0.00020564762,0.6816041],"study_design_scores_gemma":[0.00043845942,0.00024571663,0.0004661938,0.00040033067,0.000008574383,0.000012775975,6.371253e-8,0.8929017,0.00046365228,0.09915831,0.0054333643,0.0004708267],"about_ca_topic_score_codex":0.0000080156005,"about_ca_topic_score_gemma":0.00014802392,"teacher_disagreement_score":0.6811332,"about_ca_system_score_codex":0.00030431466,"about_ca_system_score_gemma":0.00022965674,"threshold_uncertainty_score":0.99985766},"labels":[],"label_agreement":null},{"id":"W2521066248","doi":"10.1609/aaai.v31i1.10755","title":"Enabling Dark Energy Science with Deep Generative Models of Galaxy Images","year":2017,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Autoencoder; Dark energy; Generative grammar; Galaxy; Cosmology; Calibration; Computer science; Astrophysics; Artificial intelligence; Physics; Deep learning","score_opus":0.07212541502478928,"score_gpt":0.28402776183954914,"score_spread":0.21190234681475986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2521066248","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008150147,0.00020695863,0.9673262,0.001568533,0.0008743625,0.00054271985,0.00002061436,0.00006822223,0.021242194],"genre_scores_gemma":[0.9518378,0.0002863595,0.0473761,0.00007530652,0.00016721089,0.000052546122,9.4420506e-7,0.000024963327,0.00017878479],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9958607,0.000044563047,0.00083431375,0.0013736676,0.0012658373,0.00062093546],"domain_scores_gemma":[0.9931119,0.00011214033,0.00188724,0.0012366507,0.003487456,0.00016462176],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0011003213,0.0005685074,0.0007814652,0.00035102194,0.0007401468,0.0011826225,0.0074888663,0.00019941405,0.000016662532],"category_scores_gemma":[0.00050538464,0.0003927813,0.00023327983,0.0006405084,0.002329285,0.001343597,0.0032903193,0.00061714917,0.0000041597527],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101343256,0.00014908513,0.00003630507,0.00008529524,0.00007953532,0.000001607435,0.0020717126,0.05133182,0.09037136,0.78072655,0.000086552274,0.074958794],"study_design_scores_gemma":[0.000018193858,0.00011196013,0.00002232895,0.00043754492,0.000023613973,0.0000019169606,0.00016444143,0.2996957,0.4903858,0.20887452,0.0000074072527,0.00025658042],"about_ca_topic_score_codex":0.00033063156,"about_ca_topic_score_gemma":0.000041276802,"teacher_disagreement_score":0.9436876,"about_ca_system_score_codex":0.00010041355,"about_ca_system_score_gemma":0.00093109865,"threshold_uncertainty_score":0.99985427},"labels":[],"label_agreement":null},{"id":"W2529583158","doi":"","title":"Universal approximation results for the temporal restricted Boltzmann machine and the recurrent temporal restricted Boltzmann machine","year":2016,"lang":"en","type":"article","venue":"UVic’s Research and Learning Repository (University of Victoria)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Boltzmann machine; Restricted Boltzmann machine; Boltzmann constant; Block (permutation group theory); Computer science; Markov chain; Deep belief network; Mathematics; Artificial intelligence; Algorithm; Theoretical computer science; Deep learning; Machine learning; Combinatorics; Physics","score_opus":0.02328710822824992,"score_gpt":0.2501985168564724,"score_spread":0.22691140862822246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2529583158","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16535094,0.0065061874,0.7818916,0.035256624,0.0021170971,0.003992365,0.00013356497,0.00042653736,0.0043251184],"genre_scores_gemma":[0.99055225,0.0007052019,0.0040087253,0.000009100329,0.0002901897,0.000004047232,0.000022640936,0.00001339687,0.0043944647],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996699,0.001341269,0.00027178,0.0006014495,0.00064245233,0.0004440894],"domain_scores_gemma":[0.9957508,0.0026101205,0.00030558894,0.00055242283,0.0005990528,0.00018204843],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0018333805,0.00020064591,0.00030017653,0.00021908502,0.0023126684,0.00022665695,0.00085484126,0.00012792164,0.0000052090363],"category_scores_gemma":[0.0007675091,0.00012502862,0.00010370137,0.0006638892,0.0008334923,0.0006242836,0.00057333714,0.00057608355,0.0000029458877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.07518457,0.0020732759,0.060679458,0.00092103623,0.0036409593,0.00065998465,0.06752787,0.0041994574,0.06143942,0.074932195,0.1393678,0.50937396],"study_design_scores_gemma":[0.019199302,0.003357074,0.050474092,0.00037609288,0.00015630585,0.000051548825,0.004010376,0.6110346,0.00085818616,0.0021275564,0.3075426,0.0008122864],"about_ca_topic_score_codex":0.0019446631,"about_ca_topic_score_gemma":0.0001810152,"teacher_disagreement_score":0.8252013,"about_ca_system_score_codex":0.0001022045,"about_ca_system_score_gemma":0.00015909366,"threshold_uncertainty_score":0.9989862},"labels":[],"label_agreement":null},{"id":"W2560274612","doi":"10.1007/978-3-319-50835-1_74","title":"Improving Visual Feature Representations by Biasing Restricted Boltzmann Machines with Gaussian Filters","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"MNIST database; Computer science; Restricted Boltzmann machine; Artificial intelligence; Pattern recognition (psychology); Gaussian; Feature (linguistics); Boltzmann machine; Unsupervised learning; Layer (electronics); Computer vision; Machine learning; Artificial neural network; Physics","score_opus":0.009871789417977214,"score_gpt":0.24117806811079312,"score_spread":0.2313062786928159,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560274612","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006400978,0.00036434937,0.9933116,0.0027744595,0.0009960188,0.00038739239,0.00001997794,0.00016178518,0.0019204149],"genre_scores_gemma":[0.16781686,0.00007105729,0.8250269,0.0017496976,0.00159153,0.000024700827,0.000032568307,0.00010928142,0.003577393],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99606067,0.00008299448,0.0003987276,0.0018163134,0.0008873403,0.0007539822],"domain_scores_gemma":[0.9974267,0.00053407886,0.00041446582,0.0011412187,0.0002597965,0.00022373466],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00033027804,0.00063008384,0.0005085638,0.0006436455,0.00056007877,0.0010137025,0.0020617878,0.00028080674,0.000018408531],"category_scores_gemma":[0.00013012883,0.00043901126,0.00012082479,0.0007916584,0.0006620066,0.0011627756,0.0008386854,0.00066617975,0.000014916962],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026749949,0.000038229115,0.00015481494,0.000026962238,0.000044382647,0.00014386143,0.00045543863,0.0170466,0.005826748,0.0015000002,0.0009290969,0.9738071],"study_design_scores_gemma":[0.0008262839,0.0004956539,0.0004914893,0.00093929155,0.000039768416,0.00013118607,8.0386826e-7,0.97367233,0.009402321,0.010289944,0.0020594185,0.0016514928],"about_ca_topic_score_codex":0.000058915204,"about_ca_topic_score_gemma":0.00010654965,"teacher_disagreement_score":0.97215563,"about_ca_system_score_codex":0.00021637008,"about_ca_system_score_gemma":0.0004124613,"threshold_uncertainty_score":0.99980617},"labels":[],"label_agreement":null},{"id":"W2587786495","doi":"10.1109/ijcnn.2017.7966329","title":"Generative mixture of networks","year":2017,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"MNIST database; Computer science; Cluster analysis; Artificial intelligence; Generative model; Artificial neural network; Set (abstract data type); Data modeling; Process (computing); Data set; Generative grammar; Function (biology); Pattern recognition (psychology); Machine learning; Data mining","score_opus":0.014984304996097432,"score_gpt":0.24313441086506948,"score_spread":0.22815010586897205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587786495","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00045439004,0.00009634398,0.97325313,0.0012377843,0.0004046255,0.00005621896,5.5303616e-7,0.000022612909,0.02447436],"genre_scores_gemma":[0.86977804,0.000022493285,0.12867999,0.0001918381,0.00018896475,0.00000250994,3.938534e-7,0.000003152445,0.0011326424],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99941003,0.000037469206,0.00011714661,0.00019460506,0.00009818738,0.00014258159],"domain_scores_gemma":[0.9988847,0.000032885975,0.00013613881,0.0008078706,0.000092631744,0.000045806966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013350022,0.00008225229,0.00013511785,0.000018684714,0.00028295114,0.00018788908,0.00096517743,0.000043843316,0.000044043965],"category_scores_gemma":[0.00004828152,0.00006114088,0.000060648737,0.000040347262,0.000076550685,0.00047461572,0.00027887404,0.000057941885,0.0000073550596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020053782,0.00017343563,0.004129013,0.000011737446,0.00022043893,0.00003150527,0.00079980673,0.06814972,0.015674144,0.44860867,0.07010981,0.39207166],"study_design_scores_gemma":[0.00020746276,0.000051736904,0.0068072053,0.000009800994,0.0000058268597,0.0000020165012,0.000009079069,0.94605917,0.040322598,0.0024378716,0.003928801,0.00015840333],"about_ca_topic_score_codex":0.00004398789,"about_ca_topic_score_gemma":0.000025518111,"teacher_disagreement_score":0.8779095,"about_ca_system_score_codex":0.000005185949,"about_ca_system_score_gemma":0.000018970522,"threshold_uncertainty_score":0.24932529},"labels":[],"label_agreement":null},{"id":"W2587976075","doi":"10.1109/ssci.2016.7850122","title":"Biasing restricted Boltzmann machines using Gaussian filters to learn invariant visual features","year":2016,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Artificial intelligence; Gaussian filter; Computer science; Gaussian; Pattern recognition (psychology); Unsupervised learning; Preprocessor; Boltzmann machine; Restricted Boltzmann machine; Invariant (physics); Feature extraction; Gaussian blur; Filter (signal processing); Computer vision; Deep learning; Image processing; Mathematics; Image (mathematics); Image restoration","score_opus":0.02283706878601409,"score_gpt":0.26955253099652954,"score_spread":0.24671546221051543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587976075","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02076584,0.00003625933,0.9707289,0.005249542,0.0004911777,0.00015795308,0.0000023843384,0.00015830196,0.002409688],"genre_scores_gemma":[0.7772858,0.0000062813488,0.21911994,0.0010996916,0.00034101427,0.0000040991604,7.591528e-7,0.000017535704,0.002124887],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984117,0.00017576324,0.00022218654,0.0005116731,0.00025031314,0.00042837724],"domain_scores_gemma":[0.9990892,0.00016082177,0.0000689055,0.00040036748,0.00007848592,0.00020222382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001764581,0.00020746846,0.00020021049,0.00020221052,0.00025602736,0.0003346793,0.00056279555,0.00006637597,0.000075876254],"category_scores_gemma":[0.00020256027,0.00012530864,0.00007698598,0.0005759337,0.000038829403,0.00067188125,0.00027412397,0.00008118968,0.00006254767],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000061693485,0.00008766211,0.0016193077,0.000008157172,0.000089935405,0.000091743714,0.00063222524,0.004921338,0.64324534,0.0075171827,0.019242031,0.32248336],"study_design_scores_gemma":[0.0024761981,0.0008750107,0.14902528,0.0006111899,0.00007889497,0.00018871306,0.00023526774,0.6574724,0.1652474,0.0021901422,0.018863939,0.002735581],"about_ca_topic_score_codex":0.00047430178,"about_ca_topic_score_gemma":0.00010191145,"teacher_disagreement_score":0.75652,"about_ca_system_score_codex":0.000058267506,"about_ca_system_score_gemma":0.00006539447,"threshold_uncertainty_score":0.5109938},"labels":[],"label_agreement":null},{"id":"W2593299827","doi":"10.48550/arxiv.1702.01691","title":"Calibrating Energy-based Generative Adversarial Networks","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Discriminator; Adversarial system; Generator (circuit theory); Computer science; Generative grammar; Energy (signal processing); Generative adversarial network; Artificial intelligence; Mathematical optimization; Theoretical computer science; Machine learning; Algorithm; Mathematics; Power (physics); Deep learning; Statistics","score_opus":0.04914877577270201,"score_gpt":0.17532413290173374,"score_spread":0.12617535712903172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2593299827","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029804881,0.000027633,0.9907696,0.00031852178,0.0008210818,0.00008689678,0.0000035683886,0.00012822686,0.0048639663],"genre_scores_gemma":[0.9868132,0.000018727364,0.01131973,0.00044374325,0.00047676207,8.9660915e-7,0.0000050690264,0.000015253026,0.0009066564],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983471,0.00019283945,0.00016308099,0.000772643,0.00008357883,0.00044073453],"domain_scores_gemma":[0.99795514,0.00012276342,0.00028684628,0.001309023,0.00012877389,0.00019745862],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00021044504,0.00025323388,0.0002483174,0.00008477165,0.0014080792,0.000517431,0.0017714857,0.0001311684,0.000046820216],"category_scores_gemma":[0.00007494334,0.0002647164,0.00017705878,0.00023504409,0.00019975177,0.0015091698,0.0005008978,0.00016643204,0.00001966702],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028660783,0.000040849707,0.0010883722,0.0000018907641,0.000046535693,0.0001597492,0.000037903956,0.84909177,0.00019233834,0.14537959,0.0009319202,0.0030004093],"study_design_scores_gemma":[0.0007698729,0.000059667567,0.0005022915,0.000014993607,0.000024040766,0.0000012270524,0.000017180539,0.99219966,0.0018990313,0.0029272395,0.0012612604,0.00032355817],"about_ca_topic_score_codex":0.00029726335,"about_ca_topic_score_gemma":0.00014956311,"teacher_disagreement_score":0.98383266,"about_ca_system_score_codex":0.00007529535,"about_ca_system_score_gemma":0.00012770173,"threshold_uncertainty_score":0.9999805},"labels":[],"label_agreement":null},{"id":"W2612164513","doi":"","title":"Texture Transfer Based on Texture Descriptor Variations","year":2017,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Texture filtering; Texture (cosmology); Texture compression; Projective texture mapping; Bidirectional texture function; Texture atlas; Artificial intelligence; Image texture; Computer science; Luminance; Displacement mapping; Computer vision; Texel; Pattern recognition (psychology); Orientation (vector space); Texture mapping; Mathematics; Image (mathematics); Geometry; Image segmentation","score_opus":0.016205844423762227,"score_gpt":0.22014157919301092,"score_spread":0.2039357347692487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612164513","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026338256,0.00032499345,0.92976654,0.027072983,0.0007496488,0.0004916264,0.00008878069,0.00026014284,0.040981926],"genre_scores_gemma":[0.80245847,0.00011341002,0.19008835,0.00057543296,0.000093019546,0.000101189486,0.00021629242,0.00004655997,0.0063072885],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9929876,0.0042666537,0.0004541833,0.0012457079,0.00059153803,0.00045432049],"domain_scores_gemma":[0.99179554,0.0011010453,0.0003343294,0.004763104,0.0017616667,0.00024429394],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003403973,0.00049885747,0.00045692406,0.0002211778,0.0010356967,0.0017938716,0.003796988,0.00047490105,0.0001621843],"category_scores_gemma":[0.0012992335,0.00048076408,0.000380676,0.00025812787,0.00019375919,0.00036221676,0.00095866853,0.0009800743,0.00006752437],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004296828,0.0023078085,0.0006788929,0.0002676145,0.00037204238,0.000054674743,0.012988908,0.024633063,0.0045520887,0.5117991,0.027008845,0.415294],"study_design_scores_gemma":[0.0005927596,9.760047e-7,0.0034346702,0.0012793475,0.000060423296,0.000002991407,0.000012647307,0.94341195,0.01120183,0.00607809,0.033222236,0.00070209615],"about_ca_topic_score_codex":0.00046230614,"about_ca_topic_score_gemma":0.0006229314,"teacher_disagreement_score":0.9187789,"about_ca_system_score_codex":0.00012714445,"about_ca_system_score_gemma":0.0005398048,"threshold_uncertainty_score":0.9997644},"labels":[],"label_agreement":null},{"id":"W2614634292","doi":"","title":"What Regularized Auto-Encoders Learn from the Data Generating Distribution","year":2013,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":252,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Encoder; Algorithm; Computer science; Probability density function; Autoencoder; Function (biology); Pattern recognition (psychology); Mathematics; Artificial intelligence; Statistics; Deep learning","score_opus":0.03234249990471007,"score_gpt":0.23857543805488393,"score_spread":0.20623293815017385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2614634292","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017971871,0.00026238413,0.9798994,0.016618788,0.00085219543,0.00020121477,0.000012263814,0.00010782368,0.0002487444],"genre_scores_gemma":[0.55748594,0.00027034973,0.43158302,0.0042786375,0.001256771,0.00004405614,0.00074017525,0.00002062008,0.004320446],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857444,0.00023173353,0.00020238267,0.0005032296,0.00023216507,0.00025605026],"domain_scores_gemma":[0.99793625,0.00026637973,0.0000792738,0.0015589481,0.00009372224,0.000065444394],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00037877684,0.00013296431,0.00012821995,0.000008732747,0.00038452935,0.002070459,0.0018144996,0.00005156571,0.00023502459],"category_scores_gemma":[0.0001530757,0.000081061575,0.00004298477,0.00019038831,0.000061289764,0.004025831,0.00094073033,0.00012580435,0.00018304883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035245457,0.000051252067,0.00016721374,0.0000018896102,0.00010463969,0.0000032317744,0.00086147845,0.00596883,0.028697578,0.0052973023,0.49646357,0.46237952],"study_design_scores_gemma":[0.00013926443,0.000009452924,0.0005876051,0.000011126532,0.000007760537,9.0538606e-7,0.00024757787,0.9744575,0.0014048882,0.0013805404,0.021626817,0.00012654961],"about_ca_topic_score_codex":0.0012080249,"about_ca_topic_score_gemma":0.00009219836,"teacher_disagreement_score":0.9684887,"about_ca_system_score_codex":0.000022485281,"about_ca_system_score_gemma":0.000045479985,"threshold_uncertainty_score":0.9989655},"labels":[],"label_agreement":null},{"id":"W2735582123","doi":"10.1109/ijcnn.2017.7965877","title":"Relational autoencoder for feature extraction","year":2017,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":169,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Autoencoder; Pattern recognition (psychology); Benchmark (surveying); Feature extraction; Feature (linguistics); Data set; Artificial neural network","score_opus":0.047355841289273434,"score_gpt":0.2927587655728269,"score_spread":0.24540292428355343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2735582123","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000046174137,0.000017010985,0.9760853,0.0073521584,0.00059626624,0.00008983668,0.0000017237278,0.000040558196,0.015770964],"genre_scores_gemma":[0.25007653,0.0000027464548,0.7384078,0.0002112074,0.0003135307,0.000011592499,0.0000028512213,0.0000032790833,0.010970455],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995874,0.000010208764,0.0000539441,0.0001691273,0.00007978821,0.00009952657],"domain_scores_gemma":[0.9994135,0.000055794382,0.00006843088,0.0003612641,0.000071895614,0.000029148194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012157801,0.000051609928,0.00005371628,0.000015523627,0.0005646349,0.0002719161,0.0003232664,0.000040690058,0.00002716557],"category_scores_gemma":[0.0000892313,0.000041105697,0.00004731188,0.000016039445,0.000018593524,0.0009651888,0.000058222115,0.000043103937,0.000019469097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014848483,0.000058577913,0.0010920909,0.0000049757814,0.000046251782,0.0000031760926,0.00012914937,0.008646148,0.0041301074,0.5898222,0.20007437,0.19597813],"study_design_scores_gemma":[0.00019363762,0.00002111733,0.037009556,0.000003150421,0.0000036659455,0.0000027292674,0.000002628349,0.8672048,0.002529226,0.0085142795,0.08441972,0.00009550615],"about_ca_topic_score_codex":0.0000116051615,"about_ca_topic_score_gemma":0.000012761966,"teacher_disagreement_score":0.85855865,"about_ca_system_score_codex":0.000010904582,"about_ca_system_score_gemma":0.000022783155,"threshold_uncertainty_score":0.43427724},"labels":[],"label_agreement":null},{"id":"W2735624697","doi":"10.1109/ijcnn.2017.7966133","title":"Using information fractal dimension as temperature in restricted Boltzmann Machine","year":2017,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Boltzmann machine; MNIST database; Restricted Boltzmann machine; Fractal; Dimension (graph theory); Convergence (economics); Fractal dimension; Computer science; Similarity (geometry); Divergence (linguistics); Intrinsic dimension; Generalization; Algorithm; Mathematics; Boltzmann constant; Multifractal system; Artificial intelligence; Pattern recognition (psychology); Artificial neural network; Mathematical analysis; Physics","score_opus":0.017222528576094263,"score_gpt":0.26500930202106426,"score_spread":0.24778677344497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2735624697","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5999127,0.00006255466,0.37685072,0.0026405137,0.00091332017,0.00030722874,0.000003080514,0.00011077323,0.01919913],"genre_scores_gemma":[0.96059304,0.00001058135,0.038835425,0.00035031492,0.0000578972,0.0000016067712,0.000004867054,0.0000029392932,0.00014331985],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993024,0.000042568383,0.00017403527,0.00015118255,0.00016198207,0.00016784253],"domain_scores_gemma":[0.99922734,0.000022714683,0.00012220356,0.00050747336,0.000071065144,0.000049221766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012495749,0.00010142059,0.00011035542,0.000095198135,0.0003682736,0.0006345028,0.00046094976,0.00007171127,0.00001517704],"category_scores_gemma":[0.00015643174,0.00008017061,0.000030669376,0.00012006649,0.000022696031,0.0035138016,0.00025238362,0.00013448886,0.00003994401],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029689536,0.0005809423,0.038678586,0.000065799024,0.00014905188,0.0003394947,0.0057226946,0.08232508,0.40303883,0.091244824,0.01894375,0.35861406],"study_design_scores_gemma":[0.00044052996,0.000038841557,0.03416527,0.000026191792,0.0000029122516,0.000010096421,0.000020921985,0.9508552,0.011597874,0.0005648395,0.00210086,0.00017647845],"about_ca_topic_score_codex":0.0013868788,"about_ca_topic_score_gemma":0.000087726614,"teacher_disagreement_score":0.8685301,"about_ca_system_score_codex":0.000030205876,"about_ca_system_score_gemma":0.000044243297,"threshold_uncertainty_score":0.6118525},"labels":[],"label_agreement":null},{"id":"W2751076446","doi":"10.48550/arxiv.1706.00531","title":"PixelGAN Autoencoders","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Autoencoder; MNIST database; Computer science; Artificial intelligence; Prior probability; Categorical variable; Autoregressive model; Pattern recognition (psychology); Convolutional neural network; Code (set theory); Path (computing); Generative model; Latent variable; Machine learning; Generative grammar; Artificial neural network; Mathematics; Statistics; Bayesian probability","score_opus":0.07077785933164851,"score_gpt":0.17832673428462967,"score_spread":0.10754887495298115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2751076446","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01330194,0.000010847845,0.9635822,0.00042050422,0.00040136333,0.000064116684,0.0000010877965,0.00010247342,0.022115448],"genre_scores_gemma":[0.9914165,0.000026952346,0.0051524034,0.00012724311,0.00007846621,1.5367294e-7,4.7107105e-7,0.000006007003,0.0031918078],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990993,0.000052186868,0.00007287379,0.00046585215,0.000048341582,0.00026142012],"domain_scores_gemma":[0.9984553,0.000036505462,0.000119010416,0.0012013242,0.00006600379,0.000121841134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013879628,0.00012278491,0.0001254713,0.00005529854,0.0007803994,0.00028205593,0.001735341,0.000051952175,0.00004499693],"category_scores_gemma":[0.00005420278,0.00012830782,0.00009260862,0.00012651672,0.00013877414,0.0012497067,0.00044072676,0.0000937347,0.00015931757],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002771584,0.00012984987,0.011761015,0.000009792212,0.00012321684,0.0005681184,0.0003605806,0.33297515,0.00070712884,0.63453317,0.006073519,0.012730765],"study_design_scores_gemma":[0.00034307528,0.000035279354,0.0076704333,0.000008451916,0.000013212866,0.000002513595,0.000030748553,0.974228,0.000535061,0.012438535,0.004476641,0.00021802504],"about_ca_topic_score_codex":0.000116917596,"about_ca_topic_score_gemma":0.00009006685,"teacher_disagreement_score":0.97811455,"about_ca_system_score_codex":0.00003845419,"about_ca_system_score_gemma":0.00004538309,"threshold_uncertainty_score":0.6002281},"labels":[],"label_agreement":null},{"id":"W2751842161","doi":"","title":"Improving Generative Adversarial Networks with Denoising Feature Matching","year":2017,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":160,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Discriminator; Generator (circuit theory); Computer science; Artificial intelligence; Generative grammar; Set (abstract data type); Adversarial system; Pattern recognition (psychology); Feature (linguistics); Matching (statistics); Task (project management); Noise reduction; Encoder; Image (mathematics); Feature extraction; Machine learning; Mathematics; Power (physics); Engineering","score_opus":0.027347600635553772,"score_gpt":0.2982712933071036,"score_spread":0.27092369267154987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2751842161","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006258005,0.000011021975,0.9649398,0.0063131903,0.0009801749,0.00014729398,0.000002713923,0.000106855616,0.021240944],"genre_scores_gemma":[0.95088595,0.000017067825,0.045364995,0.00015854185,0.0006397744,0.00003766918,0.000019766298,0.0000159183,0.0028602881],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984215,0.00014186036,0.00017917872,0.00056999235,0.0004245693,0.00026291076],"domain_scores_gemma":[0.9984544,0.00015078692,0.00040675775,0.00059258565,0.00030303033,0.0000924737],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00021926395,0.0002008797,0.00016579885,0.00011061923,0.0015607564,0.00229326,0.0012362656,0.000074629526,0.000078464545],"category_scores_gemma":[0.00030470197,0.00017360186,0.000074376134,0.00008042408,0.000115586045,0.0014284323,0.0003160682,0.0005036902,0.000025293943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001382996,0.00009559592,0.0060495157,0.0000039715515,0.0003037454,0.00011908489,0.0030473033,0.77270263,0.0059791524,0.118900865,0.0010167555,0.091643065],"study_design_scores_gemma":[0.00061419094,0.00010477029,0.0066691255,0.00007612257,0.000016330314,0.000017085677,0.00035394606,0.9886411,0.0011478964,0.0012025053,0.00087522087,0.0002817005],"about_ca_topic_score_codex":0.00035971243,"about_ca_topic_score_gemma":0.000107361215,"teacher_disagreement_score":0.944628,"about_ca_system_score_codex":0.00006890718,"about_ca_system_score_gemma":0.00010816987,"threshold_uncertainty_score":0.99973905},"labels":[],"label_agreement":null},{"id":"W2765811365","doi":"10.1109/msp.2017.2765202","title":"Generative Adversarial Networks: An Overview","year":2018,"lang":"en","type":"article","venue":"IEEE Signal Processing Magazine","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4422,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Concordia University","funders":"Victoria University of Wellington; Imperial College London; University of Georgia; Engineering and Physical Sciences Research Council; Massachusetts Institute of Technology","keywords":"Computer science; Generative grammar; Adversarial system; Artificial intelligence; Variety (cybernetics); Process (computing); Image (mathematics); Point (geometry); Machine learning","score_opus":0.041854680906337496,"score_gpt":0.28987676147729413,"score_spread":0.24802208057095665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765811365","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006140013,0.0013256668,0.99295485,0.0004448648,0.0010384085,0.00018168965,0.0000027806666,0.0002515802,0.0031861763],"genre_scores_gemma":[0.8881054,0.000063214495,0.10335048,0.0017792425,0.005995813,0.000015312364,0.000008452913,0.00003597771,0.0006461281],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976036,0.00025263615,0.00037911886,0.00079173484,0.00038828715,0.0005846126],"domain_scores_gemma":[0.9985252,0.000055304346,0.00020542259,0.0004909323,0.00048733922,0.0002357714],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000515379,0.00033856297,0.0003379858,0.00010592339,0.00057860307,0.00062084646,0.0009622183,0.00012200768,0.00017280823],"category_scores_gemma":[0.000022496943,0.0002951276,0.00009704982,0.0007527636,0.00025041265,0.002030638,0.00015180258,0.00021445249,0.00020628952],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000120386816,0.00030050272,0.000059870625,0.000040883104,0.00008500378,0.00005819276,0.0012728494,0.03852045,0.038203966,0.0038875388,0.020349834,0.8971005],"study_design_scores_gemma":[0.000496922,0.00044868552,0.00021214462,0.00006962534,0.000025187048,0.00001748968,0.0000115092635,0.97369254,0.009490452,0.0019884587,0.0131029,0.00044406037],"about_ca_topic_score_codex":0.000014962164,"about_ca_topic_score_gemma":0.000049714094,"teacher_disagreement_score":0.93517214,"about_ca_system_score_codex":0.000053686068,"about_ca_system_score_gemma":0.00025696727,"threshold_uncertainty_score":0.9999501},"labels":[],"label_agreement":null},{"id":"W2765932136","doi":"10.1145/3123266.3123334","title":"Metric-based Generative Adversarial Network","year":2017,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"New York University Abu Dhabi; Canadian Institute for Advanced Research","keywords":"Discriminator; Margin (machine learning); Metric (unit); Generator (circuit theory); Computer science; Artificial intelligence; Sample (material); Feature (linguistics); Feature vector; Generative grammar; Energy (signal processing); Focus (optics); Pattern recognition (psychology); Adversarial system; Machine learning; Mathematics; Power (physics); Statistics; Engineering","score_opus":0.021924888726178992,"score_gpt":0.25575391217170695,"score_spread":0.23382902344552797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765932136","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013943532,0.00006800343,0.95775926,0.0027386732,0.001791021,0.00014276984,0.000001380579,0.00010939597,0.037250068],"genre_scores_gemma":[0.6522967,0.000005824717,0.34459233,0.00096693577,0.0011252422,0.000010965245,0.0000015199255,0.00000809851,0.000992337],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855965,0.000112775044,0.00019339724,0.00046276502,0.0002628612,0.00040853495],"domain_scores_gemma":[0.99808013,0.00013270378,0.00018791118,0.0013342778,0.00013225147,0.00013273588],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041026933,0.00018404935,0.00022211163,0.000060755854,0.0012321313,0.0009354185,0.0016879344,0.00007277508,0.0001422003],"category_scores_gemma":[0.00022133092,0.00014858514,0.00013193347,0.00018365699,0.00009460113,0.00090524065,0.00038834772,0.00011009026,0.00011800992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006967771,0.00021038,0.0038392688,0.000008294185,0.00025576583,0.00010202988,0.00020954617,0.35508022,0.0015544055,0.24673143,0.18368928,0.20824969],"study_design_scores_gemma":[0.0008653381,0.00010066381,0.0044212504,0.0000094048955,0.000016144872,0.0000014330855,0.000005458814,0.9463723,0.011518846,0.003872549,0.0324455,0.00037113146],"about_ca_topic_score_codex":0.0001304267,"about_ca_topic_score_gemma":0.000064063424,"teacher_disagreement_score":0.6521573,"about_ca_system_score_codex":0.00003337386,"about_ca_system_score_gemma":0.00010748802,"threshold_uncertainty_score":0.94766825},"labels":[],"label_agreement":null},{"id":"W2768910279","doi":"10.48550/arxiv.1711.06020","title":"Global versus Localized Generative Adversarial Nets","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Manifold (fluid mechanics); Tangent space; Subspace topology; Generator (circuit theory); Mathematics; Manifold alignment; Classifier (UML); Topology (electrical circuits); Tangent; Computer science; Locality; Orthonormality; Artificial intelligence; Algorithm; Nonlinear dimensionality reduction; Geometry; Orthonormal basis; Combinatorics; Physics","score_opus":0.08737791151025937,"score_gpt":0.21942035059362566,"score_spread":0.1320424390833663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2768910279","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059575127,0.00016621538,0.9717439,0.00038384626,0.0069755535,0.0004166443,0.00007553447,0.0002511671,0.014029628],"genre_scores_gemma":[0.9859331,0.00021493479,0.011735384,0.00014881522,0.00073847576,0.0000022667116,0.000037915812,0.000022130931,0.0011669487],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99656165,0.0004075352,0.00028823293,0.0018776128,0.00019821685,0.0006667834],"domain_scores_gemma":[0.9961486,0.00013278621,0.0005543201,0.002496824,0.00032505387,0.00034244495],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030451213,0.0006300102,0.00067428057,0.00012264011,0.0006836181,0.0006329706,0.0038244196,0.00053410797,0.00007541051],"category_scores_gemma":[0.00015626194,0.0006991036,0.0004942809,0.000353499,0.00032624463,0.00084979786,0.0040383707,0.0004980107,0.00015617526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042545074,0.00010505126,0.00036596804,0.000018186553,0.0004942674,0.00061107345,0.00013236572,0.89501566,0.000014902949,0.09187455,0.0068993303,0.0040431763],"study_design_scores_gemma":[0.0028767108,0.00013330234,0.0003590308,0.000060501385,0.00017740672,0.0000032338517,0.0000338138,0.9569345,0.00015769049,0.029607566,0.008764252,0.0008919824],"about_ca_topic_score_codex":0.00074700674,"about_ca_topic_score_gemma":0.00041503526,"teacher_disagreement_score":0.97997564,"about_ca_system_score_codex":0.0005307124,"about_ca_system_score_gemma":0.0006102504,"threshold_uncertainty_score":0.999546},"labels":[],"label_agreement":null},{"id":"W2771857061","doi":"10.1109/smc.2017.8122884","title":"Hairstyle pattern recognition based on CNNs","year":2017,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Artificial intelligence; Leverage (statistics); Computer vision; Task (project management); Pattern recognition (psychology); Engineering","score_opus":0.03361614520295545,"score_gpt":0.24517630074936805,"score_spread":0.2115601555464126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2771857061","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007564078,0.000001923392,0.9408257,0.003793583,0.00039450274,0.00006317665,0.0000019923777,0.000064522836,0.05409819],"genre_scores_gemma":[0.9663926,0.0000018139428,0.031421863,0.0015316155,0.00015255935,0.0000070623123,0.0000021321184,0.000004549731,0.0004858062],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993665,0.000038366903,0.000079071375,0.0002422683,0.00012624363,0.0001475257],"domain_scores_gemma":[0.99905527,0.000049184546,0.000066422974,0.00072950847,0.00004713483,0.000052457504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001416926,0.00008099586,0.000075877724,0.00003110441,0.0003987123,0.0004314193,0.0005697041,0.000029943489,0.00018372],"category_scores_gemma":[0.000061882085,0.00006491828,0.000050351387,0.000026439924,0.00002708895,0.00042067314,0.000089452944,0.000052362466,0.00038735959],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004124788,0.00006453913,0.0007140763,0.0000024388125,0.0000067528704,0.000010550722,0.000034757828,0.00089693186,0.00026745017,0.000261401,0.008170133,0.98956686],"study_design_scores_gemma":[0.00030579374,0.00009124225,0.009660318,0.000020892001,0.0000030341296,5.978325e-7,0.000003902142,0.97279054,0.012513587,0.00073780643,0.0037137114,0.00015856298],"about_ca_topic_score_codex":0.00010604065,"about_ca_topic_score_gemma":0.000051485757,"teacher_disagreement_score":0.98940825,"about_ca_system_score_codex":0.000011793333,"about_ca_system_score_gemma":0.000016518286,"threshold_uncertainty_score":0.49788532},"labels":[],"label_agreement":null},{"id":"W2773981138","doi":"","title":"Parametric Adversarial Divergences are Good Task Losses for Generative Modeling","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Parametric statistics; Generative grammar; Machine learning; Artificial intelligence; Task (project management); Divergence (linguistics); Nonparametric statistics; Generator (circuit theory); Adversarial system; Parametric model; Generative model; Mathematics; Econometrics","score_opus":0.11974810169704711,"score_gpt":0.21723471674240824,"score_spread":0.09748661504536113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773981138","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019940872,0.0003471649,0.97479904,0.0002120244,0.0029612693,0.0007086631,0.00012360969,0.00015491013,0.0007524343],"genre_scores_gemma":[0.9792404,0.00053247216,0.018296314,0.00007131194,0.000806124,0.000008657579,0.000032950426,0.000027819224,0.0009839396],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967708,0.00023045733,0.00032597018,0.0018688538,0.00017939991,0.0006245286],"domain_scores_gemma":[0.9964901,0.00027158175,0.000746233,0.001680721,0.00057434017,0.00023697957],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004115714,0.0005756033,0.00070811476,0.00035726078,0.0010710857,0.00063575164,0.003335033,0.00043023037,0.00001916333],"category_scores_gemma":[0.00032430628,0.00060639135,0.00055640104,0.00043611322,0.00017863308,0.0010309542,0.00246668,0.000480866,0.00003364027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049013197,0.00008024599,0.00056792074,0.000043379638,0.00025879877,0.000069600304,0.00014204251,0.9792566,0.00002309954,0.017811688,0.000692144,0.0010055237],"study_design_scores_gemma":[0.0006070227,0.00007953975,0.00010063191,0.000076928496,0.0001752149,0.0000012266389,0.00010831806,0.95139545,0.00027707926,0.04590421,0.00058530597,0.0006890651],"about_ca_topic_score_codex":0.00042416452,"about_ca_topic_score_gemma":0.00015243598,"teacher_disagreement_score":0.95929956,"about_ca_system_score_codex":0.00019676347,"about_ca_system_score_gemma":0.00035944703,"threshold_uncertainty_score":0.99963874},"labels":[],"label_agreement":null},{"id":"W2784067649","doi":"10.48550/arxiv.1801.03558","title":"Inference Suboptimality in Variational Autoencoders","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Inference; Imperfect; Divergence (linguistics); Approximate inference; Computer science; Latent variable; Artificial intelligence; Artificial neural network; Generator (circuit theory); Algorithm; Machine learning; Mathematics; Applied mathematics; Pattern recognition (psychology); Power (physics); Physics","score_opus":0.07834561634935609,"score_gpt":0.20282025004742138,"score_spread":0.12447463369806529,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2784067649","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019093193,0.000018883116,0.97522396,0.00016161636,0.00071636256,0.00019265537,0.000013040632,0.00011372978,0.0044665765],"genre_scores_gemma":[0.96794516,0.000051673618,0.03134878,0.00011492535,0.00014224209,0.0000012571785,0.000014047293,0.000009444433,0.00037245447],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997846,0.00028788164,0.00023973061,0.0011384102,0.0001155778,0.0003724121],"domain_scores_gemma":[0.99827754,0.00018685007,0.00022082012,0.00096356444,0.00022591342,0.00012529698],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046327576,0.0002890652,0.00031895004,0.00024155223,0.00012456784,0.00016709999,0.0016592399,0.00026835906,0.00009722907],"category_scores_gemma":[0.00011229404,0.00033542886,0.00014758995,0.00063972396,0.00015582202,0.000570681,0.0017766957,0.0004571198,0.00009859589],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013403938,0.00007095978,0.007015851,0.000014209198,0.000036402194,0.00006730431,0.00017633718,0.90928715,0.000007128641,0.08280186,0.00027395875,0.00023541387],"study_design_scores_gemma":[0.00025162264,0.000026484367,0.018667039,0.00004374991,0.000015211505,6.9130107e-7,0.000012444595,0.91778797,0.000037808462,0.06261221,0.00021312626,0.00033163617],"about_ca_topic_score_codex":0.00048138123,"about_ca_topic_score_gemma":0.00023120995,"teacher_disagreement_score":0.948852,"about_ca_system_score_codex":0.00024592935,"about_ca_system_score_gemma":0.00041985282,"threshold_uncertainty_score":0.99990976},"labels":[],"label_agreement":null},{"id":"W2786720420","doi":"10.48550/arxiv.1805.03644","title":"Improving GAN Training via Binarized Representation Entropy (BRE) Regularization","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Royal Bank of Canada","funders":"","keywords":"Discriminator; Computer science; Extrapolation; Cross entropy; Regularization (linguistics); Binary number; Entropy (arrow of time); Stability (learning theory); Artificial intelligence; Machine learning; Generative grammar; Generator (circuit theory); Representation (politics); Pattern recognition (psychology); Mathematics; Statistics","score_opus":0.06697326294661823,"score_gpt":0.19371033551839442,"score_spread":0.1267370725717762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2786720420","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012006114,0.000022059243,0.9845922,0.0001297848,0.001207261,0.0003677419,0.0000051778784,0.00025814533,0.0014115078],"genre_scores_gemma":[0.96174777,0.000033874687,0.03645829,0.00007826433,0.00043495474,0.0000017485439,0.000049797163,0.000025769745,0.0011695417],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973622,0.00037936508,0.00029249108,0.0014002174,0.00014401361,0.00042170245],"domain_scores_gemma":[0.9976905,0.000099425364,0.00050806487,0.0012204798,0.00032400843,0.00015753556],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035956322,0.0003499699,0.00038443264,0.0002736825,0.00034866054,0.0003144682,0.0012427652,0.0003009661,0.0000529128],"category_scores_gemma":[0.000087914974,0.00040679253,0.00023450814,0.000720677,0.00014062479,0.00082562387,0.0010295176,0.00035960556,0.000048388334],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013756954,0.0001571221,0.0007050693,0.000089112014,0.00033423802,0.00026386557,0.0025262244,0.8990545,0.01821765,0.046509326,0.0007648242,0.031240463],"study_design_scores_gemma":[0.0005114061,0.00006063545,0.00022910189,0.00005407637,0.000081648934,0.0000037462703,0.000087501525,0.9703249,0.0039492683,0.024057353,0.00021794355,0.00042247292],"about_ca_topic_score_codex":0.00023743162,"about_ca_topic_score_gemma":0.000022125363,"teacher_disagreement_score":0.94974166,"about_ca_system_score_codex":0.000195296,"about_ca_system_score_gemma":0.0002010085,"threshold_uncertainty_score":0.9998384},"labels":[],"label_agreement":null},{"id":"W2787032417","doi":"10.1109/icci-cc.2018.8482059","title":"Style Memory: Making a Classifier Network Generative","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Autoencoder; Classifier (UML); Artificial intelligence; Generative grammar; Artificial neural network; Deep learning; Machine learning; Pattern recognition (psychology)","score_opus":0.03639034069867635,"score_gpt":0.2702397615647228,"score_spread":0.23384942086604643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2787032417","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014151564,0.00039174999,0.9235842,0.0016479993,0.0042451113,0.00041251243,0.0000058083415,0.00029482506,0.06927628],"genre_scores_gemma":[0.23564814,0.00005443728,0.74842393,0.0033135004,0.0069991183,0.000099550394,0.000015600805,0.000047402493,0.0053983303],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966958,0.00040468483,0.00045112436,0.0013214729,0.00042229376,0.00070463005],"domain_scores_gemma":[0.99748546,0.00012698829,0.0003339533,0.001593825,0.0003205839,0.00013921778],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006363152,0.000524836,0.0005774809,0.00010065568,0.0003784501,0.00094290235,0.0018977653,0.00038508978,0.00047617842],"category_scores_gemma":[0.000059380713,0.00044284377,0.00028072103,0.00033454588,0.00014639695,0.00034858414,0.0040836995,0.0005911775,0.00024728433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021410358,0.00009798103,0.0001086407,0.00004574352,0.0005065029,0.000060241044,0.0014587181,0.14624281,0.000210296,0.024774456,0.7754326,0.051040635],"study_design_scores_gemma":[0.00019494689,0.00007401724,0.00018630007,0.00015389582,0.000040169063,0.0000058730056,0.000035648656,0.94096994,0.0014106042,0.020166194,0.035937615,0.0008247736],"about_ca_topic_score_codex":0.00004188076,"about_ca_topic_score_gemma":0.00008731796,"teacher_disagreement_score":0.79472715,"about_ca_system_score_codex":0.00011257697,"about_ca_system_score_gemma":0.00027414592,"threshold_uncertainty_score":0.99980235},"labels":[],"label_agreement":null},{"id":"W2787038193","doi":"","title":"Boundary Seeking GANs","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of Waterloo","funders":"","keywords":"Discriminator; Generator (circuit theory); Boundary (topology); Measure (data warehouse); Computer science; Decision boundary; Image (mathematics); Differentiable function; Stability (learning theory); Generative grammar; Scale (ratio); Artificial intelligence; Character (mathematics); Pattern recognition (psychology); Algorithm; Mathematics; Machine learning; Data mining; Mathematical analysis; Geometry; Power (physics)","score_opus":0.04253164387224141,"score_gpt":0.32565739840824387,"score_spread":0.28312575453600247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2787038193","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048914864,0.0000062869603,0.79039574,0.0060496368,0.0011231896,0.00006960284,0.000002333736,0.00015189154,0.19730987],"genre_scores_gemma":[0.980822,0.000014295862,0.011691254,0.0003725034,0.00053375016,0.000024198354,0.000011887492,0.000007919728,0.0065221535],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988113,0.00011871042,0.0001787445,0.0003754899,0.00033832216,0.00017740582],"domain_scores_gemma":[0.99898374,0.00013015434,0.000102706625,0.0002740466,0.00044664863,0.00006271565],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016854859,0.00010746725,0.00008727701,0.00014204386,0.00040831382,0.0005371855,0.00066822505,0.000035722383,0.0009636235],"category_scores_gemma":[0.00027241837,0.00010592186,0.00005787909,0.00021009534,0.00012576535,0.00053859234,0.00015876799,0.00019945836,0.0005133149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053562704,0.00022613583,0.011251303,0.0000042948636,0.0002592361,0.00004528329,0.009239326,0.010603655,0.03754551,0.77206385,0.0141639365,0.14454389],"study_design_scores_gemma":[0.00028710344,0.0001688373,0.011242269,0.000044070166,0.000006312097,0.000013559559,0.0003528607,0.92698044,0.003725295,0.010972479,0.045968153,0.00023862091],"about_ca_topic_score_codex":0.000057051333,"about_ca_topic_score_gemma":0.00001863999,"teacher_disagreement_score":0.9759306,"about_ca_system_score_codex":0.00004109326,"about_ca_system_score_gemma":0.00008635797,"threshold_uncertainty_score":0.99994963},"labels":[],"label_agreement":null},{"id":"W2787266142","doi":"10.1109/crv.2019.00025","title":"Generative Adversarial Networks Using Adaptive Convolution","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Upsampling; Convolution (computer science); Computer science; Margin (machine learning); Generator (circuit theory); Context (archaeology); Artificial intelligence; Feature (linguistics); Baseline (sea); Pattern recognition (psychology); Image (mathematics); Algorithm; Machine learning; Artificial neural network; Power (physics)","score_opus":0.03829399933512447,"score_gpt":0.2517887654718297,"score_spread":0.21349476613670523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2787266142","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00036508092,0.0005947757,0.9848718,0.0002480338,0.008174015,0.00079773343,0.000014375036,0.00020395026,0.004730242],"genre_scores_gemma":[0.6574035,0.00007154912,0.3393465,0.000446818,0.0019623733,0.000023339951,0.00003156172,0.000032067866,0.00068230036],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967091,0.00046879397,0.0004974692,0.0013148461,0.00041501728,0.0005947773],"domain_scores_gemma":[0.9976683,0.00015327177,0.00043213353,0.0012054073,0.00038934677,0.0001514989],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043050788,0.0005725417,0.0006753119,0.00016200909,0.00024112375,0.000474171,0.0013122283,0.00057219825,0.00009150641],"category_scores_gemma":[0.000039491493,0.00052689464,0.00034593526,0.00027875256,0.00010438666,0.00060983247,0.0027646131,0.0008067791,0.00006964683],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023148563,0.00003333366,0.000032961405,0.00000744258,0.00017230456,0.00000787485,0.00017229025,0.98273474,0.00021150312,0.010809498,0.0029076766,0.0028872231],"study_design_scores_gemma":[0.00037410486,0.000071958224,0.00008659517,0.00007069748,0.000058506932,0.000004461357,0.000035700486,0.99490196,0.0008183185,0.0023818421,0.0005674356,0.00062844536],"about_ca_topic_score_codex":0.00046710178,"about_ca_topic_score_gemma":0.00003422322,"teacher_disagreement_score":0.65703845,"about_ca_system_score_codex":0.00033164807,"about_ca_system_score_gemma":0.0005213572,"threshold_uncertainty_score":0.99971825},"labels":[],"label_agreement":null},{"id":"W2788592841","doi":"10.1007/978-3-319-93040-4_21","title":"MIDA: Multiple Imputation Using Denoising Autoencoders","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":281,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Imputation (statistics); Missing data; Computer science; Artificial intelligence; Noise reduction; Data mining; Pattern recognition (psychology); Machine learning","score_opus":0.024484699020664805,"score_gpt":0.2509454465976662,"score_spread":0.2264607475770014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2788592841","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026536227,0.00026629187,0.9957481,0.00021878786,0.0024535747,0.0003118203,0.000002975713,0.00013535896,0.00059771916],"genre_scores_gemma":[0.16997352,0.000013216576,0.8281757,0.00064224174,0.0010377276,0.0000024163814,0.0000032085945,0.000035979792,0.00011598018],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963677,0.0000617754,0.00051184057,0.0015415037,0.0008054178,0.0007117939],"domain_scores_gemma":[0.9976575,0.0004346631,0.00035572812,0.0009996801,0.00038644942,0.00016598805],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00079855486,0.0005285319,0.00048299553,0.0006752187,0.0005097031,0.0008507507,0.002091486,0.00029147143,0.000036332487],"category_scores_gemma":[0.00016333778,0.0004982229,0.00015280931,0.00061405584,0.00075499935,0.0010945511,0.0010353072,0.00046602997,0.00004657723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000049557743,0.000016378915,0.00006163413,0.0000165385,0.000017796308,0.000045426346,0.0011342679,0.73298526,0.0009647235,0.000587188,0.00005032349,0.2641155],"study_design_scores_gemma":[0.00018499898,0.00008545932,0.000046488272,0.00024106543,0.000011267953,0.000036653706,3.2373822e-7,0.95820695,0.0032386403,0.037009522,0.00039625657,0.00054236123],"about_ca_topic_score_codex":0.00005664077,"about_ca_topic_score_gemma":0.0001251916,"teacher_disagreement_score":0.26357314,"about_ca_system_score_codex":0.00043053235,"about_ca_system_score_gemma":0.0005729879,"threshold_uncertainty_score":0.9997469},"labels":[],"label_agreement":null},{"id":"W2792021479","doi":"10.1007/978-3-319-94544-6_9","title":"Image Colorization Using Generative Adversarial Networks","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":157,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Generative grammar; Adversarial system; Image (mathematics); Convolutional neural network; Deep learning; Process (computing); Pattern recognition (psychology); Theme (computing)","score_opus":0.017597090998139768,"score_gpt":0.24158482902173578,"score_spread":0.223987738023596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792021479","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028050878,0.00020744186,0.9922198,0.00022130061,0.005261782,0.00046941717,0.0000057198818,0.000118390584,0.0014681136],"genre_scores_gemma":[0.035108294,0.000047006186,0.95847046,0.0010455681,0.0050519337,0.000006577072,0.000012858889,0.000053370644,0.00020392826],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959443,0.00010530686,0.000584304,0.0017630452,0.0008112586,0.00079179154],"domain_scores_gemma":[0.9972862,0.0003082024,0.00043575602,0.0011501343,0.0006241553,0.00019556822],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00086025574,0.0006520543,0.00061887625,0.00056510716,0.0005847841,0.0009613112,0.0023717782,0.0004334849,0.0001123155],"category_scores_gemma":[0.00011644364,0.0006108894,0.00017064225,0.00079419237,0.0011118299,0.0012987145,0.0013845927,0.00061385566,0.000042912525],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021720725,0.000034091237,0.000013867016,0.000013026383,0.0000443795,0.00008615198,0.0008871901,0.87537223,0.0014738045,0.0047725993,0.00031686385,0.11696407],"study_design_scores_gemma":[0.00027140373,0.00016591944,0.000011903256,0.0001408897,0.000018343888,0.00002285559,1.9701724e-7,0.9668376,0.0017992283,0.029333444,0.00074972154,0.0006484912],"about_ca_topic_score_codex":0.000024396919,"about_ca_topic_score_gemma":0.00007025004,"teacher_disagreement_score":0.11631558,"about_ca_system_score_codex":0.0004526522,"about_ca_system_score_gemma":0.00064246723,"threshold_uncertainty_score":0.99963427},"labels":[],"label_agreement":null},{"id":"W2792196892","doi":"10.1109/cvprw.2018.00262","title":"Totally Looks Like - How Humans Compare, Compared to Machines","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Consistency (knowledge bases); Similarity (geometry); Matching (statistics); Artificial intelligence; Convolutional neural network; Set (abstract data type); Code (set theory); Task (project management); Perception; Image (mathematics); Entertainment; Pattern recognition (psychology); Machine learning; Information retrieval; Mathematics","score_opus":0.03056097896151593,"score_gpt":0.2604527930590128,"score_spread":0.22989181409749687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792196892","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032686477,0.00011722304,0.95877075,0.0035124063,0.0035919999,0.00063242274,0.000026675301,0.00042067686,0.029659173],"genre_scores_gemma":[0.6961905,0.000009134191,0.29308617,0.0020167711,0.001181123,0.00006043305,0.00003636684,0.000034356566,0.0073851636],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969894,0.00020689626,0.00039134573,0.0013328464,0.000502164,0.0005773272],"domain_scores_gemma":[0.9970559,0.00009519284,0.00020674971,0.0019004216,0.0004143033,0.00032745427],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00032935038,0.0005845004,0.00074646325,0.00021354039,0.0002843249,0.0014684501,0.0029483053,0.00016607305,0.00024143528],"category_scores_gemma":[0.000040114723,0.0005000112,0.0002704852,0.00024621203,0.000112384405,0.00027481446,0.0046181125,0.00040145422,0.00032383826],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004859125,0.0003373141,0.0010060944,0.00013194664,0.000494779,0.00005619285,0.002725145,0.0537694,0.0012971679,0.008916391,0.90815,0.023066934],"study_design_scores_gemma":[0.0005643792,0.00020213333,0.0076209977,0.00026224126,0.00006859153,0.00000994518,0.00006176177,0.88598126,0.0024705057,0.0068692164,0.09384797,0.0020410023],"about_ca_topic_score_codex":0.0004662474,"about_ca_topic_score_gemma":0.0007774955,"teacher_disagreement_score":0.83221185,"about_ca_system_score_codex":0.000076384946,"about_ca_system_score_gemma":0.00014476171,"threshold_uncertainty_score":0.99974513},"labels":[],"label_agreement":null},{"id":"W2803117117","doi":"10.48550/arxiv.1802.08249","title":"On the Convergence and Robustness of Training GANs with Regularized Optimal Transport","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"MNIST database; Robustness (evolution); Mathematical optimization; Wasserstein metric; Computer science; Discriminator; Convergence (economics); Metric (unit); Algorithm; Probability distribution; Mathematics; Artificial intelligence; Deep learning; Applied mathematics","score_opus":0.05172647181330694,"score_gpt":0.15915847718377954,"score_spread":0.1074320053704726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803117117","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43166795,0.0000024816823,0.56765395,0.00009150838,0.00004817825,0.00005716679,9.4372626e-7,0.000015184261,0.0004626131],"genre_scores_gemma":[0.9938159,0.000009375734,0.005812681,0.00005265308,0.00003434105,2.5370412e-7,3.717258e-7,0.0000050403087,0.00026937606],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99928755,0.00007083997,0.000080113554,0.00033181632,0.000060144263,0.00016953268],"domain_scores_gemma":[0.9993145,0.000114667644,0.00007244324,0.00033867286,0.000101685946,0.000058058726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018556727,0.000108561246,0.00013917894,0.0000442123,0.0001738799,0.000017055998,0.00042288203,0.000034956603,0.000040930736],"category_scores_gemma":[0.000011815068,0.00007747757,0.000037696947,0.00040354117,0.00038113946,0.00025648117,0.000045063523,0.000072202085,0.000002640997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003633224,0.00008895971,0.0016437944,0.000013394225,0.00015224359,0.00008843316,0.002734482,0.5970274,0.002013172,0.39440832,0.00016487473,0.0013015892],"study_design_scores_gemma":[0.0004942098,0.00029079063,0.0021610751,0.000033480996,0.00002947223,0.0000048599945,0.00034755908,0.992087,0.0035653082,0.00075568754,0.000077975375,0.0001525511],"about_ca_topic_score_codex":0.000019859766,"about_ca_topic_score_gemma":0.000026073758,"teacher_disagreement_score":0.562148,"about_ca_system_score_codex":0.000010127824,"about_ca_system_score_gemma":0.000047997135,"threshold_uncertainty_score":0.31594437},"labels":[],"label_agreement":null},{"id":"W2805274379","doi":"10.1007/978-3-030-17798-0_41","title":"CapsGAN: Using Dynamic Routing for Generative Adversarial Networks","year":2019,"lang":"en","type":"book-chapter","venue":"Advances in intelligent systems and computing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Normalization (sociology); Artificial intelligence; MNIST database; Clipping (morphology); Knot (papermaking); Image translation; Computer vision; Algorithm; Pattern recognition (psychology); Image (mathematics); Deep learning","score_opus":0.019524620303792435,"score_gpt":0.2670360464849232,"score_spread":0.24751142618113076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805274379","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000039134,0.024534343,0.95946556,0.000026359947,0.005966638,0.0011781648,0.000010423809,0.00006412995,0.008715243],"genre_scores_gemma":[0.7904942,0.008313793,0.15807301,0.00034948424,0.0056949086,0.00005009857,0.00009800823,0.0003295136,0.036596972],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968357,0.00009700286,0.0010084622,0.0011499979,0.00028338894,0.00062542874],"domain_scores_gemma":[0.9977705,0.0006182508,0.000793692,0.0005101812,0.00020371146,0.00010367192],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006860704,0.00062487595,0.0009861251,0.00022198289,0.00033351532,0.00036010685,0.00062828424,0.0003427237,0.0000045029155],"category_scores_gemma":[0.000041466108,0.00060791464,0.00021458276,0.000103076985,0.00008926613,0.0005519115,0.00046378575,0.00044516215,0.000005598243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014511468,0.000008937983,0.00002011728,0.0001112466,0.00007277245,0.000009892246,0.00028624496,0.8074314,0.000020175052,0.13022676,0.000027059044,0.06177091],"study_design_scores_gemma":[0.00029651576,0.000099906436,0.0000016225736,0.0012187519,0.000034675275,0.000023732488,0.0001058126,0.97419107,0.000032186217,0.0021291838,0.021219552,0.0006470186],"about_ca_topic_score_codex":0.000065537686,"about_ca_topic_score_gemma":0.000059190006,"teacher_disagreement_score":0.80139256,"about_ca_system_score_codex":0.0002829016,"about_ca_system_score_gemma":0.000121898534,"threshold_uncertainty_score":0.99963725},"labels":[],"label_agreement":null},{"id":"W2806863256","doi":"10.1609/aaai.v32i1.12155","title":"Training Autoencoders in Sparse Domain","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Discrete cosine transform; Artificial intelligence; Computer science; Sparse approximation; Fast Fourier transform; Encoding (memory); Pattern recognition (psychology); Domain (mathematical analysis); Frequency domain; Dimensionality reduction; Feature (linguistics); Representation (politics); Autoencoder; Discrete Fourier transform (general); Fourier transform; Algorithm; Image (mathematics); Computer vision; Deep learning; Mathematics; Short-time Fourier transform; Fourier analysis","score_opus":0.1123061887485974,"score_gpt":0.2962036159536301,"score_spread":0.18389742720503272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806863256","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1708442,0.000027931403,0.7227837,0.00990305,0.0016723032,0.00075762405,0.000004969006,0.00015777916,0.09384845],"genre_scores_gemma":[0.9716377,0.000010175843,0.027757194,0.0002981427,0.00015484226,0.00001429901,1.2261246e-7,0.0000089970745,0.000118527234],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824584,0.000031389183,0.0004712938,0.00048321288,0.0003559202,0.00041234025],"domain_scores_gemma":[0.9989521,0.00007523048,0.00024668305,0.00026934958,0.00038058712,0.00007607193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070570136,0.00019853248,0.00025321165,0.0001488294,0.0001836609,0.00020267536,0.0017207613,0.00007621268,0.00008324029],"category_scores_gemma":[0.00029574241,0.00014977361,0.00009312413,0.0008640681,0.0004625154,0.00047497725,0.00029696716,0.00022788468,0.00010409978],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050857445,0.000110089735,0.00019630301,0.000010132323,0.000012897672,0.0000010969533,0.009266371,0.00041865627,0.038621485,0.8068381,0.00024902914,0.14422497],"study_design_scores_gemma":[0.000046193953,0.0002810648,0.00040355782,0.00024639093,0.0000058016763,0.0000040032855,0.0022351216,0.35143647,0.33226818,0.31222355,0.0005397728,0.00030989439],"about_ca_topic_score_codex":0.00005782591,"about_ca_topic_score_gemma":0.00008160253,"teacher_disagreement_score":0.8007935,"about_ca_system_score_codex":0.00004346349,"about_ca_system_score_gemma":0.00011110509,"threshold_uncertainty_score":0.610759},"labels":[],"label_agreement":null},{"id":"W2891678505","doi":"10.48550/arxiv.1809.01818","title":"Improving Explorability in Variational Inference with Annealed Variational Objectives","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal","funders":"","keywords":"Inference; Robustness (evolution); Computer science; Mathematical optimization; Artificial intelligence; Machine learning; Algorithm; Mathematics","score_opus":0.04073361515774715,"score_gpt":0.17968754639631568,"score_spread":0.13895393123856853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891678505","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09922659,0.0000036247743,0.8992588,0.00008852703,0.00012336423,0.00011692916,0.0000030269084,0.0000538349,0.0011253265],"genre_scores_gemma":[0.97575164,0.0000026575833,0.023939205,0.00007012884,0.000120402234,0.0000012456125,0.0000026500707,0.0000051164748,0.00010697544],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987661,0.00017154272,0.0001288388,0.00059648586,0.00009122344,0.00024576203],"domain_scores_gemma":[0.99891615,0.00025789675,0.00010571447,0.00036475985,0.00027834743,0.00007712955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029632967,0.00013865031,0.00014097027,0.00013239213,0.00018823515,0.00007835056,0.00047914893,0.00005496184,0.000064270265],"category_scores_gemma":[0.00013736468,0.00013434522,0.00003701782,0.00088553346,0.00014569706,0.0013640404,0.00018066206,0.00011318033,0.00003134331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022169529,0.0003576862,0.09173792,0.000012842138,0.00007740906,0.00007004117,0.0017987165,0.44460708,0.0008419466,0.45673445,0.00004877791,0.0034914573],"study_design_scores_gemma":[0.00052270875,0.00013098172,0.094102636,0.000010292927,0.000006900638,0.0000013089225,0.000064486594,0.891597,0.00028042032,0.013074266,0.00003280776,0.00017620911],"about_ca_topic_score_codex":0.00023226964,"about_ca_topic_score_gemma":0.00034754683,"teacher_disagreement_score":0.87652504,"about_ca_system_score_codex":0.00013077866,"about_ca_system_score_gemma":0.00022741563,"threshold_uncertainty_score":0.54784393},"labels":[],"label_agreement":null},{"id":"W2891926718","doi":"10.48550/arxiv.1709.02043","title":"The Mating Rituals of Deep Neural Networks: Learning Compact Feature\\n Representations through Sexual Evolutionary Synthesis","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"MNIST database; Artificial intelligence; Modern evolutionary synthesis; Computer science; Artificial neural network; Evolutionary algorithm; Feature (linguistics); Mating; Evolutionary programming; Machine learning; Biology; Evolutionary biology; Ecology","score_opus":0.06496836358718759,"score_gpt":0.22628281188405547,"score_spread":0.16131444829686786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891926718","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011565606,0.00073121616,0.9827957,0.00068221404,0.0008649293,0.00033184228,0.000012316788,0.00013538325,0.0028807682],"genre_scores_gemma":[0.9935023,0.00025916353,0.004894024,0.000026799198,0.00028873092,0.000002352334,0.000013954212,0.000022209813,0.0009904361],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972189,0.00082568836,0.00032424595,0.00096115435,0.00018219116,0.00048780453],"domain_scores_gemma":[0.9952944,0.0016045058,0.00095737935,0.0017119766,0.0003234582,0.00010826576],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00052369037,0.00037158918,0.0004963444,0.00009390028,0.0018182767,0.0004044044,0.0025862947,0.00025208088,0.000015123445],"category_scores_gemma":[0.0006182025,0.00033477286,0.00030317032,0.00032874008,0.00042447794,0.00086086214,0.0017755053,0.00089159317,0.000008614326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022429615,0.00003717098,0.002640126,0.0000219852,0.00019841146,0.000040105304,0.00030496911,0.9849148,0.000022811608,0.0075822305,0.00091919134,0.0032957646],"study_design_scores_gemma":[0.00015442944,0.00003365881,0.00428315,0.000068298534,0.000112879585,0.000006106814,0.00049195386,0.98937434,0.00007988958,0.004818123,0.00025006646,0.00032709166],"about_ca_topic_score_codex":0.00057264266,"about_ca_topic_score_gemma":0.000100994126,"teacher_disagreement_score":0.98193675,"about_ca_system_score_codex":0.00012153548,"about_ca_system_score_gemma":0.000097351214,"threshold_uncertainty_score":0.9999104},"labels":[],"label_agreement":null},{"id":"W2891997758","doi":"","title":"Probabilistic Neural Programmed Networks for Scene Generation","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Rendering (computer graphics); Artificial intelligence; Generative grammar; Inpainting; Probabilistic logic; Encoder; Generative model; Semantics (computer science); Pixel; Visualization; Computer vision; Pattern recognition (psychology); Theoretical computer science; Image (mathematics); Programming language","score_opus":0.03288886030649794,"score_gpt":0.26020008877347306,"score_spread":0.22731122846697513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891997758","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032527677,0.00016447323,0.9922513,0.0004825553,0.002187214,0.001099766,0.00000309677,0.00028553462,0.0002733272],"genre_scores_gemma":[0.9852617,0.0000017339668,0.01209023,0.00047799372,0.001723913,0.00029347965,0.000055106593,0.000011039166,0.00008483898],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983785,0.0000848061,0.000600484,0.00025867476,0.00027091661,0.00040658854],"domain_scores_gemma":[0.9982804,0.00004451584,0.00039173296,0.00029195927,0.0008903638,0.000101048594],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004565692,0.00020385296,0.0002091775,0.00010544563,0.00060692773,0.0017322336,0.0004334073,0.00009793024,0.000002244254],"category_scores_gemma":[0.00013583274,0.00016869651,0.00006490608,0.00045239317,0.00008326995,0.0044902028,0.00006892981,0.00009404711,0.00001500837],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029536599,0.000035196183,0.000052381034,0.00020913096,0.000016605662,4.856674e-7,0.0010850107,0.28683895,0.00041224057,0.0025428322,0.006159654,0.702618],"study_design_scores_gemma":[0.0003263723,0.00019183852,0.000068860005,0.00003515558,0.000009395999,0.000016413018,0.000039443195,0.99129534,0.0003507392,0.000042980817,0.00742045,0.00020301266],"about_ca_topic_score_codex":0.000023251778,"about_ca_topic_score_gemma":0.0000070476594,"teacher_disagreement_score":0.9820089,"about_ca_system_score_codex":0.00006005596,"about_ca_system_score_gemma":0.000073392795,"threshold_uncertainty_score":0.99930406},"labels":[],"label_agreement":null},{"id":"W2892051732","doi":"10.1109/icassp.2018.8462534","title":"Reg-Gan: Semi-Supervised Learning Based on Generative Adversarial Networks for Regression","year":2018,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Task (project management); Artificial intelligence; Regression; Machine learning; Generative grammar; Context (archaeology); Supervised learning; Point (geometry); Semi-supervised learning; Adversarial system; Labeled data; Artificial neural network; Mathematics; Statistics","score_opus":0.018092086138989515,"score_gpt":0.2518107922582548,"score_spread":0.2337187061192653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2892051732","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029958287,0.000031668933,0.9882807,0.0016190483,0.0014934642,0.0004202064,0.0000018638788,0.00021364172,0.0076398114],"genre_scores_gemma":[0.82264423,0.000007825241,0.17014161,0.002230678,0.00274972,0.000051880314,0.000017847544,0.000027690514,0.0021285394],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978568,0.00029606617,0.00028488084,0.00074883865,0.00030093835,0.0005124829],"domain_scores_gemma":[0.9983532,0.0004462978,0.00013627688,0.0005717454,0.00033585972,0.00015665701],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054420956,0.0002991522,0.00029480763,0.00010869099,0.0007398232,0.0002475718,0.00062465307,0.00016112691,0.00016260176],"category_scores_gemma":[0.00023457075,0.00022403056,0.00017688512,0.00038314483,0.00010568807,0.00042535,0.0001205809,0.00021462106,0.000042761036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048075576,0.00015685325,0.00016483657,0.000009917364,0.00006848938,0.000009205537,0.0006212627,0.8350638,0.0051732603,0.0059800437,0.065083325,0.087188214],"study_design_scores_gemma":[0.0011263869,0.0008036201,0.000057471952,0.000048571485,0.000012030367,8.6099436e-7,0.00003454255,0.95609075,0.02271839,0.00021312246,0.01859642,0.00029780806],"about_ca_topic_score_codex":0.000020442943,"about_ca_topic_score_gemma":0.000019035922,"teacher_disagreement_score":0.82234466,"about_ca_system_score_codex":0.00006183917,"about_ca_system_score_gemma":0.00009387169,"threshold_uncertainty_score":0.9135701},"labels":[],"label_agreement":null},{"id":"W2893036483","doi":"10.1109/tnnls.2018.2868809","title":"On the Representational Power of Restricted Boltzmann Machines for Symmetric Functions and Boolean Functions","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Concordia University; National Natural Science Foundation of China","keywords":"Boltzmann machine; Boolean function; Power (physics); Boltzmann constant; Mathematics; Computer science; Theoretical computer science; Discrete mathematics; Physics; Artificial intelligence; Quantum mechanics; Artificial neural network","score_opus":0.016967376354281152,"score_gpt":0.23513078747338728,"score_spread":0.21816341111910614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2893036483","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030315652,0.00020542275,0.9663669,0.0006900975,0.0016420599,0.0003895559,0.000014081951,0.00006247392,0.00031374526],"genre_scores_gemma":[0.9975318,0.000025457963,0.00027636107,0.00008997855,0.00027010153,0.00007142662,0.000003549739,0.0000149857415,0.001716339],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986008,0.00031658463,0.0002859554,0.00038755196,0.00018586773,0.00022327741],"domain_scores_gemma":[0.99793434,0.0013833651,0.00015202988,0.00027015829,0.00018269022,0.000077423036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026823508,0.00017260868,0.00019872967,0.00019012054,0.0011909003,0.00019361984,0.00015822047,0.00007539118,0.000014362524],"category_scores_gemma":[0.00005690686,0.0001214296,0.00009199909,0.0006310958,0.00014278872,0.00020375609,0.0000052100054,0.00032764475,0.0000029939054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011607577,0.00007261595,0.000097902004,0.000012196001,0.00011045482,0.000001071757,0.00021684142,0.9737661,0.00024119679,0.0024921042,0.0028795134,0.019993939],"study_design_scores_gemma":[0.00031025888,0.00077390147,0.0011563397,0.00003702391,0.000035373276,0.000019573366,0.00019933021,0.99605376,0.0000504766,0.000052268188,0.0011806953,0.00013101046],"about_ca_topic_score_codex":0.00010090412,"about_ca_topic_score_gemma":0.000014811551,"teacher_disagreement_score":0.96721613,"about_ca_system_score_codex":0.0000133167005,"about_ca_system_score_gemma":0.000014059287,"threshold_uncertainty_score":0.9159563},"labels":[],"label_agreement":null},{"id":"W2895302585","doi":"10.1007/s11063-018-9923-4","title":"Low-Dimensional Perturb-and-MAP Approach for Learning Restricted Boltzmann Machines","year":2018,"lang":"en","type":"article","venue":"Neural Processing Letters","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of British Columbia","funders":"","keywords":"Maximum a posteriori estimation; Boltzmann machine; Algorithm; Mathematics; Gradient descent; Restricted Boltzmann machine; Boltzmann distribution; Function (biology); Divergence (linguistics); Computer science; Energy (signal processing); Mathematical optimization; Artificial intelligence; Statistical physics; Deep learning; Artificial neural network; Statistics; Maximum likelihood","score_opus":0.01484261004209037,"score_gpt":0.23518712914086493,"score_spread":0.22034451909877456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895302585","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06569704,0.00019498887,0.9258681,0.0073275524,0.0003551211,0.00020593351,0.0000010791949,0.00018755635,0.00016264283],"genre_scores_gemma":[0.8487504,0.0000013707917,0.14621383,0.004084757,0.0007310225,0.000020566811,0.000008686979,0.000017302302,0.00017208181],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986555,0.00008153837,0.00018236152,0.00052227406,0.00019966392,0.0003586933],"domain_scores_gemma":[0.99941933,0.00009963434,0.00010818583,0.00016357178,0.00012494979,0.0000843065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013996036,0.00019045481,0.00018055932,0.000080939055,0.00066590315,0.00035204945,0.00033465613,0.000050188617,0.0000031220475],"category_scores_gemma":[0.00008294584,0.00015355677,0.000057266727,0.0002210255,0.00015670325,0.00059700815,0.0001104161,0.00017438286,0.0000035719986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015881976,0.00013484365,0.00085879,0.0002818118,0.00007083984,0.00001845345,0.003231812,0.0397666,0.38234225,0.00035968213,0.027106484,0.5456696],"study_design_scores_gemma":[0.0002999683,0.00009128624,0.00049411214,0.000025784399,0.000010816368,0.0000128318,0.000013834103,0.99404,0.002562032,0.00009924268,0.0021342933,0.00021576883],"about_ca_topic_score_codex":0.000011920684,"about_ca_topic_score_gemma":9.151269e-7,"teacher_disagreement_score":0.9542734,"about_ca_system_score_codex":0.000016150689,"about_ca_system_score_gemma":0.000035327666,"threshold_uncertainty_score":0.6261864},"labels":[],"label_agreement":null},{"id":"W2896125160","doi":"10.48550/arxiv.1807.08024","title":"Explaining Image Classifiers by Counterfactual Generation","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Classifier (UML); Artificial intelligence; Computer science; Pattern recognition (psychology); Counterfactual thinking; Generative grammar; Generative model; Image (mathematics); Ask price; Contextual image classification; Computer vision; Machine learning","score_opus":0.0629509378043967,"score_gpt":0.18201830080271134,"score_spread":0.11906736299831464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896125160","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.100738116,0.000013848784,0.8943404,0.00011653961,0.000419537,0.00006751294,0.0000043264704,0.000096868505,0.004202847],"genre_scores_gemma":[0.99287224,0.000020722084,0.0052405302,0.00023511161,0.00029285986,3.2637678e-7,0.0000062992267,0.000009071666,0.0013228549],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988779,0.00010470505,0.00011254515,0.00054232706,0.00006979505,0.00029274466],"domain_scores_gemma":[0.9991932,0.00004939995,0.00008219219,0.00041146847,0.00014771787,0.00011605489],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017230521,0.00015094462,0.0001262502,0.00007305019,0.00034924838,0.00016036801,0.0005666767,0.00006827367,0.00011248154],"category_scores_gemma":[0.000028565102,0.00016172804,0.000060123064,0.0003945234,0.0001755477,0.0012023082,0.0001623544,0.00009501562,0.00022203483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014907731,0.00036806343,0.002052906,0.000016231388,0.00034527667,0.0002997606,0.0038934909,0.06360668,0.38826525,0.1449827,0.37442297,0.021597605],"study_design_scores_gemma":[0.00032427066,0.00011455687,0.00007546095,0.0000052091973,0.000011911425,0.0000023094965,0.00014206112,0.96389264,0.027577596,0.00042422634,0.0072063897,0.00022335535],"about_ca_topic_score_codex":0.000037718662,"about_ca_topic_score_gemma":0.000026786327,"teacher_disagreement_score":0.90028596,"about_ca_system_score_codex":0.00007897158,"about_ca_system_score_gemma":0.000043370077,"threshold_uncertainty_score":0.6595078},"labels":[],"label_agreement":null},{"id":"W2898252619","doi":"10.1049/iet-ipr.2018.5613","title":"Mixture separability loss in a deep convolutional network for image classification","year":2018,"lang":"en","type":"article","venue":"IET Image Processing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Computer science; Pattern recognition (psychology); Convolutional neural network; Contextual image classification; Image (mathematics)","score_opus":0.01920796489809165,"score_gpt":0.28286113188231643,"score_spread":0.2636531669842248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898252619","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032662044,0.00034643695,0.9931627,0.001491068,0.00031659752,0.0003424307,0.0000062322133,0.000095630414,0.0009726889],"genre_scores_gemma":[0.58038384,0.000003908055,0.4185777,0.00025104484,0.00066659454,0.000055333592,0.0000091815755,0.000010365952,0.00004205431],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99822927,0.0001187476,0.00034592135,0.0006137594,0.00020201513,0.0004903091],"domain_scores_gemma":[0.9986998,0.00013952501,0.00017199379,0.00035137823,0.0005570977,0.000080196856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000758348,0.00019117299,0.00021998309,0.00006128971,0.00038480014,0.00037854048,0.0005181151,0.000098172786,0.000020472615],"category_scores_gemma":[0.00020776478,0.0001801902,0.00008008814,0.0005790005,0.0003197295,0.0014435033,0.00011439364,0.00014596342,0.00002599863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006205186,0.0011470389,0.017372742,0.00073735317,0.00011724896,0.000055163033,0.0071549388,0.0045742276,0.14192846,0.01608646,0.036230274,0.77397555],"study_design_scores_gemma":[0.0004953814,0.00006154376,0.012366607,0.00006279684,0.000009669128,0.000010601178,0.000038397273,0.9647402,0.0036494262,0.015414989,0.0028774256,0.0002729689],"about_ca_topic_score_codex":0.000011842656,"about_ca_topic_score_gemma":0.00005727598,"teacher_disagreement_score":0.960166,"about_ca_system_score_codex":0.000096498356,"about_ca_system_score_gemma":0.0001876543,"threshold_uncertainty_score":0.7347943},"labels":[],"label_agreement":null},{"id":"W2903194017","doi":"10.1109/mmsp.2018.8547106","title":"Image Inpainting Detection Based on a Modified Formulation of Canonical Correlation Analysis","year":2018,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Science Foundation of Tianjin City; National Natural Science Foundation of China","keywords":"Inpainting; Artificial intelligence; Image (mathematics); Pattern recognition (psychology); Computer science; Feature (linguistics); JPEG; Computer vision; Mathematics","score_opus":0.012738129507267958,"score_gpt":0.2410066917691133,"score_spread":0.22826856226184533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903194017","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020637685,9.703064e-7,0.9737034,0.00009522335,0.000110800516,0.0000829931,5.117779e-7,0.000047129073,0.0053213015],"genre_scores_gemma":[0.90407175,1.8007479e-7,0.09572557,0.000087086184,0.000071134324,0.0000030441165,0.0000026243981,0.0000030661004,0.000035564444],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99914527,0.00009815032,0.00021979908,0.00022565534,0.00018834035,0.00012278742],"domain_scores_gemma":[0.99920833,0.00013708496,0.00012985973,0.00028219112,0.0002090268,0.00003352871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036059777,0.00007735241,0.00013461873,0.00023136553,0.000114158946,0.000052890075,0.00014670631,0.00004807418,0.000039867176],"category_scores_gemma":[0.0001160269,0.00006584691,0.00010545231,0.0009696859,0.000030102057,0.00033094134,0.000033826145,0.00004893534,0.0000093520985],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010643264,0.00015830137,0.0027676919,0.000009040448,0.00019922739,0.0000011136765,0.00039433327,0.79669726,0.065702744,0.008683218,0.00009589414,0.12518474],"study_design_scores_gemma":[0.00016211321,0.00012386983,0.011939103,0.0000039542965,0.000041395582,1.0726748e-7,0.0000046088685,0.9448579,0.042597212,0.00018586758,0.000015120322,0.000068746536],"about_ca_topic_score_codex":0.00019951448,"about_ca_topic_score_gemma":0.0002621132,"teacher_disagreement_score":0.88343406,"about_ca_system_score_codex":0.000036653117,"about_ca_system_score_gemma":0.000025013785,"threshold_uncertainty_score":0.26851588},"labels":[],"label_agreement":null},{"id":"W2904464104","doi":"10.1609/aaai.v33i01.33013248","title":"Deep Convolutional Sum-Product Networks","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Convolutional neural network; Pooling; Computer science; Inference; Artificial intelligence; Robustness (evolution); Pattern recognition (psychology); Probabilistic logic; Differentiable function; Benchmark (surveying); Algorithm; Mathematics","score_opus":0.03965008146062683,"score_gpt":0.2524805903209098,"score_spread":0.21283050886028299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904464104","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052012995,0.00020684587,0.89728534,0.007098137,0.0033010852,0.0010720982,0.0000036701094,0.00017188561,0.03884794],"genre_scores_gemma":[0.99375266,0.00003916188,0.0051041218,0.0002998049,0.00021183578,0.00001421767,5.745822e-7,0.0000106807865,0.0005669548],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980356,0.000028091774,0.00045441824,0.0006092565,0.00046623906,0.00040640382],"domain_scores_gemma":[0.99837947,0.000106406005,0.00031841773,0.0004026298,0.0007068363,0.00008624022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004941234,0.00023427916,0.00028134353,0.000083716855,0.0001870873,0.0002441445,0.0019682222,0.0000762555,0.00020456559],"category_scores_gemma":[0.00020911294,0.00017272244,0.00015445183,0.0006254741,0.00022494547,0.0005356713,0.0004416258,0.0002960167,0.0002611312],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004444125,0.000102376594,0.00073634647,0.000015522639,0.00002764064,2.653708e-7,0.0002758364,0.013451215,0.018509736,0.9252744,0.0005541391,0.041008133],"study_design_scores_gemma":[0.000027884083,0.00011324748,0.00060340355,0.000081990016,0.0000090252615,0.000003300059,0.00012179996,0.8072956,0.14664705,0.044575512,0.00028628716,0.00023486187],"about_ca_topic_score_codex":0.000026367761,"about_ca_topic_score_gemma":0.000007073896,"teacher_disagreement_score":0.9417397,"about_ca_system_score_codex":0.000042975957,"about_ca_system_score_gemma":0.00008031709,"threshold_uncertainty_score":0.70434165},"labels":[],"label_agreement":null},{"id":"W2906191032","doi":"10.1109/cvpr.2019.00155","title":"Latent Filter Scaling for Multimodal Unsupervised Image-To-Image Translation","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"King Abdullah University of Science and Technology","keywords":"Computer science; Image translation; Artificial intelligence; Benchmark (surveying); Image (mathematics); Hyperparameter; Translation (biology); Code (set theory); Pattern recognition (psychology); Domain (mathematical analysis); Convolutional neural network; Filter (signal processing); Machine learning; Computer vision; Mathematics","score_opus":0.03741701280440942,"score_gpt":0.27235891424693964,"score_spread":0.23494190144253022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906191032","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012218594,0.00006843574,0.9901128,0.0031482854,0.0016617745,0.001838144,0.000059033257,0.00019614863,0.0016935555],"genre_scores_gemma":[0.19725999,0.000013504996,0.8008141,0.0006463405,0.00040278435,0.0001447894,0.00006951164,0.00003678152,0.0006121947],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974793,0.00012031823,0.00047421636,0.0011255916,0.00030954002,0.00049100746],"domain_scores_gemma":[0.998132,0.00022941259,0.00012476237,0.0010078545,0.0003421183,0.00016383489],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004610022,0.00042072215,0.00048950623,0.00017488755,0.0001370196,0.00071140553,0.001151238,0.0002521104,0.000114955634],"category_scores_gemma":[0.000052222902,0.0003703689,0.0004057963,0.00016092864,0.00003007074,0.00050844887,0.00068497163,0.00028669732,0.00019473965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015572697,0.00029108557,0.00010516436,0.00053754344,0.00035182998,0.000011106264,0.0036329618,0.59132516,0.08137702,0.001039286,0.015242278,0.30593082],"study_design_scores_gemma":[0.0006033622,0.00005270579,0.00038559397,0.00008625116,0.000032314045,7.40342e-7,0.000013184085,0.9781566,0.0173337,0.0009383374,0.0018858324,0.0005113804],"about_ca_topic_score_codex":0.00011096503,"about_ca_topic_score_gemma":0.000014501522,"teacher_disagreement_score":0.38683143,"about_ca_system_score_codex":0.000063563755,"about_ca_system_score_gemma":0.000114948896,"threshold_uncertainty_score":0.99987483},"labels":[],"label_agreement":null},{"id":"W2906729185","doi":"10.1109/tpami.2018.2889948","title":"Group Maximum Differentiation Competition: Model Comparison with Few Samples","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sample (material); Constraint (computer-aided design); Computer science; Set (abstract data type); Artificial intelligence; Quality (philosophy); Space (punctuation); Sample space; Competition (biology); Exploit; Computational model; Machine learning; Perception; Focus (optics); Sample size determination; Computer vision; Mathematics; Statistics; Computer security","score_opus":0.02746554561027486,"score_gpt":0.2575376066203482,"score_spread":0.23007206101007333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906729185","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034321577,0.000038946306,0.995721,0.0003938887,0.00012969151,0.00010509518,0.000025721198,0.000070978065,0.000082563565],"genre_scores_gemma":[0.97886133,0.000093742776,0.020598555,0.00029859974,0.00004844563,0.000016121501,0.000011829343,0.000009674771,0.00006171021],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985958,0.00009377473,0.00030411727,0.00052229094,0.00026370023,0.00022034551],"domain_scores_gemma":[0.9991602,0.00007241877,0.00011797431,0.00041804,0.00012342377,0.000107974905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013148997,0.00022511404,0.0003258164,0.00028908555,0.00038590925,0.00022465215,0.0003201915,0.000049206392,0.00015944624],"category_scores_gemma":[0.0000014179979,0.00017412798,0.00014191972,0.0007445693,0.00015800957,0.0003091135,0.000006658028,0.00015780563,0.000021452415],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044915374,0.00038226583,0.0015499105,0.000013159836,0.0007822286,0.0000026634377,0.000726935,0.25438255,0.00069967954,0.0012235724,0.000020370115,0.74017173],"study_design_scores_gemma":[0.00009326911,0.00023231602,0.0013451632,0.000018887014,0.0003064943,0.000002904042,0.00003408753,0.94470906,0.052158993,0.0008486217,0.00002887096,0.00022132292],"about_ca_topic_score_codex":0.00048562718,"about_ca_topic_score_gemma":0.004760655,"teacher_disagreement_score":0.9754292,"about_ca_system_score_codex":0.000025061903,"about_ca_system_score_gemma":0.000011845718,"threshold_uncertainty_score":0.7100733},"labels":[],"label_agreement":null},{"id":"W2907097116","doi":"10.48550/arxiv.1901.00212","title":"EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":587,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Inpainting; Hallucinating; Generator (circuit theory); Image (mathematics); Enhanced Data Rates for GSM Evolution; Artificial intelligence; Computer science; Filling-in; Code (set theory); A priori and a posteriori; Generative grammar; Deep learning; Pattern recognition (psychology); Computer vision; Power (physics)","score_opus":0.034753094093114306,"score_gpt":0.17052011075109713,"score_spread":0.13576701665798283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2907097116","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04190781,0.00006148791,0.9467519,0.00015746588,0.001234576,0.0004909754,0.000008787009,0.00028905307,0.009097962],"genre_scores_gemma":[0.9732144,0.00007289344,0.022911582,0.00013479278,0.0006071913,0.00000231375,0.000028037863,0.00004739963,0.0029814008],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964255,0.00057789485,0.00029128927,0.0018681779,0.0001632065,0.0006739002],"domain_scores_gemma":[0.9973087,0.0002934178,0.00052207505,0.0012240122,0.00044274805,0.00020904605],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005120975,0.0006166423,0.0006646717,0.00029200615,0.00044868924,0.0004690236,0.0017896172,0.00035250167,0.000088229106],"category_scores_gemma":[0.00013128057,0.00062067393,0.0002985712,0.0006595736,0.00019443048,0.0010267699,0.002476333,0.0012678507,0.00022651824],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006371713,0.00005812526,0.0012943116,0.00004675979,0.0002491661,0.00024845492,0.0006291782,0.9826382,0.00029913892,0.012642005,0.0005907513,0.0012402004],"study_design_scores_gemma":[0.000979315,0.00018036654,0.00035862843,0.0001434512,0.00011418223,0.0000065349286,0.00025104042,0.9916211,0.0015322005,0.002477336,0.001429219,0.00090662367],"about_ca_topic_score_codex":0.00018056785,"about_ca_topic_score_gemma":0.0000652939,"teacher_disagreement_score":0.9313066,"about_ca_system_score_codex":0.00026319234,"about_ca_system_score_gemma":0.00039702334,"threshold_uncertainty_score":0.99962443},"labels":[],"label_agreement":null},{"id":"W2907966865","doi":"10.1016/j.neucom.2018.12.046","title":"Variational-based latent generalized Dirichlet allocation model in the collapsed space and applications","year":2018,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Latent Dirichlet allocation; Hierarchical Dirichlet process; Dirichlet distribution; Gibbs sampling; Codebook; Inference; Computer science; Dirichlet process; Prior probability; Artificial intelligence; Generative model; Bayesian inference; Pattern recognition (psychology); Machine learning; Topic model; Bayesian probability; Mathematics; Generative grammar; Boundary value problem","score_opus":0.018598322834793107,"score_gpt":0.24307610596728357,"score_spread":0.22447778313249048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2907966865","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011830901,0.000024086734,0.9837316,0.0034849881,0.00006296039,0.00036475266,8.450793e-7,0.000044818007,0.00045504235],"genre_scores_gemma":[0.8510958,0.0000027307328,0.14652531,0.0020881244,0.0002205,0.00004411186,0.0000027511126,0.000005822241,0.000014842626],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989628,0.00017108908,0.00017739802,0.00032853545,0.00017971492,0.00018046623],"domain_scores_gemma":[0.99930626,0.00018088089,0.0000843999,0.00029024004,0.00010401182,0.000034212644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038801212,0.00010313219,0.00009559559,0.00006659728,0.00028569193,0.00017462629,0.00037973592,0.000030721712,0.0000015746757],"category_scores_gemma":[0.000030932508,0.000081981794,0.000024619954,0.00046555483,0.00004371048,0.00013247812,0.0000927737,0.00007882006,0.000005890031],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008058521,0.000098003096,0.0011110888,0.000008350464,0.000008103095,0.0000020207963,0.0009047628,0.83182234,0.0056295944,0.14632626,0.00073421357,0.013347192],"study_design_scores_gemma":[0.00028751744,0.000022847218,0.005851007,0.0000052581036,0.000003976049,0.0000018992456,0.000005281176,0.99005836,0.00051585346,0.0017198408,0.001441581,0.00008660239],"about_ca_topic_score_codex":0.000043296688,"about_ca_topic_score_gemma":0.000018962317,"teacher_disagreement_score":0.8392649,"about_ca_system_score_codex":0.00002506433,"about_ca_system_score_gemma":0.00005892641,"threshold_uncertainty_score":0.33431205},"labels":[],"label_agreement":null},{"id":"W2910601191","doi":"10.48550/arxiv.1901.02199","title":"FIGR: Few-shot Image Generation with Reptile","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Polytechnique Montréal","funders":"","keywords":"Shot (pellet); Computer science; Artificial intelligence; Benchmark (surveying); MNIST database; Image (mathematics); Novelty; Generative grammar; Set (abstract data type); Class (philosophy); Limiting; Field (mathematics); Domain (mathematical analysis); One shot; Deep learning; Machine learning; Computer vision; Pattern recognition (psychology); Cartography; Mathematics; Geography; Engineering","score_opus":0.0786742616169836,"score_gpt":0.1812348152687094,"score_spread":0.10256055365172581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910601191","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032959234,0.000051480725,0.955575,0.00015598473,0.00075895234,0.00039119346,0.000017538905,0.00017398308,0.009916628],"genre_scores_gemma":[0.9770144,0.00009647538,0.017475456,0.00015662507,0.00032364985,0.0000017835915,0.000048745682,0.000025794669,0.00485702],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976848,0.00020100872,0.00019194008,0.0014082362,0.00013145083,0.00038256924],"domain_scores_gemma":[0.9975666,0.000065206994,0.00028189327,0.0016660269,0.00027913525,0.00014118139],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022004974,0.00038558443,0.00038017542,0.000167939,0.00019808317,0.00034099692,0.0013522733,0.00023885179,0.000115847404],"category_scores_gemma":[0.00002270978,0.00037652202,0.00018631555,0.0004298898,0.00009874423,0.0007729774,0.0011983082,0.0004499453,0.0002530681],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029673578,0.0000747931,0.0004621113,0.00003632196,0.00013177836,0.00025906347,0.00017616172,0.9811251,0.0013364994,0.010219961,0.0054330067,0.00071549625],"study_design_scores_gemma":[0.00040029854,0.00009845892,0.00032287394,0.000058317728,0.000067526715,0.0000075426647,0.000030599425,0.99322647,0.0024633333,0.0012636185,0.0015115944,0.0005493421],"about_ca_topic_score_codex":0.00013496049,"about_ca_topic_score_gemma":0.0000688925,"teacher_disagreement_score":0.9440552,"about_ca_system_score_codex":0.000159859,"about_ca_system_score_gemma":0.00024855658,"threshold_uncertainty_score":0.9998687},"labels":[],"label_agreement":null},{"id":"W2913117037","doi":"10.48550/arxiv.1902.01893","title":"TzK: Flow-Based Conditional Generative Model","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Inference; Prior probability; Joint probability distribution; Computer science; Class (philosophy); Generative model; Conditional probability distribution; Generative grammar; A priori and a posteriori; Machine learning; Artificial intelligence; Conditional probability; Mathematics; Statistics; Bayesian probability","score_opus":0.0722996957571259,"score_gpt":0.18227284884851083,"score_spread":0.10997315309138493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913117037","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053010364,0.000048417645,0.99012226,0.00027626957,0.00071090466,0.0003367183,0.0001342222,0.00015715654,0.002913011],"genre_scores_gemma":[0.939368,0.00003003571,0.057336535,0.000605589,0.00017883786,0.0000022754868,0.00013712222,0.000021368014,0.0023202114],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99768287,0.00021829667,0.0002110258,0.0013382788,0.00015056033,0.0003989607],"domain_scores_gemma":[0.9979514,0.00013402586,0.00023883778,0.0011898006,0.00031361898,0.00017234712],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019871227,0.0004169235,0.00041737614,0.00021218328,0.00022042668,0.0001935646,0.0015570212,0.00030938137,0.00009077153],"category_scores_gemma":[0.000026435697,0.00046254133,0.00033682733,0.0003339468,0.00013076309,0.00046612872,0.0011592113,0.0005201244,0.00021615256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001674238,0.00006524384,0.000092727,0.000017843242,0.00008385344,0.000056240482,0.00005700232,0.950174,0.00008032451,0.046505623,0.0026919097,0.0001585101],"study_design_scores_gemma":[0.00049402734,0.000033725242,0.0000936902,0.00003661112,0.000050064613,8.3592613e-7,0.000010566219,0.9580311,0.0008939653,0.039577384,0.00027656203,0.00050142716],"about_ca_topic_score_codex":0.00003396427,"about_ca_topic_score_gemma":0.000018525514,"teacher_disagreement_score":0.934067,"about_ca_system_score_codex":0.00025228426,"about_ca_system_score_gemma":0.0006856734,"threshold_uncertainty_score":0.9997826},"labels":[],"label_agreement":null},{"id":"W2913342496","doi":"10.1111/1559-8918.2018.01210","title":"Screenplay, Novel, and Poem: The Value of Borrowing From Three Literary Genres to Frame Our Thinking as We Gather, Analyze, and Elevate Data in Applied Ethnographic Work","year":2018,"lang":"en","type":"article","venue":"Ethnographic Praxis in Industry Conference Proceedings","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Red Deer Polytechnic","funders":"","keywords":"Framing (construction); Ethnography; Poetry; Data collection; Computer science; Sociology; Value (mathematics); Work (physics); Survey data collection; Aesthetics; Epistemology; Data science; Literature; History; Art; Social science; Philosophy; Engineering; Mathematics","score_opus":0.050071567414149865,"score_gpt":0.29197304958664927,"score_spread":0.2419014821724994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913342496","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.941567,0.0011465303,0.049635682,0.006221696,0.00017462047,0.0006101381,0.000021795466,0.00007316169,0.00054935564],"genre_scores_gemma":[0.9516362,0.00021571692,0.047134567,0.0007311882,0.00020192027,0.000044179687,0.000005387161,0.000023010794,0.000007811515],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99681324,0.00007813209,0.0006736333,0.0012462431,0.0005666754,0.00062208687],"domain_scores_gemma":[0.99812907,0.00029246064,0.0003292314,0.00084448006,0.00021288116,0.00019188046],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022009916,0.00042733847,0.00053503795,0.0007490819,0.0003182127,0.00067440746,0.0025783265,0.0005722698,0.000009787743],"category_scores_gemma":[0.00036400743,0.00034884052,0.000050558257,0.0037278156,0.00048730941,0.0012374055,0.0021682153,0.0015759862,0.000001635598],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024869028,0.00023000641,0.73650956,0.00008923273,0.00027894182,0.000015958072,0.056491528,0.000054055294,0.017044611,0.028513491,0.00065335364,0.15987056],"study_design_scores_gemma":[0.00345045,0.00085007696,0.60121065,0.0060014613,0.00018958739,0.000034570985,0.028375024,0.15018553,0.008068777,0.19669569,0.002121261,0.0028169297],"about_ca_topic_score_codex":0.0009892073,"about_ca_topic_score_gemma":0.000458358,"teacher_disagreement_score":0.1681822,"about_ca_system_score_codex":0.000015374837,"about_ca_system_score_gemma":0.00012117658,"threshold_uncertainty_score":0.99989635},"labels":[],"label_agreement":null},{"id":"W2914914077","doi":"10.1609/aaai.v33i01.33018901","title":"A Layer-Based Sequential Framework for Scene Generation with GANs","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Generative grammar; Artificial intelligence; Task (project management); Affine transformation; Computer vision; Adversarial system; Mathematics","score_opus":0.09918387295695763,"score_gpt":0.29796823514722526,"score_spread":0.19878436219026763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914914077","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04823957,0.000009028117,0.9461122,0.0030022797,0.00053264294,0.00073096534,0.0000059145714,0.000050588143,0.0013167745],"genre_scores_gemma":[0.8752626,0.00000419185,0.12403619,0.00034162262,0.00018135292,0.00004750509,0.0000010182661,0.000013368743,0.000112129295],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984256,0.000019727397,0.00033783691,0.00051783526,0.00038157948,0.00031740274],"domain_scores_gemma":[0.9984597,0.00012012966,0.00031012282,0.00032003576,0.00072388793,0.00006611654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035490762,0.00021399888,0.00024435984,0.00008030657,0.00018964327,0.0003175579,0.0011383014,0.00009653439,0.00007111147],"category_scores_gemma":[0.00018037725,0.00014621517,0.00012054526,0.00045122355,0.0001283453,0.00037458824,0.0001099184,0.0001842027,0.000042658765],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012687568,0.00011131958,0.00016512965,0.000032555443,0.000023584993,1.8591935e-7,0.0003343349,0.0056393524,0.19394441,0.77634394,0.00010862202,0.023169685],"study_design_scores_gemma":[0.000032512722,0.00027906412,0.000016169315,0.00010670998,0.000009899062,7.806798e-7,0.00005691799,0.42329374,0.5460674,0.029935848,0.00007066738,0.00013024006],"about_ca_topic_score_codex":0.000018515078,"about_ca_topic_score_gemma":0.00000968909,"teacher_disagreement_score":0.827023,"about_ca_system_score_codex":0.00003738265,"about_ca_system_score_gemma":0.00015175006,"threshold_uncertainty_score":0.59624815},"labels":[],"label_agreement":null},{"id":"W2919115771","doi":"10.1038/nature14539","title":"Deep learning","year":2015,"lang":"en","type":"review","venue":"Nature","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":81659,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of New Brunswick; Université de Montréal","funders":"","keywords":"Computer science; Deep learning; Artificial intelligence; Abstraction; Representation (politics); Layer (electronics); Object (grammar); Backpropagation; Convolutional neural network; Feature learning; Pattern recognition (psychology); Speech recognition; Artificial neural network","score_opus":0.02716068263395695,"score_gpt":0.3089172964918412,"score_spread":0.28175661385788425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2919115771","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.3256444e-9,0.8822984,0.1116949,0.000044979253,0.0009406568,0.00013676968,7.878148e-7,0.00009262008,0.0047909017],"genre_scores_gemma":[0.0000017070731,0.98142,0.016286364,0.00011493032,0.0006859018,0.000012452365,0.00001712317,0.000020554184,0.0014409572],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99858975,0.00026775606,0.00019411721,0.00043693982,0.00027337953,0.00023807862],"domain_scores_gemma":[0.99906194,0.00009629477,0.00017067231,0.00044620797,0.0001239092,0.000100978745],"candidate_categories":["research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0003331136,0.00027194247,0.0007841624,0.000094775176,0.00009075168,0.00018368587,0.0010949296,0.0018751549,0.000019345776],"category_scores_gemma":[0.00014447297,0.00019422227,0.00027572393,0.00047694048,0.000016590819,0.00020274866,0.0003120626,0.0040981825,0.00023142781],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.08829035e-7,0.000004212882,5.1781686e-8,0.00027807776,0.000027469667,0.000012149265,0.000019702613,0.00006594797,1.3365872e-8,0.00077176694,0.007660908,0.9911596],"study_design_scores_gemma":[0.000030054794,0.00001520424,9.0970765e-8,0.0007100464,0.00006011538,0.000016907814,0.0000018734094,0.0037428413,1.8369673e-7,0.00011045329,0.99509484,0.00021740484],"about_ca_topic_score_codex":0.0000012342308,"about_ca_topic_score_gemma":0.0000012899824,"teacher_disagreement_score":0.9909422,"about_ca_system_score_codex":0.00006610643,"about_ca_system_score_gemma":0.00015554231,"threshold_uncertainty_score":0.99942064},"labels":[],"label_agreement":null},{"id":"W2922263752","doi":"10.1016/j.neucom.2019.03.011","title":"Toward AI fashion design: An Attribute-GAN model for clothing match","year":2019,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":136,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Clothing; Computer science; Discriminator; Generator (circuit theory); Matching (statistics); Artificial intelligence; Similarity (geometry); Generative adversarial network; Collocation (remote sensing); Adversarial system; Generative grammar; Pattern recognition (psychology); Machine learning; Image (mathematics); Mathematics","score_opus":0.0666801175193587,"score_gpt":0.27958798144234026,"score_spread":0.21290786392298156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2922263752","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026275853,0.000012410476,0.97118616,0.0009476582,0.0006286061,0.0005951394,0.0000017288341,0.00025223533,0.00010019633],"genre_scores_gemma":[0.7206813,0.0000013796706,0.2775069,0.0014749862,0.00022746547,0.000009574785,0.0000028344991,0.000022604134,0.000072928226],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980948,0.00015842015,0.0002959948,0.00070827035,0.00023056968,0.0005119226],"domain_scores_gemma":[0.9988452,0.00026183072,0.00013294542,0.00049432507,0.00014409111,0.00012157033],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005734587,0.00022147704,0.000262261,0.00007576695,0.00026248494,0.00041635736,0.00085459865,0.00007943229,0.0000034871675],"category_scores_gemma":[0.00004639679,0.00021603142,0.0001120837,0.00022351724,0.000014099583,0.000921427,0.00023197892,0.00019578442,0.000030873834],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000789541,0.000033594093,0.00018524201,0.000019994333,0.000008035334,0.000003042111,0.0009272962,0.96286285,0.010912913,0.0019439729,0.00043631523,0.022658823],"study_design_scores_gemma":[0.0003560586,0.00015206292,0.00015428179,0.00001929116,0.0000063895404,0.000007510413,0.00002815525,0.99363446,0.00431066,0.0007875293,0.00029900862,0.00024460664],"about_ca_topic_score_codex":0.0000058278897,"about_ca_topic_score_gemma":9.977974e-7,"teacher_disagreement_score":0.6944055,"about_ca_system_score_codex":0.00003423374,"about_ca_system_score_gemma":0.00007122299,"threshold_uncertainty_score":0.88095057},"labels":[],"label_agreement":null},{"id":"W2923183188","doi":"10.1145/3355089.3356494","title":"LOGAN","year":2019,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Autoencoder; Translation (biology); Artificial neural network; Domain (mathematical analysis); Key (lock); Pattern recognition (psychology); Encoding (memory); Deep learning; Shape analysis (program analysis)","score_opus":0.013793784853277001,"score_gpt":0.2229376142580692,"score_spread":0.2091438294047922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2923183188","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003341546,0.00002887262,0.9924854,0.0020701387,0.0005765118,0.000110076406,0.0000026270868,0.00011189573,0.001272914],"genre_scores_gemma":[0.95360863,0.00007075134,0.044694733,0.0011217706,0.000028474753,0.0000075118983,7.515696e-7,0.000007949324,0.00045940632],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992182,0.00004772985,0.00010926513,0.00027687618,0.00016576846,0.00018212516],"domain_scores_gemma":[0.9988801,0.0001276041,0.000028730063,0.0008542989,0.00004911707,0.000060156122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011024122,0.000105185805,0.00010346898,0.00012850987,0.000135636,0.00007391465,0.0006874703,0.000059299735,0.00011531117],"category_scores_gemma":[0.000006682039,0.00009515812,0.0001101312,0.00050085917,0.000029332667,0.00032068836,0.000009497115,0.00017228785,0.00029524902],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059007667,0.0008946523,0.0014445456,0.000039067756,0.00037790905,0.000026135676,0.0013096802,0.07004533,0.008664307,0.1311507,0.0034728302,0.7825158],"study_design_scores_gemma":[0.0037852295,0.0021027876,0.016529001,0.0001565562,0.00014043527,0.00006851341,0.0003136331,0.46303773,0.10365112,0.14057098,0.26690924,0.0027347694],"about_ca_topic_score_codex":0.000015105976,"about_ca_topic_score_gemma":0.000017879169,"teacher_disagreement_score":0.9502671,"about_ca_system_score_codex":0.00001087344,"about_ca_system_score_gemma":0.00002352232,"threshold_uncertainty_score":0.38804355},"labels":[],"label_agreement":null},{"id":"W2929742901","doi":"10.18653/v1/w19-4303","title":"Generative Adversarial Networks for Text Using Word2vec Intermediaries","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"Vector Institute; Canadian Institute for Advanced Research","keywords":"Generative grammar; Word2vec; Computer science; Adversarial system; Vocabulary; Artificial intelligence; Estimator; Word (group theory); Sentence; Generative adversarial network; Machine learning; Natural language processing; Theoretical computer science; Deep learning; Embedding; Mathematics; Linguistics; Statistics","score_opus":0.031136953528345973,"score_gpt":0.2696983701654211,"score_spread":0.2385614166370751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2929742901","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025401742,0.00042712764,0.9827922,0.00068763853,0.012747164,0.0015890735,0.000030299183,0.00017817057,0.0012943102],"genre_scores_gemma":[0.37746254,0.00007243632,0.6152565,0.0009257455,0.0044052484,0.00016192347,0.00007502049,0.000061749546,0.0015788445],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967938,0.00023284511,0.0005982888,0.0013520396,0.00031291373,0.0007101023],"domain_scores_gemma":[0.997257,0.00048239814,0.00042650025,0.0012835895,0.00039216792,0.00015832264],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00050634774,0.00063227385,0.00082496245,0.00018080589,0.0002854866,0.0010020946,0.0018269159,0.00055904244,0.00007688426],"category_scores_gemma":[0.0001540236,0.000555569,0.00049851974,0.00021552148,0.00021018666,0.00055887486,0.0029925718,0.00062586,0.000022349914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005636372,0.000047084475,0.00004613109,0.00004466042,0.00028023828,0.0000044679855,0.0005776357,0.9558455,0.00019511624,0.0109096235,0.011801897,0.020191284],"study_design_scores_gemma":[0.00053559267,0.00007824475,0.000024054338,0.00010818348,0.00006756387,0.0000028912343,0.000047196216,0.9881409,0.0013406351,0.0044711754,0.0045085438,0.0006750103],"about_ca_topic_score_codex":0.00010337888,"about_ca_topic_score_gemma":0.000051267114,"teacher_disagreement_score":0.37720853,"about_ca_system_score_codex":0.00019033042,"about_ca_system_score_gemma":0.0005106666,"threshold_uncertainty_score":0.9996896},"labels":[],"label_agreement":null},{"id":"W2936485314","doi":"","title":"Survey on generative adversarial networks","year":2019,"lang":"en","type":"article","venue":"International journal of advance research, ideas and innovations in technology","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Discriminator; Adversarial system; Generator (circuit theory); Computer science; Image translation; Image (mathematics); Generative grammar; Scope (computer science); Artificial intelligence; Generative adversarial network; Translation (biology); Deep learning; Theoretical computer science; Telecommunications; Programming language; Power (physics)","score_opus":0.026702432588931617,"score_gpt":0.34530830145710756,"score_spread":0.31860586886817593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2936485314","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16805981,0.0007897766,0.814602,0.012457856,0.0025257077,0.0002721437,0.000010102835,0.000028172723,0.0012544238],"genre_scores_gemma":[0.97725165,0.0005419587,0.021618638,0.00025655152,0.00020973361,0.0000053531057,0.0000036146976,0.0000074441878,0.00010507621],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982535,0.00020545576,0.0004895027,0.00025785796,0.0005284086,0.00026524928],"domain_scores_gemma":[0.99633074,0.0004571333,0.00023894709,0.000247686,0.002687067,0.000038442406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017405271,0.000108282904,0.00022152178,0.0016159236,0.00007766566,0.00011179759,0.0010539602,0.000114683084,0.000019537027],"category_scores_gemma":[0.0013299001,0.000094245064,0.000033246524,0.0016926475,0.00017845187,0.0006648347,0.000323065,0.00073770265,0.000008935027],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024391232,0.0002613422,0.037700314,0.0000030544802,0.00015643795,0.000106611194,0.00013070126,0.06808656,0.0026083088,0.61258656,0.0032300246,0.2748862],"study_design_scores_gemma":[0.006720336,0.0030779638,0.18935907,0.0005743954,0.000007077774,0.0002150514,0.00057746825,0.39633787,0.00969291,0.342755,0.04981166,0.00087122194],"about_ca_topic_score_codex":0.000036081638,"about_ca_topic_score_gemma":0.000058533664,"teacher_disagreement_score":0.8091918,"about_ca_system_score_codex":0.00015229142,"about_ca_system_score_gemma":0.00013144137,"threshold_uncertainty_score":0.38432023},"labels":[],"label_agreement":null},{"id":"W2937602321","doi":"10.1109/crv.2019.00033","title":"Automatic Temporally Coherent Video Colorization","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Anime; Computer science; Artificial intelligence; Computer vision; Grayscale; Discriminator; Generator (circuit theory); Line (geometry); Code (set theory); Image (mathematics); Frame (networking); Flicker; Process (computing); Key (lock); Computer graphics (images); Power (physics); Mathematics; Computer security","score_opus":0.017490662621708876,"score_gpt":0.23810790178996832,"score_spread":0.22061723916825945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2937602321","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001570479,0.00010451764,0.9821327,0.0011563161,0.002744145,0.0006970009,0.0000037900338,0.0003534482,0.0112376325],"genre_scores_gemma":[0.81480795,0.000031665648,0.18148918,0.00051414623,0.00024891444,0.00006276323,0.000034695913,0.000019559131,0.0027910976],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982018,0.00016177406,0.0003756112,0.00067365635,0.0003364542,0.00025069324],"domain_scores_gemma":[0.9983301,0.00009785063,0.0002662411,0.0010506273,0.00017402787,0.00008112095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028951088,0.00028020513,0.00037324024,0.00009962722,0.00007449871,0.0005157176,0.0011764773,0.00021136121,0.00030030144],"category_scores_gemma":[0.000050850642,0.0002357121,0.00014161016,0.00017423555,0.000025016589,0.00029369662,0.00156223,0.00025597058,0.00038348653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012390353,0.0004280389,0.0024302122,0.0006627019,0.000548329,0.000033581975,0.0012791267,0.5129613,0.001680037,0.05007015,0.19876222,0.2311319],"study_design_scores_gemma":[0.00013937183,0.000044318727,0.0010596585,0.00008367198,0.000015390131,0.0000011687093,0.0000072444946,0.99003637,0.0009623968,0.0034583735,0.0038773096,0.0003147247],"about_ca_topic_score_codex":0.000089914975,"about_ca_topic_score_gemma":0.000017342465,"teacher_disagreement_score":0.8132375,"about_ca_system_score_codex":0.000088968205,"about_ca_system_score_gemma":0.0002845497,"threshold_uncertainty_score":0.9612061},"labels":[],"label_agreement":null},{"id":"W2940988007","doi":"10.1109/iccv.2019.00770","title":"Improved Conditional VRNNs for Video Prediction","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal","funders":"","keywords":"Latent variable; Computer science; Probabilistic logic; Artificial intelligence; Generative model; Machine learning; Generative grammar; Latent variable model; Hierarchy; Sequence (biology); Conditional probability; Variable (mathematics); Sign (mathematics); Mathematics; Statistics","score_opus":0.018966196443171046,"score_gpt":0.24357964108587005,"score_spread":0.224613444642699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2940988007","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000058880833,0.000056300018,0.9924167,0.00086241565,0.003282509,0.00084988767,0.00021420998,0.00016494782,0.0020941552],"genre_scores_gemma":[0.5777985,0.0000184622,0.41347823,0.0013723827,0.0016585436,0.00041213195,0.00043732175,0.000027381764,0.0047970465],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986302,0.000046648114,0.0002589965,0.0006644791,0.00016585301,0.00023379941],"domain_scores_gemma":[0.9987519,0.00016343506,0.0001583923,0.000622171,0.00023924845,0.000064845066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024116802,0.00020937755,0.00024567274,0.00007354087,0.00010124611,0.00026952077,0.00066498324,0.00016706578,0.00007971196],"category_scores_gemma":[0.00005892173,0.00018537321,0.00021548309,0.000060080394,0.000051906685,0.00028392734,0.0006661724,0.00019836571,0.000034463654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000072265415,0.00030413285,0.00027959832,0.00037303643,0.0007515101,0.0000035332025,0.00036811217,0.3724463,0.010407304,0.18469529,0.39851698,0.03178192],"study_design_scores_gemma":[0.00028951923,0.00006986503,0.00022081449,0.000020806741,0.000018962639,0.0000014867128,0.0000051060506,0.9616592,0.0031106367,0.01935212,0.015047126,0.00020436553],"about_ca_topic_score_codex":0.000020088453,"about_ca_topic_score_gemma":0.000004792967,"teacher_disagreement_score":0.5892129,"about_ca_system_score_codex":0.000060144303,"about_ca_system_score_gemma":0.00020862288,"threshold_uncertainty_score":0.75593},"labels":[],"label_agreement":null},{"id":"W2941736865","doi":"10.1109/tmi.2019.2945521","title":"Missing MRI Pulse Sequence Synthesis Using Multi-Modal Generative Adversarial Network","year":2019,"lang":"en","type":"preprint","venue":"IEEE Transactions on Medical Imaging","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Western Canada Research Grid; Compute Canada; Nvidia","keywords":"Computer science; Missing data; Sequence (biology); Artificial intelligence; Generative adversarial network; Modal; Generative grammar; Data mining; Pattern recognition (psychology); Machine learning; Image (mathematics); Biology","score_opus":0.04021084906225624,"score_gpt":0.2983306180085902,"score_spread":0.2581197689463339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2941736865","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034957257,0.000378883,0.9829975,0.003400855,0.011642791,0.00064456876,0.00005439599,0.000320722,0.00021075271],"genre_scores_gemma":[0.61302555,0.00021821243,0.3833975,0.001478567,0.0016035971,0.000078050856,0.0000074361897,0.00008636471,0.00010473118],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9935511,0.0009922932,0.0009382062,0.0018779386,0.0014803172,0.0011601713],"domain_scores_gemma":[0.9964436,0.0007848343,0.00042536607,0.0014501995,0.00025187354,0.000644121],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0013177415,0.0008787098,0.0010215996,0.0003218285,0.0008865154,0.0007574554,0.0020390553,0.00057942537,0.00036594493],"category_scores_gemma":[0.00016895431,0.00085678464,0.00062358374,0.00056537107,0.0003904229,0.0008371496,0.00011506807,0.0024392884,0.00007948917],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029500825,0.00016721876,0.000015887625,0.000053545875,0.00020776245,0.00015975775,0.00033889725,0.82820636,0.0014225068,0.00002736322,0.00028360586,0.16908759],"study_design_scores_gemma":[0.0005582869,0.000019616347,0.000018589844,0.0010574807,0.00018819032,0.00006111075,0.000044075245,0.98653084,0.01010142,0.00029785614,0.00026121936,0.00086133636],"about_ca_topic_score_codex":0.00070507865,"about_ca_topic_score_gemma":0.00004798356,"teacher_disagreement_score":0.61267596,"about_ca_system_score_codex":0.00051521114,"about_ca_system_score_gemma":0.001426975,"threshold_uncertainty_score":0.99986213},"labels":[],"label_agreement":null},{"id":"W2942354470","doi":"10.1002/mrm.27772","title":"Conditional generative adversarial network for 3D rigid‐body motion correction in MRI","year":2019,"lang":"en","type":"article","venue":"Magnetic Resonance in Medicine","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Western Canada Research Grid","keywords":"Artificial intelligence; Computer science; Ground truth; Computer vision; Discriminator; Image quality; Image (mathematics); Motion (physics); Artifact (error); Pattern recognition (psychology); Mathematics","score_opus":0.01006326330246969,"score_gpt":0.24356872840963417,"score_spread":0.2335054651071645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2942354470","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0072649224,0.002458972,0.9789005,0.002671943,0.0053716144,0.0011698181,0.0000065158424,0.000041103725,0.002114645],"genre_scores_gemma":[0.8415249,0.00043313464,0.14878845,0.0016929329,0.0036489153,0.0003517391,0.000113131005,0.000032290543,0.003414489],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99801064,0.00020184784,0.00046229365,0.0005771652,0.0003265771,0.00042145257],"domain_scores_gemma":[0.9989604,0.00041892208,0.00012135788,0.00032259114,0.00011561819,0.000061117295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007871473,0.00020231654,0.00038998746,0.00016014698,0.00008530683,0.000033575496,0.00033506754,0.0001076249,0.0002726895],"category_scores_gemma":[0.0001831636,0.00017868998,0.000047895413,0.0006368104,0.00011135771,0.00032266515,0.00006379472,0.00020667804,0.000030263816],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005498009,0.00030486585,0.039408363,0.00005298456,0.000020982998,0.000053831813,0.0024137686,0.35375223,0.0023997365,0.02107621,0.11366063,0.4663066],"study_design_scores_gemma":[0.002777683,0.0006515056,0.07206635,0.00015466519,0.0000065362933,0.0000058528267,0.000052316187,0.88018674,0.00012467893,0.0048534498,0.038920898,0.00019932534],"about_ca_topic_score_codex":0.0002121581,"about_ca_topic_score_gemma":0.00023984938,"teacher_disagreement_score":0.83426,"about_ca_system_score_codex":0.0001259501,"about_ca_system_score_gemma":0.00006682078,"threshold_uncertainty_score":0.72867656},"labels":[],"label_agreement":null},{"id":"W2943142229","doi":"10.1109/cvpr.2019.00594","title":"Deep Video Inpainting","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Inpainting; Computer science; Artificial intelligence; Computer vision; Encoder; Retargeting; Deep learning; Image (mathematics); Domain (mathematical analysis); Task (project management); Mathematics","score_opus":0.0157302261095906,"score_gpt":0.2317937077509374,"score_spread":0.2160634816413468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943142229","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016024512,0.00022367606,0.954169,0.0009750912,0.0021062642,0.00021567993,5.1602274e-7,0.00019450684,0.041955054],"genre_scores_gemma":[0.63262904,0.00003397259,0.3637833,0.0009383123,0.0004445669,0.00001534626,0.0000044807325,0.000015337711,0.0021356705],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838585,0.00012331447,0.00025404358,0.0007042506,0.00022844764,0.00030412464],"domain_scores_gemma":[0.99839574,0.00013604542,0.00014933482,0.0011341517,0.00011547274,0.00006926756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038752184,0.00023870404,0.00029866668,0.00008836652,0.00007409801,0.00048979546,0.0014335094,0.00018414753,0.00012384976],"category_scores_gemma":[0.00008329475,0.00020449945,0.00017192897,0.00012919905,0.000021948548,0.00024058032,0.0032542136,0.0003849525,0.0003718996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035025248,0.00006484605,0.00066208513,0.00011095072,0.00016967359,0.00001946031,0.0007879946,0.70738685,0.0004627174,0.02876315,0.019192433,0.24237631],"study_design_scores_gemma":[0.00007178618,0.000011501872,0.00027008593,0.000041146584,0.0000072362773,0.0000014254081,0.0000125604465,0.98727506,0.0011175788,0.005176786,0.0057240296,0.00029079756],"about_ca_topic_score_codex":0.0000837593,"about_ca_topic_score_gemma":0.000015528496,"teacher_disagreement_score":0.63246876,"about_ca_system_score_codex":0.000041314026,"about_ca_system_score_gemma":0.00009889973,"threshold_uncertainty_score":0.83392453},"labels":[],"label_agreement":null},{"id":"W2943468268","doi":"10.1007/978-3-030-18305-9_9","title":"TextKD-GAN: Text Generation Using Knowledge Distillation and Generative Adversarial Networks","year":2019,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Automatic summarization; Generator (circuit theory); Generative grammar; Artificial intelligence; Representation (politics); Natural language processing; Machine translation; Text generation; Translation (biology); Word (group theory); Adversarial system; Measure (data warehouse); BLEU; Language model; Exploit; Machine learning; Data mining; Mathematics","score_opus":0.02682350185918448,"score_gpt":0.2701453311191642,"score_spread":0.24332182925997975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943468268","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012474735,0.0013432861,0.97705036,0.0004883884,0.0078062923,0.0007159637,0.0000055559626,0.000085526175,0.000029882529],"genre_scores_gemma":[0.67723465,0.000052533487,0.32016432,0.00021557423,0.0022909772,0.000009839811,0.000012300167,0.000017922295,0.0000018786324],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957616,0.0003786908,0.0005188818,0.002091367,0.0005326854,0.0007168279],"domain_scores_gemma":[0.99753875,0.00035569284,0.00037600606,0.0011625239,0.00039103517,0.00017600428],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0011243632,0.0006020269,0.00062393316,0.00050081365,0.0005079818,0.0015590272,0.001554898,0.00042245822,0.0000056871927],"category_scores_gemma":[0.0001608994,0.00055416435,0.000121386605,0.0012659675,0.0004605244,0.0009976273,0.0027241793,0.0008156514,0.0000072858807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000046079526,0.000027762453,0.00038132616,0.000015922786,0.000013454744,0.0000048446423,0.0008225043,0.83516634,0.0013657738,0.0001638565,0.000028877403,0.16200472],"study_design_scores_gemma":[0.0003221009,0.00007276005,0.0008577951,0.00013550498,0.000017502214,0.000015141099,6.215444e-7,0.9920187,0.0035344744,0.0023433284,0.00006342903,0.00061864126],"about_ca_topic_score_codex":0.0000922145,"about_ca_topic_score_gemma":0.00016375478,"teacher_disagreement_score":0.66475993,"about_ca_system_score_codex":0.00040803745,"about_ca_system_score_gemma":0.0007272948,"threshold_uncertainty_score":0.999691},"labels":[],"label_agreement":null},{"id":"W2945861632","doi":"10.1007/978-3-030-18305-9_34","title":"Automatic Generation of Video Game Character Images Using Augmented Structure-and-Style Networks","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Character (mathematics); Task (project management); Artificial intelligence; Generative grammar; Image (mathematics); Theme (computing); Computer vision; Quality (philosophy); Pattern recognition (psychology)","score_opus":0.019244039617452927,"score_gpt":0.23483105946463737,"score_spread":0.21558701984718442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945861632","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024675115,0.00058304786,0.9943689,0.00015702199,0.0018279691,0.0004421385,0.000010219741,0.00005576314,0.0000874179],"genre_scores_gemma":[0.6998242,0.000048786285,0.29888675,0.000466225,0.0006569335,0.0000019206996,0.000009822527,0.000030092115,0.000075266464],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969368,0.00008108839,0.0006299002,0.0012042909,0.0006394383,0.00050847256],"domain_scores_gemma":[0.9977862,0.0002759273,0.00054991676,0.0010046831,0.00026949908,0.00011374695],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00052523636,0.00051602063,0.00070355745,0.00051232404,0.00015888302,0.00047503415,0.0012972653,0.0002923943,0.000051821346],"category_scores_gemma":[0.000056533903,0.00044972732,0.00012005078,0.00039632263,0.0004740194,0.0008716675,0.00090018415,0.0004754386,0.000004321785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000051517027,0.000020679547,0.00010421941,0.00006755007,0.00004758906,0.00001681655,0.0004847023,0.5075692,0.0154107055,0.0018395887,0.000033308075,0.4744005],"study_design_scores_gemma":[0.00022044935,0.00008988901,0.00031196457,0.00027428393,0.00002221717,0.000029861978,8.830554e-8,0.9860643,0.008748175,0.0037153228,0.000079480895,0.00044393662],"about_ca_topic_score_codex":0.000023958073,"about_ca_topic_score_gemma":0.000019769148,"teacher_disagreement_score":0.6973567,"about_ca_system_score_codex":0.00015680514,"about_ca_system_score_gemma":0.00029684303,"threshold_uncertainty_score":0.99979544},"labels":[],"label_agreement":null},{"id":"W2947024452","doi":"10.48550/arxiv.1906.00443","title":"Dimensionality compression and expansion in Deep Neural Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Curse of dimensionality; Artificial neural network; Computer science; Artificial intelligence; Generalization; Manifold (fluid mechanics); Nonlinear dimensionality reduction; Regularization (linguistics); Dimensionality reduction; Stochastic gradient descent; Deep learning; Gradient descent; Noise (video); Pattern recognition (psychology); Machine learning; Mathematics; Image (mathematics)","score_opus":0.04547687358783814,"score_gpt":0.18249469529364107,"score_spread":0.13701782170580293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947024452","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24075295,0.00029897553,0.75763315,0.00008933458,0.00071146997,0.00023973593,0.000002084832,0.00005569686,0.00021658294],"genre_scores_gemma":[0.99777293,0.00020145134,0.0016402524,0.00015226056,0.00007744384,6.517334e-7,0.000012617013,0.0000119344,0.00013047655],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979047,0.000362778,0.0002062143,0.0011112237,0.00008339868,0.00033168064],"domain_scores_gemma":[0.9985696,0.00018951582,0.00017808752,0.0008461676,0.0000855196,0.00013112494],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026563773,0.00029882565,0.00038832848,0.00015032101,0.00012002398,0.00011084762,0.00076756906,0.00027878414,0.000015016479],"category_scores_gemma":[0.000019589466,0.0003034643,0.000112135545,0.00031685535,0.000087754976,0.00042325008,0.0027332287,0.00057431054,0.000008468917],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028057448,0.000044929977,0.0065420577,0.00001896354,0.000015221751,0.00008591888,0.00007537114,0.98746645,0.00004382409,0.0027279148,0.00007874486,0.002872555],"study_design_scores_gemma":[0.00040465852,0.000027332644,0.014438821,0.00008356207,0.000016289912,0.0000022281624,0.000021689004,0.98091465,0.00003726676,0.003688852,0.00004678546,0.0003178613],"about_ca_topic_score_codex":0.00022094118,"about_ca_topic_score_gemma":0.00007967856,"teacher_disagreement_score":0.75701994,"about_ca_system_score_codex":0.000086017266,"about_ca_system_score_gemma":0.00004051433,"threshold_uncertainty_score":0.99994177},"labels":[],"label_agreement":null},{"id":"W2948700496","doi":"10.48550/arxiv.1906.02735","title":"Residual Flows for Invertible Generative Modeling","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Invertible matrix; Residual; Lipschitz continuity; Estimator; Discriminative model; Transformation (genetics); Density estimation; Mathematics; Computer science; Applied mathematics; Artificial neural network; Algorithm; Mathematical optimization; Artificial intelligence; Statistics; Pure mathematics","score_opus":0.11088932375475687,"score_gpt":0.1968654022686914,"score_spread":0.08597607851393453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2948700496","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025932426,0.00011959141,0.9705887,0.00023849285,0.0012293899,0.00068220345,0.000037142414,0.00014505647,0.0010270063],"genre_scores_gemma":[0.94401395,0.00012193767,0.05308845,0.00023238228,0.00040212405,0.0000045901797,0.000034210723,0.000028453924,0.0020738929],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975958,0.00018079065,0.00024361773,0.0014094483,0.00010048764,0.00046984013],"domain_scores_gemma":[0.9979681,0.00014889996,0.00018719977,0.0012070175,0.00034404345,0.00014477632],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031918497,0.00039164184,0.00045848204,0.00020628095,0.00025858887,0.00023215113,0.0016196894,0.0003149197,0.000017970087],"category_scores_gemma":[0.00005845163,0.00042907672,0.00030179168,0.00032133202,0.000043413398,0.00056333386,0.0016609008,0.00039494334,0.00006608582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030395464,0.00003305607,0.000051586758,0.000036950925,0.00011092493,0.000017159397,0.0001770346,0.9746669,0.00017093368,0.022727026,0.0015804574,0.00039755416],"study_design_scores_gemma":[0.00046448997,0.000063599655,0.0000069257717,0.000054690663,0.00006432664,7.694106e-7,0.000045972512,0.96459234,0.0009062986,0.032838214,0.0004764206,0.00048598356],"about_ca_topic_score_codex":0.00014053282,"about_ca_topic_score_gemma":0.00008368489,"teacher_disagreement_score":0.9180815,"about_ca_system_score_codex":0.00017553358,"about_ca_system_score_gemma":0.0003540805,"threshold_uncertainty_score":0.9998161},"labels":[],"label_agreement":null},{"id":"W2949193762","doi":"10.48550/arxiv.1202.3748","title":"Conditional Restricted Boltzmann Machines for Structured Output\\n Prediction","year":2012,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; University of Toronto","funders":"","keywords":"Boltzmann machine; Computer science; Range (aeronautics); Divergence (linguistics); Probabilistic logic; Artificial intelligence; Space (punctuation); Structured prediction; Algorithm; Machine learning; Set (abstract data type); Deep learning","score_opus":0.06733588702447911,"score_gpt":0.19421561343909924,"score_spread":0.12687972641462014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949193762","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02029682,0.00024141966,0.96999276,0.00022811063,0.005139661,0.0014812624,0.0013520744,0.00022505924,0.0010428488],"genre_scores_gemma":[0.9844702,0.00023331435,0.008286268,0.00014256105,0.002153365,0.000010465977,0.000816446,0.000056332563,0.0038310406],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952563,0.0005287119,0.00066394656,0.002223889,0.0002608328,0.0010662922],"domain_scores_gemma":[0.9957525,0.00046062065,0.0008723464,0.0014688784,0.00089630455,0.00054934155],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044229627,0.00090997136,0.0008303448,0.00047024153,0.0010563583,0.00038292713,0.0019426269,0.00078793475,0.00026077192],"category_scores_gemma":[0.0001811467,0.001032646,0.0007615694,0.0009726689,0.00038506303,0.0015288654,0.0014147792,0.00081399153,0.00008394722],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039003527,0.0003064669,0.0029285576,0.00015210574,0.0007837931,0.000048170426,0.0003885556,0.9059061,0.0005252075,0.07768688,0.0063981744,0.0044859615],"study_design_scores_gemma":[0.0016086249,0.00016848517,0.025515314,0.00008733036,0.00057634397,0.000011680608,0.000056217603,0.91579884,0.0003620278,0.048212565,0.0067098485,0.0008927009],"about_ca_topic_score_codex":0.00015504255,"about_ca_topic_score_gemma":0.00004464152,"teacher_disagreement_score":0.9641734,"about_ca_system_score_codex":0.00040969742,"about_ca_system_score_gemma":0.00042045602,"threshold_uncertainty_score":0.9992124},"labels":[],"label_agreement":null},{"id":"W2949340849","doi":"10.21256/zhaw-3872","title":"Deep Learning in the Wild","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Deep learning; Realm; Computer science; Artificial intelligence; Quality (philosophy); Face (sociological concept); Matching (statistics); Data science; Perception; Machine learning; Political science; Psychology; Sociology","score_opus":0.0510781417617373,"score_gpt":0.18004795888345962,"score_spread":0.1289698171217223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949340849","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025231756,0.00008135242,0.9670704,0.0002872463,0.00046597412,0.00018305483,6.307475e-7,0.00008790535,0.0065916847],"genre_scores_gemma":[0.9964483,0.00013066706,0.002309123,0.0002402015,0.0002229701,8.9113104e-7,0.0000037421,0.000009428121,0.00063472404],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818814,0.00049268117,0.00014039023,0.0007731731,0.000087007786,0.00031858656],"domain_scores_gemma":[0.99865854,0.00017265984,0.00014957914,0.00087411795,0.000087400775,0.000057687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005155144,0.00022555511,0.00021707857,0.00014657735,0.00020947686,0.00019767707,0.0022340738,0.00017396298,0.00003173793],"category_scores_gemma":[0.00006162834,0.00019528104,0.00014423227,0.00057504425,0.000120405166,0.00029663704,0.0013361609,0.0006861001,0.00010328194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009433342,0.00004958438,0.003003299,0.000011576863,0.00003493899,0.0001928445,0.0009200389,0.9730441,0.000006714442,0.018357148,0.0006469209,0.0037234307],"study_design_scores_gemma":[0.0001661244,0.000040917374,0.0024958071,0.000037338585,0.000019402414,0.000002334414,0.00014067274,0.98015136,0.000025018993,0.013882997,0.0027887078,0.0002493303],"about_ca_topic_score_codex":0.00015646644,"about_ca_topic_score_gemma":0.00015046002,"teacher_disagreement_score":0.9712165,"about_ca_system_score_codex":0.00008037997,"about_ca_system_score_gemma":0.00007304451,"threshold_uncertainty_score":0.79633296},"labels":[],"label_agreement":null},{"id":"W2949995983","doi":"10.48550/arxiv.1505.03906","title":"Training generative neural networks via Maximum Mean Discrepancy\\n optimization","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":222,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Generative grammar; Artificial neural network; Artificial intelligence; Computer science","score_opus":0.091277332981538,"score_gpt":0.19745216294909476,"score_spread":0.10617482996755676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949995983","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023644043,0.00018009453,0.99309754,0.00016084727,0.0016727556,0.00038136504,0.000012284279,0.0002784791,0.0018522235],"genre_scores_gemma":[0.946556,0.000099586985,0.051950578,0.00018170803,0.00059900794,0.0000026860246,0.00007580975,0.00003759549,0.0004970356],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99690247,0.0005008654,0.00032374889,0.001513221,0.00015744689,0.00060225144],"domain_scores_gemma":[0.9975871,0.00009002515,0.00040486283,0.0011774027,0.00040092875,0.0003396746],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043722094,0.00054310437,0.0005624021,0.00020716865,0.00032141438,0.00034451665,0.0016463295,0.00036829343,0.000041166724],"category_scores_gemma":[0.000039738785,0.0005834864,0.00028753426,0.0006832068,0.00015217757,0.0008764187,0.0018237244,0.0006821562,0.000013827644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022522438,0.000039843137,0.00005443614,0.0000075385233,0.000111373934,0.0001305002,0.00077767856,0.9902427,0.000007116721,0.0036438133,0.00036318036,0.004599262],"study_design_scores_gemma":[0.00038025875,0.000065761626,0.000025348043,0.00003533995,0.00008648272,0.000006326202,0.00013921394,0.9882996,0.000035278306,0.010174867,0.00012524244,0.00062625756],"about_ca_topic_score_codex":0.00014287184,"about_ca_topic_score_gemma":0.000088191344,"teacher_disagreement_score":0.9441916,"about_ca_system_score_codex":0.0002568449,"about_ca_system_score_gemma":0.00020802933,"threshold_uncertainty_score":0.9996617},"labels":[],"label_agreement":null},{"id":"W2950181755","doi":"","title":"Learning Generative Models with Visual Attention","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Generative model; Computer science; Generative grammar; Artificial intelligence; Inference; Machine learning","score_opus":0.05209607952777962,"score_gpt":0.1778900880922505,"score_spread":0.12579400856447087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950181755","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13561644,0.000035563873,0.86147296,0.00008239714,0.00025738837,0.00027204782,0.000001965878,0.00017218637,0.0020890166],"genre_scores_gemma":[0.9792134,0.00010571234,0.01678433,0.00006390011,0.00016265373,0.000003040646,0.000019421681,0.000022783126,0.0036247289],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99784887,0.00032423157,0.00016556513,0.0011649841,0.00012124689,0.00037511313],"domain_scores_gemma":[0.9986102,0.00006088377,0.0002731377,0.0005788831,0.0003216516,0.00015524996],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016706082,0.00037002203,0.0003445787,0.00017531826,0.00030762696,0.00032559657,0.00089670287,0.00021806658,0.00003856607],"category_scores_gemma":[0.000011275519,0.00035257553,0.00016455658,0.0003963925,0.000106881074,0.0010865093,0.0012072441,0.00062546314,0.00009618897],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013581108,0.000046360772,0.0003045462,0.000012443804,0.00011702778,0.00006265967,0.00019590043,0.9661555,0.00013462275,0.031567734,0.00016879878,0.00122079],"study_design_scores_gemma":[0.00030450587,0.00014474514,0.00027431682,0.00006246215,0.00005541123,0.0000025399283,0.000103139755,0.98346555,0.00022775639,0.014820768,0.00009308581,0.00044571984],"about_ca_topic_score_codex":0.00021506635,"about_ca_topic_score_gemma":0.000030954114,"teacher_disagreement_score":0.84468865,"about_ca_system_score_codex":0.00014052617,"about_ca_system_score_gemma":0.0001424039,"threshold_uncertainty_score":0.99989265},"labels":[],"label_agreement":null},{"id":"W2950292946","doi":"","title":"Generative Moment Matching Networks","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":244,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Institute for Advanced Research; University of Toronto","funders":"","keywords":"MNIST database; Computer science; Generative grammar; Artificial intelligence; Matching (statistics); Machine learning; Minimax; Generative model; Moment (physics); Perceptron; Estimator; Pattern recognition (psychology); Artificial neural network; Mathematics; Mathematical optimization; Statistics","score_opus":0.07482342689117959,"score_gpt":0.18956350178453818,"score_spread":0.11474007489335859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950292946","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007224598,0.00026790143,0.98667896,0.00026095056,0.0016353644,0.00031200974,0.000009930745,0.00021394434,0.0033963479],"genre_scores_gemma":[0.9815139,0.000212976,0.0153861,0.00025461946,0.0005154171,0.0000022369777,0.000022593811,0.000025466548,0.0020666833],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99742854,0.0003623116,0.00024831702,0.0013219179,0.000127373,0.0005115713],"domain_scores_gemma":[0.99774593,0.00007782541,0.00029359106,0.0012681049,0.0003067502,0.0003077681],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046826547,0.00045532413,0.00046982305,0.00017059884,0.00024448414,0.00032882654,0.0018494095,0.0003114607,0.00003267894],"category_scores_gemma":[0.00001613999,0.00048597396,0.00024456365,0.00047615395,0.00009540619,0.0005262787,0.0030889453,0.0006777195,0.00007154082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011394203,0.000047802976,0.00006943415,0.000008819067,0.00011852214,0.00015789754,0.0003061473,0.9520421,0.000015784619,0.042723574,0.0033613155,0.0011371897],"study_design_scores_gemma":[0.00029395145,0.000041427837,0.000058238104,0.00004914848,0.000051374835,0.0000025935467,0.00006755773,0.94648737,0.00009402136,0.05112275,0.0012183374,0.00051322056],"about_ca_topic_score_codex":0.00018389002,"about_ca_topic_score_gemma":0.000049227703,"teacher_disagreement_score":0.9742893,"about_ca_system_score_codex":0.0003730311,"about_ca_system_score_gemma":0.0002597397,"threshold_uncertainty_score":0.9997592},"labels":[],"label_agreement":null},{"id":"W2950339535","doi":"10.48550/arxiv.1806.03968","title":"CapsGAN: Using Dynamic Routing for Generative Adversarial Networks","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; MNIST database; Normalization (sociology); Artificial intelligence; Knot (papermaking); Image translation; Algorithm; Clipping (morphology); Computer vision; Image (mathematics); Deep learning","score_opus":0.07079669769047088,"score_gpt":0.20883844787792322,"score_spread":0.13804175018745235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950339535","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017683554,0.00009596365,0.97719735,0.000073432006,0.0036320703,0.00074000616,0.00003214234,0.00018690713,0.00035857107],"genre_scores_gemma":[0.9284532,0.00006100796,0.06949434,0.00014065672,0.0012794549,0.0000028987824,0.000043130432,0.00004423065,0.00048107145],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967209,0.00030553056,0.00035729157,0.001755684,0.00010613712,0.00075447175],"domain_scores_gemma":[0.9973606,0.00022293812,0.0005236082,0.0011974808,0.000482988,0.00021237988],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004994992,0.0005723925,0.0006073732,0.00020955465,0.00067313574,0.0003376522,0.0018174623,0.00051177095,0.000025322772],"category_scores_gemma":[0.000087607244,0.0006524538,0.00047031257,0.0005278603,0.00021538319,0.0006023531,0.0021268416,0.00051535346,0.000014563781],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050877672,0.00004039057,0.000066184344,0.000018453022,0.00020877569,0.000042386226,0.00019795318,0.9888924,0.00015194059,0.009186893,0.0004429139,0.0007008371],"study_design_scores_gemma":[0.0006869226,0.00008531388,0.00003801092,0.00009165688,0.00017271114,0.0000035336259,0.00005860975,0.98964906,0.00037979332,0.0078853965,0.00024817252,0.00070081145],"about_ca_topic_score_codex":0.00019369062,"about_ca_topic_score_gemma":0.000116911084,"teacher_disagreement_score":0.91076964,"about_ca_system_score_codex":0.0004887416,"about_ca_system_score_gemma":0.00037225813,"threshold_uncertainty_score":0.99959266},"labels":[],"label_agreement":null},{"id":"W2950966637","doi":"10.48550/arxiv.1503.05571","title":"GSNs : Generative Stochastic Networks","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Probabilistic logic; Computer science; Markov chain; Joint probability distribution; Artificial intelligence; Gibbs sampling; Limit (mathematics); Mathematics; Algorithm; Applied mathematics; Machine learning; Statistics; Bayesian probability","score_opus":0.0789925385596879,"score_gpt":0.18727209816113877,"score_spread":0.10827955960145087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950966637","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026999025,0.0002893869,0.99211884,0.00017428453,0.001792566,0.00034933136,0.00001570241,0.00024293724,0.0023170402],"genre_scores_gemma":[0.990494,0.0000735551,0.0066225245,0.00019922896,0.00060210994,0.0000023825753,0.000025994834,0.000027950202,0.0019522344],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99727297,0.0003617143,0.00024667408,0.0014360736,0.00012398677,0.00055859785],"domain_scores_gemma":[0.9973385,0.0001338784,0.00029649673,0.0014270525,0.00044082748,0.00036327558],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039252618,0.00049485295,0.00051506475,0.00019396016,0.00024277893,0.00028079774,0.0020718402,0.00038127595,0.000039146118],"category_scores_gemma":[0.00006728496,0.00053355173,0.000267722,0.0006189302,0.00015717893,0.0004908088,0.0028160294,0.00074784446,0.000098624216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015127312,0.00004934668,0.000034000583,0.000005308135,0.00011787833,0.00012563221,0.00017007724,0.9707424,0.000006933497,0.023544496,0.004400494,0.00078829244],"study_design_scores_gemma":[0.00033894042,0.000057229623,0.000058344136,0.00004649801,0.00007788146,0.0000033890722,0.000042684776,0.9723842,0.000028763372,0.026015664,0.00038232427,0.00056404585],"about_ca_topic_score_codex":0.00012229176,"about_ca_topic_score_gemma":0.00007441095,"teacher_disagreement_score":0.9877941,"about_ca_system_score_codex":0.00029480955,"about_ca_system_score_gemma":0.00038701043,"threshold_uncertainty_score":0.9997116},"labels":[],"label_agreement":null},{"id":"W2952742172","doi":"","title":"Better Mixing via Deep Representations","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":104,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Mixing (physics); Conjecture; Representation (politics); Space (punctuation); Markov chain; Mathematics; Variation (astronomy); Computer science; Pure mathematics; Statistics; Physics; Political science","score_opus":0.060977676553122716,"score_gpt":0.19291298649936436,"score_spread":0.13193530994624164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952742172","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010711972,0.00012208296,0.98238283,0.0002779039,0.0011725298,0.00020513804,0.0000046157006,0.00016438903,0.0049585244],"genre_scores_gemma":[0.9756598,0.000052442538,0.022684861,0.00023796097,0.00041533262,0.0000015419259,0.000015226491,0.00001802138,0.0009148541],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981094,0.00023132161,0.00019332238,0.00093406957,0.00009267516,0.00043922497],"domain_scores_gemma":[0.9980072,0.00013059705,0.00021546287,0.0013078315,0.00014448234,0.00019443608],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021405602,0.00029110615,0.000281279,0.00017741723,0.0002539699,0.00017236562,0.0014012359,0.0002165275,0.0001271804],"category_scores_gemma":[0.000027230199,0.00032985126,0.0002494965,0.00042844025,0.00008953606,0.00073940307,0.001960759,0.00044408205,0.0002159553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014424221,0.00017138726,0.006950733,0.000047104342,0.00032318122,0.00022242131,0.000883604,0.9448995,0.00052458653,0.030856732,0.0022711742,0.012835179],"study_design_scores_gemma":[0.00021700752,0.000011568038,0.002717007,0.000030595187,0.00009801388,0.000004356765,0.00003911514,0.9712319,0.0007117955,0.023265352,0.0011785891,0.0004947321],"about_ca_topic_score_codex":0.00017967826,"about_ca_topic_score_gemma":0.00003998847,"teacher_disagreement_score":0.96494776,"about_ca_system_score_codex":0.000114989234,"about_ca_system_score_gemma":0.000059426533,"threshold_uncertainty_score":0.99991536},"labels":[],"label_agreement":null},{"id":"W2952838738","doi":"","title":"MADE: Masked Autoencoder for Distribution Estimation","year":2015,"lang":"en","type":"preprint","venue":"Edinburgh Research Explorer (University of Edinburgh)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":269,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Autoencoder; Autoregressive model; Estimator; Computer science; Joint probability distribution; Artificial neural network; Simple (philosophy); Set (abstract data type); Algorithm; Artificial intelligence; Mathematics; Econometrics; Statistics","score_opus":0.13335353369304978,"score_gpt":0.33292494906882786,"score_spread":0.19957141537577808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952838738","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019553993,0.00036971713,0.9878169,0.0048545892,0.0022878377,0.0013842983,0.00025172438,0.00018400747,0.00089554524],"genre_scores_gemma":[0.5778019,0.0008245604,0.40754786,0.00005878707,0.003015324,0.00009765498,0.0018898199,0.000078699086,0.008685421],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99520427,0.0003224088,0.0004194642,0.0013188055,0.0017325319,0.0010025144],"domain_scores_gemma":[0.9939622,0.0006988406,0.00040103018,0.0014158319,0.0030243457,0.0004976987],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004380683,0.00043386017,0.0007474152,0.00062006107,0.0006710791,0.00028796706,0.0029047471,0.00058245246,0.00046171056],"category_scores_gemma":[0.00096602214,0.000498754,0.00042201005,0.00089555804,0.0005575443,0.0013242227,0.0036621909,0.0011308457,0.00001103972],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017967696,0.00020981903,0.000029861434,0.00007505022,0.00019451327,0.00002221191,0.0046400647,0.049227852,0.00046381756,0.0015049604,0.9221715,0.021280726],"study_design_scores_gemma":[0.00090301625,0.00028066887,0.00008854891,0.00024353109,0.000059767197,0.0000023509808,0.001708849,0.87233645,0.000482445,0.070463724,0.052934386,0.00049625593],"about_ca_topic_score_codex":0.00034111814,"about_ca_topic_score_gemma":0.000013261401,"teacher_disagreement_score":0.86923707,"about_ca_system_score_codex":0.0006572461,"about_ca_system_score_gemma":0.0010971559,"threshold_uncertainty_score":0.9997464},"labels":[],"label_agreement":null},{"id":"W2952940861","doi":"10.48550/arxiv.1502.02476","title":"An Infinite Restricted Boltzmann Machine","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Restricted Boltzmann machine; Boltzmann machine; Limit (mathematics); Computer science; Boltzmann constant; Function (biology); Layer (electronics); Artificial intelligence; Energy (signal processing); Algorithm; Mathematics; Deep learning; Statistics; Physics; Mathematical analysis","score_opus":0.07306386073334857,"score_gpt":0.19979047940260786,"score_spread":0.12672661866925927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952940861","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03987166,0.00014817719,0.9534777,0.00013805777,0.000921621,0.00025996834,0.00003279439,0.00037459083,0.0047754296],"genre_scores_gemma":[0.9910963,0.00014240161,0.0072152913,0.00015824482,0.0002518215,8.835572e-7,0.00006724151,0.00002365347,0.0010441202],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975304,0.0004040873,0.00023256047,0.0012719041,0.00013554681,0.00042551922],"domain_scores_gemma":[0.99694824,0.00007792855,0.00026915973,0.001927243,0.00038432245,0.00039307622],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003034617,0.00040158493,0.00040799365,0.00030791239,0.00018324611,0.0002848616,0.0025307413,0.0003233304,0.000036167858],"category_scores_gemma":[0.00006505935,0.00043665018,0.00017394227,0.0008052766,0.00010369291,0.0007973499,0.0018233468,0.00062915776,0.0001161492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040145045,0.00015162697,0.001072259,0.000017238797,0.00010203702,0.0003857318,0.00022919092,0.97130555,0.000108038366,0.021423563,0.0031237137,0.0020408817],"study_design_scores_gemma":[0.0004178957,0.00010930532,0.0010711205,0.00003117699,0.000055431443,0.0000031131326,0.000025667538,0.97160774,0.00013461745,0.022670757,0.003353184,0.00052001054],"about_ca_topic_score_codex":0.0004980446,"about_ca_topic_score_gemma":0.00010516671,"teacher_disagreement_score":0.9512247,"about_ca_system_score_codex":0.00016870802,"about_ca_system_score_gemma":0.00033124274,"threshold_uncertainty_score":0.99980855},"labels":[],"label_agreement":null},{"id":"W2954036577","doi":"","title":"A Wrapped Normal Distribution on Hyperbolic Space for Gradient-Based Learning","year":2019,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Hyperbolic space; Mathematics; MNIST database; Gaussian; Distribution (mathematics); Mathematical analysis; Artificial intelligence; Computer science; Artificial neural network; Physics","score_opus":0.020446556151040705,"score_gpt":0.2606745710653548,"score_spread":0.2402280149143141,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954036577","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049504463,0.000014276891,0.9373041,0.0045190323,0.0009801983,0.00028304747,0.000019500272,0.00016004706,0.0072153327],"genre_scores_gemma":[0.9914955,0.0000068168642,0.0055580563,0.0003139467,0.000170502,0.000031197316,0.00020270338,0.000015116699,0.0022061532],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850476,0.00015278754,0.00020052154,0.00047433432,0.00037217428,0.00029542294],"domain_scores_gemma":[0.9990815,0.00024123979,0.0001780561,0.0001999202,0.00022292795,0.0000763371],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032718302,0.00020415052,0.00018388212,0.00012344384,0.00021743815,0.00027970932,0.00057033775,0.00006108089,0.00021223316],"category_scores_gemma":[0.00027379429,0.00018848747,0.00012718278,0.0001462617,0.000025054933,0.00026965563,0.00008685361,0.00043851964,0.00023195379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036827257,0.00017118875,0.014739797,0.0000172453,0.00007294429,0.0000069712546,0.00024120949,0.60024387,0.008859514,0.3249403,0.0002714746,0.050067242],"study_design_scores_gemma":[0.0008455819,0.00053667056,0.0022783973,0.00005564279,0.0000050167023,0.0000017633565,0.000026257232,0.96445787,0.0023554415,0.00039741644,0.028822714,0.00021720314],"about_ca_topic_score_codex":0.000051947147,"about_ca_topic_score_gemma":0.000006936764,"teacher_disagreement_score":0.94199103,"about_ca_system_score_codex":0.000087667875,"about_ca_system_score_gemma":0.00006223309,"threshold_uncertainty_score":0.7686296},"labels":[],"label_agreement":null},{"id":"W2954942335","doi":"10.1109/access.2019.2926882","title":"Channel Attention Networks for Image Translation","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Key Research and Development Program of China","keywords":"Computer science; Image translation; Encoder; Feature (linguistics); Artificial intelligence; Channel (broadcasting); Translation (biology); Image (mathematics); Computer vision; Bottleneck; Convolution (computer science); Image quality; Pooling; Domain (mathematical analysis); Pattern recognition (psychology); Artificial neural network; Telecommunications; Mathematics","score_opus":0.030512668373817314,"score_gpt":0.2823225433982288,"score_spread":0.2518098750244115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954942335","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004693312,0.000073594,0.9916105,0.0005462308,0.0018506277,0.00044063205,0.0000023373316,0.000069774534,0.00071297283],"genre_scores_gemma":[0.98507637,0.000016785925,0.013897769,0.00026792908,0.00042321754,0.00004109402,0.000008289026,0.000010996537,0.00025753526],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991634,0.0000396266,0.0001510172,0.0003090825,0.00011050707,0.0002263916],"domain_scores_gemma":[0.99941325,0.00008699303,0.00007551464,0.0002868525,0.00009600766,0.00004136756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020256768,0.000104708095,0.00012695626,0.00005066354,0.000093381714,0.00035162168,0.0005951133,0.00005526447,0.00001716043],"category_scores_gemma":[0.0000059675363,0.000096127944,0.00009476372,0.0002064823,0.00001317285,0.0017149573,0.00004006542,0.000055745913,0.0000337811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011382623,0.00021722954,0.0010614976,0.00012151503,0.00015412841,0.000006869027,0.00052689284,0.5788211,0.04334483,0.0031493027,0.02213617,0.35034662],"study_design_scores_gemma":[0.00039382814,0.000040202962,0.0012648957,0.000013746226,0.000007753651,0.0000010557432,0.000003901149,0.99123985,0.0043152617,0.001147822,0.0014266588,0.0001450475],"about_ca_topic_score_codex":0.000015259151,"about_ca_topic_score_gemma":0.0000081252665,"teacher_disagreement_score":0.9803831,"about_ca_system_score_codex":0.000013982999,"about_ca_system_score_gemma":0.000013440472,"threshold_uncertainty_score":0.39199838},"labels":[],"label_agreement":null},{"id":"W2957129532","doi":"10.23919/mva.2019.8757925","title":"Face Style Transfer and Removal with Generative Adversarial Network","year":2019,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Stylized fact; Style (visual arts); Computer science; Face (sociological concept); Artificial intelligence; Generative grammar; Image (mathematics); Computer vision; Transfer (computing); Art; Visual arts; Linguistics","score_opus":0.006581234593742699,"score_gpt":0.1872090079463477,"score_spread":0.180627773352605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2957129532","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02164283,0.00012639159,0.96485746,0.0007154832,0.000359384,0.00028859425,0.0000013588747,0.0000776987,0.011930811],"genre_scores_gemma":[0.8050711,0.000021686092,0.19101453,0.0006501173,0.00031040164,0.000005895391,0.0000018237528,0.000011529415,0.0029129167],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874884,0.00010101463,0.00014055234,0.00048122462,0.00020303398,0.00032535082],"domain_scores_gemma":[0.9993923,0.00007783892,0.000023481305,0.00034794607,0.000057910194,0.00010058205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018273358,0.00018298939,0.00021777017,0.000028516704,0.00013004002,0.00017945096,0.00029272112,0.000057973037,0.00013081449],"category_scores_gemma":[0.000004630898,0.00012810285,0.000041290572,0.00023896134,0.000052718016,0.0005858322,0.00009758393,0.000107616754,0.000054456093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006024321,0.0002244732,0.0043651704,0.000042096388,0.00071736344,0.00018469329,0.007287953,0.49026516,0.015254219,0.34467113,0.019849405,0.116535895],"study_design_scores_gemma":[0.0028283924,0.000804224,0.0016889197,0.000038794646,0.000038159116,0.000087864515,0.00028506407,0.93192935,0.009049163,0.001050729,0.051344708,0.000854632],"about_ca_topic_score_codex":0.00003882018,"about_ca_topic_score_gemma":0.000049418584,"teacher_disagreement_score":0.78342825,"about_ca_system_score_codex":0.000015435984,"about_ca_system_score_gemma":0.000049153412,"threshold_uncertainty_score":0.5223883},"labels":[],"label_agreement":null},{"id":"W2958269485","doi":"10.1007/s11548-019-02022-z","title":"CycleGAN for style transfer in X-ray angiography","year":2019,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"Mitacs","keywords":"Computer science; Artificial intelligence; Similarity (geometry); Task (project management); Translation (biology); Image translation; Data set; Consistency (knowledge bases); Deep learning; Image (mathematics); Angiography; Computer vision; Radiology; Medicine","score_opus":0.011283828264697312,"score_gpt":0.22916688032761434,"score_spread":0.21788305206291703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2958269485","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19111186,0.00060698285,0.8038565,0.0016131115,0.002701143,0.00006712017,0.0000018214719,0.000007412396,0.00003403179],"genre_scores_gemma":[0.9732516,0.00008883221,0.025590422,0.0006420581,0.00040666806,0.000002214896,0.000002583872,0.000004823009,0.000010819071],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9989649,0.00015355978,0.0004171324,0.00017108629,0.00013979779,0.00015350919],"domain_scores_gemma":[0.9986147,0.0009084251,0.00011605695,0.00009583239,0.00021134305,0.000053609187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064466876,0.00010116453,0.00031970415,0.00048543,0.000025582664,0.000073249044,0.00038339297,0.00007251576,0.000009281699],"category_scores_gemma":[0.000020082714,0.00008344007,0.00032122765,0.00013991614,0.00004154366,0.00039983165,0.000034172146,0.0001201085,0.0000012607853],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010229318,0.00065798796,0.38025615,0.000041237854,0.0029657655,0.0005821797,0.0018645242,0.024244476,0.004930366,0.02021316,0.017634297,0.54558694],"study_design_scores_gemma":[0.0030852752,0.00046285847,0.7683428,0.00022951775,0.000039687857,0.0012546538,0.000042936696,0.19811283,0.00067216274,0.0018571242,0.025394117,0.0005060383],"about_ca_topic_score_codex":0.0000031377526,"about_ca_topic_score_gemma":0.0000026294983,"teacher_disagreement_score":0.7821397,"about_ca_system_score_codex":0.000017542226,"about_ca_system_score_gemma":0.00005229057,"threshold_uncertainty_score":0.34025872},"labels":[],"label_agreement":null},{"id":"W2962687528","doi":"","title":"Texture Modeling with Convolutional Spike-and-Slab RBMs and Deep Extensions","year":2013,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Boltzmann machine; Artificial intelligence; Convolution (computer science); Layer (electronics); Deep learning; Spike (software development); Deep belief network; Inpainting; Texture (cosmology); Parametric statistics; Pattern recognition (psychology); Convolutional neural network; Computer vision; Algorithm; Image (mathematics); Artificial neural network; Mathematics; Materials science","score_opus":0.006063522580150985,"score_gpt":0.16717360044815005,"score_spread":0.16111007786799905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962687528","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013522475,0.00040230266,0.9823331,0.001862616,0.000050621267,0.00011419923,3.8346397e-7,0.000044618348,0.0016696862],"genre_scores_gemma":[0.8235031,0.000029498618,0.17553419,0.0005506415,0.00005116266,0.000008626325,6.644602e-7,0.000004052067,0.0003181041],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99932104,0.00002491184,0.0000908645,0.00027918114,0.00011389592,0.00017010205],"domain_scores_gemma":[0.99953914,0.000046103385,0.000021150037,0.0001700937,0.00012250812,0.00010098475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000064271764,0.00010232152,0.0001048374,0.000030813193,0.0001790421,0.00016592281,0.00011995236,0.000036226225,0.00007321493],"category_scores_gemma":[0.000011969429,0.00006624604,0.000015307012,0.000092226255,0.00005969216,0.0005139858,0.00013357245,0.00007113364,0.00002080217],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030487481,0.0001996645,0.0039912206,0.000033099383,0.000231508,0.000034259265,0.002090316,0.19691345,0.013247429,0.48056203,0.010997937,0.2916686],"study_design_scores_gemma":[0.0001617529,0.000034932207,0.0017289324,0.000008308806,0.0000052558266,0.000024835033,0.000060796472,0.99475986,0.0000822031,0.002829842,0.00018821501,0.00011506264],"about_ca_topic_score_codex":0.00013640837,"about_ca_topic_score_gemma":0.00006433295,"teacher_disagreement_score":0.8099806,"about_ca_system_score_codex":0.0000061259616,"about_ca_system_score_gemma":0.000020048139,"threshold_uncertainty_score":0.2701435},"labels":[],"label_agreement":null},{"id":"W2962778531","doi":"10.1007/978-3-030-20887-5_18","title":"Totally Looks Like - How Humans Compare, Compared to Machines","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Similarity (geometry); Consistency (knowledge bases); Matching (statistics); Artificial intelligence; Convolutional neural network; Set (abstract data type); Perception; Task (project management); Image (mathematics); Entertainment; Pattern recognition (psychology); Machine learning; Information retrieval; Mathematics","score_opus":0.01770514157041165,"score_gpt":0.23373971117207626,"score_spread":0.21603456960166462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962778531","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000089550325,0.0003226663,0.98373985,0.002108214,0.0041325274,0.0007735994,0.000015311234,0.0001880327,0.008630235],"genre_scores_gemma":[0.4388536,0.000020355044,0.54968905,0.0053521227,0.0012627556,0.000014739118,0.000016326823,0.000078824705,0.004712213],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99491656,0.00007824264,0.0005426655,0.002253,0.0012238844,0.000985647],"domain_scores_gemma":[0.9962871,0.0004560541,0.00031554032,0.0021721916,0.00041844504,0.00035068902],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00067886786,0.0008682151,0.0010340571,0.0008708466,0.00039350058,0.0015794463,0.0049900278,0.00023648697,0.000054745662],"category_scores_gemma":[0.000064503096,0.0007750617,0.00024672836,0.0006725661,0.0004894583,0.0007715136,0.0024120384,0.0007814162,0.0002164273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002750768,0.00008524989,0.00027349993,0.00007428441,0.00007153274,0.00014325054,0.0018293689,0.5717321,0.00089380663,0.016035993,0.002784087,0.4060493],"study_design_scores_gemma":[0.00045364758,0.0002676727,0.0006654015,0.00046962808,0.000019114916,0.000036352543,4.6212472e-7,0.9600875,0.000865097,0.017536739,0.018077215,0.0015212031],"about_ca_topic_score_codex":0.000056885245,"about_ca_topic_score_gemma":0.00046964467,"teacher_disagreement_score":0.43876404,"about_ca_system_score_codex":0.00027248118,"about_ca_system_score_gemma":0.0005468965,"threshold_uncertainty_score":0.99947006},"labels":[],"label_agreement":null},{"id":"W2963185199","doi":"10.1007/978-3-030-01228-1_28","title":"Probabilistic Video Generation Using Holistic Attribute Control","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Decoding methods; Artificial intelligence; Generative model; Probabilistic logic; Encoding (memory); Generative grammar; Machine learning; Computer vision; Pattern recognition (psychology); Algorithm","score_opus":0.04667553684949441,"score_gpt":0.26384596071739247,"score_spread":0.21717042386789806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963185199","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015937255,0.00030760025,0.99492526,0.0003306881,0.0032593263,0.0005838901,0.000014759275,0.00010503123,0.0003140728],"genre_scores_gemma":[0.56688714,0.00001666087,0.42756715,0.0014155966,0.0038203148,0.000011876859,0.000010040941,0.00004570836,0.0002254804],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959338,0.00010065046,0.00060929963,0.0017428643,0.0008632925,0.00075009454],"domain_scores_gemma":[0.99707353,0.0003744992,0.00037525428,0.0013518911,0.00062758144,0.00019723296],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011009213,0.0005963679,0.00064158073,0.00050864817,0.00048729862,0.00095140503,0.0022017562,0.0003126777,0.0000656459],"category_scores_gemma":[0.00031614292,0.00053642364,0.00015689713,0.0005505087,0.0009065728,0.0007877489,0.00070755096,0.0004862723,0.00006427282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000088238685,0.000038726663,0.000031213538,0.000033684955,0.000037134156,0.00006175454,0.00042262577,0.8496134,0.0017369497,0.0048391214,0.0002523894,0.14292413],"study_design_scores_gemma":[0.00029760896,0.000144673,0.000028833278,0.00016714353,0.000027134178,0.00004165038,5.2142568e-8,0.9587069,0.00133335,0.03806619,0.0005985066,0.00058795477],"about_ca_topic_score_codex":0.000026963786,"about_ca_topic_score_gemma":0.00008640308,"teacher_disagreement_score":0.5673581,"about_ca_system_score_codex":0.00048014795,"about_ca_system_score_gemma":0.0006626579,"threshold_uncertainty_score":0.9997087},"labels":[],"label_agreement":null},{"id":"W2963359059","doi":"","title":"Variational Message Passing with Structured Inference Networks.","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Inference; Graphical model; Computer science; Message passing; Theoretical computer science; Approximate inference; Variable elimination; Probabilistic logic; Algorithm; Artificial intelligence; Programming language","score_opus":0.028791537379196184,"score_gpt":0.3079606261640736,"score_spread":0.2791690887848774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963359059","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027137958,0.000005058921,0.95272565,0.0030419377,0.0006490547,0.00011098136,0.00000387599,0.00014110275,0.040608525],"genre_scores_gemma":[0.96257013,0.000011250584,0.03511761,0.00026597033,0.0005221129,0.00004070061,0.000035636323,0.000011769818,0.001424793],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983064,0.00017773977,0.00023999621,0.0005173182,0.0005160583,0.00024247241],"domain_scores_gemma":[0.9983031,0.00028983186,0.00020613695,0.000330989,0.0007793015,0.000090654474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018091881,0.00017807512,0.00013873646,0.00016146938,0.00046413814,0.00067444664,0.0007298024,0.000059239526,0.0008890122],"category_scores_gemma":[0.00029465646,0.00015216376,0.00004865457,0.0003552059,0.00016618712,0.00076122384,0.00015487116,0.00029631561,0.00007373423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008930377,0.00010448167,0.014228767,0.0000023595833,0.00023593186,0.000024336665,0.0020141352,0.29160997,0.0017420484,0.646888,0.0012966454,0.041763987],"study_design_scores_gemma":[0.0003554166,0.0001630265,0.027602173,0.000044100256,0.000009162437,0.000009867151,0.00011954248,0.96421826,0.0005987037,0.004691644,0.0019721522,0.00021597718],"about_ca_topic_score_codex":0.00006273153,"about_ca_topic_score_gemma":0.00005391594,"teacher_disagreement_score":0.95985633,"about_ca_system_score_codex":0.000056351673,"about_ca_system_score_gemma":0.00014807565,"threshold_uncertainty_score":0.973406},"labels":[],"label_agreement":null},{"id":"W2963408680","doi":"","title":"DVAE++: Discrete Variational Autoencoders with Overlapping Transformations","year":2018,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"D-Wave Systems (Canada)","funders":"","keywords":"Latent variable; Prior probability; Transformation (genetics); Softmax function; Smoothing; Computer science; Artificial intelligence; Algorithm; Mathematics; Applied mathematics; Convolutional neural network; Statistics; Bayesian probability","score_opus":0.020686409982519808,"score_gpt":0.2663003432703145,"score_spread":0.24561393328779468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963408680","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00053105736,0.0000066649673,0.9143276,0.0068254946,0.0003451816,0.00008349942,0.0000077027335,0.0001139453,0.07775885],"genre_scores_gemma":[0.9376459,0.000020554764,0.060678408,0.00045090023,0.00027009426,0.000013281499,0.000034616383,0.000009621408,0.0008765905],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986903,0.00010305926,0.00021054171,0.00032875035,0.00045609876,0.0002112473],"domain_scores_gemma":[0.9992168,0.000087960914,0.00012768965,0.00017289125,0.0003237125,0.00007093955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021716912,0.00016381453,0.00012433981,0.00015013976,0.00035673872,0.00036853144,0.0005970229,0.000038787322,0.00054038246],"category_scores_gemma":[0.00007292841,0.0001328874,0.00005179869,0.00020114856,0.00008180848,0.0008465425,0.000071518414,0.00026685247,0.00012836716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008060288,0.00005816759,0.0010851595,0.0000036481474,0.00015763061,0.000008836001,0.0019388868,0.15071574,0.0012814511,0.8209771,0.000230354,0.023462405],"study_design_scores_gemma":[0.00035599314,0.00022026527,0.0017848903,0.000042835716,0.0000056323997,0.000010089243,0.00005086196,0.9836002,0.00023460793,0.0025848635,0.010928158,0.00018161151],"about_ca_topic_score_codex":0.00007278909,"about_ca_topic_score_gemma":0.000064382424,"teacher_disagreement_score":0.9371149,"about_ca_system_score_codex":0.000053528944,"about_ca_system_score_gemma":0.00010071034,"threshold_uncertainty_score":0.5916809},"labels":[],"label_agreement":null},{"id":"W2963444790","doi":"10.1109/iccv.2017.310","title":"DualGAN: Unsupervised Dual Learning for Image-to-Image Translation","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2105,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Image translation; Computer science; Translation (biology); Image (mathematics); Artificial intelligence; Dual (grammatical number); Task (project management); Domain (mathematical analysis); Pattern recognition (psychology); Labeled data; Generative grammar; Function (biology); Computer vision; Mathematics","score_opus":0.042571893889378196,"score_gpt":0.2904346791370451,"score_spread":0.24786278524766692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963444790","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000436294,0.00010000096,0.9822923,0.0052613653,0.0012313853,0.0011092474,0.00001508484,0.00027295682,0.009281356],"genre_scores_gemma":[0.16519319,0.000041056075,0.830521,0.00027966025,0.00088302844,0.00019970506,0.00007016026,0.00004771824,0.0027644928],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975011,0.00017277697,0.00040226488,0.0010994686,0.000328744,0.0004956898],"domain_scores_gemma":[0.9977679,0.00023730968,0.0002329026,0.001181456,0.0003876515,0.00019273802],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00070621877,0.00042130818,0.00050360453,0.00016593929,0.00060537487,0.0016819193,0.0013702917,0.00025702576,0.00007575951],"category_scores_gemma":[0.00027352243,0.00039545586,0.00033760053,0.00009756168,0.00006427742,0.0007375372,0.0009174438,0.00046544857,0.00010159909],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014237242,0.00024140827,0.00007154441,0.00046551888,0.00046518663,0.0000686806,0.006183532,0.113167256,0.0654531,0.0052934904,0.032373797,0.7760741],"study_design_scores_gemma":[0.00068855134,0.0001437451,0.00039141736,0.00010540145,0.00005472271,0.000004114824,0.00004204135,0.9546256,0.01452332,0.0041247797,0.024496643,0.00079963845],"about_ca_topic_score_codex":0.00008443422,"about_ca_topic_score_gemma":0.000041758765,"teacher_disagreement_score":0.8414584,"about_ca_system_score_codex":0.0000467224,"about_ca_system_score_gemma":0.00017865778,"threshold_uncertainty_score":0.99984974},"labels":[],"label_agreement":null},{"id":"W2963501406","doi":"10.48550/arxiv.1511.06406","title":"Denoising Criterion for Variational Auto-Encoding Framework","year":2015,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Autoencoder; MNIST database; Noise reduction; Noise (video); Upper and lower bounds; Pattern recognition (psychology); Artificial intelligence; Computer science; Encoding (memory); Encoder; Algorithm; Noise measurement; Mathematics; Deep learning","score_opus":0.1114331944100856,"score_gpt":0.20943521070192983,"score_spread":0.09800201629184423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963501406","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010326664,0.000025913443,0.98785764,0.00028074457,0.00048454214,0.0001183075,0.000002791414,0.000096961216,0.00080642704],"genre_scores_gemma":[0.9052469,0.0000045667807,0.09401592,0.00018877293,0.00021074004,5.926586e-7,0.000002570774,0.0000069824596,0.00032292271],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990988,0.00007750662,0.00010425155,0.0004124289,0.00006875102,0.00023828862],"domain_scores_gemma":[0.9990558,0.00021988929,0.00007756989,0.00030015263,0.00020536396,0.00014124386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031542106,0.00011499744,0.0001234692,0.00008770442,0.0002149517,0.00013322681,0.00048815832,0.00007798694,0.000010465184],"category_scores_gemma":[0.00019538797,0.00012660665,0.000077628865,0.00041394302,0.000033717486,0.0008689475,0.00015919222,0.000088012646,0.000029425752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028008826,0.000039984738,0.0005961045,0.000005427963,0.00003047298,0.00002360783,0.00043537223,0.45367804,0.00039241137,0.5424054,0.0011330554,0.0012320612],"study_design_scores_gemma":[0.00030534272,0.000054546723,0.00035450148,0.00001889162,0.000015293186,0.0000022351567,0.00005848543,0.909854,0.00038323758,0.08641524,0.0023753718,0.00016284535],"about_ca_topic_score_codex":0.000020902196,"about_ca_topic_score_gemma":0.000003845806,"teacher_disagreement_score":0.8949203,"about_ca_system_score_codex":0.00011162166,"about_ca_system_score_gemma":0.00010109505,"threshold_uncertainty_score":0.51628697},"labels":[],"label_agreement":null},{"id":"W2963540976","doi":"","title":"Invertible Residual Networks","year":2019,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":193,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Invertible matrix; Jacobian matrix and determinant; Normalization (sociology); Residual; Computer science; Generative grammar; Block (permutation group theory); Algorithm; Simple (philosophy); Theoretical computer science; Artificial intelligence; Mathematics; Applied mathematics","score_opus":0.02215808535166284,"score_gpt":0.2573328756627397,"score_spread":0.23517479031107688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963540976","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013410147,0.00006759267,0.8316879,0.006084707,0.0018781696,0.00015819742,0.0000023364075,0.00021910785,0.14649183],"genre_scores_gemma":[0.98803616,0.000042798656,0.0048745517,0.0007430258,0.00023244861,0.000005305606,0.000017083466,0.0000101650685,0.006038483],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875635,0.00013647623,0.00017767954,0.00037931604,0.00033282625,0.0002173482],"domain_scores_gemma":[0.9993428,0.00010188861,0.00010274685,0.00024610106,0.00014362442,0.000062816805],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00025538885,0.00014526375,0.00013758062,0.00011239181,0.00009793119,0.00030283158,0.00082588725,0.00005315095,0.001081757],"category_scores_gemma":[0.00008004016,0.00013001206,0.000056252207,0.00014014912,0.0000209288,0.0004147406,0.00023759459,0.00040612242,0.0005361688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006130378,0.000067828834,0.026320959,0.000004067026,0.000093553565,0.000020749529,0.00026066706,0.50509346,0.003242242,0.40295357,0.0013125085,0.06056908],"study_design_scores_gemma":[0.00026756353,0.000117211035,0.0020256513,0.00002961423,0.0000018675306,0.0000039371157,0.000016848864,0.9860976,0.00042677333,0.0012282036,0.009626904,0.00015785843],"about_ca_topic_score_codex":0.00007843553,"about_ca_topic_score_gemma":0.000014108907,"teacher_disagreement_score":0.974626,"about_ca_system_score_codex":0.00003734236,"about_ca_system_score_gemma":0.000039444432,"threshold_uncertainty_score":0.9998314},"labels":[],"label_agreement":null},{"id":"W2963622136","doi":"","title":"Bidirectional Helmholtz machines","year":2016,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Canadian Institute for Advanced Research","funders":"","keywords":"Inference; Autoencoder; Generative model; Computer science; Helmholtz free energy; Fiducial inference; Algorithm; Artificial intelligence; Bhattacharyya distance; Generative grammar; Frequentist inference; Machine learning; Bayesian inference; Deep learning; Bayesian probability","score_opus":0.029767150963290613,"score_gpt":0.27513869460975704,"score_spread":0.24537154364646643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963622136","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035640923,0.00003664854,0.91537356,0.019292051,0.0014073914,0.000066753935,0.000010149597,0.00023511199,0.060014267],"genre_scores_gemma":[0.98148173,0.000069666006,0.007826474,0.00039177798,0.00034666376,0.000011354714,0.00000639657,0.000010209091,0.009855716],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873906,0.00013521833,0.00018048067,0.00038404224,0.00036940956,0.00019179173],"domain_scores_gemma":[0.9992752,0.00017069714,0.00010415926,0.00018649874,0.0001917519,0.000071694114],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022634631,0.00015608278,0.00012050078,0.0001494268,0.00015623965,0.00018922832,0.00068997586,0.000041383122,0.0013133221],"category_scores_gemma":[0.00024017152,0.000102693426,0.00007726262,0.00011873013,0.000044438,0.00046382908,0.0001734028,0.00018140659,0.00040124808],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050712257,0.000083968334,0.011968198,0.0000020171692,0.000093343086,0.000023155726,0.00011944184,0.002532681,0.034570567,0.36783695,0.0009835538,0.58173543],"study_design_scores_gemma":[0.00088514655,0.00022138943,0.008293247,0.00011618257,0.000005629083,0.00003419424,0.000010974239,0.8824903,0.0060771974,0.014140942,0.08726098,0.00046385947],"about_ca_topic_score_codex":0.000056819954,"about_ca_topic_score_gemma":0.000019125962,"teacher_disagreement_score":0.9779177,"about_ca_system_score_codex":0.000052499956,"about_ca_system_score_gemma":0.00004104996,"threshold_uncertainty_score":0.99959964},"labels":[],"label_agreement":null},{"id":"W2963642948","doi":"","title":"Synthesizing Programs for Images using Reinforced Adversarial Learning.","year":2018,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Discriminator; MNIST database; Artificial intelligence; Inference; Machine learning; Graphics; Rendering (computer graphics); Adversarial system; Deep learning; Generative grammar; Generative adversarial network; Computer graphics; Reinforcement learning; Computer graphics (images)","score_opus":0.05329083591455927,"score_gpt":0.30830803711602445,"score_spread":0.2550172012014652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963642948","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037644329,0.000017686143,0.9810079,0.0011013207,0.0011213599,0.00026748967,0.000003566586,0.00023142327,0.012484829],"genre_scores_gemma":[0.9132045,0.000012492313,0.08330794,0.00015414308,0.0010105122,0.000024440415,0.000026436308,0.000023584369,0.0022359355],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981887,0.00017679752,0.00031177572,0.0005432389,0.0003973107,0.0003822035],"domain_scores_gemma":[0.99861956,0.00021979028,0.00026962443,0.00022315317,0.000574885,0.000092984905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005300883,0.00024857215,0.00022634015,0.00017984485,0.0005287972,0.0006046513,0.0008753447,0.0000836594,0.0001884722],"category_scores_gemma":[0.00073339156,0.00023176914,0.00014158135,0.00017757187,0.00011632598,0.0006332155,0.00023788598,0.00038089327,0.00006229667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068434165,0.00013842825,0.0032403143,0.000031884814,0.00045416635,0.00002880536,0.0020743434,0.12214911,0.09787249,0.21990606,0.00044657657,0.5529735],"study_design_scores_gemma":[0.00051524903,0.0004224121,0.00007943692,0.00008927421,0.00001233493,0.000008254802,0.00006592879,0.97729945,0.007825404,0.00080813887,0.012599971,0.00027413218],"about_ca_topic_score_codex":0.00013760522,"about_ca_topic_score_gemma":0.000010479116,"teacher_disagreement_score":0.9094401,"about_ca_system_score_codex":0.00008427634,"about_ca_system_score_gemma":0.00009420902,"threshold_uncertainty_score":0.9451271},"labels":[],"label_agreement":null},{"id":"W2963645527","doi":"","title":"GumBolt: Extending Gumbel trick to Boltzmann priors","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"D-Wave Systems (Canada)","funders":"","keywords":"Prior probability; Gumbel distribution; Artificial intelligence; Computer science; MNIST database; Algorithm; Latent variable; Margin (machine learning); Bayesian probability; Mathematics; Machine learning; Artificial neural network; Statistics","score_opus":0.016421402057763993,"score_gpt":0.25689467972533503,"score_spread":0.24047327766757104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963645527","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008259667,0.00013208254,0.98182315,0.0006892149,0.0019802854,0.00038978766,0.0000024876795,0.00030799114,0.0064153103],"genre_scores_gemma":[0.9873005,0.0000024568255,0.01055511,0.0010704853,0.0005976596,0.000037456313,0.0000041908634,0.0000085101165,0.00042361426],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835885,0.00006896147,0.00056021416,0.00023407886,0.00040319032,0.00037471164],"domain_scores_gemma":[0.9987161,0.00003152088,0.00028775292,0.00033981478,0.00047114547,0.00015367163],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00042679854,0.00018551495,0.00020947709,0.00024892573,0.00051364733,0.0015167327,0.00065173756,0.00006792678,0.000007777092],"category_scores_gemma":[0.00012089536,0.00015810122,0.00004952845,0.0008827785,0.000041533905,0.005761241,0.00016639325,0.00010072189,0.00042087652],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033487628,0.000039772687,0.00032777828,0.00025580244,0.000027267008,0.0000043697664,0.014417844,0.022576569,0.002574618,0.004953614,0.033154618,0.92163426],"study_design_scores_gemma":[0.0002279232,0.00012678884,0.0006521105,0.00011250369,0.0000056475146,0.000032637476,0.00032556462,0.91340804,0.0017753158,0.00004057482,0.08300981,0.00028306202],"about_ca_topic_score_codex":0.000049026505,"about_ca_topic_score_gemma":0.0000025941797,"teacher_disagreement_score":0.97904086,"about_ca_system_score_codex":0.000069565576,"about_ca_system_score_gemma":0.00006896163,"threshold_uncertainty_score":0.99951977},"labels":[],"label_agreement":null},{"id":"W2963812505","doi":"","title":"DVAE#: Discrete Variational Autoencoders with Relaxed Boltzmann Priors","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"D-Wave Systems (Canada)","funders":"","keywords":"Boltzmann machine; MNIST database; Prior probability; Restricted Boltzmann machine; Gaussian; Computer science; Binary number; Upper and lower bounds; Artificial intelligence; Boltzmann constant; Algorithm; Autoencoder; Boltzmann distribution; Mathematics; Pattern recognition (psychology); Artificial neural network; Statistical physics; Bayesian probability; Physics; Mathematical analysis","score_opus":0.02863410500574351,"score_gpt":0.1642277174748586,"score_spread":0.13559361246911508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963812505","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015217846,0.0000083954255,0.97707695,0.00037738116,0.0002433677,0.00012268356,0.0000029371488,0.00013213929,0.006818327],"genre_scores_gemma":[0.96451074,0.000014264725,0.03291667,0.00019187173,0.00015973217,4.6616725e-7,0.0000030286988,0.000010716198,0.0021924935],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998726,0.00010659476,0.0001132566,0.00062148104,0.000107879045,0.00032478443],"domain_scores_gemma":[0.998949,0.00007693286,0.00010910636,0.00053671363,0.00018676378,0.00014152088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001660993,0.00017637566,0.00015161933,0.00010647167,0.00035565707,0.00010122798,0.0007205983,0.00006475915,0.00007573563],"category_scores_gemma":[0.000026427386,0.00015931352,0.0000699547,0.00075267215,0.00022172136,0.000988001,0.00020360855,0.00011195579,0.00015763889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014242089,0.00010941705,0.004795695,0.0000070299684,0.0002130385,0.00018949292,0.0010766325,0.45874706,0.00030909717,0.53041226,0.0028992954,0.0010985585],"study_design_scores_gemma":[0.0005658318,0.0002228755,0.0064168703,0.000015299827,0.00003173725,0.0000059722897,0.00007705915,0.9832861,0.0003366192,0.0045188484,0.00423452,0.00028828712],"about_ca_topic_score_codex":0.00006327681,"about_ca_topic_score_gemma":0.00007978241,"teacher_disagreement_score":0.9492929,"about_ca_system_score_codex":0.000074168274,"about_ca_system_score_gemma":0.00013138588,"threshold_uncertainty_score":0.6496617},"labels":[],"label_agreement":null},{"id":"W2964020555","doi":"","title":"NICE: Non-linear Independent Components Estimation","year":2014,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":222,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Inpainting; Transformation (genetics); Computer science; Latent variable; Representation (politics); Algorithm; Component (thermodynamics); Linear map; Jacobian matrix and determinant; Artificial intelligence; Artificial neural network; Mathematics; Theoretical computer science; Image (mathematics); Applied mathematics","score_opus":0.01451056422384049,"score_gpt":0.2381944619302341,"score_spread":0.22368389770639363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964020555","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051038377,0.000005044292,0.98500717,0.0005607369,0.00037574768,0.00007786013,2.2823876e-7,0.00007662455,0.008792728],"genre_scores_gemma":[0.7715456,0.0000015744349,0.22756791,0.0003614279,0.00009241513,0.000003613441,0.0000024202886,0.0000037767588,0.00042126636],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991826,0.000061647246,0.00014392163,0.00023971593,0.0002065259,0.00016563085],"domain_scores_gemma":[0.99942875,0.000058160982,0.000050456933,0.00033890395,0.000054542812,0.00006920494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026947906,0.00009176824,0.000107112566,0.00004218637,0.000106611915,0.00009605135,0.00041567063,0.000036980728,0.000041917578],"category_scores_gemma":[0.000034102708,0.00007530367,0.000039696744,0.00012767834,0.000016395854,0.00040045177,0.0001566127,0.00006333176,0.0003252198],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017347767,0.0003444378,0.0017950846,0.00002509477,0.00008342941,0.00000785285,0.0007494886,0.3838385,0.02548012,0.059739698,0.014904531,0.51301444],"study_design_scores_gemma":[0.00019932729,0.000031070602,0.004857361,0.0000055712067,0.0000026217347,0.0000017767908,0.0000030760775,0.98595667,0.005759709,0.0009505265,0.002131655,0.00010063712],"about_ca_topic_score_codex":0.000055856806,"about_ca_topic_score_gemma":0.000006628454,"teacher_disagreement_score":0.76644176,"about_ca_system_score_codex":0.000015887952,"about_ca_system_score_gemma":0.0000121446055,"threshold_uncertainty_score":0.4180151},"labels":[],"label_agreement":null},{"id":"W2964249351","doi":"","title":"A Variational Inequality Perspective on Generative Adversarial Networks","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Adversarial system; Extrapolation; Generative grammar; Perspective (graphical); Variational inequality; Computer science; Saddle point; Mathematical optimization; Point (geometry); Artificial intelligence; Theoretical computer science; Machine learning; Mathematics","score_opus":0.05121513478095525,"score_gpt":0.20160257009433522,"score_spread":0.15038743531337997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964249351","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006795731,0.0000110223455,0.98031247,0.00042381772,0.00087164814,0.00016980126,0.000007243633,0.0001238903,0.011284384],"genre_scores_gemma":[0.9907669,0.000011196632,0.0066455645,0.0007380541,0.0011947107,9.037483e-7,0.0000045134434,0.000010752346,0.00062743964],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981121,0.00036469352,0.00016078184,0.0008730207,0.000114908755,0.00037449176],"domain_scores_gemma":[0.99840385,0.00021187632,0.00014214308,0.0005935509,0.0004901905,0.00015839137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033228894,0.00023495751,0.0002157893,0.00012807747,0.0004742461,0.000112360096,0.00074606936,0.000119014614,0.00015035487],"category_scores_gemma":[0.00011226777,0.00023933855,0.00013737782,0.00086090877,0.00021089759,0.00071484264,0.0002693399,0.00020373528,0.00017298413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000102997335,0.00009654998,0.00028766572,6.739048e-7,0.00008176328,0.000032315707,0.00043405112,0.29372725,0.00005991982,0.70359755,0.0012036406,0.00037562],"study_design_scores_gemma":[0.000747605,0.00030918396,0.0016946354,0.000008313453,0.000022989158,0.0000018779482,0.00015716812,0.9703102,0.00038707274,0.025472721,0.0005914855,0.00029674458],"about_ca_topic_score_codex":0.00018760365,"about_ca_topic_score_gemma":0.00008831731,"teacher_disagreement_score":0.9839711,"about_ca_system_score_codex":0.00031471543,"about_ca_system_score_gemma":0.00012948392,"threshold_uncertainty_score":0.9759943},"labels":[],"label_agreement":null},{"id":"W2964268013","doi":"","title":"Feature grouping from spatially constrained multiplicative interaction","year":2013,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Pooling; Feature (linguistics); Computer science; Artificial intelligence; Pattern recognition (psychology); ENCODE; Boltzmann machine; Image (mathematics); Transformation (genetics); Filter (signal processing); Orientation (vector space); Feature vector; Multiplicative function; Mathematics; Computer vision; Deep learning","score_opus":0.011831135297181297,"score_gpt":0.22189142550046353,"score_spread":0.21006029020328223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964268013","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050158063,0.000021468617,0.9808115,0.00592687,0.00035354245,0.00021220626,0.000001956479,0.00012690747,0.0075297914],"genre_scores_gemma":[0.74667805,0.000003621186,0.25209752,0.0006296625,0.00015500688,0.000022275051,0.000005764778,0.0000043041427,0.0004038035],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922764,0.00006968187,0.00010632612,0.00032408332,0.00010644127,0.0001657991],"domain_scores_gemma":[0.9992518,0.0001799991,0.000075218755,0.00029937088,0.00012208952,0.000071565904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000053568758,0.00011872945,0.00012367284,0.000035417972,0.000097617514,0.00026684965,0.00034857012,0.000052578187,0.00033556655],"category_scores_gemma":[0.0000491495,0.00009350154,0.000053952015,0.00013013161,0.000035428136,0.0009894026,0.00012809483,0.00011493106,0.00031224283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013788924,0.00020531077,0.0009643788,0.000005048203,0.00020627117,0.000008745364,0.0024208701,0.0030034645,0.2046102,0.015495132,0.045482755,0.727584],"study_design_scores_gemma":[0.00033504047,0.000056844518,0.0074995807,0.000020341718,0.0000061723217,0.0000027764208,0.00018320991,0.9519054,0.032614797,0.0025490536,0.0045731002,0.00025368112],"about_ca_topic_score_codex":0.0009516334,"about_ca_topic_score_gemma":0.000077265664,"teacher_disagreement_score":0.94890195,"about_ca_system_score_codex":0.000025459709,"about_ca_system_score_gemma":0.000018917579,"threshold_uncertainty_score":0.40133542},"labels":[],"label_agreement":null},{"id":"W2964332639","doi":"","title":"Understanding Minimum Probability Flow for RBMs Under Various Kinds of Dynamics.","year":2014,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Boltzmann machine; Computer science; Divergence (linguistics); Importance sampling; Partition function (quantum field theory); Artificial intelligence; Restricted Boltzmann machine; Gibbs sampling; Sampling (signal processing); Function (biology); Dynamics (music); Artificial neural network; Monte Carlo method; Machine learning; Mathematics; Statistics; Bayesian probability; Physics","score_opus":0.11615241067146911,"score_gpt":0.18133192431588485,"score_spread":0.06517951364441574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964332639","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01045996,0.0000063218536,0.98684096,0.00018515516,0.00026762922,0.00022539803,0.0000073382794,0.000058555543,0.0019486663],"genre_scores_gemma":[0.973818,0.000005521695,0.025763944,0.00007691634,0.000045099354,6.639526e-7,0.000004103025,0.000009204098,0.00027651977],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988309,0.00012278646,0.0001632492,0.000528904,0.000065680826,0.000288464],"domain_scores_gemma":[0.998797,0.0003094598,0.00013175748,0.00054374896,0.00012271249,0.000095311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038725868,0.00015360897,0.00023099293,0.00009713622,0.00017571716,0.000046084744,0.00060712034,0.00008856727,0.000011442212],"category_scores_gemma":[0.00006358206,0.00016009253,0.00014907615,0.00044568305,0.00013427454,0.0003790374,0.00017700535,0.00008039022,0.00000477166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002531841,0.00006409555,0.000514561,0.000019802774,0.0000387278,0.0000019501706,0.00008439148,0.39902902,0.000117687574,0.59945613,0.00012838664,0.0005199399],"study_design_scores_gemma":[0.00044972968,0.00010877796,0.00025121126,0.000010654631,0.000024248035,6.848511e-7,0.00006151815,0.79914844,0.0002117412,0.19950376,0.00008188421,0.00014732024],"about_ca_topic_score_codex":0.000034100736,"about_ca_topic_score_gemma":0.0001472494,"teacher_disagreement_score":0.96335804,"about_ca_system_score_codex":0.0002446867,"about_ca_system_score_gemma":0.000060881655,"threshold_uncertainty_score":0.6528384},"labels":[],"label_agreement":null},{"id":"W2964501821","doi":"10.1109/crv.2019.00018","title":"Hierarchically-Fused Generative Adversarial Network for Text to Realistic Image Synthesis","year":2019,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Discriminator; Exploit; Artificial intelligence; Image (mathematics); Similarity (geometry); Image synthesis; Adversarial system; Generative adversarial network; Generative grammar; Scheme (mathematics); Scale (ratio); Pattern recognition (psychology); Network architecture","score_opus":0.010683985220883787,"score_gpt":0.2372953983253776,"score_spread":0.22661141310449381,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964501821","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008745158,0.000021314627,0.97899497,0.004422376,0.0013951533,0.0011730286,0.000030238965,0.00018325097,0.012905171],"genre_scores_gemma":[0.22068305,0.000007097879,0.77198845,0.0027036245,0.0013473269,0.00022866669,0.000010370084,0.000035724523,0.002995709],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99732995,0.00023084565,0.00041414838,0.0009259948,0.0003279914,0.0007710956],"domain_scores_gemma":[0.99713165,0.0012915652,0.00011143302,0.00091259443,0.00025564688,0.00029710037],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006261415,0.0003332316,0.0004849345,0.0001107387,0.00028067423,0.00037751207,0.0011084016,0.00011595569,0.0003755253],"category_scores_gemma":[0.00047589507,0.00027997486,0.00023122011,0.00054281106,0.000054486285,0.0005255342,0.00036750548,0.00013819207,0.0005165546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005821497,0.00028941923,0.00024394791,0.00006402519,0.0004442705,0.000023784567,0.0013682253,0.15160944,0.055850375,0.33775708,0.34802365,0.10374364],"study_design_scores_gemma":[0.0015634886,0.0007075925,0.001063775,0.00008451909,0.00007892173,0.000007055514,0.00007041815,0.88062453,0.027133813,0.014981487,0.07235464,0.001329755],"about_ca_topic_score_codex":0.000089377034,"about_ca_topic_score_gemma":0.000066699904,"teacher_disagreement_score":0.7290151,"about_ca_system_score_codex":0.000077519806,"about_ca_system_score_gemma":0.00013663442,"threshold_uncertainty_score":0.99996525},"labels":[],"label_agreement":null},{"id":"W2965095304","doi":"","title":"Perceptual Generative Autoencoders","year":2019,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of Calgary","funders":"","keywords":"Autoencoder; Partitioned global address space; Generative model; Prior probability; Generative grammar; Dimension (graph theory); Intrinsic dimension; Computer science; Artificial intelligence; Space (punctuation); Encoder; Pattern recognition (psychology); Generator (circuit theory); Artificial neural network; Representation (politics); Machine learning; Mathematics; Bayesian probability; Curse of dimensionality; Power (physics)","score_opus":0.007993020673644022,"score_gpt":0.2037278601040518,"score_spread":0.1957348394304078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965095304","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006015767,0.000024543062,0.9273553,0.00082698074,0.00049117714,0.00010658924,4.011672e-7,0.00011031804,0.06506891],"genre_scores_gemma":[0.7269183,0.0000048461065,0.2629502,0.0012483302,0.00008956156,0.000003918973,8.612298e-7,0.0000048289776,0.008779152],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918455,0.000058715614,0.00010218392,0.0003040721,0.0001484392,0.0002020261],"domain_scores_gemma":[0.9994749,0.000042046187,0.000025441566,0.00034697293,0.00005078047,0.000059898095],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000104124025,0.00009918933,0.000110682035,0.00003782685,0.0000662547,0.00012112974,0.00042086904,0.00003277139,0.0009346734],"category_scores_gemma":[0.00000969007,0.00007662908,0.000057437057,0.00016068414,0.000023963721,0.00050655747,0.00013702105,0.00006182883,0.0013022802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015247417,0.0002037023,0.004860066,0.000012267319,0.00017167936,0.00002301521,0.008010788,0.14877877,0.057953753,0.5417699,0.11481572,0.12338508],"study_design_scores_gemma":[0.00021735871,0.000085059444,0.0017355459,0.0000031200618,0.0000023224854,0.000003599463,0.00019438748,0.97694737,0.0061033634,0.0010904614,0.013405376,0.0002120506],"about_ca_topic_score_codex":0.000023451747,"about_ca_topic_score_gemma":0.00000775223,"teacher_disagreement_score":0.8281686,"about_ca_system_score_codex":0.000019876148,"about_ca_system_score_gemma":0.000038707563,"threshold_uncertainty_score":0.9999786},"labels":[],"label_agreement":null},{"id":"W2965370967","doi":"10.24963/ijcai.2019/411","title":"Learning K-way D-dimensional Discrete Embedding for Hierarchical Data Visualization and Retrieval","year":2019,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Embedding; Computer science; Visualization; Autoencoder; Curse of dimensionality; Data visualization; Data point; Encoding (memory); Theoretical computer science; Point (geometry); Data mining; Artificial intelligence; Pattern recognition (psychology); Mathematics; Deep learning","score_opus":0.022562413136370946,"score_gpt":0.2968138747292506,"score_spread":0.2742514615928796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965370967","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019961929,0.00003990912,0.9786901,0.00043119024,0.00024150746,0.00018474058,0.0000038516982,0.000057389156,0.00038940573],"genre_scores_gemma":[0.8671239,0.000008014404,0.13065514,0.00019707959,0.00014052624,0.0000015926172,0.000060044993,0.000009345096,0.0018043478],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898136,0.00008047172,0.00013687252,0.00045496706,0.00016432576,0.00018198464],"domain_scores_gemma":[0.99919635,0.00029930164,0.000046993948,0.00034088516,0.00005407682,0.00006237496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044933596,0.0000907289,0.00012288522,0.000041707466,0.00015841112,0.000177389,0.00035356724,0.00004082516,0.000040280927],"category_scores_gemma":[0.00017550781,0.0000727523,0.000023151853,0.00012915982,0.000025138681,0.0007271586,0.00057909766,0.00007847547,0.00001261044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000593277,0.00020649447,0.008095896,0.00019595379,0.00036117694,0.000012942985,0.003749524,0.15404612,0.10822717,0.49508443,0.017298706,0.21212831],"study_design_scores_gemma":[0.00026895152,0.00010595329,0.0003862847,0.000011912375,0.000004969562,0.0000028054642,0.000021107973,0.9927726,0.0013295513,0.0007141348,0.004267071,0.00011469805],"about_ca_topic_score_codex":0.0000057645484,"about_ca_topic_score_gemma":0.0000016987316,"teacher_disagreement_score":0.8480349,"about_ca_system_score_codex":0.000008630583,"about_ca_system_score_gemma":0.000025601958,"threshold_uncertainty_score":0.29667526},"labels":[],"label_agreement":null},{"id":"W2965833116","doi":"10.1109/cvpr.2019.00878","title":"Image Generation From Layout","year":2019,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":215,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Embedding; Bounding overwatch; Set (abstract data type); Object (grammar); Image (mathematics); Boosting (machine learning); Representation (politics); Pattern recognition (psychology); Generative model; Encoding (memory); Generative grammar; Computer vision","score_opus":0.012342765472434361,"score_gpt":0.21038689072193983,"score_spread":0.1980441252495055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965833116","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029026276,0.0000346358,0.94749093,0.00083425624,0.0006113667,0.00007766371,0.000001456121,0.00007673203,0.021846712],"genre_scores_gemma":[0.6712181,0.0000029342696,0.3257136,0.000585443,0.00025694683,0.0000022888896,0.000005999885,0.00000377495,0.0022108944],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938494,0.000040304618,0.00009197945,0.00025198102,0.000110738656,0.000120054276],"domain_scores_gemma":[0.9995062,0.000028723814,0.000026588204,0.0003596182,0.00004169452,0.000037186393],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000075246324,0.000070669725,0.00008124138,0.000019243085,0.000040699233,0.0001737057,0.00029348105,0.000027059887,0.0006441666],"category_scores_gemma":[0.000008083415,0.000056721776,0.000037510436,0.000090344925,0.000008135418,0.0005952474,0.00009827669,0.00003783365,0.001497825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004243194,0.00006877854,0.0018452643,0.0000018867513,0.000051933224,0.000007757082,0.00048815564,0.0037167284,0.8021799,0.07175753,0.07248873,0.04738914],"study_design_scores_gemma":[0.0001519379,0.000020661031,0.001624655,0.0000016643862,0.0000021108451,4.2090426e-7,0.000009439588,0.9525619,0.034505986,0.00088491634,0.010118638,0.00011767939],"about_ca_topic_score_codex":0.0001277064,"about_ca_topic_score_gemma":0.000017138529,"teacher_disagreement_score":0.94884515,"about_ca_system_score_codex":0.000010702248,"about_ca_system_score_gemma":0.000015618569,"threshold_uncertainty_score":0.9992796},"labels":[],"label_agreement":null},{"id":"W2967817162","doi":"10.48550/arxiv.1908.05324","title":"Dual Adversarial Inference for Text-to-Image Synthesis","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Mitacs","keywords":"Inference; Computer science; Image (mathematics); Adversarial system; Dual (grammatical number); Style (visual arts); Artificial intelligence; Composition (language); Image synthesis; Space (punctuation); Quality (philosophy); Process (computing); Natural language processing; Linguistics","score_opus":0.056948975206100094,"score_gpt":0.20542953931362098,"score_spread":0.1484805641075209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967817162","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008212162,0.000021608446,0.9847324,0.00035157084,0.0022042627,0.0010954274,0.00012525215,0.00022019008,0.0030371647],"genre_scores_gemma":[0.95834714,0.000048840404,0.03895615,0.00023083485,0.0004972626,0.000013489385,0.000016466114,0.0000383071,0.0018515011],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99673504,0.00022405131,0.00032012336,0.0018736803,0.00015768313,0.0006894372],"domain_scores_gemma":[0.9961835,0.0010083423,0.00030755173,0.0017692816,0.00041974336,0.00031159597],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044721802,0.0005589577,0.0006833107,0.0003543898,0.00025987625,0.00037577032,0.0023766677,0.00040999075,0.000080385376],"category_scores_gemma":[0.0005509715,0.00062526215,0.00047613773,0.00058133143,0.000111016845,0.0006991598,0.0029306244,0.0004534617,0.00043253394],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016892907,0.00014299473,0.00027518164,0.00012202012,0.0002797756,0.00009497115,0.00032978968,0.9426867,0.0005772207,0.04420666,0.005931368,0.005184404],"study_design_scores_gemma":[0.0006534213,0.00014337327,0.000509794,0.00016042625,0.00018316001,0.0000018974318,0.000067245,0.9772066,0.002377853,0.010725082,0.006923911,0.0010472415],"about_ca_topic_score_codex":0.000150885,"about_ca_topic_score_gemma":0.00004877411,"teacher_disagreement_score":0.950135,"about_ca_system_score_codex":0.00023722339,"about_ca_system_score_gemma":0.00044921946,"threshold_uncertainty_score":0.99961984},"labels":[],"label_agreement":null},{"id":"W2970370162","doi":"","title":"Reducing Noise in GAN Training with Variance Reduced Extragradient","year":2019,"lang":"en","type":"article","venue":"Infoscience (Ecole Polytechnique Fédérale de Lausanne)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Hasler Stiftung; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"MNIST database; Convergence (economics); Variance (accounting); Computer science; Noise (video); Mathematical optimization; Class (philosophy); Training (meteorology); Generative grammar; Artificial intelligence; Algorithm; Machine learning; Mathematics; Deep learning; Image (mathematics)","score_opus":0.012941713471936766,"score_gpt":0.22620143077856425,"score_spread":0.2132597173066275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970370162","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24073546,0.00008065951,0.7450726,0.0011089771,0.00045102503,0.0008675842,0.0000038844655,0.00033484618,0.011344958],"genre_scores_gemma":[0.8405013,0.000021764117,0.15813166,0.0005529509,0.000078470315,0.000115978975,0.0000012996543,0.000019476656,0.0005771026],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969452,0.00016678848,0.0004614237,0.0009405353,0.00042863927,0.0010574175],"domain_scores_gemma":[0.9983043,0.00014452088,0.00023063803,0.0009773062,0.00009728949,0.00024591264],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012234551,0.00032165428,0.0003894251,0.00036049407,0.00019617748,0.00032718666,0.001557171,0.0001426914,0.000049300124],"category_scores_gemma":[0.000111765214,0.00029741426,0.00008290131,0.0017365812,0.00017886441,0.0016055282,0.00019332682,0.0004089839,0.0000380116],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010915633,0.00038550657,0.01092861,0.00007003571,0.000031245214,0.00025540963,0.012003086,0.15196043,0.68992305,0.030659085,0.0008651895,0.102809176],"study_design_scores_gemma":[0.0012090305,0.0009344958,0.02794274,0.0009783659,0.0000133971835,0.00022724012,0.00057748024,0.64780873,0.31270579,0.0025122396,0.0035592956,0.0015311871],"about_ca_topic_score_codex":0.00036258,"about_ca_topic_score_gemma":0.00011808192,"teacher_disagreement_score":0.59976584,"about_ca_system_score_codex":0.00021917463,"about_ca_system_score_gemma":0.0004891599,"threshold_uncertainty_score":0.9999478},"labels":[],"label_agreement":null},{"id":"W2970641149","doi":"","title":"Residual Flows for Invertible Generative Modeling","year":2019,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Invertible matrix; Residual; Lipschitz continuity; Discriminative model; Transformation (genetics); Computer science; Mathematics; Algorithm; Generative model; Artificial neural network; Density estimation; Applied mathematics; Mathematical optimization; Generative grammar; Artificial intelligence; Statistics; Estimator; Pure mathematics","score_opus":0.023988969713449645,"score_gpt":0.23942725955678212,"score_spread":0.21543828984333246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970641149","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014851768,0.0001675184,0.98171335,0.00040996692,0.0010297527,0.0005957883,0.0000049883683,0.00014511718,0.0010817426],"genre_scores_gemma":[0.97334486,0.000002817032,0.025512664,0.00051503186,0.00024401916,0.000080503676,0.00002165848,0.000007781265,0.00027065017],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987963,0.000051009833,0.00044759063,0.00019187473,0.00025470907,0.00025855086],"domain_scores_gemma":[0.99907166,0.000039721446,0.00019950324,0.00023445796,0.0003960702,0.000058586014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000319449,0.00014862223,0.00019229799,0.00011491588,0.00025321994,0.0009929836,0.00036692416,0.00006753514,0.0000032004004],"category_scores_gemma":[0.000044414996,0.00012390937,0.000049896167,0.00024586244,0.000009116437,0.006098606,0.00006901435,0.00008360596,0.00006522751],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010614254,0.0000055767446,0.00002543953,0.00013849835,0.000008135023,1.246845e-7,0.0012330251,0.97447646,0.0010709367,0.002030375,0.0011801801,0.019820636],"study_design_scores_gemma":[0.00031730675,0.000056934605,0.0000042625284,0.000051140745,0.0000038123271,0.000005275453,0.00021433005,0.9946348,0.0012161023,0.00014056753,0.0031908534,0.00016459744],"about_ca_topic_score_codex":0.00003064854,"about_ca_topic_score_gemma":0.0000021346973,"teacher_disagreement_score":0.9584931,"about_ca_system_score_codex":0.000044509732,"about_ca_system_score_gemma":0.00009587304,"threshold_uncertainty_score":0.95753634},"labels":[],"label_agreement":null},{"id":"W2970700221","doi":"","title":"Invertible Convolutional Flow","year":2019,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Jacobian matrix and determinant; Invertible matrix; Algorithm; Inverse; Computer science; Flow (mathematics); Computation; Applied mathematics; Convolution (computer science); Deconvolution; Mathematics; Mathematical optimization; Pure mathematics; Artificial intelligence; Artificial neural network","score_opus":0.009803219437600411,"score_gpt":0.20244898359163818,"score_spread":0.19264576415403778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970700221","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052830786,0.0002211579,0.9827415,0.000499984,0.0018296404,0.00028219543,0.000003380911,0.00021859494,0.0089204805],"genre_scores_gemma":[0.99377716,0.0000018828865,0.004989571,0.00058952684,0.00010893078,0.00001506087,0.000013528121,0.0000035071969,0.0005008407],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902225,0.000043614065,0.00031896442,0.00012769367,0.0002934928,0.00019396446],"domain_scores_gemma":[0.9993157,0.000024225139,0.00017509056,0.00019965305,0.0002290969,0.00005627123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019751354,0.00010585162,0.00012926936,0.00009210322,0.00014852968,0.0007049789,0.00033438724,0.000049526923,0.000020458916],"category_scores_gemma":[0.000022109547,0.00008868806,0.00003632634,0.00029503903,0.000018060611,0.006166317,0.000070052,0.00008438638,0.00055773713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018692226,0.00003220738,0.002161738,0.00045221738,0.000027025531,0.0000014570443,0.0023004897,0.7748884,0.0016323758,0.018279785,0.0185592,0.18164644],"study_design_scores_gemma":[0.00019113805,0.00002443369,0.0003398653,0.000036515037,0.0000015221659,0.000014444735,0.00006355543,0.9762402,0.00028804727,0.000053431813,0.02263147,0.000115372655],"about_ca_topic_score_codex":0.000022610502,"about_ca_topic_score_gemma":4.394528e-7,"teacher_disagreement_score":0.9884941,"about_ca_system_score_codex":0.000040926177,"about_ca_system_score_gemma":0.00008202049,"threshold_uncertainty_score":0.71687686},"labels":[],"label_agreement":null},{"id":"W2981988113","doi":"10.1109/iccv.2019.00028","title":"Learning Fixed Points in Generative Adversarial Networks: From Image-to-Image Translation to Disease Detection and Localization","year":2019,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":99,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"National Heart, Lung, and Blood Institute","keywords":"Image translation; Adversarial system; Computer science; Translation (biology); Artificial intelligence; Generative grammar; Image (mathematics); Computer vision; Pattern recognition (psychology)","score_opus":0.007350359797905711,"score_gpt":0.21421519402289585,"score_spread":0.20686483422499014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981988113","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055154268,0.000033276385,0.9428036,0.0006984022,0.0004270741,0.000555622,0.0000026984144,0.000086998676,0.00023806022],"genre_scores_gemma":[0.8955897,0.000011706868,0.10342185,0.00060141046,0.00021364316,0.000022275999,0.00001528992,0.000014090749,0.000110019115],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838793,0.00028645308,0.0002534515,0.00061324256,0.0001953888,0.00026353096],"domain_scores_gemma":[0.9992665,0.00013309027,0.000057723588,0.0002362442,0.00009318091,0.00021328536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025796608,0.00018445963,0.0001968899,0.0001621787,0.00012909884,0.00028258355,0.00018579977,0.000062430256,0.00008044894],"category_scores_gemma":[0.00010137287,0.00017956499,0.0000436154,0.0005590017,0.000018319774,0.0010315799,0.000112956885,0.00012891878,0.00008724007],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002377356,0.00004442037,0.0035601037,0.000006027443,0.00002109138,0.0000073505885,0.0022844214,0.8589756,0.0376339,0.00013868524,0.00017701063,0.096913666],"study_design_scores_gemma":[0.0006464628,0.00011714705,0.01585978,0.000026591824,0.00000893959,2.4642407e-7,0.00008239998,0.978101,0.004178044,0.00026396356,0.0004811934,0.00023421913],"about_ca_topic_score_codex":0.00025981732,"about_ca_topic_score_gemma":0.00034142478,"teacher_disagreement_score":0.84043545,"about_ca_system_score_codex":0.000061437626,"about_ca_system_score_gemma":0.000028625074,"threshold_uncertainty_score":0.7322448},"labels":[],"label_agreement":null},{"id":"W2984827724","doi":"10.48550/arxiv.1911.02121","title":"GAN-enhanced Conditional Echocardiogram Generation","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Discriminator; Segmentation; Computer science; Artificial intelligence; Generative adversarial network; Generative grammar; Echo (communications protocol); Ventricle; Adversarial system; Pattern recognition (psychology); Machine learning; Deep learning; Cardiology; Medicine; Telecommunications; Computer security","score_opus":0.06772094733988028,"score_gpt":0.18373232756252225,"score_spread":0.11601138022264197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2984827724","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006568664,0.000062610154,0.98616093,0.00010452618,0.0016029727,0.00034777558,0.000031681317,0.0001782055,0.0049426295],"genre_scores_gemma":[0.99307996,0.00015106174,0.0043072733,0.00020209905,0.00052246347,0.0000022154777,0.00014743944,0.000017409999,0.0015700974],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99793464,0.00022230181,0.00019778618,0.0011788582,0.00013281245,0.00033360985],"domain_scores_gemma":[0.99820346,0.000075770906,0.00023069371,0.0010974687,0.0002642505,0.00012837684],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021149816,0.0003274621,0.00036278265,0.00019572751,0.00018884454,0.00024797843,0.0011654478,0.00029429098,0.00007695203],"category_scores_gemma":[0.00002629327,0.00037607484,0.0003382564,0.00040659605,0.00008112033,0.0005459689,0.0007482355,0.00041979938,0.0003146169],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006357537,0.000037188634,0.000097227,0.000012794289,0.000114982315,0.000033967994,0.000045438774,0.99075735,0.00043691092,0.0053155427,0.002404348,0.00073792017],"study_design_scores_gemma":[0.0003169881,0.000037872454,0.00040430907,0.000025098867,0.000051205596,0.0000016577727,0.000013211687,0.9827868,0.004017672,0.0109814685,0.00094742916,0.00041633827],"about_ca_topic_score_codex":0.000045906632,"about_ca_topic_score_gemma":0.000015095931,"teacher_disagreement_score":0.9865113,"about_ca_system_score_codex":0.00017278927,"about_ca_system_score_gemma":0.00021912859,"threshold_uncertainty_score":0.9998691},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W2985814454","doi":"10.1109/tpami.2019.2950317","title":"Bilinear Image Translation for Temporal Analysis of Photo Collections","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"European Regional Development Fund; Agence Nationale de la Recherche; European Research Council; Canadian Institute for Advanced Research","keywords":"Computer science; Concatenation (mathematics); Artificial intelligence; Convolutional neural network; Bilinear interpolation; Pipeline (software); Translation (biology); Encoder; Computer vision; Pattern recognition (psychology)","score_opus":0.02109817907112518,"score_gpt":0.2687036689783784,"score_spread":0.2476054899072532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2985814454","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036192904,0.000051543255,0.995384,0.000171346,0.00015224384,0.0003031735,0.00016796101,0.000034150955,0.000116330324],"genre_scores_gemma":[0.97932017,0.00009909527,0.019959686,0.000102548285,0.00001221682,0.000032393073,0.00001943964,0.000008277679,0.00044615843],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857676,0.00008219596,0.00045243817,0.0005023269,0.00020128221,0.00018501138],"domain_scores_gemma":[0.9988601,0.00028865068,0.00015290576,0.00045319702,0.00016824678,0.00007685341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028302686,0.00018669495,0.0005089298,0.0012149934,0.00018924937,0.00011161782,0.00027070253,0.000060948154,0.00037361323],"category_scores_gemma":[0.000004324734,0.0001637713,0.000667614,0.0042705582,0.000051846822,0.0002703191,0.0000028407783,0.00010976959,0.000005186645],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057988065,0.00033203454,0.0014847595,0.000027806502,0.0064711855,9.552457e-7,0.0005612955,0.62011534,0.007955174,0.00004044507,0.00002532936,0.36292768],"study_design_scores_gemma":[0.00011229498,0.00014235925,0.00033976362,0.0000056956233,0.0022604277,4.7222414e-7,0.000038186008,0.85022104,0.14656477,0.000053390122,0.00010749331,0.00015413701],"about_ca_topic_score_codex":0.0013515303,"about_ca_topic_score_gemma":0.0025553233,"teacher_disagreement_score":0.9757009,"about_ca_system_score_codex":0.000021240723,"about_ca_system_score_gemma":0.000024155626,"threshold_uncertainty_score":0.66783994},"labels":[],"label_agreement":null},{"id":"W2986635976","doi":"10.48550/arxiv.1811.10352","title":"EFANet: Exchangeable Feature Alignment Network for Arbitrary Style Transfer","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Statistic; Artificial intelligence; Swap (finance); Matching (statistics); Pattern recognition (psychology); Feature vector; Graphics; Feature (linguistics); Feature extraction; Style (visual arts); Image (mathematics); Extractor; Computer vision; Mathematics; Computer graphics (images)","score_opus":0.05363785522822508,"score_gpt":0.18312689257114964,"score_spread":0.12948903734292455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2986635976","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050339685,0.00037459083,0.98872966,0.0004082322,0.0017723158,0.0008725221,0.000074435564,0.0001910426,0.0025432622],"genre_scores_gemma":[0.9496332,0.00034927932,0.040726162,0.00069024775,0.0018833621,0.00001307283,0.00008687812,0.000051053084,0.0065667587],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972999,0.00018795214,0.00020135744,0.0014653751,0.00012243567,0.00072298077],"domain_scores_gemma":[0.9980499,0.0001484009,0.00012610125,0.0012502837,0.00019770354,0.00022758465],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00038430974,0.00048804068,0.0005059715,0.00011969454,0.00036782853,0.00021484545,0.0017373798,0.0004545849,0.0000868871],"category_scores_gemma":[0.0000126614195,0.0005202088,0.00041541975,0.000431825,0.00012602437,0.00039124803,0.00085821014,0.00041555724,0.00004793363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022840349,0.000246113,0.00040777738,0.000238076,0.0007447003,0.00019529795,0.0006931889,0.791406,0.00014007452,0.06665827,0.13666587,0.0023762772],"study_design_scores_gemma":[0.00091625756,0.00025326168,0.00025602864,0.00018313441,0.00020695565,0.0000036536903,0.000044187636,0.8962093,0.0011047921,0.044481046,0.055355206,0.0009861672],"about_ca_topic_score_codex":0.000067896835,"about_ca_topic_score_gemma":0.000072089264,"teacher_disagreement_score":0.9480035,"about_ca_system_score_codex":0.00015371575,"about_ca_system_score_gemma":0.0001666571,"threshold_uncertainty_score":0.9997249},"labels":[],"label_agreement":null},{"id":"W2987290548","doi":"10.1109/mmsp.2019.8901744","title":"Virtual Fakes: DeepFakes for Virtual Reality","year":2019,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; McGill University","funders":"","keywords":"Virtual reality; Computer science; Face (sociological concept); Human–computer interaction; Artificial intelligence; Computer graphics (images); Computer vision; Multimedia","score_opus":0.01909796822468483,"score_gpt":0.24697058893313115,"score_spread":0.22787262070844633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2987290548","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048687276,0.000016544269,0.98529744,0.00091311376,0.0008569346,0.00030357428,0.000005162757,0.0001248741,0.0076136184],"genre_scores_gemma":[0.9403411,0.0000051759193,0.052677125,0.00076065713,0.00021837169,0.00002090706,0.000005257559,0.0000095769865,0.0059618047],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988642,0.00006428311,0.00019094355,0.00042247318,0.0001709457,0.00028715818],"domain_scores_gemma":[0.9990094,0.00025145352,0.000056878132,0.00050203374,0.000100704565,0.00007953341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033029533,0.00013634961,0.0001841564,0.00004115096,0.00009985044,0.00015466708,0.000561334,0.000060704228,0.0001091433],"category_scores_gemma":[0.000060939277,0.000109033106,0.00011268854,0.00015251723,0.000029239092,0.00056833326,0.00013176324,0.000057642043,0.00020162095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056294142,0.00014156783,0.00041393036,0.000012179904,0.00008470988,0.0000021778258,0.0007934289,0.024592848,0.011374522,0.67283225,0.039628536,0.25006756],"study_design_scores_gemma":[0.0008086103,0.0006898528,0.00079279375,0.000012314773,0.000009721979,0.0000028990669,0.00027105008,0.9142279,0.018175544,0.003563409,0.06103522,0.00041070773],"about_ca_topic_score_codex":0.000035178135,"about_ca_topic_score_gemma":0.000027627511,"teacher_disagreement_score":0.93547237,"about_ca_system_score_codex":0.000023190052,"about_ca_system_score_gemma":0.00004672216,"threshold_uncertainty_score":0.44462413},"labels":[],"label_agreement":null},{"id":"W2989788785","doi":"10.1109/cvpr42600.2020.00832","title":"Image2StyleGAN++: How to Edit the Embedded Images?","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Embedding; Inpainting; Computer science; Image editing; Artificial intelligence; Image (mathematics); Computer vision; Noise (video)","score_opus":0.024643933125425326,"score_gpt":0.2455355028625573,"score_spread":0.22089156973713198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2989788785","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000036331192,0.00010002095,0.8260825,0.15883143,0.0026847518,0.0006330081,0.000016124963,0.00028773482,0.0113281],"genre_scores_gemma":[0.48687315,0.0000489745,0.4869532,0.01416461,0.0051019336,0.00019475682,0.00001623923,0.00005732201,0.0065898052],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971592,0.00028355958,0.00028659697,0.0012287201,0.0005347133,0.00050721085],"domain_scores_gemma":[0.9971122,0.00021140734,0.0001741861,0.0019424199,0.00025483448,0.0003049573],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00044038586,0.00047235316,0.00046610105,0.00008329965,0.00024625534,0.0022229822,0.0039407336,0.00017026087,0.00013285603],"category_scores_gemma":[0.00034331146,0.0003066181,0.00031241882,0.0004508132,0.000079800426,0.0003917363,0.006271093,0.00076490187,0.00043205],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000083921705,0.00003499376,0.000005328178,0.000030071002,0.0001295958,0.000050698276,0.0010869785,0.0064704665,0.004304529,0.0071398276,0.94993407,0.030805029],"study_design_scores_gemma":[0.00064964785,0.00029327816,0.0009305283,0.00016489618,0.00016695539,0.000024136252,0.0006588482,0.4806629,0.09458814,0.040076423,0.37884593,0.002938303],"about_ca_topic_score_codex":0.00010266432,"about_ca_topic_score_gemma":0.000022318227,"teacher_disagreement_score":0.57108814,"about_ca_system_score_codex":0.000053100743,"about_ca_system_score_gemma":0.00019810206,"threshold_uncertainty_score":0.9999386},"labels":[],"label_agreement":null},{"id":"W2990269423","doi":"10.1109/cvpr42600.2020.00515","title":"SEAN: Image Synthesis With Semantic Region-Adaptive Normalization","year":2020,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":341,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Normalization (sociology); Segmentation; Generative grammar; Image (mathematics); Pattern recognition (psychology); Semantics (computer science); Image segmentation; Adversarial system; Block (permutation group theory)","score_opus":0.019409946077840416,"score_gpt":0.19474822429808097,"score_spread":0.17533827822024056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990269423","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025282658,0.000022348106,0.9807214,0.0076372176,0.000049813738,0.00014264903,6.3970515e-7,0.00018517472,0.0109879095],"genre_scores_gemma":[0.8611133,0.000013333088,0.13709839,0.0014635299,0.00013102117,0.00001217293,8.359839e-7,0.000011485417,0.00015591558],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892515,0.00009856558,0.00014451625,0.00039761615,0.00021154572,0.00022260335],"domain_scores_gemma":[0.9992652,0.00010577332,0.00007237941,0.00028211396,0.00013611495,0.00013841396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007505514,0.00015367287,0.0001729911,0.00003636607,0.00013697238,0.00018196875,0.00042879218,0.000033297365,0.000058558468],"category_scores_gemma":[0.00006777195,0.00011213732,0.000049319497,0.0004986995,0.000053309148,0.00091011554,0.0001312491,0.00006691763,0.000105499115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007151504,0.00064652273,0.0063283984,0.0002609709,0.001117223,0.0015832279,0.014699251,0.0960102,0.022721183,0.43040404,0.17140934,0.2541045],"study_design_scores_gemma":[0.00020580627,0.00018447779,0.0005124522,0.00002103345,0.000026381022,0.000016949214,0.00015000957,0.96572626,0.030931635,0.00025907214,0.0016594722,0.0003064724],"about_ca_topic_score_codex":0.000038925176,"about_ca_topic_score_gemma":0.000012954002,"teacher_disagreement_score":0.86971605,"about_ca_system_score_codex":0.000016080654,"about_ca_system_score_gemma":0.000051485433,"threshold_uncertainty_score":0.45728272},"labels":[],"label_agreement":null},{"id":"W2990427715","doi":"10.48550/arxiv.1905.12304","title":"Revision in Continuous Space: Unsupervised Text Style Transfer without Adversarial Learning","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Sentence; Adversarial system; Representation (politics); Artificial intelligence; Space (punctuation); Inference; Key (lock); Style (visual arts); Encoder; Natural language processing; Transfer of learning; Transfer (computing); Machine learning","score_opus":0.033897731054814535,"score_gpt":0.1832204233669718,"score_spread":0.14932269231215728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990427715","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17990454,0.0001358404,0.8153001,0.00013824808,0.0009504632,0.0006294869,0.000006704069,0.00015771753,0.0027769133],"genre_scores_gemma":[0.9943165,0.00035053465,0.0021771716,0.00007643702,0.00019785276,0.0000010514648,0.000019043624,0.000036143698,0.0028252376],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99662733,0.0006635742,0.0003457375,0.001609427,0.00017683582,0.00057711825],"domain_scores_gemma":[0.99817365,0.00018857242,0.00015990395,0.0011240796,0.00018225076,0.00017153689],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005798801,0.00050562597,0.0007776646,0.00036659406,0.00016729673,0.00023315044,0.0015751419,0.00046138238,0.00012801695],"category_scores_gemma":[0.00008342582,0.00055442663,0.0003377449,0.00069910736,0.00009948525,0.0006481176,0.0011562937,0.0011982663,0.00017867555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013703197,0.0000990297,0.008473172,0.00007083797,0.000082317776,0.00018291839,0.00081873435,0.98005027,0.0002449929,0.006059732,0.0002471259,0.003533822],"study_design_scores_gemma":[0.0020100288,0.00013482095,0.0012188847,0.00034071348,0.00007417589,0.0000023691532,0.00025115456,0.98934364,0.00029558022,0.00073662977,0.0048285387,0.0007634488],"about_ca_topic_score_codex":0.0004086299,"about_ca_topic_score_gemma":0.00010024922,"teacher_disagreement_score":0.814412,"about_ca_system_score_codex":0.00023320632,"about_ca_system_score_gemma":0.00025208286,"threshold_uncertainty_score":0.9996907},"labels":[],"label_agreement":null},{"id":"W2990823792","doi":"10.48550/arxiv.1911.11791","title":"A Preliminary Study of Disentanglement With Insights on the Inadequacy of Metrics","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Data science; Computer science","score_opus":0.07074209356704961,"score_gpt":0.18631412519241614,"score_spread":0.11557203162536653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990823792","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66182005,0.000043146847,0.33611253,0.00005433493,0.0001908308,0.00076973747,0.0000054681855,0.000017641763,0.0009862876],"genre_scores_gemma":[0.99923086,0.000036505568,0.00045580883,0.000029246674,0.000024078001,0.0000017821029,0.000002135483,0.0000104084365,0.0002091792],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998431,0.00032131834,0.0002248997,0.0006485098,0.00020262982,0.00017163667],"domain_scores_gemma":[0.9974656,0.00036495333,0.00048036932,0.0014206071,0.00021468122,0.000053791857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019730302,0.00024335177,0.00038197677,0.0002764146,0.00008285819,0.000032565244,0.0015459693,0.00007962239,0.000010684914],"category_scores_gemma":[0.00003056598,0.00016660478,0.000117740645,0.00093461,0.00008848694,0.00015809278,0.0014849958,0.00027773555,0.000005499304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002226142,0.0013033362,0.0065826755,0.00006375246,0.0004032887,0.00007810614,0.002569002,0.95838505,0.000021065267,0.029646385,0.0001918322,0.0005328938],"study_design_scores_gemma":[0.0017950181,0.0053542634,0.015306247,0.00033896,0.0004173077,0.0000010558343,0.003837872,0.9651303,0.0026421146,0.004382645,0.00017029463,0.0006239072],"about_ca_topic_score_codex":0.00019754638,"about_ca_topic_score_gemma":0.00004321482,"teacher_disagreement_score":0.3374108,"about_ca_system_score_codex":0.00008058281,"about_ca_system_score_gemma":0.00012189219,"threshold_uncertainty_score":0.67939454},"labels":[],"label_agreement":null},{"id":"W2991377405","doi":"10.1109/iccvw.2019.00408","title":"EdgeConnect: Structure Guided Image Inpainting using Edge Prediction","year":2019,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":557,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Inpainting; Artificial intelligence; Image (mathematics); Sketch; Enhanced Data Rates for GSM Evolution; Computer science; Computer vision; Pattern recognition (psychology); Process (computing); Image restoration; Filling-in; Task (project management); Deep learning; Image processing; Algorithm","score_opus":0.014298412679622171,"score_gpt":0.2316586604951138,"score_spread":0.21736024781549163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991377405","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13730839,0.000024810624,0.8528788,0.0001789715,0.0011723984,0.0001731203,0.0000031582615,0.00014081976,0.008119541],"genre_scores_gemma":[0.79766846,0.0000014847396,0.20133436,0.00027168906,0.00030322414,9.718386e-7,0.0000023972775,0.00000913107,0.00040827956],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988856,0.000078334364,0.00021924898,0.00039110653,0.00015663891,0.00026908345],"domain_scores_gemma":[0.9992299,0.0000560186,0.00008533968,0.00044406933,0.00012349557,0.00006116894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022368663,0.00013960214,0.00015701936,0.00007515683,0.00013162753,0.00024300412,0.000403248,0.00006497024,0.0004459294],"category_scores_gemma":[0.000057386093,0.00011795965,0.000065051194,0.000275749,0.000021301144,0.0010128196,0.0002217711,0.00010616251,0.000070812624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000073018264,0.0000484166,0.008512134,0.00004279293,0.000093372095,0.000009848876,0.00087594,0.04282158,0.87648684,0.014806374,0.013225816,0.043069612],"study_design_scores_gemma":[0.00022937002,0.00002693241,0.0016267603,0.000015895659,0.0000062734384,0.000014155724,0.00003841391,0.943472,0.05201574,0.0011600839,0.0012274573,0.00016691058],"about_ca_topic_score_codex":0.000049715378,"about_ca_topic_score_gemma":0.0000073093565,"teacher_disagreement_score":0.90065044,"about_ca_system_score_codex":0.000044766726,"about_ca_system_score_gemma":0.000039267816,"threshold_uncertainty_score":0.48826143},"labels":[],"label_agreement":null},{"id":"W2992005611","doi":"10.1109/tpami.2020.2992934","title":"Normalizing Flows: An Introduction and Review of Current Methods","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1209,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Collège Boréal","funders":"","keywords":"Current (fluid); Computer science; Context (archaeology); Generative grammar; Sampling (signal processing); Artificial intelligence; Machine learning; Data science; Geography; Engineering","score_opus":0.044495169245816826,"score_gpt":0.3316204651828682,"score_spread":0.2871252959370514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2992005611","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015605622,0.0058827735,0.9913683,0.0022880093,0.00016387754,0.0000969653,0.000010064356,0.000027011956,0.000006959345],"genre_scores_gemma":[0.9341722,0.022611229,0.04226527,0.0008382693,0.00008885038,0.000009209375,0.000003847021,0.0000066333655,0.0000044838057],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986303,0.0002825353,0.00036115848,0.00045509625,0.00014834348,0.00012258555],"domain_scores_gemma":[0.99929297,0.00007110955,0.00011818045,0.00028967584,0.00009178111,0.00013628883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000420618,0.00015297825,0.0003588951,0.00014694143,0.00010388911,0.000055922592,0.00022244606,0.000024849762,0.000088955014],"category_scores_gemma":[0.000014855564,0.00012777554,0.00014178449,0.0008284766,0.000042720963,0.00034700814,0.0000075547387,0.00016308718,0.0000019495],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040162568,0.000045922694,0.000034085315,0.00020289855,0.00014901673,5.3204764e-7,0.00025531868,0.0111946175,0.0011214041,0.000045439258,0.000013847589,0.9869329],"study_design_scores_gemma":[0.000043797132,0.00017160497,0.00009473818,0.0001330346,0.00053867843,0.0000037088996,0.000027479697,0.8620876,0.13557884,0.00004869547,0.0010819078,0.00018993259],"about_ca_topic_score_codex":0.00013320667,"about_ca_topic_score_gemma":0.00007124227,"teacher_disagreement_score":0.986743,"about_ca_system_score_codex":0.000008654119,"about_ca_system_score_gemma":0.000011390086,"threshold_uncertainty_score":0.5210535},"labels":[],"label_agreement":null},{"id":"W2993921587","doi":"10.1109/cvpr42600.2020.00586","title":"Exploring Unlabeled Faces for Novel Attribute Discovery","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Artificial intelligence; Normalization (sociology); Translation (biology); Bottleneck; Labeled data; Image (mathematics); Pattern recognition (psychology); Image translation; Limiting; Machine learning","score_opus":0.3021136911512163,"score_gpt":0.288838380592467,"score_spread":0.013275310558749254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2993921587","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011760951,0.00013118947,0.9888109,0.0062561724,0.0023012427,0.00062492373,0.00009283648,0.00024147551,0.00036516198],"genre_scores_gemma":[0.51897866,0.00016562159,0.47771907,0.0006534913,0.0010250311,0.0004635505,0.00005742409,0.000033474444,0.00090370845],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99795943,0.000041096235,0.00034563665,0.0010134666,0.00024684326,0.00039350797],"domain_scores_gemma":[0.99861425,0.00023383464,0.00017565463,0.00071051496,0.00014028183,0.00012545887],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021697846,0.00035757964,0.00049243576,0.00006852382,0.00015628841,0.00094869157,0.0014448185,0.00011219505,0.00000730137],"category_scores_gemma":[0.00014224775,0.00030617497,0.00029249222,0.000191763,0.000030922434,0.0013132809,0.0024594562,0.0002856766,0.000018200606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016948597,0.00076502765,0.0003679297,0.0013373194,0.0024329787,0.000044221084,0.0048291706,0.44558007,0.08750424,0.27009153,0.060793225,0.12608482],"study_design_scores_gemma":[0.0008945879,0.00014828416,0.000522928,0.00017268983,0.00008155831,0.0000018396195,0.00012309026,0.8914495,0.07378371,0.006722993,0.024825206,0.0012735795],"about_ca_topic_score_codex":0.00006877789,"about_ca_topic_score_gemma":0.000014587354,"teacher_disagreement_score":0.51780254,"about_ca_system_score_codex":0.000055268996,"about_ca_system_score_gemma":0.00015417214,"threshold_uncertainty_score":0.999939},"labels":[],"label_agreement":null},{"id":"W2994023877","doi":"10.1007/s11063-019-10158-x","title":"Attention-Based Generative Adversarial Network for Semi-supervised Image Classification","year":2019,"lang":"en","type":"article","venue":"Neural Processing Letters","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Fundamental Research Funds for the Central Universities; Natural Science Foundation of Heilongjiang Province; National Natural Science Foundation of China","keywords":"Normalization (sociology); Artificial intelligence; Computer science; Regularization (linguistics); Pattern recognition (psychology); Generative adversarial network; Contextual image classification; Generative grammar; Image (mathematics); Semi-supervised learning; Machine learning; Adversarial system; Computational intelligence","score_opus":0.019481359299773016,"score_gpt":0.2427566084200956,"score_spread":0.2232752491203226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994023877","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04589011,0.000055980272,0.9389652,0.012845929,0.0012834239,0.00061409204,0.000005759002,0.00017080505,0.0001687177],"genre_scores_gemma":[0.81259125,0.0000010642428,0.17907599,0.0070942515,0.0009793265,0.00007458845,0.000043849635,0.000026841306,0.00011285725],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980425,0.0001405828,0.0003188169,0.0006986322,0.00028710577,0.0005123328],"domain_scores_gemma":[0.998929,0.0001635965,0.00021564499,0.00040560614,0.00019481419,0.00009128578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027945646,0.0002603462,0.00026819797,0.00007371922,0.0003974367,0.0005190093,0.0005896987,0.000080726626,0.000020960662],"category_scores_gemma":[0.00004460389,0.00023830733,0.00017259018,0.00038767382,0.00007307485,0.0011233696,0.00006293721,0.00016115548,0.000039356866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011777172,0.00006394093,0.0012797909,0.00010660881,0.00004244823,0.000005057422,0.0003770243,0.1692948,0.7516278,0.0004816514,0.02060244,0.05600063],"study_design_scores_gemma":[0.0009912128,0.00006741744,0.0014660236,0.000041657244,0.000020375783,0.0000015151097,0.000026715707,0.99162674,0.0037938298,0.00015411747,0.001503459,0.00030694573],"about_ca_topic_score_codex":0.000008273234,"about_ca_topic_score_gemma":0.0000029239968,"teacher_disagreement_score":0.8223319,"about_ca_system_score_codex":0.00007075674,"about_ca_system_score_gemma":0.00011126427,"threshold_uncertainty_score":0.9717891},"labels":[],"label_agreement":null},{"id":"W2994275717","doi":"10.18280/ria.330406","title":"Improved Artistic Images Generation Using Transfer Learning","year":2019,"lang":"fr","type":"article","venue":"Revue d intelligence artificielle","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Transfer of learning; Computer science; Artificial intelligence; Computer vision","score_opus":0.056247319653535056,"score_gpt":0.2678487512669264,"score_spread":0.21160143161339137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994275717","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028756715,0.0046215304,0.95759493,0.0013980268,0.0049087587,0.00053781265,0.000009409447,0.00008022716,0.0020926138],"genre_scores_gemma":[0.93428046,0.00045100987,0.02314363,0.00018222685,0.0011698322,0.000011896412,0.000011469657,0.0000485398,0.040700924],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99670804,0.0004482573,0.00075391796,0.0010094565,0.00025173958,0.0008286224],"domain_scores_gemma":[0.99835336,0.00023744338,0.00014363561,0.0007232952,0.00034511858,0.00019716706],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00077469274,0.00040849397,0.0004558133,0.00013520995,0.00043791597,0.0006713226,0.00058078475,0.0002200606,0.0019320163],"category_scores_gemma":[0.00016484172,0.0004524778,0.00026136954,0.0007349913,0.00018705254,0.001169663,0.00016443506,0.00052598765,0.001595102],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008113961,0.00009050793,0.00008438556,0.0000697525,0.000032602245,0.000015082492,0.0012171182,0.650441,0.26269493,0.0040843124,0.00018301854,0.08107918],"study_design_scores_gemma":[0.00005536772,0.00019977319,0.000011457275,0.00015550866,0.0000452413,0.000038984446,0.00029737764,0.7534835,0.23563208,0.00020061003,0.00947709,0.00040304917],"about_ca_topic_score_codex":0.00035784818,"about_ca_topic_score_gemma":0.000031984204,"teacher_disagreement_score":0.9344513,"about_ca_system_score_codex":0.00014315541,"about_ca_system_score_gemma":0.00015928679,"threshold_uncertainty_score":0.9997927},"labels":[],"label_agreement":null},{"id":"W2994626047","doi":"10.1109/tip.2019.2903300","title":"Texture Classification in Extreme Scale Variations Using GANet","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Tekes; Academy of Finland; Infotech Oulu; National Natural Science Foundation of China","keywords":"Pattern recognition (psychology); Texture (cosmology); Texture filtering; Image texture; Convolutional neural network; Scale (ratio); Pooling; Texture compression","score_opus":0.044390035073480806,"score_gpt":0.25560173076620285,"score_spread":0.21121169569272205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994626047","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004697998,0.000049512,0.9930904,0.0004259655,0.00038744826,0.00022800548,0.0000040882683,0.00009925481,0.0010173571],"genre_scores_gemma":[0.85197604,0.000007898523,0.14751913,0.00014458377,0.00004557268,0.000015173996,8.646182e-7,0.000015066361,0.00027568795],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865717,0.000095453164,0.00027454898,0.00047100638,0.00022376417,0.00027808754],"domain_scores_gemma":[0.99925953,0.000088656154,0.00010903487,0.00036220183,0.00011987519,0.000060720875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000215198,0.00017028094,0.00017259405,0.00019198035,0.00024998016,0.0003333507,0.00032971255,0.0000885954,0.000092902505],"category_scores_gemma":[0.000007646449,0.0001691959,0.000063247375,0.0008152655,0.00003832887,0.00155589,0.0000030212273,0.00025629235,0.00007353448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028989465,0.0004443313,0.00021636992,0.000073322575,0.000020857013,0.0000069697962,0.001839853,0.1500621,0.45992061,0.00012838763,0.000063267646,0.38719493],"study_design_scores_gemma":[0.0003117638,0.000023658238,0.0010902159,0.000084100226,0.000012021616,0.00000856065,0.000092906455,0.98095,0.016873812,0.00025600454,0.00009255165,0.00020439207],"about_ca_topic_score_codex":0.000040718725,"about_ca_topic_score_gemma":0.000035517944,"teacher_disagreement_score":0.84727806,"about_ca_system_score_codex":0.000113692375,"about_ca_system_score_gemma":0.00013214408,"threshold_uncertainty_score":0.68996084},"labels":[],"label_agreement":null},{"id":"W2995128076","doi":"","title":"A Closer Look at the Optimization Landscapes of Generative Adversarial Networks","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Concatenation (mathematics); Computer science; Adversarial system; Generative grammar; Generator (circuit theory); Saddle point; Point (geometry); Visualization; Artificial intelligence; Field (mathematics); Deep learning; Bridge (graph theory); Machine learning; Theoretical computer science; Mathematical optimization; Mathematics","score_opus":0.0342901584745485,"score_gpt":0.28078537204376,"score_spread":0.24649521356921147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995128076","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002092613,0.000025715599,0.96533453,0.018329158,0.00040339064,0.00015785746,0.000006985263,0.000053067655,0.013596652],"genre_scores_gemma":[0.98882,0.00007021487,0.009157435,0.00056750426,0.0003750098,0.000035320343,0.000053494747,0.000008395968,0.0009125831],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868596,0.00024054766,0.00025581298,0.00034185205,0.00034348524,0.00013236611],"domain_scores_gemma":[0.9988963,0.00026643652,0.00022404615,0.00020095812,0.00034899334,0.000063263775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001370555,0.00012128705,0.00013189155,0.00005041752,0.00024544916,0.00016008655,0.00059942564,0.000045524754,0.0008141882],"category_scores_gemma":[0.00033078427,0.00009321832,0.00008820007,0.0002349506,0.0000715011,0.00032085326,0.0002485867,0.0002054201,0.000035240595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041061972,0.000020485464,0.0007638909,9.564237e-7,0.000066137036,0.0000023204755,0.0014418932,0.9757748,0.00067234505,0.017553369,0.0018032957,0.0018593994],"study_design_scores_gemma":[0.00031604312,0.00008367646,0.00046820316,0.00001118356,0.000010661327,0.0000016474149,0.00023605862,0.99576324,0.0013994029,0.00018853186,0.0014254262,0.00009594798],"about_ca_topic_score_codex":0.000035970774,"about_ca_topic_score_gemma":0.000017695698,"teacher_disagreement_score":0.9867274,"about_ca_system_score_codex":0.000031000025,"about_ca_system_score_gemma":0.000060819708,"threshold_uncertainty_score":0.89147896},"labels":[],"label_agreement":null},{"id":"W2995665739","doi":"10.1109/iccv.2019.00766","title":"Dual Adversarial Inference for Text-to-Image Synthesis","year":2019,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; Concordia University","funders":"","keywords":"Inference; Computer science; Image (mathematics); Adversarial system; Artificial intelligence; Dual (grammatical number); Style (visual arts); Composition (language); Process (computing); Space (punctuation); Quality (philosophy); Image synthesis; Natural language processing; Information retrieval; Pattern recognition (psychology); Linguistics","score_opus":0.013085478889367598,"score_gpt":0.24959692541486342,"score_spread":0.23651144652549583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995665739","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002896148,0.000008015171,0.9772538,0.001557333,0.0010011937,0.0006039811,0.000010031636,0.00014177636,0.01652775],"genre_scores_gemma":[0.6818655,0.0000023963366,0.31497684,0.00069296686,0.00027486487,0.00007333352,0.0000013636901,0.0000124015705,0.0021003238],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984738,0.00006127691,0.00023171656,0.00057614053,0.00022951582,0.00042755067],"domain_scores_gemma":[0.9981725,0.00081526325,0.00006155643,0.00062425365,0.00016774192,0.00015867103],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00033069545,0.00019653543,0.00026421656,0.000106234475,0.00011900561,0.00027308628,0.0007174178,0.000071123846,0.00040783707],"category_scores_gemma":[0.0004437392,0.00016535626,0.00013357047,0.00030733718,0.000026604974,0.00073995936,0.00031739823,0.000070842936,0.0011283669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030046038,0.00043435924,0.0012546389,0.00009923825,0.00031281062,0.000019280047,0.0018173747,0.016454952,0.15850385,0.26510778,0.09600373,0.45969152],"study_design_scores_gemma":[0.0016649779,0.00072022784,0.0034130358,0.0000795056,0.00005433654,0.000008094045,0.00018882839,0.6426058,0.1823786,0.004853329,0.1625242,0.0015090868],"about_ca_topic_score_codex":0.000044952463,"about_ca_topic_score_gemma":0.000018029607,"teacher_disagreement_score":0.6789694,"about_ca_system_score_codex":0.0000344356,"about_ca_system_score_gemma":0.00008850382,"threshold_uncertainty_score":0.99964935},"labels":[],"label_agreement":null},{"id":"W2997837663","doi":"10.1609/aaai.v34i04.5852","title":"An Efficient Explorative Sampling Considering the Generative Boundaries of Deep Generative Neural Networks","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Generative grammar; Computer science; Artificial neural network; Artificial intelligence; Generative model; Set (abstract data type); Sampling (signal processing); Generative adversarial network; Image (mathematics); Mechanism (biology); Perspective (graphical); Adversarial system; Homogeneous; Pattern recognition (psychology); Scheme (mathematics); Machine learning; Computer vision; Mathematics","score_opus":0.10792846815467992,"score_gpt":0.292621238046231,"score_spread":0.1846927698915511,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997837663","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054830927,0.00010766185,0.936061,0.0074568717,0.0004771652,0.00054060307,0.0000064515584,0.000057186546,0.0004621282],"genre_scores_gemma":[0.9791396,0.00001946837,0.019614156,0.0008984662,0.0002705731,0.000035299512,8.6273303e-7,0.00001645482,0.0000050756703],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99758816,0.00012834568,0.0007163594,0.0006540252,0.0005040825,0.00040900518],"domain_scores_gemma":[0.99752575,0.00025003756,0.000646897,0.00034792637,0.0010854496,0.00014395996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049790996,0.00034416438,0.00044467114,0.000058496462,0.00080569106,0.00076150487,0.0019281792,0.00008418249,0.000034989927],"category_scores_gemma":[0.0005294094,0.00021688285,0.00016817718,0.0007991151,0.001137454,0.000576995,0.00048443652,0.00041250227,0.00000585303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010520103,0.00009684417,0.00006608712,0.000015009732,0.00005589935,6.4457515e-7,0.022316221,0.47982317,0.050572284,0.42085177,0.000046744815,0.026050135],"study_design_scores_gemma":[0.000024185716,0.00022332337,0.000028524539,0.000033377608,0.000015604888,0.0000012009334,0.0028144582,0.6799683,0.30864087,0.008066021,0.000020045294,0.00016413533],"about_ca_topic_score_codex":0.00003180871,"about_ca_topic_score_gemma":0.00002456533,"teacher_disagreement_score":0.9243087,"about_ca_system_score_codex":0.000033965738,"about_ca_system_score_gemma":0.00012712376,"threshold_uncertainty_score":0.8844226},"labels":[],"label_agreement":null},{"id":"W2998659916","doi":"10.1609/aaai.v34i05.6355","title":"Revision in Continuous Space: Unsupervised Text Style Transfer without Adversarial Learning","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"National Natural Science Foundation of China; National Science Foundation","keywords":"Computer science; Sentence; Adversarial system; Representation (politics); Artificial intelligence; Space (punctuation); Inference; Key (lock); Style (visual arts); Encoder; Transfer of learning; Natural language processing; Transfer (computing); Machine learning","score_opus":0.04887968651990926,"score_gpt":0.2600740986570526,"score_spread":0.21119441213714335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998659916","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3402278,0.00012128868,0.6147052,0.027777385,0.0008773186,0.0016878819,0.0000067911615,0.00027097168,0.014325339],"genre_scores_gemma":[0.9958395,0.00006210208,0.0034104823,0.0003979541,0.00016491042,0.000010334711,4.612966e-7,0.000016611979,0.00009769368],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997791,0.00007490234,0.0005937507,0.0006573114,0.00048644954,0.00039661254],"domain_scores_gemma":[0.99897313,0.00010551388,0.00017699946,0.00020389927,0.00040191473,0.00013856863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000524663,0.00027787947,0.00045444275,0.00009568889,0.00018119384,0.00027618656,0.001523875,0.00011212732,0.00013304774],"category_scores_gemma":[0.0007036166,0.0002135235,0.00015589836,0.00089143956,0.00018246988,0.00056939345,0.00028563017,0.00052524474,0.00007527615],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072322256,0.00030804338,0.002502823,0.00012122004,0.000050625094,0.000004944583,0.017313834,0.0070945593,0.2594021,0.40607426,0.00045028146,0.3059541],"study_design_scores_gemma":[0.00017875798,0.0005201756,0.00020011747,0.0003479485,0.000019967298,0.0000017273156,0.0016920827,0.5780625,0.41288784,0.004533151,0.0011498044,0.00040594162],"about_ca_topic_score_codex":0.000060401395,"about_ca_topic_score_gemma":0.00001252196,"teacher_disagreement_score":0.65561163,"about_ca_system_score_codex":0.000035752775,"about_ca_system_score_gemma":0.00008981391,"threshold_uncertainty_score":0.87072355},"labels":[],"label_agreement":null},{"id":"W2998926059","doi":"10.1109/ism46123.2019.00050","title":"Hybrid Generative-Discriminative Generalized Dirichlet-Based Hidden Markov Models with Support Vector Machines","year":2019,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Discriminative model; Hidden Markov model; Dirichlet distribution; Pattern recognition (psychology); Generative grammar; Hierarchical Dirichlet process; Artificial intelligence; Fisher kernel; Latent Dirichlet allocation; Computer science; Generative model; Support vector machine; Focus (optics); Machine learning; Mathematics; Speech recognition; Topic model","score_opus":0.013637245653145955,"score_gpt":0.22166347184802193,"score_spread":0.20802622619487598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998926059","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023103943,0.00007004895,0.9552345,0.0016558476,0.00039932525,0.0005592883,0.000020047062,0.00021570834,0.018741274],"genre_scores_gemma":[0.58941483,0.000006534346,0.4039504,0.0012058391,0.00013138505,0.000047657944,0.000028309774,0.000029038512,0.005185973],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974009,0.00028600503,0.00033105377,0.00090904656,0.00051857904,0.0005544525],"domain_scores_gemma":[0.9983801,0.00012367174,0.00016382057,0.00086203835,0.00027823652,0.00019209279],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028595282,0.00043933248,0.00048664917,0.00015257152,0.00018819982,0.00032127064,0.00090840517,0.000057269877,0.0008571382],"category_scores_gemma":[0.000016282895,0.00029993607,0.00015156897,0.00033016113,0.00008971791,0.0011726362,0.00022733846,0.0001635956,0.00016080476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009938972,0.0014589344,0.0032666873,0.00019011027,0.0012341948,0.00052258256,0.002732301,0.30860898,0.05258426,0.29625103,0.12888506,0.20327197],"study_design_scores_gemma":[0.0012840334,0.0004580818,0.00036527382,0.000016617609,0.000026895612,0.000011960974,0.000020611538,0.9574714,0.03743248,0.0011822917,0.0011785486,0.00055185246],"about_ca_topic_score_codex":0.00017526014,"about_ca_topic_score_gemma":0.00004996891,"teacher_disagreement_score":0.64886236,"about_ca_system_score_codex":0.00007272883,"about_ca_system_score_gemma":0.00021935785,"threshold_uncertainty_score":0.9999453},"labels":[],"label_agreement":null},{"id":"W3003244550","doi":"10.1109/access.2020.2970169","title":"Image Inpainting Based on Generative Adversarial Networks","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"State Key Laboratory of Ocean Engineering; Shanghai Jiao Tong University; Yangzhou University; Government of Jiangsu Province; National Natural Science Foundation of China","keywords":"Discriminator; Inpainting; Computer science; Generator (circuit theory); Artificial intelligence; Encoder; Image (mathematics); Context (archaeology); Pixel; Pattern recognition (psychology); Generative grammar; Consistency (knowledge bases); Computer vision; Power (physics)","score_opus":0.03103798703353154,"score_gpt":0.267500521162605,"score_spread":0.23646253412907342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003244550","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00091960275,0.00002100441,0.989012,0.0050140955,0.0012260808,0.00022030775,0.0000033970296,0.00018867805,0.0033948126],"genre_scores_gemma":[0.9247272,0.000005185848,0.059839834,0.013188749,0.0021761241,0.00001972846,0.000004542134,0.00002079954,0.000017836264],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998105,0.00025106798,0.00027197597,0.00065044285,0.0003123876,0.00040914197],"domain_scores_gemma":[0.99885094,0.00023393852,0.00014805469,0.00042847788,0.00012986817,0.00020874132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002567861,0.00025022202,0.0002658047,0.00006344348,0.00026534667,0.0007815372,0.0014773455,0.000085260996,0.00007413372],"category_scores_gemma":[0.00015719367,0.0002245607,0.00013041872,0.00063351117,0.000060319697,0.0012175865,0.0002448757,0.00026721144,0.000059419406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007490572,0.000070434566,0.0002923021,0.000010641403,0.000042264302,0.00007143594,0.00035738398,0.9434891,0.0036853962,0.0007089241,0.028149528,0.023047715],"study_design_scores_gemma":[0.0005234933,0.00010932063,0.00022038465,0.000015298352,0.00000939724,4.782943e-7,0.000007510055,0.9827871,0.014283086,0.00010570197,0.0016712794,0.00026699025],"about_ca_topic_score_codex":0.000034626722,"about_ca_topic_score_gemma":0.00000678228,"teacher_disagreement_score":0.9291722,"about_ca_system_score_codex":0.000036332032,"about_ca_system_score_gemma":0.00006761228,"threshold_uncertainty_score":0.91573197},"labels":[],"label_agreement":null},{"id":"W3003782762","doi":"10.1109/iscc47284.2019.8969638","title":"Data Augmentation using CA Evolved GANs","year":2019,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Face (sociological concept); Artificial neural network; Deep learning; Domain (mathematical analysis); Field (mathematics); Key (lock); Architecture; Task (project management); Data mining; Pattern recognition (psychology)","score_opus":0.06243347281961659,"score_gpt":0.2898838024539386,"score_spread":0.227450329634322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003782762","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01450458,0.000023650819,0.9797414,0.00023910555,0.00044083718,0.00010063225,0.0000051873362,0.000039829956,0.004904793],"genre_scores_gemma":[0.7352101,0.0000033416316,0.2635719,0.0002804212,0.00007562605,5.9802045e-7,0.000018004743,0.0000038834837,0.0008360932],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933064,0.00003892346,0.00009459478,0.00028700964,0.0001216226,0.00012723726],"domain_scores_gemma":[0.9991834,0.000032613356,0.00003419535,0.0006837014,0.0000337638,0.000032325635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014723859,0.00006210792,0.000071227514,0.000027222479,0.00005459521,0.00012291511,0.0006658657,0.000018923964,0.00035724504],"category_scores_gemma":[0.000010094838,0.000052004816,0.000016339558,0.00014169149,0.000008654528,0.0010536502,0.0003294535,0.000031155658,0.00024175375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024995568,0.0002204703,0.0070568905,0.00003649111,0.00019805731,0.000016457727,0.0010717731,0.16759135,0.6422048,0.018153874,0.0723134,0.09111145],"study_design_scores_gemma":[0.00013172865,0.000012340369,0.0005828617,0.000004274408,0.0000039124066,0.0000011884722,0.000031709715,0.9908128,0.0051113917,0.00011413429,0.0031140442,0.000079632024],"about_ca_topic_score_codex":0.00014595069,"about_ca_topic_score_gemma":0.00003143816,"teacher_disagreement_score":0.82322145,"about_ca_system_score_codex":0.000019238258,"about_ca_system_score_gemma":0.00003627265,"threshold_uncertainty_score":0.39115825},"labels":[],"label_agreement":null},{"id":"W3004484424","doi":"10.48550/arxiv.2002.03184","title":"Time-aware Large Kernel Convolutions","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Kernel (algebra); Computer science; Mathematics; Pure mathematics","score_opus":0.05933492449385821,"score_gpt":0.18000637294358793,"score_spread":0.12067144844972971,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004484424","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028891005,0.0000788054,0.9915736,0.0007144341,0.000640213,0.0002641557,0.00009170978,0.00036532842,0.0033826558],"genre_scores_gemma":[0.99313414,0.00009248991,0.0027064206,0.00037292423,0.00024554637,0.0000011920137,0.000045763594,0.000021519594,0.0033800066],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977576,0.0002229696,0.00019732391,0.001263291,0.00010028662,0.00045851615],"domain_scores_gemma":[0.998124,0.00009665068,0.00020574502,0.0011073059,0.00019356607,0.0002727378],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016597004,0.00035713168,0.00040462147,0.00012806783,0.00029437052,0.00016152859,0.0019025041,0.0002664553,0.00019817738],"category_scores_gemma":[0.000046491048,0.0004144558,0.0003190094,0.00057395356,0.00012031711,0.0004030706,0.0030495634,0.00057443534,0.0010318954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034686735,0.00026430178,0.0006312691,0.00008214852,0.00045145283,0.0007507651,0.00062787643,0.8097564,0.00023416153,0.15002654,0.03652948,0.0006108884],"study_design_scores_gemma":[0.00033655952,0.000031915788,0.00031655154,0.000041306303,0.00006948682,0.0000018772964,0.00004946783,0.9799037,0.00010966317,0.012747616,0.005939759,0.00045208467],"about_ca_topic_score_codex":0.000059316284,"about_ca_topic_score_gemma":0.000019499414,"teacher_disagreement_score":0.99024504,"about_ca_system_score_codex":0.0001458851,"about_ca_system_score_gemma":0.00025906146,"threshold_uncertainty_score":0.9998307},"labels":[],"label_agreement":null},{"id":"W3006210322","doi":"","title":"Cutting out the Middle-Man: Training and Evaluating Energy-Based Models without Sampling","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Artificial neural network; Function (biology); Sampling (signal processing); Training set; Goodness of fit; Energy (signal processing); Artificial intelligence; Feature (linguistics); Algorithm; Machine learning; Pattern recognition (psychology); Mathematics; Statistics","score_opus":0.3545926430824564,"score_gpt":0.22582460299831283,"score_spread":0.12876804008414358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006210322","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043061044,0.00007225429,0.9548867,0.0007886998,0.00009004944,0.00008707293,0.000001353129,0.000104886116,0.0009079747],"genre_scores_gemma":[0.9717223,0.000011832891,0.02661401,0.0014230349,0.00013025037,6.3006314e-7,0.0000011337664,0.000012243338,0.000084577485],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864584,0.0001991712,0.00014560271,0.0006013286,0.00010092423,0.00030713677],"domain_scores_gemma":[0.9990478,0.00027394,0.0001251145,0.00031335143,0.00008867978,0.00015111714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000356027,0.00017845316,0.00019358477,0.000046173023,0.0004777045,0.00016890855,0.00061024143,0.0000501023,0.000006650017],"category_scores_gemma":[0.00008469417,0.000155149,0.000083469735,0.00038291325,0.00008968493,0.00059462874,0.00026195875,0.00015113142,0.0000049112577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000131881925,0.000008317955,0.00022034536,0.00000691677,0.000028017255,0.000013435628,0.0031495553,0.96501917,0.00047127836,0.022108115,0.000019527575,0.008942145],"study_design_scores_gemma":[0.00037877244,0.000064499436,0.000026737061,0.00003154882,0.0000332959,0.0000011295475,0.00058376655,0.9940286,0.00037092026,0.0039920867,0.0002966965,0.00019191731],"about_ca_topic_score_codex":0.000034257493,"about_ca_topic_score_gemma":0.000012710508,"teacher_disagreement_score":0.9286612,"about_ca_system_score_codex":0.000028433966,"about_ca_system_score_gemma":0.00008624597,"threshold_uncertainty_score":0.6326792},"labels":[],"label_agreement":null},{"id":"W3006924020","doi":"10.48550/arxiv.2002.10631","title":"Batch norm with entropic regularization turns deterministic autoencoders into generative models","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Autoencoder; Regularization (linguistics); Generative grammar; Computer science; Generative model; Encoder; Algorithm; Matrix norm; Artificial neural network; Encoding (memory); Artificial intelligence; Normalization (sociology); Code (set theory); Source code; Eigenvalues and eigenvectors","score_opus":0.056963512846129376,"score_gpt":0.1735975240386822,"score_spread":0.11663401119255282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006924020","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00360219,0.000047594378,0.9933619,0.000652467,0.00042218942,0.00042328314,0.000011347798,0.000218528,0.0012604898],"genre_scores_gemma":[0.9341826,0.00010906826,0.06453032,0.00026422137,0.00019174263,0.0000033731017,0.000040591418,0.000029624274,0.00064850255],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973826,0.00027019245,0.000252636,0.0015270342,0.00017325637,0.00039430452],"domain_scores_gemma":[0.9980174,0.00008399544,0.0003327029,0.0010206432,0.00028318865,0.0002621034],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00010672107,0.00048620772,0.00048378413,0.00016993837,0.0002564771,0.00031408222,0.0014834204,0.0002525259,0.000019632911],"category_scores_gemma":[0.000031495176,0.0004816747,0.00017612275,0.0006499684,0.00017218606,0.0007843302,0.0013082472,0.0005012564,0.000029155839],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033963388,0.00004025168,0.0000889165,0.00004809395,0.000140381,0.0002513505,0.001354814,0.93859184,0.00012126264,0.05873659,0.00015331387,0.0004392062],"study_design_scores_gemma":[0.0003911784,0.00013029871,0.00008247517,0.0000647001,0.00011678443,0.0000032641542,0.000079791505,0.8934093,0.00035547654,0.104741566,0.00012446068,0.0005006898],"about_ca_topic_score_codex":0.00015398547,"about_ca_topic_score_gemma":0.00017131155,"teacher_disagreement_score":0.9305804,"about_ca_system_score_codex":0.00027072796,"about_ca_system_score_gemma":0.00043238906,"threshold_uncertainty_score":0.9997635},"labels":[],"label_agreement":null},{"id":"W3008728787","doi":"10.1007/s11263-020-01300-7","title":"Layout2image: Image Generation from Layout","year":2020,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bank of Canada; Vector Institute; University of British Columbia; Business Development Bank of Canada; Royal Bank of Canada","funders":"","keywords":"Computer science; Artificial intelligence; Bounding overwatch; Embedding; Set (abstract data type); Pattern recognition (psychology); Image (mathematics); Object (grammar); Generative model; Representation (politics); Boosting (machine learning); Generative grammar","score_opus":0.019765516309667455,"score_gpt":0.2679329790610798,"score_spread":0.24816746275141238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008728787","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016298687,0.00011670022,0.9645181,0.0160962,0.0027222433,0.000043267853,0.000006635318,0.000028573279,0.00016962975],"genre_scores_gemma":[0.6425797,0.000023322771,0.35031423,0.0025346067,0.0045241285,3.4580614e-7,0.000007074714,0.000007253708,0.000009350534],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984064,0.00012201684,0.00047824116,0.00023309949,0.00064006506,0.000120175864],"domain_scores_gemma":[0.99853176,0.00008202274,0.0003644188,0.00015281056,0.00072299934,0.00014601728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020070405,0.00013452815,0.00020148268,0.000087287815,0.00005020277,0.0005476937,0.001307338,0.000044287295,0.00006824346],"category_scores_gemma":[0.00004975335,0.000112212445,0.00016423695,0.00012292025,0.000026001713,0.0015635572,0.00032923202,0.00017803704,0.000067087814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021498097,0.0002936452,0.00041111014,0.0000040747295,0.00052842766,0.0009692094,0.0027782985,0.058092557,0.21385838,0.0053772847,0.18289599,0.53457606],"study_design_scores_gemma":[0.0007777229,0.00030442327,0.0016699962,0.00003189965,0.00001157631,0.00004016184,0.000007880074,0.96222866,0.012235063,0.0007280469,0.021811897,0.00015265438],"about_ca_topic_score_codex":0.000010956895,"about_ca_topic_score_gemma":9.731926e-7,"teacher_disagreement_score":0.9041361,"about_ca_system_score_codex":0.00003976634,"about_ca_system_score_gemma":0.000058505688,"threshold_uncertainty_score":0.52814233},"labels":[],"label_agreement":null},{"id":"W3011483492","doi":"10.1609/aaai.v35i3.16368","title":"Object-Centric Image Generation from Layouts","year":2021,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal","funders":"","keywords":"Computer science; Generator (circuit theory); Object (grammar); Artificial intelligence; Scene graph; Bounding overwatch; Fidelity; Minimum bounding box; Metric (unit); Computer vision; Image (mathematics); Similarity (geometry); Graph; Generative grammar; Theoretical computer science","score_opus":0.07616563558512626,"score_gpt":0.27850507399500796,"score_spread":0.2023394384098817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011483492","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16505735,0.00042033265,0.81137276,0.006668165,0.005541338,0.0011786143,0.00006625815,0.00021013174,0.009485082],"genre_scores_gemma":[0.96320444,0.00022225367,0.035362285,0.00027980015,0.0006658244,0.000047229092,0.000013583719,0.000024314071,0.00018025041],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9966683,0.00008050452,0.0008304151,0.0012259192,0.00075483375,0.00044007233],"domain_scores_gemma":[0.9966932,0.000106467785,0.00083130226,0.00076993916,0.001474719,0.00012438082],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00046239377,0.0004855549,0.0005844802,0.00014023107,0.00025741648,0.0014970733,0.003142291,0.0003016012,0.00018121178],"category_scores_gemma":[0.00053781405,0.00039019107,0.0003491772,0.00062091294,0.00022170375,0.00056382146,0.0023767098,0.0007968653,0.00006782011],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006464015,0.0006388584,0.00017355017,0.000107799715,0.00025028267,0.000008829995,0.0051079863,0.0057706414,0.56045836,0.28510582,0.0033242097,0.13898899],"study_design_scores_gemma":[0.000020454978,0.000043596618,0.00013625118,0.00027789344,0.000038471564,0.0000011205552,0.00022540626,0.32911658,0.6315696,0.03816768,0.00005643466,0.00034650296],"about_ca_topic_score_codex":0.0003407852,"about_ca_topic_score_gemma":0.000052051895,"teacher_disagreement_score":0.79814714,"about_ca_system_score_codex":0.00010262721,"about_ca_system_score_gemma":0.00035542468,"threshold_uncertainty_score":0.999855},"labels":[],"label_agreement":null},{"id":"W3011628670","doi":"10.1109/access.2020.2982224","title":"A State-of-the-Art Review on Image Synthesis With Generative Adversarial Networks","year":2020,"lang":"en","type":"review","venue":"IEEE Access","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":197,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences; Chinese Academy of Sciences; National Natural Science Foundation of China","keywords":"Computer science; Inpainting; Image synthesis; Artificial intelligence; Image (mathematics); Image translation; Field (mathematics); Face (sociological concept); Generative grammar; Computer vision; Adversarial system; Image editing; Animation; Translation (biology); Image processing; Generative adversarial network; Computer graphics (images)","score_opus":0.035825652780617806,"score_gpt":0.30438653342285676,"score_spread":0.26856088064223893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011628670","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.601419e-8,0.6451137,0.35139588,0.0003932458,0.0010316598,0.0012695697,0.000038304806,0.0000520177,0.0007055957],"genre_scores_gemma":[0.0000155911,0.9918437,0.005753626,0.0010540447,0.00072094414,0.0003588336,0.000009371855,0.000075851785,0.00016804817],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954578,0.001198424,0.0009674354,0.0011585962,0.0006881568,0.0005295723],"domain_scores_gemma":[0.9958207,0.0008254733,0.0012870083,0.0016262088,0.00024743867,0.00019314662],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046166152,0.00085562305,0.0027503427,0.00011557442,0.00023280352,0.00041603908,0.0045537692,0.00017006705,0.000049322603],"category_scores_gemma":[0.00023438304,0.0004907376,0.0008750493,0.0017719311,0.00020054182,0.0008139515,0.0007108423,0.00070770597,0.0000850018],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000130660155,0.000050717063,3.4325612e-7,0.0049979505,0.0003734677,0.00004778206,0.000022055734,0.0013731275,6.583153e-7,0.00007060847,0.03564181,0.9574084],"study_design_scores_gemma":[0.00014868831,0.00011587154,9.491361e-7,0.04497858,0.00092135835,0.000019831446,6.122604e-7,0.005145506,0.00018877997,0.0000390495,0.94774204,0.00069875363],"about_ca_topic_score_codex":0.000018322753,"about_ca_topic_score_gemma":0.000019080588,"teacher_disagreement_score":0.9567097,"about_ca_system_score_codex":0.00012789812,"about_ca_system_score_gemma":0.00062939135,"threshold_uncertainty_score":0.9997544},"labels":[],"label_agreement":null},{"id":"W3011675874","doi":"10.1109/tsp.2020.2979601","title":"Subsampling Generative Adversarial Networks: Density Ratio Estimation in Feature Space With Softplus Loss","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Signal Processing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Discriminator; MNIST database; Computer science; Artificial intelligence; Feature (linguistics); Pattern recognition (psychology); Convergence (economics); Generative grammar; Generative adversarial network; Sample (material); Density ratio; Algorithm; Deep learning; Telecommunications; Physics","score_opus":0.016894953224282565,"score_gpt":0.2284269665349876,"score_spread":0.21153201331070504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011675874","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016203137,0.00009958772,0.9949815,0.0026469294,0.00016674018,0.0002763802,0.0000025493346,0.00015040862,0.000055562723],"genre_scores_gemma":[0.8680502,0.0000077704135,0.13107114,0.00061174884,0.00019098342,0.000019736262,0.0000023410016,0.000019912304,0.000026135634],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830383,0.00014577994,0.00024274562,0.0006213943,0.0003348351,0.00035141318],"domain_scores_gemma":[0.9992509,0.000120732526,0.00014146217,0.00016993358,0.00016406381,0.00015293203],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018395986,0.00028427335,0.000291408,0.00010529872,0.00048847427,0.00038535646,0.00030167095,0.00012367425,0.000014466228],"category_scores_gemma":[0.000008369432,0.0002508859,0.00007168182,0.0009691852,0.00007861963,0.0013045846,0.0000048822067,0.00050259393,0.000007828148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017641859,0.000049895614,0.000020221873,0.000014836594,0.000022983158,0.000030459101,0.0014192929,0.9473442,0.0012046029,0.00006878525,0.000043277294,0.049605068],"study_design_scores_gemma":[0.000700521,0.00017357765,0.00005307397,0.00009926127,0.000026595459,0.0000117362,0.00009391463,0.9601005,0.038343634,0.000076953715,0.000030811145,0.00028945628],"about_ca_topic_score_codex":0.000023658387,"about_ca_topic_score_gemma":0.00008992055,"teacher_disagreement_score":0.8664299,"about_ca_system_score_codex":0.0001013697,"about_ca_system_score_gemma":0.00020592735,"threshold_uncertainty_score":0.99999434},"labels":[],"label_agreement":null},{"id":"W3012305599","doi":"10.1117/12.2549592","title":"Ultrasound image simulation with generative adversarial network","year":2020,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Adversarial system; Computer science; Generative grammar; Artificial intelligence; Image (mathematics); Generative adversarial network; Computer vision","score_opus":0.016039424757689012,"score_gpt":0.22458210283554347,"score_spread":0.20854267807785445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012305599","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047823723,0.000029014327,0.98943573,0.0023355791,0.00019856067,0.00019874888,0.0000017343965,0.0001809119,0.007141463],"genre_scores_gemma":[0.6695376,0.000003854256,0.32696906,0.0023196267,0.001046655,0.000005254284,0.0000045567567,0.000009870128,0.00010350025],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869263,0.00011978218,0.00018130547,0.00046214825,0.00024095387,0.00030316564],"domain_scores_gemma":[0.99911666,0.00023820097,0.00008052419,0.00026258078,0.00013502751,0.00016697843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011559839,0.00018424631,0.0001891913,0.000017667619,0.00021136149,0.00028106326,0.00039997025,0.000046426936,0.00016260044],"category_scores_gemma":[0.000075103926,0.00013656967,0.000058052356,0.00047313186,0.000056496432,0.00092633785,0.00010671556,0.00010996909,0.00009443783],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045205274,0.00001597671,0.00011796778,0.0000022008255,0.00004743968,0.000012525964,0.00057830015,0.97830486,0.002749827,0.006915168,0.008969193,0.0022413095],"study_design_scores_gemma":[0.00047198846,0.00018779695,0.00030357015,0.0000043566474,0.0000134267775,0.0000030600577,0.000034824985,0.9892361,0.003894876,0.0003911048,0.0052146898,0.00024421109],"about_ca_topic_score_codex":0.000015217174,"about_ca_topic_score_gemma":0.000012770123,"teacher_disagreement_score":0.6690594,"about_ca_system_score_codex":0.000020067662,"about_ca_system_score_gemma":0.00005964955,"threshold_uncertainty_score":0.556915},"labels":[],"label_agreement":null},{"id":"W3012860294","doi":"10.1080/10255842.2020.1742709","title":"Blood transfusion prediction using restricted Boltzmann machines","year":2020,"lang":"en","type":"article","venue":"Computer Methods in Biomechanics & Biomedical Engineering","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Restricted Boltzmann machine; Task (project management); Identification (biology); Computer science; Blood transfusion; Artificial intelligence; Machine learning; Data mining; Medicine; Medical emergency; Pattern recognition (psychology); Deep learning; Engineering; Surgery","score_opus":0.028763293821356766,"score_gpt":0.28473318324280034,"score_spread":0.25596988942144355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012860294","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029292135,0.00028743054,0.99355006,0.00071496394,0.0018895213,0.00022423161,0.000008579434,0.00038943245,0.0000065410554],"genre_scores_gemma":[0.03111998,0.000094731375,0.9676285,0.00030369728,0.00080150785,0.000009534741,0.000011097742,0.000029531,0.0000014401854],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99758667,0.00027906898,0.0005775672,0.0007195653,0.00036126905,0.0004758439],"domain_scores_gemma":[0.99892974,0.00022273777,0.00008339178,0.00035533783,0.000057458416,0.00035130704],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000659911,0.00031086276,0.0004135134,0.0004049971,0.00008865152,0.00012537435,0.00082634937,0.00022277632,0.000012030224],"category_scores_gemma":[0.00015770517,0.00029658628,0.00012788373,0.0023377882,0.000030366868,0.00035608298,0.00044365635,0.00038879627,0.0000029679],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007609049,0.00009172356,0.0000075600474,0.000055369517,0.00004749091,0.000056522087,0.00036217624,0.01845132,0.77179503,0.000814973,0.000072666786,0.20823757],"study_design_scores_gemma":[0.00058825186,0.00019360565,0.00005620207,0.000074417556,0.00002258469,0.000023991573,0.0000034380532,0.97585833,0.020305496,0.0002550765,0.002347119,0.00027151348],"about_ca_topic_score_codex":0.000024998946,"about_ca_topic_score_gemma":3.1683388e-7,"teacher_disagreement_score":0.957407,"about_ca_system_score_codex":0.000053516924,"about_ca_system_score_gemma":0.000052960022,"threshold_uncertainty_score":0.9999486},"labels":[],"label_agreement":null},{"id":"W3013518738","doi":"10.1007/978-3-030-43823-4_38","title":"Deep Generative Multi-view Learning","year":2020,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Generative grammar; Computer science; Artificial intelligence; Representation (politics); Generative model; Deep learning; Artificial neural network; Machine learning; Deep neural networks; Noise (video); Nonlinear system","score_opus":0.04984219845483839,"score_gpt":0.2814629641844362,"score_spread":0.23162076572959783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013518738","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.63567e-7,0.0008304794,0.9174146,0.001563247,0.00020296553,0.00024465995,0.0000020509362,0.00007596757,0.07966524],"genre_scores_gemma":[0.023128668,0.006545483,0.9659844,0.0027265744,0.000104265215,0.00002903468,0.000044894314,0.00001340389,0.001423265],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845386,0.0000755473,0.00057075196,0.00034675884,0.00033890194,0.00021415892],"domain_scores_gemma":[0.99781984,0.0001633613,0.00031575825,0.0011964735,0.0003685254,0.00013602847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006570084,0.00024423804,0.00029409246,0.00043286246,0.00067225914,0.00082725653,0.0028044712,0.000099623,0.000010863421],"category_scores_gemma":[0.000081052225,0.0002371842,0.000056889905,0.00042641224,0.00062021654,0.0061185453,0.0027826685,0.0005656057,0.00011784946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012120523,0.000011876264,0.000021196956,0.000017752165,0.000011183373,8.543191e-7,0.0030789995,0.011770566,0.0000072434273,0.49024683,0.00023777469,0.4945945],"study_design_scores_gemma":[0.00015117231,0.000036474838,0.00013494634,0.00006715918,0.0000037666543,0.00000566691,0.0000146428,0.84971744,0.0000127671055,0.0014144272,0.14821114,0.00023038936],"about_ca_topic_score_codex":0.0000050311073,"about_ca_topic_score_gemma":0.0000097137,"teacher_disagreement_score":0.8379469,"about_ca_system_score_codex":0.00009679335,"about_ca_system_score_gemma":0.00020881616,"threshold_uncertainty_score":0.9672091},"labels":[],"label_agreement":null},{"id":"W3014301019","doi":"10.1007/978-3-030-50516-5_10","title":"Theoretical Insights into the Use of Structural Similarity Index in Generative Models and Inferential Autoencoders","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Generative grammar; Similarity (geometry); Kernel (algebra); Pattern recognition (psychology); Norm (philosophy); Matching (statistics); Adversarial system","score_opus":0.030116069105867033,"score_gpt":0.24010995206335775,"score_spread":0.20999388295749072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014301019","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007998532,0.0002991865,0.996446,0.0013464156,0.0005253113,0.0003513992,0.0000028872385,0.000026975145,0.00020194473],"genre_scores_gemma":[0.7783198,0.000046791534,0.22052138,0.0009293082,0.00016064983,0.0000035565342,0.0000019415716,0.000012329925,0.0000043027726],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99718106,0.00016563939,0.00051357405,0.001111948,0.00066858233,0.00035918836],"domain_scores_gemma":[0.99805206,0.000709152,0.00021936209,0.00069235,0.00019766277,0.00012943336],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030903146,0.00044135514,0.0005584237,0.0003343569,0.0002174037,0.0005074618,0.0015916574,0.00025419172,0.000011809211],"category_scores_gemma":[0.00014165572,0.00029960088,0.000095450785,0.00049219746,0.0023090283,0.0010191795,0.0016603015,0.00083824527,7.653619e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000127280755,0.0000074648665,0.000058105357,0.000010776966,0.000013957473,0.00001808815,0.0044447877,0.63750654,0.0000722588,0.306761,0.000005378286,0.051088944],"study_design_scores_gemma":[0.00011935451,0.00005394596,0.0001376931,0.00005451016,0.000004724891,0.0000028252168,4.3756566e-7,0.598812,0.00039919897,0.4001906,0.000027584676,0.00019717502],"about_ca_topic_score_codex":0.00009373779,"about_ca_topic_score_gemma":0.00053091126,"teacher_disagreement_score":0.7775199,"about_ca_system_score_codex":0.00010218314,"about_ca_system_score_gemma":0.0003662532,"threshold_uncertainty_score":0.99994564},"labels":[],"label_agreement":null},{"id":"W3015613036","doi":"10.1109/icassp40776.2020.9053379","title":"Learning Semi-Supervised Anonymized Representations by Mutual Information","year":2020,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Autoencoder; Discriminator; Computer science; Mutual information; Artificial intelligence; Set (abstract data type); Data mining; Training set; Data set; Pattern recognition (psychology); Machine learning; Deep learning; Detector","score_opus":0.012039362049721227,"score_gpt":0.21609201737575634,"score_spread":0.20405265532603512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015613036","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011535538,0.000016078753,0.97493994,0.006069705,0.00008010012,0.00010579947,0.0000017970207,0.00020013585,0.017432878],"genre_scores_gemma":[0.9309577,0.000016681732,0.064883225,0.0034278622,0.00009656236,0.000011234996,0.000035062938,0.000004508259,0.00056720135],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992366,0.000095166026,0.00019034036,0.00016654743,0.0001664603,0.00014489508],"domain_scores_gemma":[0.999552,0.000079013815,0.000054950757,0.00014574757,0.000064170024,0.000104089275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009422843,0.0000832968,0.00010242372,0.000026093434,0.00015478408,0.00025398438,0.00029922725,0.000030890948,0.00015602674],"category_scores_gemma":[0.00018143003,0.00007393256,0.000047660742,0.00032172634,0.000016552107,0.0018696308,0.00013393129,0.00009869875,0.00025606755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057861453,0.000060074763,0.0015357231,0.00002124102,0.00010508829,0.000005231079,0.018497132,0.069380045,0.048540298,0.0076288027,0.65068305,0.20348543],"study_design_scores_gemma":[0.00045237562,0.00005752781,0.0000958068,0.0000018037122,0.0000037825175,7.2002166e-7,0.00034481048,0.94600284,0.012379119,0.000047395253,0.04049851,0.00011533152],"about_ca_topic_score_codex":0.000030771622,"about_ca_topic_score_gemma":9.4247105e-7,"teacher_disagreement_score":0.9298041,"about_ca_system_score_codex":0.000009165463,"about_ca_system_score_gemma":0.00002651539,"threshold_uncertainty_score":0.32913157},"labels":[],"label_agreement":null},{"id":"W3017843993","doi":"10.48550/arxiv.2004.10495","title":"Stabilizing Training of Generative Adversarial Nets via Langevin Stein Variational Gradient Descent","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Regularization (linguistics); Langevin dynamics; Gradient descent; Inference; Stability (learning theory); Mathematical optimization; Generative grammar; Artificial intelligence; Algorithm; Statistical physics; Machine learning; Mathematics; Artificial neural network; Physics","score_opus":0.1202132709674541,"score_gpt":0.19223856129106257,"score_spread":0.07202529032360847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3017843993","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018539973,0.00007869465,0.978523,0.0004376522,0.0011101273,0.0004005805,0.00004736537,0.00010244349,0.00076013344],"genre_scores_gemma":[0.96211225,0.000049011927,0.037203368,0.00014481792,0.0003450329,0.0000019548681,0.000042379404,0.000021112746,0.00008008966],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973623,0.00045211066,0.00038831614,0.0011916038,0.00020661885,0.00039902065],"domain_scores_gemma":[0.99811965,0.00019443284,0.0005000839,0.0006869364,0.0002705008,0.00022842169],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034574556,0.00039765175,0.00058233115,0.00017925884,0.0001794045,0.000098873046,0.0012574864,0.00022666159,0.000054825665],"category_scores_gemma":[0.00008982128,0.0004462842,0.00032104136,0.0005301968,0.00012372823,0.0003973471,0.0014440018,0.00048537095,0.000016679045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000072228584,0.00011782702,0.00030460992,0.000052009505,0.00031286612,0.00011616361,0.0031935426,0.92800003,0.002138074,0.06263296,0.0003474126,0.0027122984],"study_design_scores_gemma":[0.00064716674,0.000113791575,0.00077445764,0.00008046755,0.00009891065,0.0000018662166,0.00020539272,0.9801323,0.0015356519,0.0155556295,0.00039826042,0.0004561046],"about_ca_topic_score_codex":0.00020774813,"about_ca_topic_score_gemma":0.000073160365,"teacher_disagreement_score":0.9435723,"about_ca_system_score_codex":0.00026879137,"about_ca_system_score_gemma":0.00043429903,"threshold_uncertainty_score":0.9997989},"labels":[],"label_agreement":null},{"id":"W3018462530","doi":"10.1007/s11548-020-02159-2","title":"pix2xray: converting RGB images into X-rays using generative adversarial networks","year":2020,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Adversarial system; Computer science; Artificial intelligence; Generative grammar; Generative adversarial network; RGB color model; Computer vision; Computer graphics (images); Image (mathematics)","score_opus":0.026735657967679564,"score_gpt":0.2515673635443706,"score_spread":0.22483170557669102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3018462530","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031353205,0.00088271935,0.9576251,0.0056919325,0.004349743,0.000047925565,0.0000016563445,0.000024887842,0.000022839413],"genre_scores_gemma":[0.8705638,0.00018782329,0.12144876,0.0037085437,0.004073539,8.236443e-7,0.0000039756715,0.000010077768,0.0000026674384],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979391,0.00050009054,0.00073528057,0.0003095698,0.00027946383,0.00023647549],"domain_scores_gemma":[0.9976673,0.0008751965,0.0006161399,0.000113927905,0.0005328522,0.0001945485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000642677,0.00020771021,0.0005353457,0.00019382425,0.00015818879,0.00019976603,0.0006240331,0.00012352047,0.000015750196],"category_scores_gemma":[0.00016889365,0.00017763516,0.00025043215,0.00018382358,0.00015318725,0.0007653193,0.0002552177,0.0003328351,0.0000017513725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009702256,0.00025522843,0.03059378,0.000031038893,0.0041714357,0.003124629,0.0053663435,0.48856372,0.01942505,0.0021348645,0.031183124,0.41418058],"study_design_scores_gemma":[0.0006662054,0.00012189009,0.0052710697,0.000059295504,0.00003822577,0.0009836324,0.000032539705,0.9890593,0.00077752396,0.0002884036,0.0024557698,0.0002460984],"about_ca_topic_score_codex":0.000010361744,"about_ca_topic_score_gemma":7.792545e-7,"teacher_disagreement_score":0.83921057,"about_ca_system_score_codex":0.000056376044,"about_ca_system_score_gemma":0.00016645218,"threshold_uncertainty_score":0.7243751},"labels":[],"label_agreement":null},{"id":"W3020030698","doi":"10.1109/cvpr42600.2020.00518","title":"Disentangled Image Generation Through Structured Noise Injection","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Noise (video); Generator (circuit theory); Image (mathematics); Code (set theory); Face (sociological concept); Object (grammar); Grid; Artificial intelligence; Generative model; Space (punctuation); Layer (electronics); Computer vision; Pattern recognition (psychology); Generative grammar; Power (physics); Mathematics","score_opus":0.03524480576759212,"score_gpt":0.2634259380580776,"score_spread":0.2281811322904855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3020030698","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011482092,0.00011588518,0.98664427,0.0035164247,0.0032054738,0.00046338263,0.000016552069,0.00034683978,0.004542944],"genre_scores_gemma":[0.5638685,0.0000552211,0.43258607,0.0009910502,0.0020417627,0.000043261258,0.0001221073,0.000025272324,0.00026675436],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99781543,0.00020130651,0.00036833013,0.0010132719,0.00033788916,0.0002637693],"domain_scores_gemma":[0.99865794,0.00002899096,0.00022156164,0.00081643945,0.00016816022,0.00010692175],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00009970238,0.00037060544,0.00036702468,0.00005713266,0.00018618666,0.00078038726,0.00083971355,0.00022324799,0.00013240165],"category_scores_gemma":[0.000062594394,0.000325764,0.00021668684,0.0002615332,0.000044877343,0.00074197125,0.0013536109,0.00041302375,0.000067898036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006926495,0.00025525622,0.0001864945,0.00022794635,0.0006907528,0.00015225126,0.005237181,0.18731962,0.44088057,0.052426923,0.23592722,0.07662653],"study_design_scores_gemma":[0.00026350064,0.00006016277,0.00033422682,0.000017893744,0.00004222606,0.000006000788,0.0000275658,0.91504,0.06028777,0.021883061,0.0015107859,0.00052680966],"about_ca_topic_score_codex":0.0001945188,"about_ca_topic_score_gemma":0.00007391791,"teacher_disagreement_score":0.7277204,"about_ca_system_score_codex":0.000101415135,"about_ca_system_score_gemma":0.00012991569,"threshold_uncertainty_score":0.9999194},"labels":[],"label_agreement":null},{"id":"W3023788528","doi":"10.1016/j.neunet.2020.04.029","title":"Multi-projection of unequal dimension optimal transport theory for Generative Adversary Networks","year":2020,"lang":"en","type":"article","venue":"Neural Networks","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Wasserstein metric; Linear subspace; Dimension (graph theory); Metric (unit); Projection (relational algebra); Generative model; Generative grammar; Mathematical optimization; Parameterized complexity; Differentiable function; Probability distribution; Mathematics; Intrinsic dimension; Artificial intelligence; Algorithm; Applied mathematics","score_opus":0.02926115820066098,"score_gpt":0.24571772839261954,"score_spread":0.21645657019195857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023788528","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006720505,0.0006137668,0.9901254,0.0006355869,0.0010288311,0.0006730243,0.000010500616,0.00014675573,0.000045637335],"genre_scores_gemma":[0.8841546,0.00006305787,0.11347119,0.0012230644,0.00093238096,0.00004333017,0.000038160466,0.000031161253,0.00004301558],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99773914,0.00029447128,0.00051565375,0.0007196052,0.00022547903,0.00050564366],"domain_scores_gemma":[0.9987023,0.00030338895,0.00025694992,0.0003417096,0.00019644578,0.00019922954],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037819793,0.0003359834,0.00046440106,0.00005565113,0.0002505242,0.000048910606,0.0005619576,0.00019681125,0.000016355489],"category_scores_gemma":[0.00004909801,0.00029517486,0.00030692693,0.0005164854,0.000111839625,0.000585754,0.0001373681,0.0003161514,0.0000015774765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027801623,0.000058701553,0.00013840075,0.000011900401,0.000063363004,0.00000873022,0.0005433028,0.96561784,0.0019073958,0.0008814863,0.0008009277,0.029689914],"study_design_scores_gemma":[0.0009672325,0.00051993894,0.0004653031,0.000017786158,0.000051766026,0.0000027829083,0.000074289244,0.9950728,0.0021993353,0.000040760515,0.00028327122,0.0003047762],"about_ca_topic_score_codex":0.000014983518,"about_ca_topic_score_gemma":0.000008521032,"teacher_disagreement_score":0.87743413,"about_ca_system_score_codex":0.000026494814,"about_ca_system_score_gemma":0.00003917854,"threshold_uncertainty_score":0.99995005},"labels":[],"label_agreement":null},{"id":"W3024180722","doi":"10.1016/j.neucom.2020.03.090","title":"Attentional coarse-and-fine generative adversarial networks for image inpainting","year":2020,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"National Natural Science Foundation of China","keywords":"Inpainting; Computer science; Artificial intelligence; Block (permutation group theory); Image (mathematics); Residual; Pattern recognition (psychology); Dependency (UML); Pixel; Computer vision; Field (mathematics); Deep learning; Generative grammar; Algorithm; Mathematics","score_opus":0.022429575156618493,"score_gpt":0.23402969896643655,"score_spread":0.21160012380981805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024180722","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033830362,0.00007200646,0.9903168,0.00486276,0.0005634734,0.00037143618,0.0000033974611,0.00017119576,0.00025586123],"genre_scores_gemma":[0.5586643,0.0000040343493,0.43590122,0.0031060558,0.0022607232,0.000014836502,0.000007879876,0.00002191952,0.00001901821],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820226,0.00015094892,0.0003443348,0.0006987311,0.00018424071,0.00041950392],"domain_scores_gemma":[0.9989062,0.0004182797,0.00018221558,0.00016868045,0.00015222334,0.00017241012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031224123,0.00022716016,0.00027233627,0.000041905318,0.0004752199,0.0003376477,0.00042544678,0.00006175178,0.000007907074],"category_scores_gemma":[0.00025506338,0.0002258296,0.00013302949,0.00027892747,0.000061363775,0.00042847765,0.00049662724,0.00021178825,0.000006061848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000119482,0.00010992308,0.00078637217,0.00008662359,0.00018347848,0.000078150326,0.0020465297,0.46553886,0.04093547,0.030193126,0.017113844,0.44280815],"study_design_scores_gemma":[0.00071653357,0.00012122542,0.00025366098,0.000013495835,0.000014074627,0.0000088165425,0.000018978548,0.9938467,0.001277392,0.00022679311,0.003280645,0.00022166713],"about_ca_topic_score_codex":0.0000058328287,"about_ca_topic_score_gemma":0.0000019995243,"teacher_disagreement_score":0.5552813,"about_ca_system_score_codex":0.000014436493,"about_ca_system_score_gemma":0.000032526063,"threshold_uncertainty_score":0.9209064},"labels":[],"label_agreement":null},{"id":"W3033814355","doi":"10.1109/crv50864.2020.00020","title":"Automatic Classification of Woodcuts and Copperplate Engravings","year":2020,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Allison University","funders":"","keywords":"Interpretability; Woodcut; Robustness (evolution); Computer science; Artificial intelligence; Bayesian probability; Machine learning; Pattern recognition (psychology); Simple (philosophy); Outlier; Computer vision; Data mining","score_opus":0.024065037811017084,"score_gpt":0.22396931828839747,"score_spread":0.1999042804773804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033814355","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.068829216,0.000056107394,0.9240662,0.0049916864,0.0000440813,0.00007553168,5.4762756e-7,0.00007006757,0.0018665855],"genre_scores_gemma":[0.9318609,0.000010239168,0.0676825,0.00039272898,0.000020770723,0.0000016203646,3.571151e-7,0.0000022403017,0.000028598513],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99953806,0.000030457997,0.000121291545,0.00015646093,0.00008036221,0.000073375675],"domain_scores_gemma":[0.9996885,0.000046319063,0.000051889117,0.00011887407,0.0000349016,0.00005948152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000072014576,0.000052822088,0.00009500967,0.000016694961,0.00003250998,0.00004210973,0.00017132644,0.000019909448,0.000028768738],"category_scores_gemma":[0.00004148993,0.000042879605,0.000018725885,0.00014677898,0.000027433258,0.00021335008,0.00007582909,0.000030069647,0.000010352495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007313325,0.00005709796,0.001855969,0.00008867922,0.0000619545,0.0000042745055,0.0051417984,0.000532947,0.31829306,0.07609121,0.008443795,0.5894219],"study_design_scores_gemma":[0.00009672441,0.000047560832,0.0077644275,0.0000062687786,0.000003933368,0.0000010139823,0.000039039962,0.9742871,0.016666373,0.00035351698,0.0006742772,0.000059797392],"about_ca_topic_score_codex":0.000006964341,"about_ca_topic_score_gemma":0.0000010919025,"teacher_disagreement_score":0.9737541,"about_ca_system_score_codex":0.000003102005,"about_ca_system_score_gemma":0.000013150619,"threshold_uncertainty_score":0.17485796},"labels":[],"label_agreement":null},{"id":"W3034727712","doi":"","title":"Tails of Lipschitz Triangular Flows","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Waterloo","funders":"","keywords":"Lipschitz continuity; Transformation (genetics); Gaussian; Density estimation; Probability density function; Flow (mathematics); Computer science; Statistical physics; Algorithm; Mathematical optimization; Mathematics; Mathematical analysis; Physics; Geometry; Statistics; Estimator","score_opus":0.046527295370293154,"score_gpt":0.27012380389539,"score_spread":0.22359650852509683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034727712","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009581969,0.000058499732,0.9517064,0.015213708,0.00039438278,0.0000963052,0.000007059624,0.000094616116,0.02284705],"genre_scores_gemma":[0.9808546,0.000024643457,0.017965255,0.00064926135,0.00021269024,0.0000037808998,0.000010011502,0.0000073099272,0.00027245545],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988856,0.00013926243,0.00023078694,0.00029026277,0.0003245676,0.00012954591],"domain_scores_gemma":[0.99938095,0.000080306825,0.00014999132,0.0001408145,0.00016513503,0.00008282158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017035764,0.00012172573,0.00017315513,0.000068602,0.00006121206,0.000113105554,0.0007714554,0.000035790985,0.00051383936],"category_scores_gemma":[0.0003626774,0.000108994376,0.000086661144,0.00015340638,0.000022590511,0.0002493757,0.00017118365,0.00026780413,0.00008601674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024536916,0.00015827196,0.0037931458,0.000024208966,0.0002795269,0.00006138011,0.0028618786,0.1883409,0.10580378,0.42930198,0.0008643493,0.26826522],"study_design_scores_gemma":[0.00035703846,0.00017883185,0.00025640966,0.000022418624,0.0000037517768,0.0000015349302,0.00003065911,0.984418,0.0049986765,0.0007865105,0.00883074,0.000115476774],"about_ca_topic_score_codex":0.0000358453,"about_ca_topic_score_gemma":0.0000043284504,"teacher_disagreement_score":0.97127265,"about_ca_system_score_codex":0.000013114055,"about_ca_system_score_gemma":0.0000444392,"threshold_uncertainty_score":0.5626181},"labels":[],"label_agreement":null},{"id":"W3034917202","doi":"","title":"On Variational Learning of Controllable Representations for Text without Supervision","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Autoencoder; Computer science; Unsupervised learning; Artificial intelligence; Decoding methods; Space (punctuation); Encoding (memory); Simplex; Sequence (biology); Latent variable; Machine learning; Deep learning; Algorithm; Mathematics","score_opus":0.041010886409364275,"score_gpt":0.30264751106133425,"score_spread":0.26163662465196996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034917202","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029374803,0.000015435871,0.9722952,0.011482211,0.00024239245,0.00019519891,0.000014438787,0.00007157895,0.012746039],"genre_scores_gemma":[0.97481614,0.0000141450155,0.023481142,0.00063544576,0.00017610678,0.000022686856,0.000058724323,0.000011637763,0.00078398903],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859977,0.00017521117,0.00028493226,0.00039074122,0.00039819584,0.00015115672],"domain_scores_gemma":[0.9986132,0.0005497526,0.00021538042,0.00012608044,0.00042099008,0.00007458988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026539175,0.00014024078,0.00020200452,0.000098954035,0.00018549386,0.00015702519,0.0005059666,0.00004364763,0.000382546],"category_scores_gemma":[0.0013792329,0.00012832585,0.00009748625,0.00014847906,0.000026683423,0.00029052034,0.00010451183,0.0002880353,0.00004213218],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022338888,0.000058928013,0.0033472192,0.0000070554706,0.00007907305,0.0000016217126,0.00062434975,0.516586,0.010684937,0.45644033,0.00022298253,0.011724089],"study_design_scores_gemma":[0.00092558103,0.00046051302,0.0009175566,0.00003440223,0.0000069986877,8.015925e-7,0.00005370583,0.98969376,0.0013918706,0.0034502381,0.0029414431,0.00012314678],"about_ca_topic_score_codex":0.00005951398,"about_ca_topic_score_gemma":0.0000042540196,"teacher_disagreement_score":0.97187865,"about_ca_system_score_codex":0.000025138395,"about_ca_system_score_gemma":0.00006678039,"threshold_uncertainty_score":0.5232976},"labels":[],"label_agreement":null},{"id":"W3035503873","doi":"","title":"Energy-Based Processes for Exchangeable Data","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Google (Canada); University of Alberta","funders":"","keywords":"Cardinality (data modeling); Computer science; Key (lock); Point cloud; Data mining; Energy (signal processing); Artificial neural network; Data modeling; Cloud computing; Variety (cybernetics); Function (biology); Machine learning; State (computer science); Point (geometry); Artificial intelligence; Algorithm; Mathematics; Database; Computer security","score_opus":0.13709502006650395,"score_gpt":0.3115046162466212,"score_spread":0.17440959618011723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035503873","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000039164155,0.000069177804,0.96685463,0.02814497,0.00020522806,0.00006975278,0.000043552394,0.000105992505,0.0044675176],"genre_scores_gemma":[0.95254576,0.0000312129,0.043139018,0.0032023892,0.00037577713,0.000023419201,0.0002391627,0.0000114794,0.0004317566],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989674,0.00005660364,0.00014086015,0.00046874708,0.00020968897,0.00015669498],"domain_scores_gemma":[0.9991436,0.00017374751,0.000104093095,0.00023934392,0.0002621655,0.00007703625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014546067,0.00012559786,0.00012063267,0.00005091636,0.00012492231,0.00028784727,0.0015240441,0.00003005094,0.00014396661],"category_scores_gemma":[0.0005104597,0.00011330271,0.000031038697,0.00014992485,0.000018647683,0.00043562838,0.00027855302,0.00012756318,0.000018614192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042179882,0.00026859684,0.0023275765,0.00015330936,0.00025537296,0.000027627884,0.0008962453,0.18460907,0.010569615,0.3361396,0.01572806,0.44860312],"study_design_scores_gemma":[0.00028407178,0.0001332128,0.000019058041,0.000022890705,0.0000036225017,4.850971e-7,0.000009553969,0.90129644,0.0015877363,0.0008860194,0.09563661,0.000120312456],"about_ca_topic_score_codex":0.000041341962,"about_ca_topic_score_gemma":0.000024320918,"teacher_disagreement_score":0.9525066,"about_ca_system_score_codex":0.0000136671815,"about_ca_system_score_gemma":0.00012947855,"threshold_uncertainty_score":0.46203506},"labels":[],"label_agreement":null},{"id":"W3035564323","doi":"","title":"Undirected Graphical Models as Approximate Posteriors","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"D-Wave Systems (Canada)","funders":"","keywords":"Graphical model; Computer science; Markov chain Monte Carlo; Estimator; Representation (politics); Undirected graph; Posterior probability; Markov chain; Algorithm; Backpropagation; Theoretical computer science; Artificial intelligence; Machine learning; Artificial neural network; Mathematics; Bayesian probability; Graph","score_opus":0.04728826431044014,"score_gpt":0.2723734905455278,"score_spread":0.22508522623508764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035564323","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008224269,0.000029498298,0.91790324,0.025799582,0.00035504962,0.000112568385,0.0000057230627,0.00030502054,0.04726504],"genre_scores_gemma":[0.98772424,0.000039448867,0.009626595,0.0021165286,0.0001453234,0.000008054739,0.000021370623,0.000012375266,0.0003060883],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998589,0.0001644498,0.00020691965,0.00044958395,0.00038807554,0.00020200136],"domain_scores_gemma":[0.999361,0.00006712776,0.00010858839,0.00014806383,0.00017068697,0.0001445757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013081817,0.00017421885,0.00016726687,0.00009121807,0.00013211329,0.00034552405,0.00083714933,0.00005276679,0.00032951],"category_scores_gemma":[0.00017105516,0.00015681887,0.00008376347,0.00021920253,0.000038196544,0.00047446022,0.0002589035,0.00041232008,0.00014181857],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016793597,0.00008745526,0.0009611157,0.000009063269,0.00014716406,0.00008604627,0.0017161738,0.1328033,0.0141349835,0.7973547,0.00025103963,0.052281022],"study_design_scores_gemma":[0.00025335565,0.00016647867,0.00017435725,0.000020557456,0.000003601848,0.0000068516656,0.00002749161,0.98811454,0.0007220601,0.008649821,0.001686634,0.00017422637],"about_ca_topic_score_codex":0.00007180668,"about_ca_topic_score_gemma":0.0000049033993,"teacher_disagreement_score":0.97949994,"about_ca_system_score_codex":0.000021712469,"about_ca_system_score_gemma":0.000046093144,"threshold_uncertainty_score":0.6394888},"labels":[],"label_agreement":null},{"id":"W3035582376","doi":"10.1609/aaai.v35i8.16883","title":"Generalized Adversarially Learned Inference","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Generator (circuit theory); Inference; Discriminator; Consistency (knowledge bases); Latent variable; Flexibility (engineering); Scalability; Tuple; Set (abstract data type); Image (mathematics); Artificial intelligence; Maximization; Encoder; Inpainting; Machine learning; Pattern recognition (psychology); Mathematical optimization; Mathematics","score_opus":0.0827619177343025,"score_gpt":0.30218906407183455,"score_spread":0.21942714633753205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035582376","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08707643,0.0001897362,0.80588144,0.031765807,0.0035257179,0.00093363936,0.000017048931,0.00036536268,0.070244834],"genre_scores_gemma":[0.97668445,0.00012249695,0.02144131,0.00058327767,0.00015869334,0.000018626484,9.044829e-7,0.000014026628,0.00097618485],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9975791,0.000068046604,0.00060611544,0.0007157437,0.00058996375,0.0004410416],"domain_scores_gemma":[0.9973959,0.00016751228,0.0003858165,0.00052449724,0.0013998529,0.00012647687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047892777,0.00028712876,0.00037973886,0.00009052933,0.00029133027,0.00045947699,0.0020680935,0.00012115769,0.0002595115],"category_scores_gemma":[0.0012193634,0.00022138338,0.0002221652,0.0010034752,0.00024921075,0.0006001612,0.00074227265,0.00032823786,0.00011896049],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003508691,0.00012003146,0.00007057427,0.000014109833,0.000029752444,0.0000022320053,0.00051195425,0.0008293392,0.12366705,0.8137296,0.00030651505,0.06068377],"study_design_scores_gemma":[0.00005296192,0.00009040345,0.0001245643,0.00011094632,0.000017820697,0.000005047539,0.00021712449,0.084349014,0.7583438,0.15573314,0.00068589224,0.0002692593],"about_ca_topic_score_codex":0.000039499715,"about_ca_topic_score_gemma":0.000019490612,"teacher_disagreement_score":0.889608,"about_ca_system_score_codex":0.000045511893,"about_ca_system_score_gemma":0.00033516347,"threshold_uncertainty_score":0.9027752},"labels":[],"label_agreement":null},{"id":"W3037016570","doi":"10.1609/aaai.v34i07.6914","title":"EFANet: Exchangeable Feature Alignment Network for Arbitrary Style Transfer","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Shenzhen University; National Natural Science Foundation of China","keywords":"Computer science; Statistic; Artificial intelligence; Swap (finance); Pattern recognition (psychology); Feature vector; Feature (linguistics); Matching (statistics); Feature extraction; Graphics; Image (mathematics); Extractor; Mathematics; Computer graphics (images)","score_opus":0.07239168392874401,"score_gpt":0.2596019731351739,"score_spread":0.1872102892064299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037016570","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005761429,0.00017432873,0.94314647,0.041971467,0.0007637886,0.0013842935,0.000027986103,0.00013703575,0.006633227],"genre_scores_gemma":[0.97173345,0.000056653753,0.024919732,0.0024002402,0.00054828316,0.00007433776,0.0000014728392,0.000019139532,0.00024667368],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981575,0.00002329525,0.00037934395,0.0005927853,0.0003793312,0.00046774693],"domain_scores_gemma":[0.99899876,0.00010791862,0.00015124494,0.0002260684,0.00036189315,0.00015412451],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034317467,0.00026823007,0.00033337245,0.000035151737,0.0002674731,0.00025481734,0.0016437012,0.000107393724,0.00006850661],"category_scores_gemma":[0.0001336652,0.00019926706,0.00020396971,0.0005524691,0.00013441303,0.0003863396,0.00020424044,0.00024035707,0.000028930255],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002648066,0.00014549495,0.000058836653,0.00011135374,0.00007778044,8.7169e-7,0.0032914674,0.0025428163,0.058710143,0.8598967,0.014098534,0.060801174],"study_design_scores_gemma":[0.00007120716,0.0005304261,0.00004048599,0.0001505123,0.000032951506,0.0000015105014,0.00034966102,0.32075173,0.611549,0.060379334,0.005786216,0.00035692702],"about_ca_topic_score_codex":0.000012243456,"about_ca_topic_score_gemma":0.0000056970875,"teacher_disagreement_score":0.96597207,"about_ca_system_score_codex":0.000024421837,"about_ca_system_score_gemma":0.00006962633,"threshold_uncertainty_score":0.8125875},"labels":[],"label_agreement":null},{"id":"W3037248788","doi":"10.1162/neco_a_01359","title":"Unsupervised Discovery, Control, and Disentanglement of Semantic Attributes With Applications to Anomaly Detection","year":2021,"lang":"en","type":"preprint","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Maximization; Anomaly detection; Generative grammar; Discriminative model; Leverage (statistics); Artificial intelligence; Machine learning; Generative model; Semantic space; Mutual information; Unsupervised learning; Pattern recognition (psychology); Data mining; Mathematics","score_opus":0.016678127729685514,"score_gpt":0.24425344609813074,"score_spread":0.22757531836844522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037248788","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21158883,0.00014582227,0.7866567,0.00073657144,0.00013596221,0.00067116745,0.000018291326,0.000036881313,0.000009807846],"genre_scores_gemma":[0.97087216,0.000013631747,0.0287065,0.0001359155,0.00008498617,0.000116446136,0.000052419226,0.000010901025,0.000007008583],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861836,0.00014329617,0.00028856331,0.00055202446,0.00024218732,0.00015557586],"domain_scores_gemma":[0.9990692,0.000112803995,0.00019334511,0.0003014032,0.00024992632,0.000073320356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010162123,0.00020086023,0.0003091356,0.000102855076,0.00011050062,0.00037911758,0.00022736877,0.000057411627,0.000001082476],"category_scores_gemma":[0.000012647658,0.00017673834,0.000065056636,0.00028853232,0.000035120906,0.0003426085,0.0003526363,0.00012762561,7.4608374e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006751898,0.00015061692,0.0035964304,0.0002393387,0.0001730635,0.000009534733,0.0006000119,0.860575,0.022808462,0.0003156986,0.000036807876,0.11142747],"study_design_scores_gemma":[0.0005241194,0.0002297739,0.040401816,0.000091157955,0.000081799124,0.0000070892866,0.000067702254,0.9497504,0.008221421,0.00033903765,0.000026926624,0.0002587311],"about_ca_topic_score_codex":0.00012037007,"about_ca_topic_score_gemma":0.00014610207,"teacher_disagreement_score":0.75928336,"about_ca_system_score_codex":0.000042462514,"about_ca_system_score_gemma":0.000050767256,"threshold_uncertainty_score":0.720718},"labels":[],"label_agreement":null},{"id":"W3037789351","doi":"","title":"Dualing GANs","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Discriminator; Minimax; Saddle point; Computer science; Intuition; Generator (circuit theory); Maximization; Nonlinear system; Instability; Generative grammar; Mathematical optimization; Algorithm; Mathematics; Artificial intelligence; Physics","score_opus":0.0998167729325242,"score_gpt":0.19479144939332405,"score_spread":0.09497467646079985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037789351","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010807436,0.0000965759,0.9763803,0.00025868323,0.0014105744,0.00016174249,0.000009669942,0.00017734036,0.010697672],"genre_scores_gemma":[0.98957896,0.00020137781,0.006088341,0.00009121356,0.00029355785,5.322956e-7,0.0000068300624,0.000015740156,0.0037234647],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981916,0.00013942803,0.00014987252,0.0010736348,0.00008153716,0.00036396203],"domain_scores_gemma":[0.9973142,0.00007702599,0.00030516248,0.0019919195,0.00015510716,0.00015659204],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026459267,0.0002999356,0.00033383933,0.00013329883,0.0004502443,0.0004291186,0.0027722558,0.0002437767,0.000036241545],"category_scores_gemma":[0.00006462766,0.00033550657,0.00025369617,0.00014845889,0.00011822187,0.0005390069,0.0026817853,0.00045900073,0.00013354838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012521123,0.00006732615,0.00072843925,0.000039692353,0.00017019037,0.00057358533,0.00028493223,0.9037014,0.00010795535,0.08802969,0.0022875464,0.0039966838],"study_design_scores_gemma":[0.00024623208,0.00002156796,0.00048349248,0.00008746286,0.00005583665,0.0000027834258,0.000024275856,0.9551024,0.00053741777,0.039330393,0.0036127463,0.0004953918],"about_ca_topic_score_codex":0.00019631864,"about_ca_topic_score_gemma":0.00004615259,"teacher_disagreement_score":0.9787715,"about_ca_system_score_codex":0.00009738788,"about_ca_system_score_gemma":0.00017528207,"threshold_uncertainty_score":0.9999097},"labels":[],"label_agreement":null},{"id":"W3040712465","doi":"10.1016/j.neunet.2020.07.005","title":"Deep clustering with a Dynamic Autoencoder: From reconstruction towards centroids construction","year":2020,"lang":"en","type":"article","venue":"Neural Networks","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":87,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Ecole Nationale d'Ingénieurs de Tunis","keywords":"Autoencoder; Cluster analysis; Artificial intelligence; Centroid; Computer science; Pattern recognition (psychology); Deep learning","score_opus":0.009775096916755398,"score_gpt":0.19633853883010596,"score_spread":0.18656344191335056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040712465","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006590971,0.00024256793,0.98868704,0.0025507077,0.0011604776,0.00017983935,0.0000026260298,0.0002883263,0.000297417],"genre_scores_gemma":[0.7832525,0.000053735905,0.21523039,0.0008644113,0.0005548022,0.000009135945,0.000010842428,0.000017097858,0.0000071283716],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998383,0.00013197039,0.0002684439,0.0006167443,0.00021636373,0.00038346648],"domain_scores_gemma":[0.9992099,0.0000534025,0.00015221881,0.00030487138,0.00007661427,0.00020303266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005715435,0.0002450104,0.00026997173,0.000035657074,0.00021182197,0.00028010568,0.00042935507,0.00010266581,0.00005456607],"category_scores_gemma":[0.000018577366,0.00020836726,0.00008511709,0.00041515383,0.00010209371,0.00076047913,0.00018059676,0.00030756317,0.000008497286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039462397,0.0000054670472,0.00035948452,0.0000023434002,0.000027180135,0.000013666132,0.00013886997,0.6223406,0.00012474436,0.000058053498,0.00006276593,0.37682736],"study_design_scores_gemma":[0.0004546093,0.00014056095,0.0012237171,0.000020747862,0.000021101883,0.000062341365,0.00005700482,0.99734396,0.00009639579,0.00013239493,0.00019872154,0.00024843917],"about_ca_topic_score_codex":0.00007267318,"about_ca_topic_score_gemma":0.00011192911,"teacher_disagreement_score":0.77666146,"about_ca_system_score_codex":0.000054509586,"about_ca_system_score_gemma":0.00003090515,"threshold_uncertainty_score":0.849697},"labels":[],"label_agreement":null},{"id":"W3042721654","doi":"10.1109/icpr48806.2021.9413149","title":"Relatable Clothing: Detecting Visual Relationships between People and Clothing","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Clothing; Biometrics; Computer science; Artificial intelligence; Visibility; Segmentation; Field (mathematics); Computer vision; Pattern recognition (psychology); Geography; Mathematics","score_opus":0.039890762978954455,"score_gpt":0.26462506843585387,"score_spread":0.22473430545689943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3042721654","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08230455,0.00079152506,0.9126875,0.00068488653,0.0006992303,0.00022218126,0.0000021695432,0.00027153274,0.0023364169],"genre_scores_gemma":[0.7658778,0.000060011746,0.23316464,0.000066680455,0.0003967052,0.000014213728,0.0000139236145,0.000024858062,0.0003812016],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970782,0.00056628196,0.0005092691,0.0010891607,0.00033610954,0.00042099925],"domain_scores_gemma":[0.9977041,0.0009352738,0.0002759178,0.0007311748,0.00016812907,0.00018543976],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0014887772,0.00035016713,0.00052575825,0.00015345505,0.00075275905,0.0015868362,0.0006342782,0.00042774624,0.000028520453],"category_scores_gemma":[0.00067223416,0.000350728,0.00014067096,0.00037964806,0.000037634418,0.00092633435,0.0032666235,0.0015979616,0.000011943586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022297352,0.00025157188,0.4971175,0.0009587108,0.0015999029,0.00016131095,0.05863205,0.1407047,0.0036098561,0.021704312,0.0021824543,0.27305534],"study_design_scores_gemma":[0.0003887357,0.000063474705,0.054416336,0.00044536975,0.00014970453,0.000033247587,0.0013038879,0.9304893,0.004101087,0.0061858166,0.0010923761,0.0013306896],"about_ca_topic_score_codex":0.0006971723,"about_ca_topic_score_gemma":0.00030236173,"teacher_disagreement_score":0.78978455,"about_ca_system_score_codex":0.000085099346,"about_ca_system_score_gemma":0.00018454403,"threshold_uncertainty_score":0.9998945},"labels":[],"label_agreement":null},{"id":"W3045177652","doi":"","title":"Learning Structured Latent Factors from Dependent Data:A Generative Model Framework from Information-Theoretic Perspective","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Information bottleneck method; Computer science; Generative model; Artificial intelligence; Latent variable; Machine learning; Generative grammar; Dependency (UML); Latent variable model; Graphical model; Inductive bias; Flexibility (engineering); Multi-task learning; Mathematics; Mutual information","score_opus":0.07586395186275015,"score_gpt":0.20213384294542341,"score_spread":0.12626989108267328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3045177652","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08119022,0.00008972854,0.9159454,0.00030465127,0.00076980924,0.00034275168,0.000798466,0.00022810814,0.00033088197],"genre_scores_gemma":[0.94905263,0.00018671526,0.04944301,0.00022608064,0.00026979428,0.0000012078999,0.00073716824,0.000024680074,0.000058703004],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968694,0.0004163283,0.00035341008,0.0017042073,0.0002542883,0.0004023891],"domain_scores_gemma":[0.99664265,0.00036562892,0.00052912795,0.0018181358,0.00035099254,0.00029347622],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00013602228,0.0005922543,0.00059524487,0.00015812705,0.00038161312,0.00062100746,0.0034400683,0.0004744858,0.000112650254],"category_scores_gemma":[0.00031821974,0.00060824037,0.00021852093,0.0003883294,0.00014663298,0.0018198885,0.0053415215,0.001572662,0.000075142045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035483572,0.000021380223,0.00084819493,0.0000060928924,0.00037601305,0.000036783033,0.006484234,0.92942137,0.000060539605,0.062344227,0.00015072264,0.00021495769],"study_design_scores_gemma":[0.00022805833,0.000027493079,0.0006108019,0.00004265645,0.00013431848,1.6192527e-7,0.0011709983,0.73867244,0.00042088487,0.25818065,0.000035927198,0.00047561372],"about_ca_topic_score_codex":0.0019128313,"about_ca_topic_score_gemma":0.0001153545,"teacher_disagreement_score":0.8678624,"about_ca_system_score_codex":0.00040992754,"about_ca_system_score_gemma":0.0003616543,"threshold_uncertainty_score":0.9996369},"labels":[],"label_agreement":null},{"id":"W3046476051","doi":"10.1017/s1431927620018231","title":"Forget About Cleaning up Your Micrographs: Deep Learning Segmentation is Robust to Image Artifacts","year":2020,"lang":"en","type":"article","venue":"Microscopy and Microanalysis","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Object Research Systems (Canada); McMaster University","funders":"","keywords":"Artificial intelligence; Computer vision; Segmentation; Micrograph; Computer science; Deep learning; Materials science; Pattern recognition (psychology); Composite material","score_opus":0.019132666781449304,"score_gpt":0.2595833796072563,"score_spread":0.240450712825807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046476051","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09721006,0.0009419066,0.89890116,0.0024312844,0.000117385105,0.00018472856,0.000008016125,0.00009985764,0.00010562443],"genre_scores_gemma":[0.6082581,0.00036249062,0.3851804,0.0055594826,0.0001567366,0.000016204936,0.000027699987,0.00003318813,0.000405677],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979721,0.0001410267,0.00039421063,0.0008298206,0.00017777625,0.00048507686],"domain_scores_gemma":[0.9990257,0.000048108664,0.00017241137,0.00028638652,0.00014524099,0.00032215627],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024909928,0.00030207817,0.00039998235,0.00019559744,0.0005226457,0.0007683708,0.00044800376,0.00007989555,0.00006132156],"category_scores_gemma":[0.000059213224,0.00029955155,0.00021668288,0.0011076726,0.00006256926,0.0006554789,0.00031531326,0.0002151346,0.000087206034],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026554748,0.000021733897,0.0014414517,0.000021424608,0.00019517259,0.000008066107,0.007850582,0.0029875706,0.9261868,0.000017501281,0.0022642743,0.058978863],"study_design_scores_gemma":[0.0005614372,0.00016743442,0.0009360001,0.000038806593,0.0002404969,0.0000075295593,0.0017283789,0.09343851,0.8880805,0.00004106607,0.014152635,0.0006072453],"about_ca_topic_score_codex":0.000102093916,"about_ca_topic_score_gemma":0.0000357325,"teacher_disagreement_score":0.51372075,"about_ca_system_score_codex":0.000031754942,"about_ca_system_score_gemma":0.0000231885,"threshold_uncertainty_score":0.99994564},"labels":[],"label_agreement":null},{"id":"W3047371217","doi":"10.1145/3447648","title":"StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":392,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Face (sociological concept); Context (archaeology); Process (computing); Space (punctuation); Sampling (signal processing); Conditional probability distribution","score_opus":0.04644017211500441,"score_gpt":0.26913343441936854,"score_spread":0.22269326230436415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047371217","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02229183,0.00012771024,0.97591764,0.000736408,0.0003492578,0.00015782923,0.0002532123,0.00009675776,0.000069329966],"genre_scores_gemma":[0.8895504,0.00014284147,0.109633915,0.0003267087,0.00007087629,0.000022633336,0.00018891889,0.000017260112,0.00004645269],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981266,0.00026684924,0.00045776158,0.00045412633,0.00040833003,0.00028629063],"domain_scores_gemma":[0.9980984,0.00026058868,0.00017825024,0.000667173,0.00069624535,0.00009937616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002631804,0.00022870436,0.00031139492,0.00028121768,0.0005274497,0.00017165786,0.0004093137,0.0001260404,0.00014389529],"category_scores_gemma":[0.00006174578,0.00024508758,0.00021829059,0.0011418376,0.00010263889,0.001786346,0.000016835464,0.00024426333,0.000009149956],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006525831,0.0011323534,0.00027985845,0.000060847826,0.00069409923,0.00015016428,0.0010156826,0.4506174,0.52270275,0.011994718,0.0013782543,0.009908587],"study_design_scores_gemma":[0.0009931669,0.00014590558,0.0004345359,0.00006602168,0.000102620914,0.000049462335,0.00025770642,0.13098277,0.8592752,0.00633115,0.0009133453,0.00044809858],"about_ca_topic_score_codex":0.000037218062,"about_ca_topic_score_gemma":0.000055351462,"teacher_disagreement_score":0.86725855,"about_ca_system_score_codex":0.00004186063,"about_ca_system_score_gemma":0.00018713876,"threshold_uncertainty_score":0.99943817},"labels":[],"label_agreement":null},{"id":"W3086609496","doi":"10.48550/arxiv.2009.05671","title":"Inverse mapping of face GANs","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Artificial intelligence; Face (sociological concept); Image (mathematics); Generative grammar; Fidelity; Computer vision; Generative model; Pattern recognition (psychology)","score_opus":0.10484738068590678,"score_gpt":0.18003378707866816,"score_spread":0.07518640639276138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3086609496","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019039782,0.000039515224,0.9767056,0.00037574285,0.00048992824,0.0001917759,0.00001511702,0.00011675164,0.003025804],"genre_scores_gemma":[0.98642284,0.000117253876,0.01264726,0.00016038469,0.00009482877,3.4918747e-7,0.000006592659,0.000012486827,0.0005380053],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983983,0.00016181855,0.00020895146,0.0008861144,0.000087396016,0.000257432],"domain_scores_gemma":[0.9984586,0.00007985814,0.00029201515,0.0008749429,0.00013570116,0.00015884535],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014199982,0.00026293867,0.00039522638,0.0001528159,0.00008745489,0.00006201752,0.0016590044,0.00018406259,0.000032849453],"category_scores_gemma":[0.00004964185,0.00030557933,0.00025604316,0.0006326483,0.000110291396,0.0003054168,0.0022013565,0.00038608946,0.00006236459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015711845,0.000058552992,0.00069706124,0.00011298414,0.0001911526,0.00020339707,0.001191969,0.95990413,0.0012489719,0.032983717,0.0023700737,0.0010222518],"study_design_scores_gemma":[0.00024531627,0.000031998323,0.00041953733,0.00007876365,0.000042094962,9.1062157e-7,0.00021094989,0.9831185,0.0016942589,0.012441168,0.001378731,0.0003378173],"about_ca_topic_score_codex":0.00013129834,"about_ca_topic_score_gemma":0.000022098298,"teacher_disagreement_score":0.967383,"about_ca_system_score_codex":0.00007574315,"about_ca_system_score_gemma":0.00016942699,"threshold_uncertainty_score":0.9999396},"labels":[],"label_agreement":null},{"id":"W3089984691","doi":"10.1109/ijcnn52387.2021.9533449","title":"Assisting the Adversary to Improve GAN Training","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency","keywords":"Discriminator; Adversary; Regularization (linguistics); Computer science; Generator (circuit theory); Norm (philosophy); Stability (learning theory); Algorithm; Perspective (graphical); Artificial intelligence; Machine learning; Computer security; Telecommunications; Power (physics); Physics","score_opus":0.03495936617294925,"score_gpt":0.2539614238375831,"score_spread":0.21900205766463382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089984691","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007729751,0.00015985011,0.9616755,0.0065277657,0.0026404916,0.00030730673,0.0000034940904,0.0001481011,0.027764497],"genre_scores_gemma":[0.75873405,0.000010059953,0.23668472,0.002611952,0.0007403354,0.000053164385,0.0000056921504,0.000017338734,0.0011426575],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777156,0.0002204247,0.00032329586,0.00092790555,0.00032973257,0.00042705232],"domain_scores_gemma":[0.9979439,0.00026876468,0.00014270794,0.0013111559,0.0001849781,0.00014848824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006701687,0.00029942338,0.00034426997,0.000063697145,0.00029572306,0.0010333358,0.0017665412,0.00014289177,0.00007346904],"category_scores_gemma":[0.0002900757,0.00020795474,0.00023485116,0.00029227315,0.000036009526,0.00022160143,0.0027426784,0.0005569336,0.000025143283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000054183947,0.00005634584,0.000053237272,0.00004931308,0.00028857696,0.000092487884,0.0120907985,0.12012199,0.0068187118,0.0033068901,0.009481855,0.8476344],"study_design_scores_gemma":[0.00024383872,0.000077852375,0.0019555376,0.0002983453,0.0000718139,0.000016413856,0.002645292,0.964627,0.015559871,0.0020200827,0.0112828715,0.0012010369],"about_ca_topic_score_codex":0.00019773023,"about_ca_topic_score_gemma":0.000083281,"teacher_disagreement_score":0.84643334,"about_ca_system_score_codex":0.00006238546,"about_ca_system_score_gemma":0.00034563296,"threshold_uncertainty_score":0.99644816},"labels":[],"label_agreement":null},{"id":"W3090228367","doi":"","title":"Batch norm with entropic regularization turns deterministic autoencoders into generative models","year":2020,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Autoencoder; Computer science; Generative model; Regularization (linguistics); Generative grammar; Encoder; Algorithm; Artificial neural network; Artificial intelligence; Encoding (memory); Matrix norm; Source code; Normalization (sociology); Theoretical computer science; Eigenvalues and eigenvectors","score_opus":0.04116235678626784,"score_gpt":0.25221367207682416,"score_spread":0.21105131529055632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3090228367","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020394158,0.000060651357,0.99151444,0.0051794765,0.00022537916,0.00036353708,0.0000032162195,0.00010707707,0.00050681375],"genre_scores_gemma":[0.9072923,0.00003114641,0.091257185,0.0011208716,0.00020339443,0.00003688584,0.000009506556,0.000015970229,0.000032755037],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976653,0.00020212906,0.0005358087,0.0007710872,0.0003817734,0.0004438931],"domain_scores_gemma":[0.99885464,0.00016541604,0.00015876093,0.0004105969,0.00020948194,0.00020109382],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020354046,0.00029458638,0.00032322117,0.00011330048,0.00017759936,0.00030303324,0.00081921084,0.000096386364,0.000043893062],"category_scores_gemma":[0.00018109955,0.00025213938,0.0000703008,0.000995218,0.00018683694,0.00074133807,0.0001747249,0.00025092502,0.00005192933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005225503,0.000050432525,0.000028744733,0.000012300505,0.000015574491,0.000036618516,0.009294292,0.88448524,0.0015783514,0.07177978,0.000038468424,0.032627933],"study_design_scores_gemma":[0.00005584618,0.00024668244,0.000012450505,0.000031747808,0.0000095743135,0.0000026496755,0.0005237999,0.9081054,0.010871869,0.07970461,0.00014080903,0.00029458434],"about_ca_topic_score_codex":0.00030897648,"about_ca_topic_score_gemma":0.0010239517,"teacher_disagreement_score":0.9052529,"about_ca_system_score_codex":0.00013747839,"about_ca_system_score_gemma":0.00020126977,"threshold_uncertainty_score":0.9999931},"labels":[],"label_agreement":null},{"id":"W3091221243","doi":"","title":"Semi-supervised Sequential Generative Models","year":2020,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"MNIST database; Computer science; Estimator; Latent variable; Generative model; Generative grammar; Machine learning; Artificial intelligence; Trajectory; Forcing (mathematics); Variance (accounting); Variable (mathematics); Deep learning; Mathematics; Statistics","score_opus":0.09722466294154446,"score_gpt":0.28411242239710377,"score_spread":0.1868877594555593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091221243","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032414766,0.00012086965,0.9871388,0.006927011,0.00042139,0.0002999617,0.000008136414,0.00013187429,0.0017104533],"genre_scores_gemma":[0.9621336,0.00004676253,0.034620907,0.0026769033,0.0004413199,0.000029723229,0.000006912974,0.000014590159,0.000029291145],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975247,0.000258744,0.00058793824,0.0007696978,0.00035088064,0.00050805084],"domain_scores_gemma":[0.9989495,0.00015210411,0.00009876578,0.00040507654,0.00016486827,0.00022965555],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032575836,0.00027409825,0.00032482084,0.000099112156,0.00016441189,0.0002840159,0.0010908842,0.000106731044,0.0001529564],"category_scores_gemma":[0.00017719675,0.00026150205,0.00012933658,0.000949108,0.00012919992,0.00081401155,0.0003085817,0.00029440972,0.00018936831],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031594263,0.00005135535,0.000008186119,0.0000048743195,0.000013338066,0.000032092707,0.0039203116,0.8264562,0.008275614,0.10155272,0.00026818737,0.059385523],"study_design_scores_gemma":[0.00004073197,0.00008585105,0.0000025772783,0.000014346578,0.000004302084,0.0000015591635,0.00034930836,0.8884271,0.05070469,0.059737813,0.0003571258,0.00027462098],"about_ca_topic_score_codex":0.00030737653,"about_ca_topic_score_gemma":0.00021858043,"teacher_disagreement_score":0.9588921,"about_ca_system_score_codex":0.0000896528,"about_ca_system_score_gemma":0.00014312967,"threshold_uncertainty_score":0.9999837},"labels":[],"label_agreement":null},{"id":"W3092182798","doi":"10.48550/arxiv.2010.03753","title":"Uncertainty in Neural Processes","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Inference; Pooling; Artificial intelligence; Posterior probability; Machine learning; Probabilistic logic; Predictive inference; Bayesian inference; Bayesian probability; Frequentist inference","score_opus":0.08180014671703624,"score_gpt":0.18861332576422818,"score_spread":0.10681317904719194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092182798","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04152574,0.00018472577,0.95408773,0.0010504304,0.0005946108,0.00031847664,0.000011862563,0.00020696108,0.0020194422],"genre_scores_gemma":[0.9978033,0.00012932636,0.0014077047,0.00027445165,0.00013152903,0.0000011850075,0.000009196943,0.000012123862,0.0002312084],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99815357,0.00016987178,0.00017877629,0.0010965475,0.00007609829,0.00032515745],"domain_scores_gemma":[0.9988132,0.00011663711,0.00015409596,0.00063357403,0.00013947862,0.00014301017],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00012230515,0.00028466352,0.00033957695,0.0001456812,0.00008269303,0.00015012565,0.0016651292,0.00016881611,0.000020538955],"category_scores_gemma":[0.000113545175,0.00031061505,0.00012188843,0.0009769257,0.00007381641,0.00040679146,0.0017510722,0.00051206106,0.00004010544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017893824,0.00003964708,0.00085998734,0.000070407215,0.000024517722,0.00032511598,0.00023237708,0.99148434,0.000019194915,0.005465681,0.0003578121,0.0011030495],"study_design_scores_gemma":[0.0002519415,0.00003229396,0.0006637683,0.00005404712,0.000016955913,0.0000011843284,0.000046227666,0.9825214,0.00009183397,0.015408741,0.00057588215,0.00033570678],"about_ca_topic_score_codex":0.0002926022,"about_ca_topic_score_gemma":0.00027442267,"teacher_disagreement_score":0.95627755,"about_ca_system_score_codex":0.00011988426,"about_ca_system_score_gemma":0.00030334143,"threshold_uncertainty_score":0.9999346},"labels":[],"label_agreement":null},{"id":"W3092253034","doi":"10.1109/tnnls.2020.3027761","title":"Clustering Analysis via Deep Generative Models With Mixture Models","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Huaqiao University; Natural Science Foundation of Fujian Province; National Natural Science Foundation of China","keywords":"Cluster analysis; Autoencoder; Computer science; Artificial intelligence; Generative grammar; Mixture model; Generative model; Pattern recognition (psychology); Outlier; Correlation clustering; Machine learning; Deep learning; Data mining","score_opus":0.018809107226406448,"score_gpt":0.20443499821908986,"score_spread":0.18562589099268342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092253034","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011597383,0.00055202725,0.99689424,0.0005174236,0.00031309936,0.0002627257,0.000002129347,0.00019571827,0.000102901424],"genre_scores_gemma":[0.9897603,0.00008424311,0.009295734,0.00041657922,0.00024992749,0.000039864914,0.0000028887148,0.00002729158,0.00012319986],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99783456,0.00047887152,0.000313307,0.0007083628,0.0002773337,0.0003875395],"domain_scores_gemma":[0.99907243,0.00014962937,0.00014947841,0.00026570458,0.000105194704,0.0002575658],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001799375,0.00032988674,0.00048770962,0.00012887373,0.0006832286,0.0004638623,0.00029628404,0.00012204713,0.000005962739],"category_scores_gemma":[0.0000016848961,0.00025861972,0.00016448689,0.001036211,0.00005246349,0.00082209765,0.000008007775,0.000684468,0.000001730526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046908353,0.000017137216,0.000008706476,0.0000116155425,0.0003614034,0.000015116267,0.0010609864,0.98535675,0.0000781823,0.000060032562,0.000016224454,0.01296694],"study_design_scores_gemma":[0.00029122806,0.00030749643,0.0000075038265,0.000022661123,0.00019711633,0.000017527185,0.00014115192,0.99859893,0.000047353937,0.00001137621,0.00004317365,0.00031448266],"about_ca_topic_score_codex":0.00012015445,"about_ca_topic_score_gemma":0.000071572336,"teacher_disagreement_score":0.98860055,"about_ca_system_score_codex":0.000025134515,"about_ca_system_score_gemma":0.000012393657,"threshold_uncertainty_score":0.9999866},"labels":[],"label_agreement":null},{"id":"W3094065920","doi":"","title":"Implicit Variational Inference: the Parameter and the Predictor Space.","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Inference; Space (punctuation); Artificial neural network; Posterior probability; Bayesian inference; Parameter space; Distribution (mathematics); Computer science; Artificial intelligence; Mathematics; Bayesian probability; Applied mathematics; Machine learning; Mathematical optimization; Statistics; Mathematical analysis","score_opus":0.05306780710344853,"score_gpt":0.18595416924019492,"score_spread":0.1328863621367464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094065920","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006696502,0.00008595946,0.98451895,0.0065671382,0.00044889917,0.00039572778,0.000019290856,0.00007102427,0.001196496],"genre_scores_gemma":[0.99591804,0.00018951544,0.0025951,0.0006711167,0.00025450016,0.0000033120746,0.000005687466,0.000008630724,0.00035409734],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839056,0.00039046447,0.00015335038,0.00072771026,0.00011109844,0.0002268248],"domain_scores_gemma":[0.99771905,0.0010522181,0.00019869249,0.00081014616,0.000117751486,0.00010215978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034074477,0.00024378476,0.0002682078,0.000045053734,0.00032685132,0.0003538157,0.0015140801,0.00014074174,0.000031795727],"category_scores_gemma":[0.00021762871,0.00015253719,0.00016073143,0.00031568276,0.00032411743,0.00023898858,0.0023837478,0.0005317729,0.000023513787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058578367,0.00002016954,0.0009742122,0.000014268224,0.00023310819,0.000021958045,0.0007864179,0.20010471,0.000014816115,0.7954907,0.0016800186,0.0006010685],"study_design_scores_gemma":[0.00043609712,0.000017997027,0.0040203715,0.000013849888,0.00007430252,0.0000014872625,0.00003127411,0.81273687,0.000016044845,0.1815259,0.00096303463,0.00016273986],"about_ca_topic_score_codex":0.00015156994,"about_ca_topic_score_gemma":0.000017814149,"teacher_disagreement_score":0.9892215,"about_ca_system_score_codex":0.000041817853,"about_ca_system_score_gemma":0.00015975088,"threshold_uncertainty_score":0.6220286},"labels":[],"label_agreement":null},{"id":"W3094191864","doi":"","title":"Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial neural network; Sampling (signal processing); Function (biology); Artificial intelligence; Training set; Goodness of fit; Energy (signal processing); Feature (linguistics); Data modeling; Machine learning; Algorithm; Mathematics; Statistics","score_opus":0.1657884621947862,"score_gpt":0.3439734482612751,"score_spread":0.17818498606648892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094191864","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057368567,0.000069053815,0.9806064,0.011280997,0.00014065954,0.00013270196,0.000004019802,0.00011266756,0.0019166763],"genre_scores_gemma":[0.9164335,0.000015564217,0.08196206,0.0010880299,0.00024559078,0.000039843813,0.000020067408,0.00001798696,0.00017735029],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838936,0.00026467795,0.00025237066,0.00048598298,0.00036801727,0.00023960164],"domain_scores_gemma":[0.99887466,0.00050669664,0.00020360736,0.00012458886,0.00020014476,0.00009031175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005813929,0.00019416305,0.00019780602,0.000058990525,0.00048730618,0.0004924513,0.0005680693,0.000040846717,0.00003163981],"category_scores_gemma":[0.0006461898,0.00014801907,0.00008175422,0.00011445347,0.000045910663,0.0003616203,0.0001630381,0.000393723,0.000002393877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005697136,0.000010261154,0.00043370613,0.000006426517,0.000045498582,0.000001268869,0.0028716703,0.668367,0.0022927888,0.12669626,0.000006009805,0.19921213],"study_design_scores_gemma":[0.0004910691,0.0003395466,0.000055455315,0.00006420003,0.000010652312,0.0000016775311,0.00032093556,0.990494,0.000284058,0.0056480183,0.0021118673,0.00017850751],"about_ca_topic_score_codex":0.00005542408,"about_ca_topic_score_gemma":0.000010907246,"teacher_disagreement_score":0.9106966,"about_ca_system_score_codex":0.000023690665,"about_ca_system_score_gemma":0.00008889322,"threshold_uncertainty_score":0.6036042},"labels":[],"label_agreement":null},{"id":"W3096831136","doi":"10.1145/3422622","title":"Generative adversarial networks","year":2020,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":13622,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Generative grammar; Computer science; Adversarial system; Artificial intelligence; Generative Design; Machine learning; Generative model; Variety (cybernetics); Generative adversarial network; Deep learning","score_opus":0.05331489208555869,"score_gpt":0.25914233121555963,"score_spread":0.20582743913000096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3096831136","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002534975,0.0009048269,0.7211376,0.27387857,0.000314997,0.00021319691,0.000004091875,0.000056616143,0.0032366135],"genre_scores_gemma":[0.6458602,0.00010222597,0.35242993,0.0014636092,0.00010536877,0.0000079696065,0.0000017761581,0.0000044520516,0.000024463146],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991148,0.00029479022,0.00019626484,0.000160802,0.000116308416,0.00011702266],"domain_scores_gemma":[0.98213387,0.0002464248,0.0001423123,0.017311366,0.00011146043,0.00005454905],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00014879703,0.00008480739,0.00013067956,0.0000143033885,0.00028237997,0.000047683443,0.035399597,0.00003687773,0.000008940502],"category_scores_gemma":[0.0031498321,0.00006147038,0.00011009065,0.0004378811,0.00017235435,0.00022073311,0.027292771,0.0001642531,0.000011333802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042948624,0.00029561023,0.001669282,0.000014899824,0.00036711918,0.0000010227826,0.007507393,0.2461294,0.015832677,0.23356825,0.45498317,0.03958823],"study_design_scores_gemma":[0.00029257897,0.0000424712,0.0010022692,0.0000138960995,0.000023585066,9.981933e-7,0.00006174556,0.94957685,0.0061903237,0.018348532,0.024298007,0.00014872492],"about_ca_topic_score_codex":0.000016550892,"about_ca_topic_score_gemma":0.00000871448,"teacher_disagreement_score":0.70344746,"about_ca_system_score_codex":0.000012863333,"about_ca_system_score_gemma":0.00004931738,"threshold_uncertainty_score":0.9805743},"labels":[],"label_agreement":null},{"id":"W3100754158","doi":"","title":"CcGAN: Continuous Conditional Generative Adversarial Networks for Image Generation","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Discriminator; Categorical variable; Generator (circuit theory); Computer science; Regression; Benchmark (surveying); Scalar (mathematics); Algorithm; Generative adversarial network; Artificial intelligence; Mathematics; Pattern recognition (psychology); Image (mathematics); Machine learning; Statistics","score_opus":0.061834860776070075,"score_gpt":0.18121168452299322,"score_spread":0.11937682374692314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3100754158","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038381636,0.00003473362,0.9933757,0.001138627,0.00051047624,0.00040271867,0.00003672138,0.00013712102,0.0005257318],"genre_scores_gemma":[0.9702439,0.000023303424,0.026301887,0.0014990298,0.0015226298,0.000003729162,0.00009554201,0.000016208542,0.00029378224],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984129,0.00015410231,0.00019941802,0.0007922846,0.00008346432,0.00035783605],"domain_scores_gemma":[0.998894,0.00014015893,0.0001528015,0.00029339455,0.00029091246,0.00022877938],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015533027,0.00023429276,0.0002690193,0.00005628945,0.00038329914,0.0001754719,0.00059923506,0.00011291355,0.00007160774],"category_scores_gemma":[0.000086982,0.0002579081,0.00019386069,0.00045738558,0.00011145794,0.0010423489,0.00017738341,0.00014275456,0.000045805133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077386765,0.000051267856,0.00007236607,0.0000049616315,0.00009859299,0.00006998209,0.00020358007,0.8627915,0.0042603654,0.11389806,0.017648134,0.00082381896],"study_design_scores_gemma":[0.0012974143,0.00019053926,0.000061048246,0.0000032539403,0.00004263108,0.0000026451135,0.000050813476,0.98902816,0.003152498,0.0020963156,0.003770175,0.0003044808],"about_ca_topic_score_codex":0.000013041401,"about_ca_topic_score_gemma":0.000012706507,"teacher_disagreement_score":0.9670738,"about_ca_system_score_codex":0.00006763457,"about_ca_system_score_gemma":0.0000916176,"threshold_uncertainty_score":0.9999873},"labels":[],"label_agreement":null},{"id":"W3104195492","doi":"","title":"Relational autoencoder for feature extraction","year":2017,"lang":"en","type":"article","venue":"UTS ePRESS (University of Technology Sydney)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":198,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Autoencoder; Computer science; Feature extraction; Artificial intelligence; Pattern recognition (psychology); Feature (linguistics); Data mining; Artificial neural network","score_opus":0.024181451738318607,"score_gpt":0.23794832393650203,"score_spread":0.2137668721981834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3104195492","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029630626,0.00007016264,0.97969455,0.014581511,0.00030579008,0.00014292648,0.000013943818,0.00011510426,0.0021129397],"genre_scores_gemma":[0.5725609,0.00001947976,0.42512658,0.000023552082,0.000036594913,7.9807216e-7,0.00000435031,0.0000043044556,0.0022234477],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938756,0.0000144611,0.00005881396,0.00028937578,0.00009613538,0.00015366316],"domain_scores_gemma":[0.99886847,0.000043998043,0.0002163496,0.0006895596,0.00014895028,0.000032701715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010101351,0.00008626745,0.00015436637,0.00016569253,0.00074424787,0.00003393073,0.0011009816,0.00022813912,0.000019823294],"category_scores_gemma":[0.000109388326,0.00009606887,0.00008546833,0.00008906456,0.0002431696,0.00082302646,0.00032975964,0.000138247,0.000008821734],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011575579,0.0002665061,0.017481113,0.00004792856,0.000387441,0.000064846,0.00073581905,0.0046773925,0.020691197,0.5974716,0.058108382,0.29995206],"study_design_scores_gemma":[0.0021510457,0.0002268411,0.118611895,0.000088652414,0.000110080146,0.00003138696,0.00033001188,0.5910655,0.016965706,0.05253104,0.21726908,0.0006187231],"about_ca_topic_score_codex":0.000053783257,"about_ca_topic_score_gemma":0.00004065979,"teacher_disagreement_score":0.5863882,"about_ca_system_score_codex":0.00002293198,"about_ca_system_score_gemma":0.000034410215,"threshold_uncertainty_score":0.5724228},"labels":[],"label_agreement":null},{"id":"W3106068426","doi":"","title":"Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Discriminator; Generator (circuit theory); Computer science; Sampling (signal processing); Parameter space; Algorithm; Energy (signal processing); Space (punctuation); Artificial intelligence; Statistics; Mathematics; Physics; Power (physics); Detector; Quantum mechanics","score_opus":0.23681087073815404,"score_gpt":0.21538186680014165,"score_spread":0.021429003938012392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3106068426","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16554515,0.000013018631,0.8333557,0.0007799206,0.00004671734,0.00006616962,0.000011977836,0.000100922334,0.00008039594],"genre_scores_gemma":[0.98390347,0.00003010711,0.01320254,0.0026300054,0.000057330733,3.8054466e-7,0.0000070026003,0.000016403283,0.00015278648],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986118,0.00008555609,0.00012656595,0.0007855855,0.000089390785,0.00030107138],"domain_scores_gemma":[0.99897677,0.000047482496,0.00008137113,0.0004267086,0.00009233589,0.00037531048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006714512,0.0002173854,0.00020429037,0.00007476029,0.00022783718,0.00020842609,0.00057629554,0.000085461885,0.00001381945],"category_scores_gemma":[0.00001929381,0.00022436505,0.00009524857,0.00037254975,0.000081664395,0.0012152615,0.00021048046,0.00012610329,0.000005725849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003537483,0.00004674365,0.0026530295,0.000008146444,0.000029798719,0.00006405512,0.00066459144,0.97033423,0.0019505192,0.023464326,0.00016339788,0.00058576703],"study_design_scores_gemma":[0.00039067498,0.000099617624,0.00054335984,0.00001113082,0.00004247022,9.0842934e-7,0.00007149926,0.9952845,0.0014252571,0.0014391677,0.0004044486,0.00028699712],"about_ca_topic_score_codex":0.00014349022,"about_ca_topic_score_gemma":0.000040012852,"teacher_disagreement_score":0.8201532,"about_ca_system_score_codex":0.000039187238,"about_ca_system_score_gemma":0.000068848494,"threshold_uncertainty_score":0.9149341},"labels":[],"label_agreement":null},{"id":"W3107020245","doi":"10.48550/arxiv.1910.06922","title":"Gradient penalty from a maximum margin perspective","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Discriminator; Margin (machine learning); Hinge loss; Maximization; Norm (philosophy); Computer science; Mathematical optimization; Gradient method; Mathematics; Applied mathematics; Algorithm; Artificial intelligence; Law; Support vector machine; Machine learning","score_opus":0.05205662847975387,"score_gpt":0.18001309943661284,"score_spread":0.12795647095685897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3107020245","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04128548,0.00025026195,0.9467496,0.00042217926,0.0017342197,0.00044068106,0.00006932915,0.00017972031,0.008868492],"genre_scores_gemma":[0.9907719,0.0001885621,0.006385354,0.0001829455,0.00026332567,0.0000014255955,0.000024096005,0.000024608187,0.0021577822],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99704146,0.00029183214,0.0002051855,0.0018341364,0.00014218003,0.00048520052],"domain_scores_gemma":[0.99729496,0.00016587024,0.0002864326,0.001733147,0.00030857796,0.00021098075],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020063565,0.00045873973,0.0005143375,0.0002157868,0.0001768053,0.00024298356,0.002216927,0.00028731927,0.00016152964],"category_scores_gemma":[0.000042428965,0.0004961808,0.00040070852,0.00045203135,0.000114630224,0.00046190165,0.002778715,0.0006766038,0.00045351786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007607909,0.00021241662,0.001820226,0.000028351433,0.00049168325,0.00049660227,0.001345627,0.8687763,0.00009727164,0.121904925,0.0037149715,0.001035504],"study_design_scores_gemma":[0.0005489744,0.0000629374,0.0026769273,0.00008663013,0.0001040128,0.0000020251716,0.00037835623,0.84036934,0.00024854683,0.15324472,0.0015758363,0.0007016625],"about_ca_topic_score_codex":0.0021991152,"about_ca_topic_score_gemma":0.00015480781,"teacher_disagreement_score":0.94948643,"about_ca_system_score_codex":0.00054708414,"about_ca_system_score_gemma":0.00026724106,"threshold_uncertainty_score":0.999749},"labels":[],"label_agreement":null},{"id":"W3107195298","doi":"10.1109/access.2020.3041480","title":"Conditional Activation GAN: Improved Auxiliary Classifier GAN","year":2020,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"National Research Foundation of Korea","keywords":"Discriminator; Generative adversarial network; Classifier (UML); Normalization (sociology); Computer science; Hyperparameter; Computation; Generative grammar; Pattern recognition (psychology); Algorithm; Artificial intelligence; Deep learning","score_opus":0.2569520545195722,"score_gpt":0.5006444155062364,"score_spread":0.2436923609866642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3107195298","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03275821,0.0015673959,0.94842356,0.006650879,0.0010099523,0.00068683753,0.000048605434,0.00012060846,0.008733932],"genre_scores_gemma":[0.99166304,0.0005171096,0.003972622,0.0029790709,0.00062015746,0.000027554324,0.000021929938,0.000028356853,0.00017016398],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9974216,0.00031952898,0.0006641314,0.000614501,0.00061485585,0.00036535252],"domain_scores_gemma":[0.99780095,0.0003255946,0.0006749912,0.0004411547,0.000396623,0.0003606959],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00060323684,0.00029862337,0.0005377895,0.00026650415,0.00034295677,0.0018402422,0.0033380992,0.00010888961,0.003960714],"category_scores_gemma":[0.0003658018,0.00027225426,0.00020009873,0.001044517,0.000115106326,0.0057454547,0.00075238483,0.00038896248,0.00003409188],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015452178,0.0002250423,0.013620537,0.00004490713,0.0002735939,0.000029792624,0.00037601628,0.0045808633,0.7809234,0.0012077731,0.1624144,0.03614912],"study_design_scores_gemma":[0.0012699392,0.00005317101,0.3127217,0.00019823553,0.00007204042,0.00001257173,0.00009235141,0.14558259,0.4796897,0.01646674,0.042808782,0.0010321852],"about_ca_topic_score_codex":0.00012405185,"about_ca_topic_score_gemma":0.0000064732803,"teacher_disagreement_score":0.9589048,"about_ca_system_score_codex":0.00007272365,"about_ca_system_score_gemma":0.00023217301,"threshold_uncertainty_score":0.99997294},"labels":[],"label_agreement":null},{"id":"W3107547765","doi":"10.1007/978-3-030-58452-8_10","title":"House-GAN: Relational Generative Adversarial Networks for Graph-Constrained House Layout Generation","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":259,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Theoretical computer science; Adjacency list; Graph; Algorithm","score_opus":0.02765445398485078,"score_gpt":0.2303174894395121,"score_spread":0.20266303545466133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3107547765","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009943626,0.0003698204,0.99069136,0.0022205103,0.0046775932,0.0010532076,0.000028745086,0.00040744897,0.000541341],"genre_scores_gemma":[0.19294716,0.000054702312,0.7960577,0.0032972514,0.0072555663,0.00005395818,0.000048695132,0.00013283709,0.00015215925],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953207,0.00010818711,0.0007886562,0.0021404838,0.0008844348,0.0007575705],"domain_scores_gemma":[0.9970322,0.00074059307,0.000495838,0.0009351885,0.00050818024,0.00028800202],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008115285,0.00078017125,0.00076520024,0.0005059065,0.0006935871,0.0007591862,0.0019227155,0.0005291905,0.000021384361],"category_scores_gemma":[0.00024359702,0.0007433959,0.00035651744,0.0006594531,0.00071959506,0.0010072475,0.0005479179,0.00079393614,0.000024495132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024335532,0.000022244009,0.000010659489,0.000009260801,0.000052264862,0.000026052248,0.00048779446,0.8856007,0.00037728305,0.03271889,0.00075205293,0.07991846],"study_design_scores_gemma":[0.00070143654,0.0002784688,0.000016879383,0.000079682635,0.00003225552,0.000017451799,2.940351e-7,0.9643267,0.001258159,0.03054473,0.0019533536,0.0007906227],"about_ca_topic_score_codex":0.000012924354,"about_ca_topic_score_gemma":0.000113141374,"teacher_disagreement_score":0.19463372,"about_ca_system_score_codex":0.00027202454,"about_ca_system_score_gemma":0.0008109013,"threshold_uncertainty_score":0.9995017},"labels":[],"label_agreement":null},{"id":"W3108330873","doi":"10.1109/cvpr46437.2021.00785","title":"HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histograms","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Artificial intelligence; Computer science; Histogram; Color histogram; Color normalization; Computer vision; Histogram equalization; Feature (linguistics); Color image; Focus (optics); Image (mathematics); Semantics (computer science); Histogram matching; Pattern recognition (psychology); Image processing","score_opus":0.013312927670489812,"score_gpt":0.22509190238787716,"score_spread":0.21177897471738735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108330873","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022990294,0.0021043,0.9690286,0.0006057123,0.0013922962,0.0004458161,0.000013989544,0.0001423841,0.00327659],"genre_scores_gemma":[0.840576,0.0006739996,0.1575327,0.00016660977,0.00015862647,0.000037072678,0.000034178945,0.000022220294,0.0007985652],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99746364,0.00029472355,0.00061362423,0.00095523277,0.0003124199,0.00036034128],"domain_scores_gemma":[0.99787235,0.0002074995,0.00043288252,0.0007711842,0.0005573109,0.00015878653],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004430312,0.00040042322,0.00090589054,0.00013624046,0.00015067976,0.00031951294,0.00072269177,0.00030281034,0.0000631724],"category_scores_gemma":[0.000074031756,0.00036820013,0.00021202669,0.0002703954,0.0002158772,0.00023541383,0.0009310424,0.0003350303,0.000002631032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025841966,0.0010225648,0.0021167153,0.00076586165,0.001973053,0.00047054875,0.0046683233,0.17969278,0.6378053,0.0062008486,0.018781401,0.14624421],"study_design_scores_gemma":[0.0011151242,0.00022650165,0.0009746854,0.00014742969,0.00017134233,0.00001841192,0.00014567495,0.85689354,0.13697729,0.000574427,0.0018441553,0.00091141753],"about_ca_topic_score_codex":0.0023555337,"about_ca_topic_score_gemma":0.0003002014,"teacher_disagreement_score":0.8175857,"about_ca_system_score_codex":0.0001226458,"about_ca_system_score_gemma":0.00028523573,"threshold_uncertainty_score":0.999877},"labels":[],"label_agreement":null},{"id":"W3109507914","doi":"10.1007/s00530-020-00714-0","title":"A TextCNN and WGAN-gp based deep learning frame for unpaired text style transfer in multimedia services","year":2020,"lang":"en","type":"article","venue":"Multimedia Systems","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"Yunnan Provincial Science and Technology Department","keywords":"Computer science; Style (visual arts); Sentence; Natural language processing; Encoder; Multimedia; Representation (politics); Artificial intelligence; Frame (networking); Information retrieval; Feature (linguistics); Linguistics; Telecommunications","score_opus":0.016023210428324587,"score_gpt":0.2154907238792844,"score_spread":0.1994675134509598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3109507914","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00738564,0.0012005852,0.9880683,0.0013350861,0.00054618507,0.001178749,0.000019212559,0.00020021212,0.000066028115],"genre_scores_gemma":[0.89071274,0.000018494156,0.1081914,0.0004198261,0.00037706326,0.00018157165,0.000022607774,0.00003246025,0.00004381473],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99773425,0.00030625478,0.00046424902,0.0007211625,0.00028791302,0.00048615102],"domain_scores_gemma":[0.99849343,0.0007498338,0.00008925571,0.00026714263,0.00011158095,0.00028878156],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044200508,0.0003020186,0.0004981537,0.00012148295,0.00015526137,0.0003064142,0.00052248227,0.00016908562,0.00001533752],"category_scores_gemma":[0.00016920747,0.000274184,0.0001011846,0.0004157938,0.00005940233,0.0004798113,0.00007953163,0.00024016974,0.000035765464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039912332,0.00044362075,0.018129975,0.002197858,0.0002818994,0.00011379539,0.07720384,0.19040008,0.07754872,0.00014719943,0.0007438531,0.63239],"study_design_scores_gemma":[0.0019323907,0.00014982457,0.0009316384,0.000110321125,0.00001539819,0.0000015993849,0.000651163,0.98803407,0.0014204885,0.0000052520245,0.0064296382,0.0003182368],"about_ca_topic_score_codex":0.0003641611,"about_ca_topic_score_gemma":0.0001672689,"teacher_disagreement_score":0.8833271,"about_ca_system_score_codex":0.000037174308,"about_ca_system_score_gemma":0.0000482676,"threshold_uncertainty_score":0.99997103},"labels":[],"label_agreement":null},{"id":"W3110500283","doi":"10.48550/arxiv.2004.04795","title":"Exemplar VAE: Linking Generative Models, Nearest Neighbor Retrieval, and\\n Data Augmentation","year":2020,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"MNIST database; Generative model; Artificial intelligence; Computer science; Pattern recognition (psychology); k-nearest neighbors algorithm; Estimator; Nearest neighbor search; Generative grammar; Mathematics; Artificial neural network; Statistics","score_opus":0.22246553511100883,"score_gpt":0.23110567694988893,"score_spread":0.008640141838880094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110500283","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012675118,0.00073731685,0.9815565,0.0011576593,0.0015169875,0.0009429749,0.00031334406,0.00017042427,0.0009297147],"genre_scores_gemma":[0.96665907,0.0050997697,0.025580881,0.00058200967,0.0008861197,0.000001102606,0.0005339032,0.00006741506,0.0005897011],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99236745,0.0010200548,0.000711231,0.004688749,0.00035456443,0.00085796166],"domain_scores_gemma":[0.99434245,0.00038356872,0.00086535176,0.0032219116,0.0005149412,0.00067178876],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008360265,0.0010082745,0.001001797,0.0002817103,0.001197098,0.001275485,0.0044469964,0.0005964811,0.00011671175],"category_scores_gemma":[0.00015452708,0.0012133967,0.00025289846,0.0015291136,0.0004663242,0.0040671066,0.011390876,0.0013185189,0.00009221351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041337052,0.00013726823,0.00025423642,0.00013870078,0.0005326596,0.00050655816,0.0018080893,0.9612098,0.00083081884,0.02941673,0.0013006297,0.0034511648],"study_design_scores_gemma":[0.0011509857,0.00019416325,0.00025275446,0.000253553,0.00047797442,0.000008678007,0.000350556,0.97003484,0.00079806807,0.024005026,0.0013217507,0.0011516362],"about_ca_topic_score_codex":0.00042188927,"about_ca_topic_score_gemma":0.000103015074,"teacher_disagreement_score":0.9559756,"about_ca_system_score_codex":0.0003210899,"about_ca_system_score_gemma":0.0007127746,"threshold_uncertainty_score":0.9997613},"labels":[],"label_agreement":null},{"id":"W3111025744","doi":"10.1007/978-3-030-88210-5_5","title":"Conditional Generation of Medical Images via Disentangled Adversarial Inference","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Inference; Regularization (linguistics); Adversarial system; Artificial intelligence; Image (mathematics); Content (measure theory); Machine learning; Algorithm; Mathematics","score_opus":0.02258513356379293,"score_gpt":0.26399085297556135,"score_spread":0.24140571941176842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111025744","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000033385953,0.0004108008,0.9947155,0.0013121351,0.0024041652,0.00021076598,0.00001853451,0.000043658434,0.0008510148],"genre_scores_gemma":[0.67892814,0.00016555464,0.31695202,0.0010826766,0.00252197,0.000010941015,0.000093058596,0.00002924628,0.00021637235],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995546,0.000096735464,0.00064572797,0.0012060214,0.002079777,0.00042576794],"domain_scores_gemma":[0.9975098,0.0005797944,0.00035050022,0.0008574419,0.0004950274,0.00020746919],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00083938026,0.00041834833,0.0005954324,0.0003961148,0.00019913958,0.00033096914,0.002314493,0.0003767141,0.0003289566],"category_scores_gemma":[0.00032202492,0.00038572156,0.00018522964,0.00046766404,0.00087782944,0.0006699888,0.0012964555,0.0005658728,0.000014553169],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000116549145,0.00014153948,0.00011456938,0.00005912405,0.00008416131,0.00034335122,0.00048692644,0.19076341,0.0046640383,0.06013646,0.00042909183,0.74276567],"study_design_scores_gemma":[0.00038690004,0.00009552399,0.000080959464,0.0002256952,0.000014823248,0.000032197942,1.5376071e-7,0.95005065,0.015071853,0.033101834,0.00047695707,0.0004624561],"about_ca_topic_score_codex":0.000034324436,"about_ca_topic_score_gemma":0.000102322476,"teacher_disagreement_score":0.75928724,"about_ca_system_score_codex":0.00015545674,"about_ca_system_score_gemma":0.0012418536,"threshold_uncertainty_score":0.99985945},"labels":[],"label_agreement":null},{"id":"W3116383660","doi":"10.1162/neco_a_01416","title":"Least kth-Order and Rényi Generative Adversarial Networks","year":2021,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Generator (circuit theory); MNIST database; Parameterized complexity; Discriminator; Function (biology); Measure (data warehouse); Minimax; Distortion (music)","score_opus":0.013367779135035165,"score_gpt":0.23252476752363985,"score_spread":0.21915698838860467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116383660","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014160779,0.00038750083,0.98166937,0.0019055663,0.0011238388,0.00011212207,0.0000015306794,0.00008467779,0.00055460253],"genre_scores_gemma":[0.91537166,0.000028956489,0.082919315,0.0009478926,0.0005643227,0.0000059321965,0.000023830364,0.000010187735,0.00012791273],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986369,0.00024871444,0.00020566228,0.0004804285,0.0001874011,0.00024089032],"domain_scores_gemma":[0.999214,0.00014706701,0.00008503172,0.00018250466,0.00027794956,0.00009346951],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011167386,0.00016650479,0.0001809612,0.0000446303,0.00026030448,0.00033149956,0.00015936441,0.00006694158,0.000017214139],"category_scores_gemma":[0.00006248905,0.00016096029,0.00005285603,0.00042894413,0.00004944646,0.00061347557,0.00020793626,0.00015030942,0.000009023595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017272292,0.000039317314,0.00026354866,0.000004917119,0.000035962712,0.000050291394,0.0004041003,0.84883034,0.0021347746,0.0032225407,0.0019775536,0.14301938],"study_design_scores_gemma":[0.0004941599,0.000055432563,0.0026729223,0.0000068395498,0.000011594542,0.000031784613,0.000033369575,0.99377155,0.0012883338,0.00085107813,0.00060353347,0.00017941333],"about_ca_topic_score_codex":0.000018781013,"about_ca_topic_score_gemma":0.000025821775,"teacher_disagreement_score":0.90121084,"about_ca_system_score_codex":0.000025046995,"about_ca_system_score_gemma":0.00005929681,"threshold_uncertainty_score":0.656377},"labels":[],"label_agreement":null},{"id":"W3118369280","doi":"10.48550/arxiv.2101.00734","title":"Factor Analysis, Probabilistic Principal Component Analysis, Variational Inference, and Variational Autoencoder: Tutorial and Survey","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Principal component analysis; Dimensionality reduction; Autoencoder; Latent variable; Probabilistic logic; Generative model; Curse of dimensionality; Factor analysis; Computer science; Artificial intelligence; Inference; Expectation–maximization algorithm; Joint probability distribution; Pattern recognition (psychology); Mathematics; Algorithm; Machine learning; Generative grammar; Deep learning; Statistics","score_opus":0.06299836203886927,"score_gpt":0.20791187455102358,"score_spread":0.1449135125121543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118369280","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11499813,0.000073144656,0.88377696,0.00005120682,0.00052194623,0.00022680352,0.00021365365,0.00006226051,0.0000759155],"genre_scores_gemma":[0.9813291,0.00012013825,0.017599802,0.00003304173,0.00017058125,0.0000024256212,0.00060363655,0.000009339283,0.00013195747],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964264,0.0008987153,0.00040556447,0.001661017,0.00026618916,0.00034210496],"domain_scores_gemma":[0.99704754,0.0008626115,0.00041823302,0.0008063636,0.0006026844,0.00026259362],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006692751,0.00042169736,0.00082893024,0.0006574114,0.00030270894,0.0006760007,0.0007261962,0.00029892108,0.00011063323],"category_scores_gemma":[0.00029167588,0.00045960105,0.00031936172,0.002290881,0.0001517584,0.0004947654,0.0019007466,0.0004280169,0.0000026541043],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022413426,0.00010921272,0.09723825,0.000019530064,0.0037373635,0.000029704643,0.00021571919,0.86381465,0.000008838422,0.03471543,0.000010626222,0.00007823692],"study_design_scores_gemma":[0.00021255318,0.000014942523,0.41910592,0.0000067365727,0.0010903885,5.2979135e-7,0.000006561724,0.5772987,0.0000020137395,0.0019629302,0.000025366662,0.00027338427],"about_ca_topic_score_codex":0.0014479813,"about_ca_topic_score_gemma":0.0020963438,"teacher_disagreement_score":0.8663309,"about_ca_system_score_codex":0.00018399382,"about_ca_system_score_gemma":0.00056053366,"threshold_uncertainty_score":0.99978554},"labels":[],"label_agreement":null},{"id":"W3119931323","doi":"10.1007/s42979-020-00403-9","title":"RGAN: Rényi Generative Adversarial Network","year":2021,"lang":"en","type":"article","venue":"SN Computer Science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ericsson (Canada)","funders":"","keywords":"Discriminator; Generative grammar; Adversarial system; Function (biology); Stability (learning theory); Computer science; Generative adversarial network; Artificial intelligence; Machine learning; Deep learning; Telecommunications","score_opus":0.011080564407144874,"score_gpt":0.22312205414594316,"score_spread":0.21204148973879827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119931323","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010508343,0.0002597406,0.9869703,0.0020571004,0.0061621876,0.00012859043,0.0000019342401,0.00017009892,0.0031992241],"genre_scores_gemma":[0.30366024,0.000023729704,0.6908279,0.0024705867,0.002730167,0.00000792311,0.0000027905176,0.0000109175635,0.00026570464],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965454,0.00021203185,0.00033279025,0.0012596799,0.00076763076,0.0008824742],"domain_scores_gemma":[0.9976803,0.00014720303,0.00012594585,0.0011422462,0.000604102,0.00030020223],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00087171106,0.00027183117,0.00030689535,0.000109742745,0.0009510776,0.0011391895,0.002090107,0.000068399844,0.00006479543],"category_scores_gemma":[0.000082274724,0.00025173373,0.0001337885,0.0027596876,0.0004197897,0.0017433476,0.0017869415,0.00021164888,0.00013483696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016797901,0.00027500262,0.0007501793,0.000013471422,0.000109163055,0.00055736315,0.0024480212,0.37644142,0.016973907,0.216103,0.071086906,0.31522477],"study_design_scores_gemma":[0.00040841528,0.0000998947,0.0014843295,0.000026738173,0.000008808551,0.000070601185,0.000012083174,0.94304305,0.029842481,0.006873906,0.017657941,0.0004717578],"about_ca_topic_score_codex":0.000012183612,"about_ca_topic_score_gemma":0.0000165777,"teacher_disagreement_score":0.56660163,"about_ca_system_score_codex":0.00010254981,"about_ca_system_score_gemma":0.0008926324,"threshold_uncertainty_score":0.9999935},"labels":[],"label_agreement":null},{"id":"W3121130100","doi":"10.48550/arxiv.2101.11744","title":"On the mapping between Hopfield networks and Restricted Boltzmann Machines","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Boltzmann machine; MNIST database; Binary number; Initialization; Restricted Boltzmann machine; Uncorrelated; Gaussian; Computer science; Boltzmann constant; Theoretical computer science; Artificial intelligence; Hopfield network; Statistical physics; Statistical mechanics; Algorithm; Machine learning; Artificial neural network; Pattern recognition (psychology); Mathematics; Physics","score_opus":0.06333163699085079,"score_gpt":0.1767309694938363,"score_spread":0.1133993325029855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121130100","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13513517,0.00023238678,0.86176354,0.00084345776,0.0004501439,0.00021338089,0.0000047019994,0.00009562243,0.0012616315],"genre_scores_gemma":[0.997091,0.00046294805,0.0012523548,0.00038837918,0.0002925959,0.000001121357,0.000014296339,0.000014178519,0.0004831544],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980189,0.0003908892,0.00018320698,0.0009819911,0.00009117612,0.00033384215],"domain_scores_gemma":[0.9977477,0.0007465503,0.00019509693,0.0010709668,0.00011579896,0.00012386582],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023304278,0.00032267772,0.000348328,0.00013478922,0.00037090143,0.00041041293,0.0012193756,0.00026944946,0.000026096059],"category_scores_gemma":[0.000104460014,0.0002726851,0.00016557494,0.0006237388,0.00010440957,0.00023320221,0.002138554,0.0008081426,0.0000063418506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001542615,0.000046963887,0.0050805197,0.000029345096,0.00031923503,0.00034957967,0.00027164494,0.9428019,0.000024108289,0.040004443,0.002708343,0.008348511],"study_design_scores_gemma":[0.00017114439,0.000032700576,0.009250883,0.00013092389,0.000054921537,0.000001921743,0.00006734953,0.98076004,0.000040085055,0.0087871775,0.00034521555,0.00035762324],"about_ca_topic_score_codex":0.00019838638,"about_ca_topic_score_gemma":0.00003433446,"teacher_disagreement_score":0.8619558,"about_ca_system_score_codex":0.000049687584,"about_ca_system_score_gemma":0.00007483596,"threshold_uncertainty_score":0.9999725},"labels":[],"label_agreement":null},{"id":"W3122717230","doi":"10.1109/scisisis50064.2020.9322714","title":"Unsupervised Feature Learning for Output Control of Generative Models","year":2020,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Global Institution for Collaborative Research and Education, Hokkaido University; Japan Society for the Promotion of Science; Hokkaido University; Telecommunications Advancement Foundation; Institute for Catastrophic Loss Reduction","keywords":"Artificial intelligence; Computer science; Cluster analysis; Generative model; Class (philosophy); Pattern recognition (psychology); Generative grammar; Unsupervised learning; Point (geometry); Feature (linguistics); Data modeling; Machine learning; Mathematics","score_opus":0.03299584363253637,"score_gpt":0.2239093068096609,"score_spread":0.19091346317712454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122717230","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017725806,0.0001659009,0.98813665,0.009774414,0.00007570749,0.00026897644,0.000004130142,0.00006357296,0.0013333791],"genre_scores_gemma":[0.7731927,0.0000069953912,0.22443724,0.0017320269,0.0001507094,0.000014710671,0.0000023445432,0.000006863513,0.00045638817],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999167,0.00008899338,0.00014683219,0.00029306422,0.00012726692,0.00017681843],"domain_scores_gemma":[0.9993708,0.00013786336,0.00006870297,0.00014282142,0.00018862716,0.00009114233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000114558345,0.00011854381,0.00023807814,0.000022650955,0.00009472162,0.00006111309,0.00035558114,0.00005106321,0.000011228312],"category_scores_gemma":[0.000079692974,0.0000934263,0.00011662347,0.00015906722,0.000023734763,0.0003647272,0.00006699139,0.00009000466,0.0000035454168],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005002613,0.000025332427,0.000050935185,0.000017414755,0.00009197254,0.0000014359898,0.0018879867,0.9092283,0.024573576,0.03354253,0.007988795,0.02254168],"study_design_scores_gemma":[0.0007183084,0.00017803194,0.000018008703,0.000003804481,0.0000110446135,3.4442715e-7,0.00006505995,0.9809661,0.014008043,0.0009186599,0.0030020177,0.00011056989],"about_ca_topic_score_codex":0.0000061699066,"about_ca_topic_score_gemma":0.0000014635198,"teacher_disagreement_score":0.7730155,"about_ca_system_score_codex":0.000007172223,"about_ca_system_score_gemma":0.000041221338,"threshold_uncertainty_score":0.38098142},"labels":[],"label_agreement":null},{"id":"W3124178031","doi":"10.15353/jcvis.v6i1.3536","title":"Pal-GAN: Palette-conditioned Generative Adversarial Networks","year":2021,"lang":"en","type":"article","venue":"Journal of Computational Vision and Imaging Systems","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Palette (painting); Artificial intelligence; Adversarial system; Generative grammar; Image translation; Intersection (aeronautics); Image (mathematics); Variety (cybernetics); Segmentation; Discriminative model; Class (philosophy); Machine learning","score_opus":0.006727752864173138,"score_gpt":0.2368859368188145,"score_spread":0.23015818395464138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3124178031","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027752216,0.0025227827,0.9887518,0.0031981026,0.0023375638,0.00007447905,0.0000034689006,0.000019470684,0.00031706164],"genre_scores_gemma":[0.9628324,0.00006964081,0.03497737,0.00086676003,0.0011483326,0.0000015815187,0.00001010247,0.000009778372,0.00008403975],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980805,0.00039591396,0.0006218975,0.00022371898,0.00048571904,0.00019223303],"domain_scores_gemma":[0.9979049,0.00036417058,0.00047917428,0.00014756645,0.00095428224,0.00014993602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056793797,0.00016997305,0.00035153914,0.000137427,0.00025769172,0.0006442873,0.0002357785,0.00004373592,0.000018227905],"category_scores_gemma":[0.00009135058,0.00013956596,0.0001357947,0.00028087918,0.0000606242,0.0009733037,0.00008656969,0.00020096022,0.000004754019],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002293891,0.0000782986,0.00050247944,0.000014065501,0.00011721258,0.00021388248,0.0004144383,0.95803916,0.0013490159,0.007819325,0.018299386,0.013129784],"study_design_scores_gemma":[0.0009618646,0.00007138379,0.0037193766,0.00012862428,0.000021976275,0.00070888107,0.00019185901,0.9862103,0.00022135129,0.0022617383,0.005326173,0.000176488],"about_ca_topic_score_codex":0.000004910489,"about_ca_topic_score_gemma":6.1178724e-7,"teacher_disagreement_score":0.9600572,"about_ca_system_score_codex":0.000043301097,"about_ca_system_score_gemma":0.0001714092,"threshold_uncertainty_score":0.62128776},"labels":[],"label_agreement":null},{"id":"W3125376726","doi":"10.48550/arxiv.2106.13024","title":"Symmetric Wasserstein Autoencoders","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Artificial intelligence; Mathematics","score_opus":0.062143008767350925,"score_gpt":0.17391007519524748,"score_spread":0.11176706642789655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125376726","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020514231,0.00029215103,0.9709594,0.0002344164,0.0013672877,0.0001939594,0.0000054885763,0.00023768972,0.00619535],"genre_scores_gemma":[0.97877604,0.00031332244,0.018573876,0.00018475116,0.00014060794,9.467975e-7,0.000016733671,0.0000207121,0.0019730218],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973627,0.0003141836,0.0002259924,0.0014836214,0.00013570234,0.0004778378],"domain_scores_gemma":[0.9975692,0.00015026605,0.00023834432,0.0015594545,0.00025937706,0.0002233315],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027598068,0.0003914596,0.00045904468,0.00039223567,0.0002134741,0.00043062572,0.0020631978,0.00032222059,0.000074770614],"category_scores_gemma":[0.000086644744,0.00045282912,0.00039543278,0.0016203669,0.00009082841,0.0006333185,0.0026740541,0.0005995654,0.00007234954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061712403,0.00008634322,0.00034728038,0.000038539343,0.00017793915,0.00063656946,0.00018082772,0.95882314,0.000055813784,0.03685398,0.0009152156,0.0018781963],"study_design_scores_gemma":[0.00026155636,0.000030741765,0.00047992432,0.00006953668,0.00007513099,0.0000040014233,0.00016720952,0.9919817,0.00043415665,0.005273576,0.0006810088,0.00054148684],"about_ca_topic_score_codex":0.0002601278,"about_ca_topic_score_gemma":0.00007175088,"teacher_disagreement_score":0.9582618,"about_ca_system_score_codex":0.0002457468,"about_ca_system_score_gemma":0.00036674368,"threshold_uncertainty_score":0.99979234},"labels":[],"label_agreement":null},{"id":"W3126624604","doi":"10.1371/journal.pone.0287736","title":"Using deep LSD to build operators in GANs latent space with meaning in real space","year":2023,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"TRIUMF","funders":"National Institute of General Medical Sciences; National Institutes of Health; National Science Foundation","keywords":"MNIST database; Autoencoder; Orthonormal basis; Latent variable; Space (punctuation); Eigenvalues and eigenvectors; Dimensionality reduction; Probabilistic latent semantic analysis; Artificial intelligence; Latent class model; Computer science; Pattern recognition (psychology); Representation (politics); Mathematics; Deep learning; Machine learning; Physics","score_opus":0.06443923413368993,"score_gpt":0.25047121047282794,"score_spread":0.186031976339138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126624604","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8898555,0.00002232542,0.106808975,0.0020941251,0.000060395603,0.00029260805,9.681013e-7,0.00010161847,0.0007634535],"genre_scores_gemma":[0.8544208,0.000028296676,0.14521581,0.0001139827,0.00006870094,0.000013710787,8.3722756e-7,0.000016534072,0.00012131634],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986273,0.0000998183,0.00016652922,0.0004065473,0.00029786208,0.00040194928],"domain_scores_gemma":[0.9994338,0.000060517767,0.00003768421,0.00030796687,0.00005724551,0.000102752485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003041656,0.00014277849,0.00023943048,0.00024784054,0.000073606316,0.00012113649,0.0003259822,0.000042891945,0.000006856187],"category_scores_gemma":[0.000056110253,0.0001286351,0.00001994308,0.0016318088,0.000018544262,0.00031667156,0.00022330938,0.00014140972,0.00003953371],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060136674,0.0005967034,0.09240614,0.000046088284,0.000115402225,0.00038957753,0.01173296,0.7272967,0.16066381,0.004909316,0.00015009409,0.0016330577],"study_design_scores_gemma":[0.00044086983,0.00013028798,0.0132643245,0.00039848697,0.000014749964,0.0000015600757,0.00024954992,0.93968886,0.045325436,0.00012984278,0.00003326329,0.0003227698],"about_ca_topic_score_codex":0.00093281025,"about_ca_topic_score_gemma":0.0027570187,"teacher_disagreement_score":0.21239215,"about_ca_system_score_codex":0.0001089405,"about_ca_system_score_gemma":0.000052961754,"threshold_uncertainty_score":0.5245587},"labels":[],"label_agreement":null},{"id":"W3127077437","doi":"","title":"On the Theoretical Equivalence of Several Trade-Off Curves Assessing Statistical Proximity","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Safran Electronics (Canada)","funders":"","keywords":"Equivalence (formal languages); Econometrics; Mathematics; Economics; Statistical physics; Physics; Pure mathematics","score_opus":0.07907622823540807,"score_gpt":0.21763156706705297,"score_spread":0.1385553388316449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127077437","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009424575,0.00008357188,0.9841892,0.0030960112,0.00030592844,0.0003410568,0.00004162834,0.00007717985,0.0024408305],"genre_scores_gemma":[0.99387974,0.0002088292,0.0050821174,0.0006907171,0.000080677855,0.0000011422133,0.000007511063,0.000013272659,0.00003599079],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974919,0.0007704615,0.0002538531,0.0009428476,0.0002109463,0.00033001084],"domain_scores_gemma":[0.9974068,0.0011966991,0.00024553933,0.00090171985,0.00009128736,0.00015795791],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004759083,0.00031005434,0.00042213337,0.000056894158,0.0001802863,0.00014458223,0.0018467995,0.00015633318,0.0001250473],"category_scores_gemma":[0.0004229473,0.00024551642,0.00020504418,0.00037622196,0.00065181486,0.00034669836,0.001444852,0.00076692575,0.000015428152],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025565112,0.00008543664,0.000059000064,0.00010876891,0.000066172775,0.000092760696,0.00010289782,0.070149705,0.000051678293,0.9271407,0.0012397575,0.00087752665],"study_design_scores_gemma":[0.00012298216,0.00007511769,0.00083929783,0.00028972724,0.000062637395,0.0000015387196,0.000027352517,0.7851026,0.00033918244,0.21286319,0.00003640396,0.00023995174],"about_ca_topic_score_codex":0.000014826441,"about_ca_topic_score_gemma":0.0000016617203,"teacher_disagreement_score":0.98445517,"about_ca_system_score_codex":0.00007260264,"about_ca_system_score_gemma":0.0002479063,"threshold_uncertainty_score":0.9999997},"labels":[],"label_agreement":null},{"id":"W3128475979","doi":"10.48550/arxiv.2101.11744","title":"On the mapping between Hopfield networks and Restricted Boltzmann\\n Machines","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Boltzmann machine; Hopfield network; Boltzmann constant; Computer science; Restricted Boltzmann machine; Artificial intelligence; Theoretical computer science; Artificial neural network; Physics; Thermodynamics","score_opus":0.06362805813593986,"score_gpt":0.1766164173975322,"score_spread":0.11298835926159234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128475979","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1287027,0.00022832025,0.86819226,0.0008459409,0.00046377868,0.00021307671,0.000004937646,0.0000947695,0.001254221],"genre_scores_gemma":[0.99696344,0.0005032172,0.0013453108,0.00039532073,0.00029194006,0.0000010855509,0.000014380015,0.000014503822,0.0004708273],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980215,0.00038621208,0.00018586851,0.0009788905,0.00009237364,0.0003351832],"domain_scores_gemma":[0.997715,0.0007596064,0.00019887905,0.0010797827,0.000121612415,0.00012509909],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023910005,0.00032443154,0.00034944885,0.00013557446,0.00037425826,0.00041892214,0.0012315972,0.00027644975,0.000025168949],"category_scores_gemma":[0.00010831913,0.00027569718,0.0001662367,0.00062634796,0.000106289524,0.00023071909,0.0021733267,0.0008330931,0.0000059265503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014316548,0.00004520301,0.0048153037,0.000028625254,0.00030084664,0.00032748413,0.00026445717,0.9392645,0.000021088166,0.044533797,0.002476034,0.0079083815],"study_design_scores_gemma":[0.00016625911,0.000031934065,0.008027755,0.00012648113,0.000053401076,0.0000018434453,0.0000670671,0.98097086,0.000038396367,0.009826857,0.00033569502,0.00035345732],"about_ca_topic_score_codex":0.00019212315,"about_ca_topic_score_gemma":0.000035199122,"teacher_disagreement_score":0.86826074,"about_ca_system_score_codex":0.000050969153,"about_ca_system_score_gemma":0.000077610006,"threshold_uncertainty_score":0.99996954},"labels":[],"label_agreement":null},{"id":"W3129224130","doi":"10.2196/23328","title":"Realistic High-Resolution Body Computed Tomography Image Synthesis by Using Progressive Growing Generative Adversarial Network: Visual Turing Test","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Research Foundation of Korea; National Research Foundation","keywords":"Artificial intelligence; Set (abstract data type); Computer science; Generative adversarial network; Test set; Image (mathematics); Computed tomography; Pattern recognition (psychology); Test (biology); Deep learning; Generator (circuit theory); Data set; Medicine; Radiology","score_opus":0.010385953595136653,"score_gpt":0.2623816635386571,"score_spread":0.25199570994352044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129224130","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012790522,0.0003033294,0.9841592,0.0006257993,0.0010643104,0.00040517215,0.000036310317,0.00024518414,0.00037018646],"genre_scores_gemma":[0.6209012,0.000051752428,0.37506253,0.0016443875,0.0020170722,0.0000957037,0.00016324951,0.000040134764,0.000023946193],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960765,0.0003538665,0.001032559,0.00042041438,0.0012299423,0.00088668684],"domain_scores_gemma":[0.9971991,0.00091569906,0.00046958472,0.0004952246,0.00042835984,0.00049199397],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00067197205,0.00042097943,0.00058775366,0.00013850503,0.0006458093,0.00060314336,0.000777091,0.00030982203,0.0001118595],"category_scores_gemma":[0.0007999375,0.00038554243,0.00022038617,0.0011515365,0.00028263335,0.002063584,0.00079583604,0.0005215538,0.000019424786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038798308,0.0058365106,0.001908071,0.0019799215,0.003936291,0.004184558,0.019460078,0.20474823,0.043288615,0.029254027,0.27284035,0.41217536],"study_design_scores_gemma":[0.00064287224,0.000094159484,0.00014730876,0.0003813701,0.00006615486,0.00007686671,0.000261849,0.9837155,0.013036273,0.0002073505,0.0008983368,0.0004719924],"about_ca_topic_score_codex":0.00004575794,"about_ca_topic_score_gemma":0.0000058186797,"teacher_disagreement_score":0.77896726,"about_ca_system_score_codex":0.00015032776,"about_ca_system_score_gemma":0.00042688948,"threshold_uncertainty_score":0.99985963},"labels":[],"label_agreement":null},{"id":"W3131298545","doi":"","title":"Differentially Private Generative Models Through Optimal Transport","year":2021,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Differential privacy; Computer science; Generative grammar; Generative model; Adversarial system; Artificial intelligence; Synthetic data; Machine learning; Data mining","score_opus":0.02652168241920233,"score_gpt":0.23113684424398673,"score_spread":0.2046151618247844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131298545","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00801465,0.00014775452,0.9767923,0.0012595085,0.0003556082,0.000090354966,0.0000036403064,0.0001162846,0.0132199],"genre_scores_gemma":[0.5054279,0.00006178931,0.49206302,0.00065591134,0.0001202856,0.0000084131125,0.000008031095,0.000008181099,0.0016464856],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858314,0.00009690921,0.00023194743,0.0005319961,0.00024435233,0.000311643],"domain_scores_gemma":[0.9991977,0.0000336955,0.000046374127,0.0004913282,0.00015148277,0.00007937204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007668379,0.00018595002,0.00022826044,0.000020468751,0.00016252972,0.00015172116,0.00046231275,0.00005986739,0.00022299417],"category_scores_gemma":[0.0000073298916,0.00015401065,0.00013660593,0.00026515868,0.00004023514,0.0011045437,0.00015749589,0.00010278106,0.000025510975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000117198515,0.00023364276,0.00006983621,0.000008876484,0.00017884039,0.00018537755,0.0022013427,0.28670663,0.034065504,0.66158545,0.0018469816,0.012905777],"study_design_scores_gemma":[0.00036913023,0.000041268846,0.0003173869,0.000009636444,0.000017427283,0.000013255084,0.00003690889,0.76090235,0.21614708,0.018052861,0.0037674087,0.00032531307],"about_ca_topic_score_codex":0.000024357343,"about_ca_topic_score_gemma":0.000034192704,"teacher_disagreement_score":0.64353263,"about_ca_system_score_codex":0.000019060355,"about_ca_system_score_gemma":0.00010345372,"threshold_uncertainty_score":0.62803715},"labels":[],"label_agreement":null},{"id":"W3131435758","doi":"","title":"Image Completion via Inference in Deep Generative Models","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Inference; Leverage (statistics); Computer science; Artificial intelligence; Generative grammar; Generative model; Image (mathematics); Perspective (graphical); Bayesian inference; Machine learning; Pattern recognition (psychology); Bayesian probability","score_opus":0.07680241438404604,"score_gpt":0.195674236800266,"score_spread":0.11887182241621995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131435758","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029632328,0.00011791741,0.9677265,0.00012028903,0.00045541688,0.00025955064,0.000006804727,0.00009116972,0.0015899967],"genre_scores_gemma":[0.93934315,0.00024047977,0.060005516,0.00013744274,0.00008833716,0.0000024701262,0.000038847127,0.000015029897,0.00012872923],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99739516,0.00047160024,0.00027338578,0.0013328609,0.00011992493,0.00040704213],"domain_scores_gemma":[0.9980968,0.00017429164,0.0002218432,0.00102529,0.00034316545,0.00013860675],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025297728,0.00037774778,0.00048979843,0.0002527848,0.0001499708,0.00031727037,0.0013152919,0.00025639188,0.000057502988],"category_scores_gemma":[0.00005198899,0.00044753434,0.0002003824,0.0007280003,0.00012100911,0.0011760513,0.0021204937,0.0006073433,0.000028855622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000088891275,0.000087565626,0.00023855458,0.00002011899,0.000042783042,0.00031513578,0.0005454698,0.9803586,0.00060241803,0.016748905,0.0000307536,0.0010008299],"study_design_scores_gemma":[0.00029958328,0.000023497418,0.0006297526,0.00006901658,0.000022245915,0.000001654209,0.00009146624,0.96055275,0.0005223176,0.037326895,0.000019001027,0.00044179338],"about_ca_topic_score_codex":0.0005625631,"about_ca_topic_score_gemma":0.0007867152,"teacher_disagreement_score":0.9097108,"about_ca_system_score_codex":0.00027143708,"about_ca_system_score_gemma":0.0002133789,"threshold_uncertainty_score":0.99979764},"labels":[],"label_agreement":null},{"id":"W3131495249","doi":"","title":"Using MMD GANs to correct physics models and improve Bayesian parameter estimation","year":2021,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Inference; Fiducial inference; Bayesian inference; Computer science; Artificial intelligence; Bayes' theorem; Machine learning; Algorithm; Bayesian probability; Uncertainty quantification; Estimation theory; Frequentist inference","score_opus":0.04120423736067441,"score_gpt":0.27139504677917653,"score_spread":0.23019080941850212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131495249","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002832548,0.000023912018,0.99561685,0.0003733279,0.0002628342,0.00008909526,0.0000012814332,0.000037500526,0.0007626463],"genre_scores_gemma":[0.46836385,0.0000020896277,0.5310069,0.00044798755,0.000047416775,0.0000022524387,7.211603e-7,0.000004013212,0.00012477693],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992489,0.000050783685,0.000109542176,0.00031775673,0.00010643177,0.0001665457],"domain_scores_gemma":[0.9994632,0.00007495899,0.00002831703,0.00026263687,0.00008854759,0.00008232175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007847874,0.000098351615,0.00012122223,0.00001978533,0.000096576725,0.00025402723,0.00011877173,0.000028341392,0.000009650671],"category_scores_gemma":[0.0000379256,0.00008839434,0.000033822434,0.0002200943,0.000013838067,0.00061869796,0.00014810773,0.000045575896,0.0000051243533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029445257,0.000034179975,0.000027423397,0.000006533637,0.000021532995,0.000008903579,0.0007637582,0.6551878,0.023821896,0.010232346,0.00037008745,0.3095226],"study_design_scores_gemma":[0.000071355345,0.000020783365,0.00001811785,0.00000869204,0.0000071964255,0.0000048299567,0.000026053947,0.93535674,0.053648233,0.010694269,0.00002818826,0.00011555816],"about_ca_topic_score_codex":0.000051790135,"about_ca_topic_score_gemma":0.0000135660775,"teacher_disagreement_score":0.46553132,"about_ca_system_score_codex":0.000019632098,"about_ca_system_score_gemma":0.00004595087,"threshold_uncertainty_score":0.36046168},"labels":[],"label_agreement":null},{"id":"W3132648081","doi":"10.48550/arxiv.2102.09532","title":"Clockwork Variational Autoencoders","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Clockwork; Computer science; Benchmark (surveying); Artificial intelligence; Abstraction; Hierarchy; Machine learning; Term (time); Pattern recognition (psychology)","score_opus":0.05467910025840562,"score_gpt":0.17156348249850092,"score_spread":0.11688438224009531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132648081","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004259631,0.00011634332,0.98968446,0.000348146,0.0015605526,0.00015076941,0.000008367131,0.00018216926,0.0036895638],"genre_scores_gemma":[0.9433576,0.00012551094,0.054495428,0.00025522112,0.00025989913,0.0000010154519,0.000032365937,0.000014989949,0.0014580078],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99784774,0.00026120918,0.00019740913,0.0012105119,0.00012731962,0.00035583647],"domain_scores_gemma":[0.9981084,0.00014114045,0.00021002904,0.0011120946,0.00026387337,0.00016448645],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000231213,0.0003092539,0.00033074047,0.00014184997,0.0002311165,0.00034736693,0.0015144428,0.0002800807,0.00016059559],"category_scores_gemma":[0.000057846446,0.00036687413,0.0002935937,0.0006236689,0.00007639839,0.0005047504,0.0020358772,0.00050071947,0.000060123828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000052146283,0.000055951055,0.00032120995,0.000013118292,0.00012102614,0.00020463551,0.00017058579,0.9326751,0.000015583484,0.06478804,0.0010957303,0.00053376943],"study_design_scores_gemma":[0.00021005874,0.000015505742,0.0011439975,0.000052425396,0.000049697614,0.0000031797622,0.000063416526,0.97916925,0.00008012143,0.017847065,0.00096658414,0.00039869515],"about_ca_topic_score_codex":0.00012867505,"about_ca_topic_score_gemma":0.000044882614,"teacher_disagreement_score":0.93909794,"about_ca_system_score_codex":0.00017944118,"about_ca_system_score_gemma":0.00047302054,"threshold_uncertainty_score":0.99987835},"labels":[],"label_agreement":null},{"id":"W3134020311","doi":"10.48550/arxiv.2103.06331","title":"Face Images as Jigsaw Puzzles: Compositional Perception of Human Faces for Machines Using Generative Adversarial Networks","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Jigsaw; Face (sociological concept); Perception; Generative grammar; Artificial intelligence; Adversarial system; Computer science; Computer vision; Facial recognition system; Machine learning; Pattern recognition (psychology); Psychology; Sociology; Social psychology","score_opus":0.0661748536992891,"score_gpt":0.23085058668618277,"score_spread":0.16467573298689367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134020311","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16547455,0.00012380428,0.8326862,0.00008073449,0.00078543427,0.0004868319,0.00008867903,0.00006488064,0.00020891188],"genre_scores_gemma":[0.957475,0.000099512465,0.041283704,0.00007470191,0.0005013279,0.0000032351059,0.00026144658,0.000025736974,0.00027532777],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99747205,0.00039206631,0.00037367374,0.0012296999,0.00014810267,0.0003844043],"domain_scores_gemma":[0.9979016,0.00018482136,0.0005134833,0.0006934785,0.0005737922,0.0001328192],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027072433,0.0004609191,0.00063415396,0.00020104446,0.00052581355,0.00028086873,0.0011075985,0.0003403113,0.00007828546],"category_scores_gemma":[0.00003425636,0.00052070507,0.00049539533,0.00036958736,0.0002452318,0.00074168266,0.0012663023,0.00038828774,0.0000029149564],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049346952,0.00011142281,0.00022292198,0.00005227682,0.00024092209,0.000031507894,0.0004649316,0.97983134,0.012783949,0.005582599,0.00022186586,0.0004069042],"study_design_scores_gemma":[0.0006993212,0.000109703455,0.0004115759,0.00014827344,0.00018047223,0.0000051010234,0.0005491922,0.99066913,0.0030832123,0.0036023105,0.000023155264,0.0005185594],"about_ca_topic_score_codex":0.0005546458,"about_ca_topic_score_gemma":0.00007034117,"teacher_disagreement_score":0.7920005,"about_ca_system_score_codex":0.00021130123,"about_ca_system_score_gemma":0.00024424083,"threshold_uncertainty_score":0.99972445},"labels":[],"label_agreement":null},{"id":"W3134610548","doi":"10.48550/arxiv.2103.05461","title":"Analytically Tractable Inference in Deep Neural Networks","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Backpropagation; Inference; Computer science; Artificial neural network; Artificial intelligence; Scalability; Deep learning; Machine learning; Deep neural networks; Rprop; Types of artificial neural networks; Recurrent neural network","score_opus":0.05205970518305795,"score_gpt":0.1906063279885047,"score_spread":0.13854662280544675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134610548","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0414018,0.00018346804,0.9560418,0.0001341266,0.0006214912,0.00017030135,0.0000017665909,0.000087393666,0.0013578675],"genre_scores_gemma":[0.99461776,0.00020641422,0.004569865,0.00018407516,0.00011967022,0.0000010901512,0.000014596423,0.000014765909,0.00027179028],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974482,0.00032545367,0.00029013405,0.001284391,0.00009544102,0.00055637513],"domain_scores_gemma":[0.9979596,0.00033379957,0.00018572318,0.001124924,0.00019874658,0.0001971716],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028637532,0.00035955865,0.0005020112,0.00022103176,0.00011236792,0.00040806303,0.0016727138,0.00033411974,0.00008389476],"category_scores_gemma":[0.00013143633,0.0004139125,0.00024191166,0.0010955877,0.00009352395,0.00074732676,0.0019895893,0.0009180808,0.000011015708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010248672,0.00008385694,0.0032447083,0.0000125587185,0.00004325283,0.0006512691,0.00009840312,0.98733336,0.000011498936,0.005634364,0.000023613295,0.002852844],"study_design_scores_gemma":[0.00026073572,0.00002537752,0.0033762387,0.00005125522,0.00003631496,0.0000019798806,0.00005918898,0.9934111,0.00003198048,0.0022913513,0.000033757013,0.00042069418],"about_ca_topic_score_codex":0.00033943218,"about_ca_topic_score_gemma":0.0008297,"teacher_disagreement_score":0.95321596,"about_ca_system_score_codex":0.00017019035,"about_ca_system_score_gemma":0.00016875201,"threshold_uncertainty_score":0.99983126},"labels":[],"label_agreement":null},{"id":"W3135319480","doi":"10.1145/3441233.3441238","title":"Generating Stylistic Images by Extending Neural Style Transfer Method","year":2020,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Style (visual arts); Artificial intelligence; Natural language processing; Transfer (computing); Computer vision; Art; Visual arts","score_opus":0.022227289121190326,"score_gpt":0.2595045298036522,"score_spread":0.23727724068246187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135319480","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005729004,0.00027335563,0.99301004,0.0035881165,0.00013618139,0.000111977184,0.000007407329,0.00019046145,0.0021095413],"genre_scores_gemma":[0.51743126,0.00001041047,0.4787164,0.0032578188,0.00020116726,0.0000075011963,0.0000033525987,0.000013057416,0.00035905084],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984829,0.00022292869,0.00023781491,0.0005176631,0.00020955264,0.0003291456],"domain_scores_gemma":[0.9993391,0.00016921562,0.000027558443,0.00022650878,0.000050422444,0.0001871734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022843418,0.0001860658,0.00021709569,0.000026588013,0.00021114282,0.00036879934,0.000539144,0.000039297167,0.00025675143],"category_scores_gemma":[0.0000801173,0.00015527116,0.00009376353,0.0002947036,0.000024976396,0.0006340525,0.00012956957,0.00013917948,0.00002928697],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008722247,0.000041983163,0.000055868797,0.000018089888,0.000052739146,0.000030379862,0.0009153699,0.0440894,0.65066344,0.005034749,0.018956915,0.28013232],"study_design_scores_gemma":[0.00018345982,0.000062353596,0.000026090958,0.0000028570848,0.000010039428,0.0000036876443,0.00005359282,0.93364954,0.061179135,0.000027765596,0.004596343,0.00020512666],"about_ca_topic_score_codex":0.00003796118,"about_ca_topic_score_gemma":0.0000022478318,"teacher_disagreement_score":0.88956016,"about_ca_system_score_codex":0.000013429002,"about_ca_system_score_gemma":0.000018969788,"threshold_uncertainty_score":0.6331774},"labels":[],"label_agreement":null},{"id":"W3135339232","doi":"10.1109/tip.2021.3064268","title":"Thanka Mural Inpainting Based on Multi-Scale Adaptive Partial Convolution and Stroke-Like Mask","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Natural Science Foundation of China","keywords":"Inpainting; Mural; Convolution (computer science); Artificial intelligence; Computer science; Computer vision; Scale (ratio); Kernel (algebra); Pixel; Image restoration; Image (mathematics); Mathematics; Image processing; Art; Visual arts; Painting","score_opus":0.020564949450220766,"score_gpt":0.24249260580076096,"score_spread":0.22192765635054018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135339232","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026724646,0.00010860288,0.99572414,0.00052050414,0.0004434391,0.00013346168,0.000013587214,0.00013664011,0.00024716332],"genre_scores_gemma":[0.75066143,0.000008481985,0.24868566,0.00036071576,0.00006280452,0.000022426251,0.0000013931174,0.0000142366,0.00018284713],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998362,0.00018806054,0.00024032619,0.0005948537,0.00026574734,0.00034898098],"domain_scores_gemma":[0.9991948,0.00012652072,0.00010052398,0.0002661184,0.00019885068,0.0001131909],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022566861,0.00022456668,0.00020757304,0.00011525343,0.000628747,0.0004082532,0.00017382271,0.00008004617,0.000024883571],"category_scores_gemma":[0.000014590084,0.00022152382,0.000098006945,0.00035053058,0.00012995071,0.0009074533,0.0000061137166,0.00030035857,0.000012921134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000159018,0.00074157637,0.000077615645,0.0000850785,0.000063760366,0.00007863189,0.0020602841,0.14464727,0.18906988,0.000030820036,0.00006964215,0.6629164],"study_design_scores_gemma":[0.0006020878,0.00008057313,0.00012515065,0.00009246764,0.000024341492,0.0000079009415,0.00023275484,0.7895202,0.20904383,0.00001746574,0.00005643646,0.0001968097],"about_ca_topic_score_codex":0.000022317177,"about_ca_topic_score_gemma":0.00003914431,"teacher_disagreement_score":0.747989,"about_ca_system_score_codex":0.000071927185,"about_ca_system_score_gemma":0.00015682763,"threshold_uncertainty_score":0.9033479},"labels":[],"label_agreement":null},{"id":"W3135485589","doi":"10.1007/s11263-022-01606-8","title":"Countering Malicious DeepFakes: Survey, Battleground, and Horizon","year":2022,"lang":"en","type":"article","venue":"International Journal of Computer Vision","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":185,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China; National Research Foundation Singapore; National Satellite of Excellence in Trustworthy Software Systems, National University of Singapore; National Postdoctoral Program for Innovative Talents; National Research Foundation; Natural Science Foundation of Hubei Province; Nvidia","keywords":"Computer science; Misinformation; Categorization; Data science; Limiting; Artificial intelligence; Computer security","score_opus":0.011222976218972683,"score_gpt":0.2578077704744552,"score_spread":0.24658479425548252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135485589","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10816938,0.00021693036,0.88559896,0.00079602347,0.005103396,0.000037219223,0.000005707242,0.000012313825,0.000060063725],"genre_scores_gemma":[0.9628352,0.000052851712,0.035987355,0.00035088416,0.00073925214,0.0000010920693,0.0000032007624,0.0000074350046,0.00002273275],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836737,0.00026741135,0.00039538025,0.00018000508,0.00066488725,0.00012493005],"domain_scores_gemma":[0.99890363,0.00020628115,0.00032402182,0.00013295363,0.00036467833,0.00006846091],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010149473,0.00010575627,0.00016555696,0.00020092062,0.00014244366,0.00035423384,0.000999252,0.000019313584,0.00003159181],"category_scores_gemma":[0.000024625526,0.00009577215,0.00007583158,0.00012471217,0.000026156664,0.00067177566,0.0007698049,0.00019478939,0.0000026532457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003541565,0.00035117797,0.005184389,0.0000072393973,0.0003697764,0.00057391496,0.0011741276,0.07749646,0.004984866,0.00345484,0.015510384,0.8905387],"study_design_scores_gemma":[0.0017521343,0.0027613079,0.048347384,0.00008321418,0.00001530808,0.002932665,0.00006583692,0.8711752,0.0006284327,0.0017008698,0.07013921,0.00039840853],"about_ca_topic_score_codex":0.000032891836,"about_ca_topic_score_gemma":0.0000060052134,"teacher_disagreement_score":0.89014024,"about_ca_system_score_codex":0.00010218534,"about_ca_system_score_gemma":0.000044134857,"threshold_uncertainty_score":0.39054748},"labels":[],"label_agreement":null},{"id":"W3135719787","doi":"10.1002/gamm.202100008","title":"An introduction to deep generative modeling","year":2021,"lang":"en","type":"preprint","venue":"GAMM-Mitteilungen","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Air Force Office of Scientific Research; Advanced Scientific Computing Research; U.S. Department of Energy; National Science Foundation","keywords":"Generative grammar; Computer science; Presentation (obstetrics); Artificial intelligence; Adversarial system; Deep learning; Artificial neural network; Deep neural networks; Machine learning","score_opus":0.01810169717749934,"score_gpt":0.25437604461767804,"score_spread":0.2362743474401787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135719787","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016314933,0.0010312,0.9686797,0.008746092,0.0041423384,0.0005475769,0.000008785777,0.00024898892,0.00028034215],"genre_scores_gemma":[0.5139853,0.00007799638,0.47530824,0.0017305894,0.008257686,0.00015870438,0.0001441152,0.000056062057,0.00028130977],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957433,0.0005176706,0.00053983665,0.002053882,0.0005243173,0.0006210341],"domain_scores_gemma":[0.99650294,0.000033066615,0.00017683046,0.00230946,0.00060403347,0.00037364513],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00057834835,0.00055828155,0.00061421626,0.00024022335,0.0002988391,0.0012439004,0.0017234002,0.00033938227,0.00010210575],"category_scores_gemma":[0.00009571705,0.0005760199,0.000245372,0.0004785199,0.000032603817,0.0007701371,0.0018233471,0.0006512648,0.00006240445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009241987,0.00008429031,0.000018519226,0.00001970093,0.00015122876,0.000018463359,0.0031198573,0.9393491,0.008715158,0.00057820807,0.0032828136,0.044653423],"study_design_scores_gemma":[0.00012474765,0.00007877971,0.000050577186,0.00002993799,0.00005811055,0.0000088930865,0.00017245644,0.98397017,0.009760778,0.0010636455,0.00400127,0.00068066746],"about_ca_topic_score_codex":0.0001818552,"about_ca_topic_score_gemma":0.00023556464,"teacher_disagreement_score":0.49767035,"about_ca_system_score_codex":0.00022087195,"about_ca_system_score_gemma":0.0002798321,"threshold_uncertainty_score":0.99979293},"labels":[],"label_agreement":null},{"id":"W3138602767","doi":"","title":"Isolating Sources of Disentanglement in Variational Autoencoders.","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Autoencoder; Hyperparameter; Mutual information; Correlation; Classifier (UML); Latent variable; Artificial intelligence; Total correlation; Computer science; Pattern recognition (psychology); Machine learning; Mathematics; Deep learning","score_opus":0.03819528323690188,"score_gpt":0.31948798933381134,"score_spread":0.2812927060969095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138602767","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026695512,0.000006163908,0.9203491,0.0038759434,0.00051609916,0.00011520244,0.0000051130833,0.000049040915,0.048387796],"genre_scores_gemma":[0.9721096,0.0000072090497,0.027063012,0.00008362857,0.00015780781,0.000023642253,0.000010808029,0.0000047854414,0.00053950987],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998781,0.00012858861,0.00030171755,0.00029115874,0.000359726,0.00013775393],"domain_scores_gemma":[0.9990875,0.00019229835,0.00018976007,0.00017373354,0.00032133143,0.00003535631],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022332589,0.00008993857,0.00010573272,0.00020800377,0.000119228964,0.00011564306,0.00045836234,0.000028718026,0.0005809174],"category_scores_gemma":[0.00029487186,0.00008965715,0.000047176713,0.00025511277,0.000081726444,0.00036625692,0.00013063457,0.00013369677,0.00003635418],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051850133,0.00032221075,0.12311205,0.0000059544545,0.00012711136,0.000012237829,0.011365543,0.16329852,0.007944396,0.67067105,0.0006252543,0.02246386],"study_design_scores_gemma":[0.00028113445,0.00009514495,0.03428851,0.00004328583,0.0000028646068,0.0000019865565,0.00046241572,0.95626765,0.0023467455,0.005701827,0.00041138558,0.000097055185],"about_ca_topic_score_codex":0.00015563621,"about_ca_topic_score_gemma":0.000058447895,"teacher_disagreement_score":0.94541407,"about_ca_system_score_codex":0.000045552642,"about_ca_system_score_gemma":0.00007610318,"threshold_uncertainty_score":0.6360638},"labels":[],"label_agreement":null},{"id":"W3138960167","doi":"10.1088/1361-6560/abf1bb","title":"A feature invariant generative adversarial network for head and neck MRI/CT image synthesis","year":2021,"lang":"en","type":"article","venue":"Physics in Medicine and Biology","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Polytechnique Montréal","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada","keywords":"Discriminator; Artificial intelligence; Computer science; Feature (linguistics); Pattern recognition (psychology); Convolutional neural network; Ground truth; Hounsfield scale; Feature learning; Histogram; Generative model; Image registration; Computer vision; Image (mathematics); Computed tomography; Radiology; Generative grammar; Medicine","score_opus":0.08334431156475747,"score_gpt":0.32733599286177584,"score_spread":0.24399168129701837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138960167","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007501943,0.0024522184,0.9654819,0.022933189,0.00074926356,0.00028861949,0.000021375368,0.000022506256,0.0005489904],"genre_scores_gemma":[0.47558782,0.0025864476,0.5086696,0.005921396,0.0067994553,0.00014925108,0.00008681071,0.000027765185,0.00017145791],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986758,0.00022802714,0.00017335784,0.0005337716,0.000059705962,0.00032931607],"domain_scores_gemma":[0.9987911,0.00070957094,0.00007986148,0.00023594797,0.000103727005,0.000079802885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034149742,0.00019096085,0.00045577236,0.000032839245,0.00015465698,0.00004165262,0.00017453953,0.00006617684,0.0000070295237],"category_scores_gemma":[0.00026153933,0.00014198374,0.000044616878,0.00028528553,0.00021366964,0.00016983329,0.0001977939,0.00016209773,8.4254856e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033523436,0.00036193486,0.006445368,0.0001900642,0.0006168439,0.00038429003,0.0034044478,0.002867527,0.07579189,0.35061008,0.10952391,0.4494684],"study_design_scores_gemma":[0.009650536,0.0019227656,0.0064868983,0.00078752206,0.00031621478,0.00025393124,0.0008299763,0.54024804,0.032077916,0.30927896,0.09641147,0.0017357434],"about_ca_topic_score_codex":0.000063697604,"about_ca_topic_score_gemma":0.00011155859,"teacher_disagreement_score":0.5373805,"about_ca_system_score_codex":0.000015660484,"about_ca_system_score_gemma":0.00006986738,"threshold_uncertainty_score":0.5789929},"labels":[],"label_agreement":null},{"id":"W3139123588","doi":"10.1007/978-3-030-87202-1_56","title":"Rapid Treatment Planning for Low-dose-rate Prostate Brachytherapy with TP-GAN","year":2021,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Radiation treatment planning; Brachytherapy; Simulated annealing; Plan (archaeology); Computer science; Prostate; Medical physics; Prostate brachytherapy; Generative model; Dose rate; Medicine; Operations management; Nuclear medicine; Radiation therapy; Artificial intelligence; Surgery; Algorithm; Generative grammar; Engineering; Internal medicine","score_opus":0.022329961863238445,"score_gpt":0.2645064045352531,"score_spread":0.24217644267201466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139123588","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025262313,0.0010931473,0.96893466,0.0014154994,0.001935458,0.001202497,0.000010150992,0.00013289701,0.000013380563],"genre_scores_gemma":[0.55082935,0.00006557126,0.4478632,0.0006973315,0.00038069556,0.00012557817,0.000013778488,0.000021454627,0.000003050662],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99568677,0.00021987187,0.00045670505,0.0021993292,0.0004939425,0.00094336784],"domain_scores_gemma":[0.99703974,0.0005889874,0.0003262331,0.0014692998,0.00038649898,0.00018923849],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00087476865,0.0006597041,0.00071431213,0.0003560617,0.0004444797,0.001990304,0.0020006788,0.00019260249,0.0000053618523],"category_scores_gemma":[0.00007259779,0.0004938576,0.00018323645,0.0012033812,0.00035899607,0.0006980659,0.00082395604,0.00045439252,0.0000018695634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030761148,0.000084569474,0.0002409795,0.0000326505,0.00003366504,0.00006382927,0.003232839,0.64282525,0.0008842776,0.000015645854,0.000006697364,0.3525488],"study_design_scores_gemma":[0.0008623614,0.000688431,0.0011112692,0.00046215544,0.000013206583,0.000022786766,0.00000335209,0.944068,0.04991463,0.0020225344,0.0001880925,0.0006431473],"about_ca_topic_score_codex":0.00006825272,"about_ca_topic_score_gemma":0.00009507139,"teacher_disagreement_score":0.52556705,"about_ca_system_score_codex":0.0003285089,"about_ca_system_score_gemma":0.0012539641,"threshold_uncertainty_score":0.9997513},"labels":[],"label_agreement":null},{"id":"W3143614868","doi":"10.1109/iccv48922.2021.01371","title":"Labels4Free: Unsupervised Segmentation using StyleGAN","year":2021,"lang":"en","type":"preprint","venue":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"King Abdullah University of Science and Technology","keywords":"Segmentation; Computer science; Artificial intelligence; Segmentation-based object categorization; Scale-space segmentation; Pattern recognition (psychology); Object (grammar); Image segmentation; Generator (circuit theory); Computer vision; Power (physics)","score_opus":0.06634207614877823,"score_gpt":0.32330667191237966,"score_spread":0.2569645957636014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3143614868","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03205578,0.00010132246,0.9490695,0.0032682037,0.013167513,0.0004928585,0.000069080575,0.00014596553,0.0016297722],"genre_scores_gemma":[0.71790206,0.00029872032,0.27686882,0.0014349207,0.0023376504,0.00004731613,0.00040103597,0.000057549303,0.0006519419],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99459064,0.00058765337,0.00093140604,0.0019305248,0.0014257582,0.0005339924],"domain_scores_gemma":[0.99606794,0.0001874408,0.00057808677,0.0013600452,0.0015408988,0.00026557996],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004537742,0.00076596666,0.00072436186,0.00047835585,0.00028526766,0.0031596832,0.002779376,0.00040835704,0.001144473],"category_scores_gemma":[0.000042170766,0.0007739912,0.00042480056,0.00041235078,0.00008317719,0.0010271099,0.0023955002,0.00097466714,0.00013785592],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016533899,0.0015172291,0.0003611764,0.00018100924,0.0014413194,0.000779175,0.0024594364,0.40401658,0.07734988,0.022627296,0.017648624,0.47145292],"study_design_scores_gemma":[0.00068272697,0.0001756439,0.00021779606,0.00082262896,0.000035783207,0.000022038299,0.00010256954,0.98689276,0.008312802,0.0011483945,0.00081468426,0.00077216903],"about_ca_topic_score_codex":0.0003128707,"about_ca_topic_score_gemma":0.00008728388,"teacher_disagreement_score":0.68584627,"about_ca_system_score_codex":0.0005004277,"about_ca_system_score_gemma":0.0006504015,"threshold_uncertainty_score":0.9997686},"labels":[],"label_agreement":null},{"id":"W3146526033","doi":"10.48550/arxiv.2103.15812","title":"LatentKeypointGAN: Controlling Images via Latent Keypoints","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Image (mathematics); Set (abstract data type); Matching (statistics); Pattern recognition (psychology); Computer vision; Position (finance); Generative adversarial network; Space (punctuation); Generative grammar; Domain (mathematical analysis); Mathematics","score_opus":0.04725434967459104,"score_gpt":0.1714861754683885,"score_spread":0.12423182579379748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3146526033","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027503178,0.00038691366,0.9684148,0.00036637686,0.0015578206,0.00031744974,0.000011716509,0.00025139577,0.0011903844],"genre_scores_gemma":[0.9853567,0.0004532409,0.011864588,0.00024981494,0.00024112624,0.0000017543064,0.000025841198,0.000031533687,0.001775393],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996859,0.00036983058,0.00035061344,0.00166042,0.00015863717,0.0006014578],"domain_scores_gemma":[0.99731314,0.00015357936,0.00034660814,0.001505395,0.00041642095,0.00026485033],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036112292,0.000519867,0.00068166165,0.00021046538,0.00027296835,0.0005204727,0.0017143711,0.00033626633,0.00012321904],"category_scores_gemma":[0.00005385575,0.0005716129,0.0005367192,0.00043821937,0.0001235312,0.0007136792,0.0027019987,0.00071418984,0.00012508672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028978531,0.00016740848,0.0010931776,0.000056935638,0.00040840323,0.001462613,0.0002641573,0.98821163,0.0015516281,0.003765162,0.0006235217,0.002366355],"study_design_scores_gemma":[0.00075957185,0.000042042273,0.0009408003,0.00013866552,0.00013320812,0.0000121117155,0.000048141243,0.9852413,0.004284419,0.007385663,0.00029736658,0.00071672414],"about_ca_topic_score_codex":0.00026910365,"about_ca_topic_score_gemma":0.000049790775,"teacher_disagreement_score":0.95785356,"about_ca_system_score_codex":0.00019710968,"about_ca_system_score_gemma":0.0002071045,"threshold_uncertainty_score":0.99967355},"labels":[],"label_agreement":null},{"id":"W3157361525","doi":"","title":"Good Artists Copy, Great Artists Steal: Model Extraction Attacks Against Image Translation Generative Adversarial Networks.","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Inference; Image (mathematics); Artificial intelligence; Adversary; Translation (biology); Image translation; Task (project management); Generative model; Machine learning; Generative grammar; Natural language processing; Information retrieval; Computer security","score_opus":0.06481233346821734,"score_gpt":0.21443671694148653,"score_spread":0.14962438347326917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157361525","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018542975,0.00025946996,0.9751443,0.00021422785,0.0018746913,0.000622636,0.00006822565,0.000295083,0.0029783396],"genre_scores_gemma":[0.9519841,0.00075827853,0.04514069,0.00019491834,0.00063665677,0.0000064954565,0.0003414242,0.000054515825,0.00088291866],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99565166,0.0006742563,0.0005398695,0.0021492222,0.0002538568,0.0007311266],"domain_scores_gemma":[0.9969915,0.00018168305,0.0005703851,0.0014112239,0.0005029677,0.00034221212],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041219074,0.0007476551,0.0007428516,0.00025069213,0.00049879705,0.00069782016,0.0012028476,0.0006530241,0.000049416598],"category_scores_gemma":[0.00003763943,0.0008961367,0.00055445195,0.0007544301,0.00019179455,0.0019987111,0.0009110924,0.0010424306,0.000029129968],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000078806144,0.0001367498,0.00010728769,0.000031435473,0.00021437119,0.00041351956,0.0003603272,0.98799384,0.0012174413,0.0026056368,0.0009615445,0.005879046],"study_design_scores_gemma":[0.00095433247,0.00005317265,0.00019266793,0.000115135255,0.00017997154,0.00000750427,0.0000775972,0.99433714,0.0014836254,0.0014437723,0.0002910292,0.0008640227],"about_ca_topic_score_codex":0.00014356742,"about_ca_topic_score_gemma":0.00038142386,"teacher_disagreement_score":0.9334411,"about_ca_system_score_codex":0.00048429176,"about_ca_system_score_gemma":0.0004198304,"threshold_uncertainty_score":0.99934894},"labels":[],"label_agreement":null},{"id":"W3157877050","doi":"10.1109/access.2021.3075608","title":"Synthesis of 3D MRI Brain Images With Shape and Texture Generative Adversarial Deep Neural Networks","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Yayasan UTP; Universiti Teknologi Petronas; Ministry of Higher Education, Malaysia","keywords":"Computer science; Artificial intelligence; Human Connectome Project; Pattern recognition (psychology); Deep learning; Artificial neural network; Feature (linguistics); Generative grammar; Voxel; Image (mathematics); Generative adversarial network; Computer vision; Functional connectivity","score_opus":0.011351519753001242,"score_gpt":0.24341818409431176,"score_spread":0.2320666643413105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157877050","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012173562,0.0008475704,0.98322713,0.0023198724,0.00060737116,0.0001802888,0.00001124469,0.000053032403,0.00057994004],"genre_scores_gemma":[0.9671704,0.00009259068,0.0311348,0.000897709,0.0005702153,0.000024563462,0.0000039554548,0.000021019938,0.00008474581],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981076,0.0003054935,0.00028293702,0.00065545534,0.00028225553,0.0003662641],"domain_scores_gemma":[0.9983083,0.0005676325,0.00019095518,0.00051424315,0.00029387834,0.0001250171],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020836422,0.0002757082,0.00041870744,0.000073368654,0.0002062813,0.00048064152,0.00076627627,0.00011076045,0.000065955755],"category_scores_gemma":[0.000116407566,0.00021863749,0.00007551225,0.0005665417,0.00017675513,0.0013288932,0.00035171196,0.00019792072,0.0000014315435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018176566,0.00021638339,0.0030240214,0.00006621463,0.00047329182,0.00041236661,0.0009409637,0.5485636,0.013485295,0.00073836604,0.009290633,0.4226071],"study_design_scores_gemma":[0.000444988,0.000072861534,0.002163229,0.00003626576,0.000051855142,0.00003840833,0.00004605755,0.92280775,0.0736466,0.00012378854,0.00025388095,0.0003143209],"about_ca_topic_score_codex":0.000053704694,"about_ca_topic_score_gemma":0.00014104685,"teacher_disagreement_score":0.9549968,"about_ca_system_score_codex":0.000019735218,"about_ca_system_score_gemma":0.00007387715,"threshold_uncertainty_score":0.89157784},"labels":[],"label_agreement":null},{"id":"W3159647175","doi":"","title":"StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows","year":2021,"lang":"en","type":"article","venue":"UCL Discovery (University College London)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":125,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Face (sociological concept); Context (archaeology); Space (punctuation); Process (computing); Artificial intelligence; Quality (philosophy); Expression (computer science); Computer vision; Data mining; Geography","score_opus":0.021846893427647576,"score_gpt":0.21670388888986053,"score_spread":0.19485699546221297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159647175","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21963988,0.00012011449,0.777174,0.00034980293,0.0003095459,0.0001969907,0.0014436919,0.00006689143,0.0006990919],"genre_scores_gemma":[0.96518487,0.00005357168,0.031452563,0.00014020906,0.00011428493,0.0000015589692,0.00053299917,0.000015547083,0.0025043872],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979158,0.0003771005,0.0003146336,0.00058476033,0.00043497756,0.00037275272],"domain_scores_gemma":[0.9983417,0.00016636073,0.00027613333,0.00047412622,0.00061861874,0.00012309874],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022047757,0.00026116104,0.00044716505,0.0002592146,0.00062026473,0.00018685313,0.000495167,0.00011715411,0.00022236702],"category_scores_gemma":[0.000065017884,0.000313921,0.00022855814,0.0011760474,0.00012605458,0.0077840863,0.0002951877,0.00015945167,0.000020019834],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003134407,0.0009936184,0.0018644426,0.000112420305,0.0008682024,0.0028013024,0.0013474231,0.15029773,0.6688776,0.14178003,0.029966457,0.000777363],"study_design_scores_gemma":[0.0056663994,0.00027113192,0.0040527415,0.00018382429,0.00027794275,0.00016544395,0.005263207,0.44955155,0.523382,0.0021088924,0.0075698234,0.0015070321],"about_ca_topic_score_codex":0.00012734388,"about_ca_topic_score_gemma":0.0001113528,"teacher_disagreement_score":0.74572146,"about_ca_system_score_codex":0.00017682128,"about_ca_system_score_gemma":0.00045751221,"threshold_uncertainty_score":0.9999313},"labels":[],"label_agreement":null},{"id":"W3159735872","doi":"10.48550/arxiv.2104.15082","title":"Semantic Relation Preserving Knowledge Distillation for Image-to-Image Translation","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"March of Dimes Canada","funders":"","keywords":"Computer science; Image (mathematics); Relation (database); Task (project management); Inference; Image translation; Translation (biology); Artificial intelligence; Feature (linguistics); Distillation; Generative grammar; Machine learning; Semantic feature; Matrix (chemical analysis); Natural language processing; Pattern recognition (psychology); Data mining","score_opus":0.07756189650363152,"score_gpt":0.21573903210120074,"score_spread":0.13817713559756922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159735872","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023983583,0.0000983015,0.97161233,0.00030095087,0.0007417852,0.00079232635,0.000017189068,0.00015709907,0.0022964447],"genre_scores_gemma":[0.9099974,0.00004956557,0.088961475,0.000024973624,0.00021174917,0.000005263784,0.00009295611,0.000025032132,0.0006315882],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99789363,0.00024773946,0.00027310944,0.0011687046,0.00008895983,0.0003278598],"domain_scores_gemma":[0.9979633,0.00028178058,0.00021669772,0.00088467455,0.00050837843,0.00014515435],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035971566,0.0003085879,0.00033835406,0.00023449831,0.00028607412,0.00041075022,0.0008282585,0.0002364425,0.000028079929],"category_scores_gemma":[0.00013957219,0.00037494517,0.00027913973,0.00065750093,0.00004302778,0.0011250676,0.00074922893,0.00026456604,0.000032456686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005149373,0.00012460629,0.0003172176,0.00030050892,0.0001438115,0.000041814932,0.0017910167,0.97457373,0.005545491,0.0076805986,0.0006672769,0.008762443],"study_design_scores_gemma":[0.00035173926,0.00003503847,0.0023426542,0.0001592448,0.00010186284,0.0000010742082,0.000065749286,0.98974824,0.001458447,0.0047479966,0.00058245094,0.00040548362],"about_ca_topic_score_codex":0.00006395564,"about_ca_topic_score_gemma":0.00014815634,"teacher_disagreement_score":0.8860138,"about_ca_system_score_codex":0.00017311174,"about_ca_system_score_gemma":0.00016453896,"threshold_uncertainty_score":0.99987024},"labels":[],"label_agreement":null},{"id":"W3160150257","doi":"10.1109/icassp39728.2021.9413532","title":"Fast Inverse Mapping of Face GANs","year":2021,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Artificial intelligence; Face (sociological concept); Generator (circuit theory); Computer vision; Generative grammar; Pixel; Pattern recognition (psychology)","score_opus":0.021169481043766092,"score_gpt":0.21801159681872995,"score_spread":0.19684211577496386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160150257","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027298888,0.000045952263,0.97591186,0.0008880625,0.0001788318,0.000026123042,7.573628e-7,0.000028651113,0.020189878],"genre_scores_gemma":[0.73633856,0.000017347242,0.26027054,0.00042172562,0.00004491924,0.0000011685411,8.752378e-7,0.00000301706,0.002901827],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994394,0.000046405312,0.00011534303,0.00017866449,0.00010197349,0.00011819884],"domain_scores_gemma":[0.99954057,0.00003759947,0.000034359513,0.00025722527,0.00009120531,0.000039037503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007743503,0.000057215846,0.00010043037,0.000026259273,0.000038891223,0.00004005785,0.00023123344,0.00002137108,0.00012714375],"category_scores_gemma":[0.00003197341,0.000050620638,0.000050692946,0.0003027369,0.000021765325,0.00021768946,0.00017522868,0.00003650641,0.000032383152],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036268077,0.00021577072,0.0013230445,0.000047592675,0.00014819003,0.00010658964,0.0057550194,0.03618219,0.69493985,0.06722166,0.035020325,0.15903613],"study_design_scores_gemma":[0.00024313106,0.000022238684,0.0015949933,0.00002428024,0.000005028334,0.000008848836,0.0010281502,0.4289403,0.55355483,0.00089487445,0.013490293,0.00019303877],"about_ca_topic_score_codex":0.000021545588,"about_ca_topic_score_gemma":0.000028381102,"teacher_disagreement_score":0.7336087,"about_ca_system_score_codex":0.0000073273172,"about_ca_system_score_gemma":0.000049161845,"threshold_uncertainty_score":0.20642498},"labels":[],"label_agreement":null},{"id":"W3161307971","doi":"10.3390/jimaging9030069","title":"GANs for Medical Image Synthesis: An Empirical Study","year":2023,"lang":"en","type":"article","venue":"Journal of Imaging","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":241,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Medical imaging; Computer vision; RGB color model; Pattern recognition (psychology)","score_opus":0.026364980552897082,"score_gpt":0.34027293844331835,"score_spread":0.31390795789042125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161307971","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03897286,0.00006826413,0.9498896,0.0099024335,0.00078529207,0.00014950943,0.0000015201446,0.00006926539,0.00016126047],"genre_scores_gemma":[0.94834423,0.00001711686,0.050153162,0.00051839347,0.000905249,0.000010534921,3.245635e-7,0.00001723792,0.00003375653],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811774,0.00023930697,0.00048801015,0.00022499815,0.0006155444,0.00031442288],"domain_scores_gemma":[0.9983526,0.0006088951,0.00021457892,0.0002744918,0.0003036256,0.00024580242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026082408,0.00012762843,0.00029183715,0.00023400136,0.00017014366,0.00027074578,0.00096925057,0.000028703691,0.000030516627],"category_scores_gemma":[0.0011951725,0.00009715685,0.00016186618,0.00042920865,0.000045451423,0.001156646,0.00015231193,0.00019042585,0.000016512806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017916581,0.0022050694,0.04770386,0.000056038785,0.00053296034,0.0034493653,0.010967512,0.0027510673,0.011897178,0.0003803427,0.1560543,0.76382315],"study_design_scores_gemma":[0.0014726865,0.00053275924,0.022417776,0.00012254628,0.00009854556,0.0003105608,0.0030738134,0.959762,0.0041219653,0.001841322,0.00586255,0.00038351165],"about_ca_topic_score_codex":0.0000049959735,"about_ca_topic_score_gemma":0.0000047628037,"teacher_disagreement_score":0.9570109,"about_ca_system_score_codex":0.000032489243,"about_ca_system_score_gemma":0.00018518679,"threshold_uncertainty_score":0.39619413},"labels":[],"label_agreement":null},{"id":"W3162226155","doi":"10.1109/cvpr46437.2021.00374","title":"Stochastic Image-to-Video Synthesis using cINNs","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Vector Institute; Centre for Social Innovation","funders":"Natural Sciences and Engineering Research Council of Canada; Deutsche Forschungsgemeinschaft; Deutscher Akademischer Austauschdienst; Baden-Württemberg Stiftung","keywords":"Computer science; Image (mathematics); Residual; Frame (networking); Artificial intelligence; Invertible matrix; Video processing; Computer vision; Domain (mathematical analysis); Algorithm; Mathematics","score_opus":0.0302571636806015,"score_gpt":0.2683484109889294,"score_spread":0.23809124730832792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162226155","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028839617,0.00019137457,0.99098325,0.0015428575,0.0018454605,0.00038096638,0.000010585174,0.000218154,0.0019434061],"genre_scores_gemma":[0.43092754,0.000009389168,0.56771904,0.00059562456,0.000401693,0.000052312094,0.0000035889148,0.000031826006,0.00025896312],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99680114,0.00029162256,0.0004748729,0.0013846866,0.00046411998,0.0005835628],"domain_scores_gemma":[0.9969658,0.00031604542,0.0001833903,0.0018326961,0.000403325,0.00029870993],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00044201873,0.00050011394,0.00068587105,0.0002515567,0.00022392783,0.0014731833,0.0018116415,0.00024044262,0.00034168226],"category_scores_gemma":[0.00062705507,0.0004747521,0.0003348313,0.0005096583,0.000056054752,0.0004536605,0.0048835194,0.00046347757,0.00010002723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008904294,0.00015452199,0.000011000491,0.000097477634,0.00032294454,0.00013388843,0.0009241904,0.9226828,0.017314194,0.0008782875,0.0044363798,0.053035375],"study_design_scores_gemma":[0.0000787306,0.000017695236,0.00017316289,0.0003543679,0.000089098205,0.00001757256,0.0001067826,0.98224854,0.015235308,0.0006835931,0.00019826116,0.0007968543],"about_ca_topic_score_codex":0.0006748814,"about_ca_topic_score_gemma":0.0000598915,"teacher_disagreement_score":0.42804357,"about_ca_system_score_codex":0.00015854262,"about_ca_system_score_gemma":0.00044822897,"threshold_uncertainty_score":0.9997704},"labels":[],"label_agreement":null},{"id":"W3164110046","doi":"10.1016/j.media.2021.102106","title":"Conditional generation of medical images via disentangled adversarial inference","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Heart Institute; Université de Montréal","funders":"","keywords":"Inference; Computer science; Latent variable; Artificial intelligence; Regularization (linguistics); Machine learning; Adversarial system; Image (mathematics); Unsupervised learning; Variable (mathematics); Pattern recognition (psychology); Mathematics","score_opus":0.018622804010336474,"score_gpt":0.29449437174993365,"score_spread":0.2758715677395972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164110046","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002148539,0.00021000167,0.98960245,0.007007162,0.00031598,0.00005276988,0.000020566982,0.00004354275,0.0005989961],"genre_scores_gemma":[0.9665704,0.00017507798,0.03113148,0.0009510092,0.00069146627,0.000012441306,0.0003035643,0.000008138629,0.00015645775],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955598,0.0004549062,0.00061640306,0.0005765437,0.002493282,0.00029903505],"domain_scores_gemma":[0.9978969,0.00040957305,0.00018247525,0.000569197,0.00051386043,0.00042800902],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008881918,0.00019117177,0.0005425227,0.0002099678,0.00014062892,0.00014705815,0.0009105556,0.00019386313,0.0077298535],"category_scores_gemma":[0.0021472273,0.00016678903,0.00043268522,0.0017825752,0.0002977963,0.000574695,0.00047233683,0.00024946782,0.0000454907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009697467,0.0055247983,0.023735018,0.00021345101,0.020369537,0.009044494,0.0022046352,0.021181088,0.18461487,0.050367426,0.10179166,0.580856],"study_design_scores_gemma":[0.0006219537,0.000027574779,0.0018124519,0.00001680509,0.00045015436,0.000013261035,0.000025055908,0.96039736,0.03488422,0.00083538494,0.0006961533,0.00021962168],"about_ca_topic_score_codex":0.00014922819,"about_ca_topic_score_gemma":0.0002078966,"teacher_disagreement_score":0.9644218,"about_ca_system_score_codex":0.000035290337,"about_ca_system_score_gemma":0.00053855503,"threshold_uncertainty_score":0.99317724},"labels":[],"label_agreement":null},{"id":"W3166104071","doi":"10.21203/rs.3.rs-3027011/v1","title":"Multi-Resolution Continuous Normalizing Flows","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal; Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Samsung; Institut de Valorisation des Données; McGill University; Canadian Institute for Advanced Research","keywords":"Transformation (genetics); Invertible matrix; Image (mathematics); Computer science; Generative grammar; Distribution (mathematics); Ode; Conditional probability distribution; Ordinary differential equation; Algorithm; Applied mathematics; Generative model; Mathematics; Perspective (graphical); Artificial intelligence; Pattern recognition (psychology); Statistics; Differential equation; Mathematical analysis","score_opus":0.1356743159674273,"score_gpt":0.3837862226472649,"score_spread":0.24811190667983762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3166104071","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011526938,0.0011797011,0.99220175,0.0017049657,0.0016168973,0.000952299,0.000040959072,0.0004932012,0.00065752654],"genre_scores_gemma":[0.6326513,0.000999429,0.35915664,0.00007622703,0.0017923091,0.00051397935,0.00011994917,0.0001073696,0.0045827306],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950008,0.0011419859,0.00039481642,0.0011272056,0.0012544871,0.0010807385],"domain_scores_gemma":[0.99676716,0.00048819496,0.00011646929,0.00147675,0.00090874755,0.00024269006],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003124624,0.00030292186,0.0004114051,0.00054596725,0.0005697434,0.00096112536,0.002054419,0.00034655412,0.000033356097],"category_scores_gemma":[0.00082499644,0.0002874122,0.00024886132,0.00083443907,0.00011256264,0.00034725168,0.0056796903,0.0015535852,0.0007666629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000813163,0.00074459286,0.0025828585,0.0017160008,0.0005395306,0.0010697462,0.006049912,0.728817,0.008989687,0.0066791936,0.1320323,0.11069785],"study_design_scores_gemma":[0.00024755014,0.00007362603,0.003266505,0.00045672184,0.000005676325,0.000002472587,0.00012765796,0.9845357,0.00063290057,0.0011987796,0.009119013,0.00033340414],"about_ca_topic_score_codex":0.001469387,"about_ca_topic_score_gemma":0.00040764385,"teacher_disagreement_score":0.6330451,"about_ca_system_score_codex":0.00024571276,"about_ca_system_score_gemma":0.00037976328,"threshold_uncertainty_score":0.9999578},"labels":[],"label_agreement":null},{"id":"W3166610402","doi":"10.48550/arxiv.2102.08431","title":"Complex Momentum for Optimization in Games","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Momentum (technical analysis); Differentiable function; Convergence (economics); Bilinear interpolation; Generative grammar; Generalization; Adversarial system; Computer science; Mathematical optimization; Perspective (graphical); Gradient descent; Applied mathematics; Mathematics; Algorithm; Artificial intelligence; Pure mathematics; Artificial neural network; Mathematical analysis; Economics","score_opus":0.08543563773179376,"score_gpt":0.19579593974754078,"score_spread":0.11036030201574702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3166610402","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062706186,0.000067811496,0.991886,0.00021265353,0.0004795483,0.00035152823,0.000010197802,0.00006407762,0.0006575359],"genre_scores_gemma":[0.93080103,0.00016543509,0.06830111,0.00009467915,0.00007462377,0.0000032221833,0.00006213054,0.0000120106515,0.00048574706],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985012,0.00013600619,0.00017442362,0.00086101796,0.000053738433,0.00027364827],"domain_scores_gemma":[0.9988737,0.00009863042,0.00014980212,0.00063021894,0.0001731497,0.00007448862],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016773792,0.00021384658,0.00030201575,0.00018136259,0.00009043059,0.00019418013,0.000842447,0.00015517176,0.000047132467],"category_scores_gemma":[0.00003843244,0.00025930288,0.00016704695,0.0004428588,0.00004388826,0.00037258735,0.000968899,0.00018740202,0.0000035464004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009240824,0.00005917572,0.00021137814,0.000027346052,0.000033699267,0.000039335515,0.00013623272,0.9914561,0.000040033072,0.0070995362,0.00041141067,0.00047653288],"study_design_scores_gemma":[0.00040354155,0.000022928776,0.0003829777,0.00005229902,0.000020631893,5.8401787e-7,0.00009930236,0.9951375,0.0001658305,0.0029946794,0.00045234134,0.00026736737],"about_ca_topic_score_codex":0.00009584042,"about_ca_topic_score_gemma":0.00007060371,"teacher_disagreement_score":0.92453045,"about_ca_system_score_codex":0.00015145399,"about_ca_system_score_gemma":0.00013624273,"threshold_uncertainty_score":0.99998593},"labels":[],"label_agreement":null},{"id":"W3168283161","doi":"10.1016/j.media.2022.102624","title":"Towards annotation-efficient segmentation via image-to-image translation","year":2022,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Artificial intelligence; Translation (biology); Automatic image annotation; Image (mathematics); Computer vision; Computer science; Annotation; Image translation; Image segmentation; Segmentation; Pattern recognition (psychology); Image processing; Biology","score_opus":0.01095319566051169,"score_gpt":0.26759391648783776,"score_spread":0.2566407208273261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3168283161","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035961024,0.0000734221,0.98542255,0.008994014,0.00026348897,0.00025591874,0.000021364849,0.00012183659,0.0012512957],"genre_scores_gemma":[0.63824975,0.000012240792,0.35902154,0.0020483418,0.00018135092,0.000148805,0.0001549166,0.00001893477,0.00016413443],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99607235,0.00054261624,0.00053112354,0.0007089383,0.0017377196,0.0004072738],"domain_scores_gemma":[0.9985696,0.0001492318,0.00015353375,0.0005429338,0.0002372338,0.00034744453],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013301675,0.00022174152,0.00037707176,0.0005922868,0.000578898,0.00028265515,0.0009027488,0.00004912763,0.003201654],"category_scores_gemma":[0.00020790682,0.00021381995,0.00035845273,0.004119103,0.00009206841,0.0005442842,0.00033467865,0.00026604533,0.00012603436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050887786,0.0007839343,0.0001783785,0.0000223363,0.0012366263,0.00026673777,0.0063067563,0.16703793,0.08118984,0.00028000228,0.008254673,0.73439187],"study_design_scores_gemma":[0.0003692697,0.00008070353,0.0012508179,0.0000030012204,0.0003159585,0.000005363891,0.00023729283,0.9898847,0.0059809564,0.00016660237,0.0014415107,0.00026387302],"about_ca_topic_score_codex":0.00025377117,"about_ca_topic_score_gemma":0.000043282802,"teacher_disagreement_score":0.8228467,"about_ca_system_score_codex":0.00015039783,"about_ca_system_score_gemma":0.00013145385,"threshold_uncertainty_score":0.9977096},"labels":[],"label_agreement":null},{"id":"W3169447391","doi":"10.48550/arxiv.2106.06620","title":"Robust Representation Learning via Perceptual Similarity Metrics","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Overfitting; Computer science; Spurious relationship; Artificial intelligence; Metric (unit); Representation (politics); Machine learning; Feature learning; Similarity (geometry); Task (project management); Information bottleneck method; Bottleneck; Feature (linguistics); Generalization; Transformation (genetics); Mutual information; Pattern recognition (psychology); Artificial neural network; Mathematics","score_opus":0.13127294894148228,"score_gpt":0.20034865807114746,"score_spread":0.06907570912966518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3169447391","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05285225,0.00010436302,0.9440341,0.00011346172,0.0008213105,0.00017591509,0.0000030300052,0.00019236973,0.0017031865],"genre_scores_gemma":[0.9765259,0.00029574218,0.021563368,0.00008858653,0.00019298066,7.9607116e-7,0.000049336177,0.000019162437,0.0012641228],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99712497,0.0006298302,0.00023679317,0.001458957,0.00017099353,0.0003784731],"domain_scores_gemma":[0.9978537,0.00023391584,0.00027866138,0.0010487293,0.0004109631,0.00017405316],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037215097,0.00033267788,0.0004138275,0.00029394298,0.00035156176,0.0004178666,0.0012529973,0.00033506844,0.00012808031],"category_scores_gemma":[0.00024818134,0.00040467276,0.00032892887,0.0013937107,0.00009777625,0.0007712926,0.0025749728,0.0009706158,0.000035956728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007578435,0.000063959225,0.0027263993,0.000018449604,0.00009237923,0.00024469275,0.00044128622,0.99165934,0.00012204266,0.001550704,0.00023463016,0.0028385401],"study_design_scores_gemma":[0.0002261144,0.00003329036,0.0022711381,0.000032098797,0.00008212609,0.000004258735,0.00044915613,0.99435514,0.00043629415,0.0014209173,0.0002609859,0.0004284862],"about_ca_topic_score_codex":0.00041440022,"about_ca_topic_score_gemma":0.00007963502,"teacher_disagreement_score":0.9236736,"about_ca_system_score_codex":0.00022144918,"about_ca_system_score_gemma":0.00018140885,"threshold_uncertainty_score":0.9998405},"labels":[],"label_agreement":null},{"id":"W3170150828","doi":"10.48550/arxiv.2106.09015","title":"Cascading Modular Network (CAM-Net) for Multimodal Image Synthesis","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Modular design; Image (mathematics); Range (aeronautics); Focus (optics); Artificial intelligence; Limit (mathematics); Mode (computer interface); Generative grammar; Generative model; Mathematics","score_opus":0.04703540862810597,"score_gpt":0.18606726596166653,"score_spread":0.13903185733356055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170150828","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030551117,0.0002459816,0.965805,0.0001681936,0.0014024667,0.0005995025,0.000031461797,0.0002281582,0.00096813234],"genre_scores_gemma":[0.8716559,0.00019355901,0.12661007,0.00012180582,0.0006666798,0.00001187954,0.00002655346,0.00004702156,0.0006665767],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99635744,0.00037210959,0.00034487256,0.0019418863,0.00013681535,0.00084684987],"domain_scores_gemma":[0.9966275,0.0006507521,0.00035297428,0.0016684682,0.0004279644,0.00027231607],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005563338,0.0005811927,0.0007590716,0.0001743012,0.00050685514,0.00057039416,0.0020670972,0.00043944165,0.00006120547],"category_scores_gemma":[0.00023710998,0.00068201026,0.00071575376,0.0006367846,0.00013541449,0.0007907244,0.0023844636,0.00052692124,0.000027312331],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028747594,0.00007760314,0.000182371,0.000083943174,0.0003023894,0.00024290907,0.0001508055,0.9883665,0.00058005797,0.0060146307,0.0014000249,0.002570021],"study_design_scores_gemma":[0.00035260362,0.000031198528,0.00028585328,0.00018612339,0.00019273197,0.0000053544377,0.000087669214,0.9892975,0.0022604458,0.0056586983,0.00088792335,0.0007538865],"about_ca_topic_score_codex":0.00025262454,"about_ca_topic_score_gemma":0.00008733097,"teacher_disagreement_score":0.84110475,"about_ca_system_score_codex":0.00026446226,"about_ca_system_score_gemma":0.00027479898,"threshold_uncertainty_score":0.9995631},"labels":[],"label_agreement":null},{"id":"W3173104782","doi":"","title":"Markpainting: Adversarial Machine Learning meets Inpainting","year":2021,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Inpainting; Computer science; Watermark; Artificial intelligence; Computer vision; Image (mathematics); Interpolation (computer graphics); Generative grammar; Adversarial system; Image editing","score_opus":0.027111261133747993,"score_gpt":0.2661754514699486,"score_spread":0.2390641903362006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173104782","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008758462,0.00030207552,0.84763277,0.018432679,0.002921214,0.00019135488,0.0000108678305,0.00061124243,0.12113936],"genre_scores_gemma":[0.96809703,0.00012493633,0.02533878,0.0006387932,0.0005558671,0.000009992447,0.00009213583,0.000029389887,0.0051130694],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99684197,0.00073926366,0.00044824442,0.0008138862,0.00069911056,0.0004575257],"domain_scores_gemma":[0.99828035,0.00039098077,0.0003151044,0.00033053945,0.0005411579,0.00014186517],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00091593433,0.00032966715,0.00031843528,0.0002097635,0.00048854953,0.0007504803,0.0009884764,0.0001080893,0.0014692673],"category_scores_gemma":[0.0018616266,0.00033010557,0.00018955074,0.00035584308,0.000054211527,0.00059530884,0.0007071626,0.0011205863,0.0001681447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001893194,0.00037691247,0.030390214,0.0000359333,0.00060352846,0.0007429465,0.0022513357,0.23733333,0.053649645,0.34401172,0.0006295021,0.32978562],"study_design_scores_gemma":[0.0006529338,0.00011478517,0.00068803283,0.00009309249,0.000011191011,0.000035600053,0.00012248113,0.94889563,0.0029965218,0.0010296699,0.044996407,0.00036366336],"about_ca_topic_score_codex":0.00017301796,"about_ca_topic_score_gemma":0.00007463067,"teacher_disagreement_score":0.95933855,"about_ca_system_score_codex":0.000100044344,"about_ca_system_score_gemma":0.00015413282,"threshold_uncertainty_score":0.9999151},"labels":[],"label_agreement":null},{"id":"W3173180830","doi":"10.1016/j.jvcir.2021.103187","title":"EdgeGAN: One-way mapping generative adversarial network based on the edge information for unpaired training set","year":2021,"lang":"en","type":"article","venue":"Journal of Visual Communication and Image Representation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Alberta","funders":"","keywords":"Consistency (knowledge bases); Computer science; Kernel (algebra); Adversarial system; Enhanced Data Rates for GSM Evolution; Convolution (computer science); Image translation; Artificial intelligence; Set (abstract data type); Image (mathematics); Generative adversarial network; Translation (biology); Pattern recognition (psychology); Algorithm; Data mining; Mathematics; Artificial neural network","score_opus":0.078268872872566,"score_gpt":0.3202820429658205,"score_spread":0.24201317009325451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173180830","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027144663,0.00017665417,0.9852145,0.010293784,0.00031502004,0.00025350452,0.000003721172,0.000015659336,0.0010127206],"genre_scores_gemma":[0.78947324,0.00019744864,0.2082476,0.0015549123,0.00042078222,0.000019298875,0.000048197493,0.000008037579,0.000030498037],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803793,0.00082305266,0.00054849265,0.00013505698,0.000292445,0.00016302541],"domain_scores_gemma":[0.99682426,0.0012042904,0.00063429534,0.00039464148,0.0008763269,0.000066161825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014079274,0.00012369647,0.00022176518,0.000100375124,0.00053007825,0.00052833103,0.0003816892,0.000054140277,0.000013531472],"category_scores_gemma":[0.0008754711,0.00009875474,0.00013006864,0.00040626657,0.00007378678,0.0017785873,0.00011969508,0.00021477697,0.0000021428941],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00094346964,0.00076046656,0.0004375819,0.00012646486,0.0007926339,0.000013569707,0.044908185,0.16135253,0.056939587,0.048302364,0.07406636,0.6113568],"study_design_scores_gemma":[0.0015335218,0.00025262695,0.0017402926,0.00014746631,0.00004137552,0.000015393243,0.0032152715,0.9713369,0.012222561,0.0032340148,0.00607941,0.00018114438],"about_ca_topic_score_codex":0.0000051808875,"about_ca_topic_score_gemma":0.0000039008764,"teacher_disagreement_score":0.8099844,"about_ca_system_score_codex":0.00004883022,"about_ca_system_score_gemma":0.0001744827,"threshold_uncertainty_score":0.5094708},"labels":[],"label_agreement":null},{"id":"W3174139848","doi":"10.1609/aaai.v35i9.16967","title":"IB-GAN: Disentangled Representation Learning with Information Bottleneck Generative Adversarial Networks","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Defense Acquisition Program Administration; Agency for Defense Development","keywords":"Representation (politics); Bottleneck; Generator (circuit theory); Computer science; Information bottleneck method; Layer (electronics); Generative grammar; Artificial intelligence; Quality (philosophy); Space (punctuation); Mutual information; Power (physics); Materials science","score_opus":0.032913505239313176,"score_gpt":0.2531786174233732,"score_spread":0.22026511218406003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174139848","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021530306,0.000027275342,0.96374094,0.003364764,0.00067976967,0.0003908589,0.0000029960443,0.00008772525,0.010175361],"genre_scores_gemma":[0.989066,0.00005957983,0.010194625,0.00024191299,0.0001953524,0.000025129037,0.00000538462,0.000009546521,0.00020246043],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818,0.0000710362,0.0004955384,0.00042371565,0.0005135965,0.00031613343],"domain_scores_gemma":[0.9978329,0.00011332483,0.0004762832,0.00026584705,0.0012256709,0.000085955035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002957174,0.00022920547,0.00026942894,0.00008070426,0.00037079447,0.00054160185,0.00078011834,0.00008585998,0.000065361724],"category_scores_gemma":[0.0004478748,0.00016740896,0.00011352632,0.0009198543,0.00017754662,0.0015271701,0.0002585352,0.0003317597,0.000028967865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040240353,0.00022329121,0.0012926621,0.000035685985,0.00014176591,0.000004915986,0.0055068,0.19776718,0.03620306,0.5903208,0.0006401333,0.16746128],"study_design_scores_gemma":[0.00006925251,0.00015270493,0.00023050705,0.00010021422,0.00002135463,0.0000059106083,0.0011859479,0.55729187,0.43357718,0.007005924,0.00015977747,0.00019937906],"about_ca_topic_score_codex":0.000035556583,"about_ca_topic_score_gemma":0.000021905393,"teacher_disagreement_score":0.9675357,"about_ca_system_score_codex":0.000054464537,"about_ca_system_score_gemma":0.00014892449,"threshold_uncertainty_score":0.68267393},"labels":[],"label_agreement":null},{"id":"W3174600408","doi":"10.1609/aaai.v35i9.16982","title":"Deep Probabilistic Canonical Correlation Analysis","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Canonical correlation; Probabilistic logic; Artificial intelligence; Generative grammar; Inference; Computer science; Representation (politics); Generative model; Set (abstract data type); Latent variable model; Latent variable; Interpretation (philosophy); Machine learning; Algorithm; Mathematics","score_opus":0.04804200418101987,"score_gpt":0.27169572563000577,"score_spread":0.2236537214489859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174600408","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015443086,0.000045774876,0.96846646,0.0036253282,0.00047575196,0.00023160444,0.0000024062674,0.000056951667,0.011652634],"genre_scores_gemma":[0.98883766,0.00001982722,0.01058836,0.00016496073,0.0000662411,0.000014187049,0.0000011107609,0.0000061906358,0.00030143835],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826366,0.000042890675,0.00047275584,0.0005263139,0.00042343506,0.0002709643],"domain_scores_gemma":[0.9980637,0.00014818257,0.0002784477,0.00035194776,0.0010741644,0.00008359936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035555224,0.00017315858,0.00029698154,0.00010575849,0.00020002191,0.00028457245,0.0010676814,0.000080535356,0.00015906729],"category_scores_gemma":[0.00082273106,0.00013116725,0.0002305603,0.0019097303,0.00017842032,0.00032755715,0.00032947102,0.00021618925,0.000045763874],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001987014,0.00016152742,0.0005347864,0.000013918798,0.00012238047,0.0000013966309,0.00061609334,0.027594913,0.01107683,0.9178565,0.00007947186,0.041922312],"study_design_scores_gemma":[0.000013814817,0.000048680402,0.0008030129,0.00003520601,0.000099868266,0.0000023282041,0.00014890856,0.7979424,0.1343734,0.06632992,0.000053704953,0.00014877555],"about_ca_topic_score_codex":0.000035751957,"about_ca_topic_score_gemma":0.000099347715,"teacher_disagreement_score":0.9733946,"about_ca_system_score_codex":0.000050612176,"about_ca_system_score_gemma":0.00017050642,"threshold_uncertainty_score":0.5348846},"labels":[],"label_agreement":null},{"id":"W3174711319","doi":"10.1609/aaai.v35i3.16368","title":"Object-Centric Image Generation from Layouts","year":2021,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal","funders":"","keywords":"Computer science; Object (grammar); Generator (circuit theory); Artificial intelligence; Bounding overwatch; Scene graph; Fidelity; Metric (unit); Spurious relationship; Similarity (geometry); Minimum bounding box; Computer vision; Image (mathematics); Graph; Generative grammar; Pattern recognition (psychology); Theoretical computer science; Machine learning","score_opus":0.016643216756704424,"score_gpt":0.22103656153949813,"score_spread":0.2043933447827937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174711319","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052763205,0.0003241188,0.98180556,0.0014768958,0.00067949045,0.00004586195,0.000003370329,0.00008846021,0.010299942],"genre_scores_gemma":[0.6201724,0.000045856166,0.37573028,0.001111155,0.00061681273,0.0000044123467,0.000026273281,0.0000065581216,0.0022862935],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990296,0.00010913673,0.0001402584,0.00037351574,0.00016472867,0.00018280282],"domain_scores_gemma":[0.99929893,0.000050503953,0.00003488955,0.00041255774,0.00013522051,0.00006791065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000079575766,0.000097899094,0.00011205883,0.000026456804,0.000107325446,0.00032851892,0.0002574105,0.000038130143,0.00045688185],"category_scores_gemma":[0.00005148067,0.0000864054,0.0000612607,0.00032427162,0.000013157813,0.0005212546,0.00017005406,0.000056670804,0.00023746365],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037604266,0.00022909424,0.0006566745,0.00000279558,0.00010617589,0.00025411416,0.00063179486,0.0030535343,0.69949126,0.035859156,0.14676394,0.1129477],"study_design_scores_gemma":[0.00032316585,0.000016409987,0.0024309102,0.000004000769,0.000010857804,0.0000058789137,0.000029082117,0.50554025,0.47368845,0.0015102099,0.016199946,0.00024084242],"about_ca_topic_score_codex":0.00008933554,"about_ca_topic_score_gemma":0.00007410431,"teacher_disagreement_score":0.61489606,"about_ca_system_score_codex":0.000022062046,"about_ca_system_score_gemma":0.00007355297,"threshold_uncertainty_score":0.5002536},"labels":[],"label_agreement":null},{"id":"W3175691375","doi":"10.1145/3404890","title":"Blockchain-enabled Tensor-based Conditional Deep Convolutional GAN for Cyber-physical-Social Systems","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Internet Technology","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Computer science; Cyber-physical system; Discriminator; Tensor (intrinsic definition); Artificial intelligence; Deep learning; Physical system; Big data; Theoretical computer science; Machine learning; Data mining","score_opus":0.016111622229878386,"score_gpt":0.2474896238196813,"score_spread":0.2313780015898029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175691375","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005166477,0.00005705486,0.9860878,0.0071918727,0.000649682,0.00026804174,0.00007949582,0.00032886557,0.00017072995],"genre_scores_gemma":[0.97557026,0.0000019221416,0.02272551,0.00038442633,0.00017728221,0.00026502582,0.00003344772,0.000018487288,0.0008236168],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984765,0.00008832898,0.00027296602,0.0005758677,0.00020985158,0.00037648034],"domain_scores_gemma":[0.998506,0.00036596128,0.00010046938,0.00052958605,0.0004380579,0.00005990164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009741567,0.0002152448,0.00031578622,0.0002627353,0.00030638682,0.000098120654,0.0007666156,0.00022156676,0.00008444027],"category_scores_gemma":[0.00008945725,0.00021933379,0.00021647627,0.0005501548,0.00020520408,0.00009793353,0.00002327729,0.00028348237,0.00005322016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021723796,0.0026163922,0.000117798,0.0001085246,0.0012749023,0.00014285064,0.0006486086,0.34651807,0.03740389,0.5498236,0.009249231,0.0518789],"study_design_scores_gemma":[0.0014247214,0.00032745043,0.00009488584,0.000035046713,0.00006478366,0.00006315388,0.0001871969,0.87431926,0.08893432,0.021313058,0.012847216,0.00038890328],"about_ca_topic_score_codex":0.00001888217,"about_ca_topic_score_gemma":0.000030229343,"teacher_disagreement_score":0.9704038,"about_ca_system_score_codex":0.00012254293,"about_ca_system_score_gemma":0.00013844429,"threshold_uncertainty_score":0.8944172},"labels":[],"label_agreement":null},{"id":"W3176009039","doi":"10.1109/cvpr46437.2021.01624","title":"Saliency-Guided Image Translation","year":2021,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Translation (biology); Artificial intelligence; Image (mathematics); Image translation; Encoder; Generator (circuit theory); Saliency map; Task (project management); Representation (politics); Generative grammar; Computer vision; Pattern recognition (psychology)","score_opus":0.029041825910683095,"score_gpt":0.25693956080597674,"score_spread":0.22789773489529364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176009039","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003506743,0.00010952726,0.9283877,0.0029030163,0.0002285308,0.000034534034,4.391059e-7,0.00008201398,0.06790358],"genre_scores_gemma":[0.3702856,0.000022408682,0.6272617,0.0006776088,0.00009326978,0.000003092602,0.0000028438444,0.000004236041,0.0016492723],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993166,0.00006579058,0.000120100805,0.00023577316,0.00012227784,0.00013948798],"domain_scores_gemma":[0.99950236,0.000044567707,0.000019889621,0.0002874582,0.00010101781,0.00004471083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000104818275,0.00006607668,0.00007803549,0.000021065875,0.00007406091,0.00015294926,0.00020588019,0.00002420032,0.0002692821],"category_scores_gemma":[0.000026089037,0.000057766174,0.000054673128,0.00026364543,0.000015363075,0.0005189834,0.000051797433,0.000037290683,0.000095287745],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003013256,0.00015310668,0.00015439514,0.0000117068585,0.000047375466,0.00012248181,0.0010460209,0.0021344454,0.37103,0.103997,0.046075314,0.47522515],"study_design_scores_gemma":[0.00041648143,0.000025930354,0.0010941715,0.00000854632,0.000009072599,0.000033052533,0.00005210712,0.47055632,0.4795921,0.008227996,0.039683085,0.00030112843],"about_ca_topic_score_codex":0.00001224208,"about_ca_topic_score_gemma":0.000014960022,"teacher_disagreement_score":0.47492403,"about_ca_system_score_codex":0.000008368637,"about_ca_system_score_gemma":0.000051391413,"threshold_uncertainty_score":0.29484504},"labels":[],"label_agreement":null},{"id":"W3179205254","doi":"10.3390/fi13070179","title":"Fast Flow Reconstruction via Robust Invertible n × n Convolution","year":2021,"lang":"en","type":"article","venue":"Future Internet","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Invertible matrix; Convolution (computer science); Computer science; Convolution theorem; Generative model; Algorithm; Overlap–add method; Simple (philosophy); Flow (mathematics); Generative grammar; Mathematics; Artificial intelligence; Pure mathematics; Fourier transform; Artificial neural network; Mathematical analysis; Fourier analysis","score_opus":0.010141369870634393,"score_gpt":0.18993336874269265,"score_spread":0.17979199887205827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3179205254","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018556874,0.0003368004,0.9881816,0.0011653303,0.0051832376,0.000056453475,0.00000287993,0.00009483439,0.003123184],"genre_scores_gemma":[0.6809743,0.00007973935,0.31074402,0.0011401057,0.0032114408,0.000013347522,0.000034940098,0.000017708278,0.0037844214],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989832,0.00011114253,0.00018421265,0.00037791108,0.00013872814,0.00020482576],"domain_scores_gemma":[0.99933684,0.00002101737,0.00006694386,0.00033551294,0.00016700705,0.0000726971],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000101254576,0.00012961224,0.00014349837,0.000047834143,0.00006692242,0.00016921932,0.00029399144,0.00008983161,0.00034085347],"category_scores_gemma":[0.000023041639,0.00012072334,0.00008373811,0.00026660753,0.00003287001,0.0005283546,0.00015728537,0.00014907097,0.00015868699],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023889681,0.000104383886,0.00077598,0.000024240857,0.0001440748,0.00009288446,0.0009909637,0.01399474,0.01299951,0.015410409,0.0888105,0.8666284],"study_design_scores_gemma":[0.00026284272,0.000047404672,0.0008306241,0.000039827988,0.00001111265,0.00021028417,0.000106196094,0.91755563,0.042635597,0.0014479675,0.036623962,0.00022855881],"about_ca_topic_score_codex":0.000035248537,"about_ca_topic_score_gemma":0.00010492719,"teacher_disagreement_score":0.9035609,"about_ca_system_score_codex":0.00005695504,"about_ca_system_score_gemma":0.000053104915,"threshold_uncertainty_score":0.4922955},"labels":[],"label_agreement":null},{"id":"W3180352537","doi":"","title":"FAST-ADAM in Semi-Supervised Generative Adversarial Networks","year":2019,"lang":"en","type":"article","venue":"International Journal of Internet, Broadcasting and Communication","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Discriminator; Generator (circuit theory); Computer science; Benchmark (surveying); Generative grammar; Adversarial system; Stability (learning theory); Machine learning; Artificial intelligence; Convergence (economics); Artificial neural network; Power (physics)","score_opus":0.010661342132262996,"score_gpt":0.23808583896119653,"score_spread":0.22742449682893354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3180352537","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21845903,0.0014667421,0.774164,0.0017116728,0.0015667041,0.00013720835,0.0000014619527,0.000021577263,0.0024715746],"genre_scores_gemma":[0.9709082,0.00037786327,0.027946789,0.0002815903,0.0002633871,0.0000028105985,0.000004774102,0.000008916787,0.00020561961],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844784,0.00028732006,0.0005822685,0.0001968364,0.00032365878,0.0001620868],"domain_scores_gemma":[0.9984031,0.00028641685,0.00045755476,0.00029871488,0.00048824368,0.00006599608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006572543,0.00014747443,0.00023653555,0.00021575172,0.000040928913,0.00027272588,0.001392402,0.00007265634,0.000037436886],"category_scores_gemma":[0.00012929732,0.00013321504,0.000092042304,0.00015699513,0.00004625247,0.00088133785,0.00045904677,0.00037384994,0.000007876506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059383496,0.00047704115,0.058088616,0.000019347222,0.000646494,0.000086572065,0.009928923,0.3699836,0.00796593,0.015435752,0.0022426944,0.5345312],"study_design_scores_gemma":[0.0012979282,0.00014220759,0.0055405064,0.00032293546,0.000008105012,0.00011462639,0.00026603878,0.98935086,0.0008969162,0.0006471324,0.0012435222,0.00016922837],"about_ca_topic_score_codex":0.00014503725,"about_ca_topic_score_gemma":0.00004018921,"teacher_disagreement_score":0.7524492,"about_ca_system_score_codex":0.00010515552,"about_ca_system_score_gemma":0.00005773453,"threshold_uncertainty_score":0.5432351},"labels":[],"label_agreement":null},{"id":"W3183193032","doi":"","title":"Symmetric Wasserstein Autoencoders","year":2021,"lang":"en","type":"article","venue":"NPARC","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Representation (politics); Computer science; Pattern recognition (psychology); Generative model; Autoencoder; Latent variable; Artificial intelligence; Generative grammar; Space (punctuation); Algorithm; Machine learning; Deep learning","score_opus":0.013684586028286885,"score_gpt":0.2188162683760395,"score_spread":0.20513168234775264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3183193032","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007325422,0.00013388693,0.8964574,0.0032324018,0.0004605676,0.00003537262,6.832242e-7,0.00008275364,0.098864436],"genre_scores_gemma":[0.68897206,0.000028736265,0.30831268,0.0006474647,0.00010744781,0.0000043655386,0.0000013652508,0.000005727321,0.0019201128],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990793,0.000090120186,0.000116422365,0.00030116382,0.00018786482,0.00022511721],"domain_scores_gemma":[0.9992921,0.00008344183,0.00003270878,0.0004133815,0.00009925251,0.00007915049],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013826757,0.00008617032,0.00011636416,0.0000669575,0.00010187177,0.0001556785,0.0003691063,0.000035728088,0.00021721334],"category_scores_gemma":[0.00011166929,0.00008043733,0.00007125061,0.00084105565,0.000020222507,0.0002917199,0.00017365013,0.00007785879,0.00011706305],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000049349023,0.00020563455,0.00041218323,0.000020141193,0.000121508834,0.00038403252,0.0006586042,0.007674347,0.116779625,0.38473368,0.0714269,0.4175784],"study_design_scores_gemma":[0.00036813578,0.000050215138,0.0010952449,0.000017133358,0.000013753027,0.00002867995,0.000091860915,0.83142453,0.09112458,0.028820818,0.04661453,0.0003504976],"about_ca_topic_score_codex":0.0000045377215,"about_ca_topic_score_gemma":0.0000053545164,"teacher_disagreement_score":0.8237502,"about_ca_system_score_codex":0.00002679236,"about_ca_system_score_gemma":0.000092359616,"threshold_uncertainty_score":0.3280139},"labels":[],"label_agreement":null},{"id":"W3183287321","doi":"","title":"PROVIDE: A Probabilistic Framework for Unsupervised Video Decomposition","year":2021,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Inference; Leverage (statistics); Artificial intelligence; Probabilistic logic; Unsupervised learning; Benchmark (surveying); Machine learning; Decomposition; Pattern recognition (psychology)","score_opus":0.04810708885814038,"score_gpt":0.32039773356764245,"score_spread":0.2722906447095021,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3183287321","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028347499,0.00015812245,0.99184525,0.0034942275,0.00070881733,0.0006054102,0.000008900217,0.0000870105,0.00025748662],"genre_scores_gemma":[0.7329317,0.00002127809,0.26600444,0.00058061903,0.00022421211,0.00017670017,0.000014222248,0.000012516219,0.00003433622],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777615,0.00020492848,0.0005734894,0.0007321488,0.0002341453,0.0004791248],"domain_scores_gemma":[0.99771184,0.0010903832,0.00010307177,0.0005908507,0.00039565403,0.00010818105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005066144,0.00021480228,0.00028462018,0.00010400878,0.00019872632,0.0003434424,0.00060967973,0.0001306028,0.00007025931],"category_scores_gemma":[0.0016592038,0.000213604,0.00014172832,0.000880632,0.00009402125,0.0003757043,0.00015661688,0.00021080894,0.000046223777],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046993704,0.00021418127,0.000025326697,0.00003110941,0.000013673106,0.000024324354,0.00085655495,0.19244249,0.0032868683,0.62216806,0.0000839702,0.18080643],"study_design_scores_gemma":[0.000029627543,0.00006102262,0.00002230782,0.00007638909,0.0000057051984,0.0000037493476,0.00015260038,0.50836104,0.025547799,0.46508276,0.0004807885,0.00017620719],"about_ca_topic_score_codex":0.00009179114,"about_ca_topic_score_gemma":0.0004793052,"teacher_disagreement_score":0.73009694,"about_ca_system_score_codex":0.00014563021,"about_ca_system_score_gemma":0.00025309192,"threshold_uncertainty_score":0.8710518},"labels":[],"label_agreement":null},{"id":"W3184159859","doi":"10.48550/arxiv.2107.12521","title":"Restricted Boltzmann Machine and Deep Belief Network: Tutorial and Survey","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Boltzmann machine; Restricted Boltzmann machine; Deep belief network; Graphical model; Gibbs sampling; Conditional random field; Artificial intelligence; Computer science; Belief propagation; Ising model; Divergence (linguistics); Artificial neural network; Boltzmann constant; Hidden Markov model; Markov chain Monte Carlo; Machine learning; Statistical physics; Algorithm; Physics; Bayesian probability","score_opus":0.04767065689551333,"score_gpt":0.17712189866175557,"score_spread":0.12945124176624223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3184159859","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12553892,0.0017912547,0.8697128,0.000091513684,0.0019811143,0.00026320954,0.000024706695,0.00012303726,0.00047341557],"genre_scores_gemma":[0.99144393,0.0020801325,0.0054075094,0.00008842579,0.0005000475,7.1062004e-7,0.00006929499,0.000018848099,0.00039110184],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99722445,0.00066502666,0.00022366742,0.0013464921,0.00010140539,0.00043897858],"domain_scores_gemma":[0.9981197,0.00034013824,0.00020857941,0.0008564414,0.0002324169,0.00024269252],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045101607,0.00037638456,0.00048591496,0.00012028433,0.0003157038,0.00045482774,0.0007545179,0.0003151101,0.000017932543],"category_scores_gemma":[0.00013191596,0.00042016423,0.000101732345,0.0006316633,0.00014461872,0.0004173701,0.0032288465,0.000538376,0.000003730352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024057532,0.00023958518,0.060776375,0.0001277978,0.0007684267,0.0014182258,0.0007065859,0.89531195,0.00010827553,0.024268912,0.0028105597,0.013222705],"study_design_scores_gemma":[0.0006732528,0.00006500708,0.071761005,0.000060931387,0.000086194996,0.0000082869865,0.00002264739,0.9224633,0.000027740176,0.0033570565,0.0008957433,0.0005788132],"about_ca_topic_score_codex":0.001406602,"about_ca_topic_score_gemma":0.0013499376,"teacher_disagreement_score":0.86590505,"about_ca_system_score_codex":0.0000654568,"about_ca_system_score_gemma":0.00014878772,"threshold_uncertainty_score":0.999825},"labels":[],"label_agreement":null},{"id":"W3184623357","doi":"10.48550/arxiv.2106.13435","title":"NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image\\n Generation","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Latent variable; Artificial intelligence; MNIST database; Interpretability; Parsing; Image (mathematics); Parametric statistics; Generative model; Heuristics; Variable (mathematics); Latent variable model; Machine learning; Dependency grammar; Generative grammar; Deep learning; Mathematics","score_opus":0.07431892535437394,"score_gpt":0.19199094768395975,"score_spread":0.1176720223295858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3184623357","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021723015,0.00008194246,0.9758943,0.00009950986,0.0011202883,0.00062855263,0.000047152633,0.00010858426,0.00029666311],"genre_scores_gemma":[0.7469997,0.00009014139,0.25109583,0.00014583486,0.0002306028,0.0000061894652,0.0000954198,0.000023936282,0.0013123484],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99738896,0.00014360598,0.0002939188,0.0015543055,0.00013062602,0.0004885942],"domain_scores_gemma":[0.99749476,0.000106804844,0.0003059151,0.0012750966,0.0006324794,0.00018496618],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030107802,0.00043146906,0.0005077779,0.00031864078,0.00031832702,0.0006094867,0.0013132258,0.00037141895,0.00002964422],"category_scores_gemma":[0.00009810676,0.00048577724,0.00034708282,0.0009905582,0.00006258566,0.000742499,0.0013518385,0.00039526023,0.000009366529],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014260129,0.00006290881,0.000039851584,0.000044511322,0.00013321279,0.000039928047,0.00013194565,0.9878236,0.0023867148,0.007259318,0.0016125636,0.00045117585],"study_design_scores_gemma":[0.0005290023,0.000036206016,0.0000567435,0.000028798371,0.00013032442,0.0000033294848,0.000014443886,0.98456883,0.002229381,0.011794488,0.00009667661,0.0005117814],"about_ca_topic_score_codex":0.00013482654,"about_ca_topic_score_gemma":0.000053811924,"teacher_disagreement_score":0.7252767,"about_ca_system_score_codex":0.00025079746,"about_ca_system_score_gemma":0.0005215309,"threshold_uncertainty_score":0.9997594},"labels":[],"label_agreement":null},{"id":"W3186739292","doi":"10.3390/informatics8030049","title":"Fashion Recommendation Systems, Models and Methods: A Review","year":2021,"lang":"en","type":"review","venue":"Informatics","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Recommender system; Computer science; sort; Product (mathematics); Collaborative filtering; Order (exchange); Fashion industry; Data science; Artificial intelligence; Clothing; World Wide Web; Information retrieval; Business","score_opus":0.10432507724204451,"score_gpt":0.38722306242573085,"score_spread":0.28289798518368636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186739292","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.0165313e-10,0.5036154,0.49477193,0.000033482236,0.00026814322,0.0003311577,0.0000049626174,0.00002590092,0.00094904716],"genre_scores_gemma":[2.344337e-8,0.732839,0.26667133,0.00023611673,0.00005493279,0.000059319205,0.000076447766,0.000009197029,0.000053677897],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997681,0.0006640135,0.0011120761,0.0001877074,0.00015566098,0.00019951827],"domain_scores_gemma":[0.9981354,0.0003634776,0.00072180695,0.00054446585,0.00014979085,0.00008506805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013906532,0.0003001253,0.0014563438,0.00010029918,0.000098427816,0.00042136016,0.0004527517,0.00015451275,0.000009517582],"category_scores_gemma":[0.00014031539,0.00022849481,0.00019414586,0.00042000218,0.000016683785,0.0012056109,0.00041122374,0.00023458003,0.000023248027],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.3965471e-8,0.0000037554294,3.0602705e-9,0.028007694,0.000045162426,6.056758e-7,0.00007667471,0.000064136264,2.8535654e-9,0.002586942,0.004880809,0.9643342],"study_design_scores_gemma":[0.00002387518,0.0000084373105,2.74154e-9,0.030735243,0.00018121178,0.000053506265,0.000022141954,0.16314569,5.4619726e-8,0.000037398084,0.80559283,0.00019957926],"about_ca_topic_score_codex":0.0000025801767,"about_ca_topic_score_gemma":2.9191202e-7,"teacher_disagreement_score":0.96413463,"about_ca_system_score_codex":0.00006230421,"about_ca_system_score_gemma":0.00017097656,"threshold_uncertainty_score":0.9317748},"labels":[],"label_agreement":null},{"id":"W3192788685","doi":"","title":"A Variational Perspective on Diffusion-Based Generative Models and Score Matching","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Autoencoder; Generative model; Generative grammar; Matching (statistics); Diffusion; Computer science; Applied mathematics; Diffusion process; Bridging (networking); Function (biology); Score; Mathematics; Algorithm; Mathematical optimization; Artificial intelligence; Statistics; Machine learning; Deep learning; Physics","score_opus":0.053808954329275856,"score_gpt":0.1851875168588595,"score_spread":0.13137856252958366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3192788685","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07531622,0.00004003429,0.92112494,0.0006349375,0.000114993076,0.000074675234,0.00000631011,0.000048173664,0.0026396946],"genre_scores_gemma":[0.98313105,0.000023396826,0.015711604,0.0006473839,0.00007072763,5.5426716e-7,0.0000038857115,0.0000072698485,0.00040414033],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882275,0.00017527539,0.00008293201,0.00064394367,0.00008620814,0.0001888898],"domain_scores_gemma":[0.9990733,0.00020068295,0.00006142526,0.00031128488,0.00024892742,0.000104355284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000099428886,0.00015062487,0.00014683661,0.00008653668,0.00031575724,0.00012004958,0.00024726347,0.000054647448,0.000034019562],"category_scores_gemma":[0.00003357457,0.00015566556,0.00007198715,0.000433669,0.000056328117,0.0005062566,0.00017748456,0.00012701761,0.000011131001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000119642855,0.00005368639,0.00011782124,0.000001466544,0.000021846785,0.00009153754,0.00031818307,0.5480208,0.00044526174,0.4507131,0.000041126892,0.00016321965],"study_design_scores_gemma":[0.00043808745,0.00004088819,0.0009551478,0.000017791848,0.000013598872,0.0000026836965,0.0002655071,0.8842969,0.0008551365,0.1129261,0.000023460398,0.00016468113],"about_ca_topic_score_codex":0.00007510634,"about_ca_topic_score_gemma":0.00003738491,"teacher_disagreement_score":0.9078148,"about_ca_system_score_codex":0.00013410469,"about_ca_system_score_gemma":0.00016525161,"threshold_uncertainty_score":0.6347858},"labels":[],"label_agreement":null},{"id":"W3194913784","doi":"10.48550/arxiv.2108.10430","title":"CoverTheFace: face covering monitoring and demonstrating using deep learning and statistical shape analysis","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Landmark; Computer science; Overlay; Face (sociological concept); Artificial intelligence; Computer vision; Margin (machine learning); Pipeline (software); Face masks; Facial recognition system; Coronavirus disease 2019 (COVID-19); Pattern recognition (psychology); Machine learning","score_opus":0.04883306318564095,"score_gpt":0.21066988523335442,"score_spread":0.16183682204771346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194913784","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42045417,0.0003327818,0.57891864,0.000006989444,0.00010765047,0.00006437518,0.000003206502,0.000043272015,0.00006892137],"genre_scores_gemma":[0.9456675,0.0005480243,0.05364335,0.0000076962915,0.000064464315,3.3175073e-7,0.0000068561662,0.000014158204,0.000047593312],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978634,0.0003025443,0.00021642275,0.0011519965,0.000109939305,0.00035568175],"domain_scores_gemma":[0.9987932,0.0003300677,0.00021676203,0.00034502608,0.00011873141,0.00019625499],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026679013,0.00032121455,0.000501837,0.00020814138,0.00044523724,0.00066192466,0.00035330924,0.00019169546,0.000018672146],"category_scores_gemma":[0.00011416384,0.0003887383,0.00012312825,0.0006815102,0.00012206422,0.0005220768,0.0017863968,0.0005920706,9.768795e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061327323,0.000013579359,0.05882918,0.000038760303,0.0004436083,0.00019482484,0.00037883132,0.933286,0.00056172255,0.0008913155,3.5609153e-7,0.005355659],"study_design_scores_gemma":[0.00016859372,0.000019363266,0.007538357,0.00007886816,0.00047479855,0.0000069110765,0.00082347717,0.98994523,0.00026593573,0.0002884569,0.000008787447,0.0003812226],"about_ca_topic_score_codex":0.0002143887,"about_ca_topic_score_gemma":0.00003267895,"teacher_disagreement_score":0.5252753,"about_ca_system_score_codex":0.00010758572,"about_ca_system_score_gemma":0.00008504064,"threshold_uncertainty_score":0.9998565},"labels":[],"label_agreement":null},{"id":"W3197235162","doi":"10.1007/s10489-022-03199-8","title":"VARGAN: variance enforcing network enhanced GAN","year":2022,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Generator (circuit theory); Variance (accounting); Set (abstract data type); Convergence (economics); Mode (computer interface); Process (computing); Modality (human–computer interaction); Modal; Generative grammar; Network architecture; Artificial intelligence; Diversity (politics); Image (mathematics); Machine learning; Algorithm; Pattern recognition (psychology); Human–computer interaction","score_opus":0.011479360941281899,"score_gpt":0.21381679251075125,"score_spread":0.20233743156946934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197235162","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017801861,0.00017124148,0.9611344,0.00023288291,0.0009438818,0.0002577937,0.0000017835326,0.00017861678,0.036901426],"genre_scores_gemma":[0.9195335,0.00003450757,0.078062706,0.001368772,0.00034218328,0.00016244497,0.000003725856,0.000017953322,0.00047420178],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978788,0.000101405654,0.00035169232,0.00066730817,0.0004061976,0.0005946025],"domain_scores_gemma":[0.9987122,0.00020205222,0.0001605692,0.0007632853,0.000053060423,0.00010886401],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059039454,0.00022257843,0.00024052558,0.00005781175,0.0008397833,0.00015460317,0.0016497062,0.000039012117,0.00055874913],"category_scores_gemma":[0.000025446338,0.00023514355,0.00008029671,0.001035883,0.00005764068,0.00025843023,0.0007214815,0.00033747515,0.00016798748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014733979,0.00003971666,0.0000067043534,0.000003797494,0.00002444065,0.000007792499,0.0007965723,0.62181884,0.009312078,0.24867705,0.0024142347,0.11688406],"study_design_scores_gemma":[0.00021625403,0.00023275656,0.00013612784,0.000019728319,0.000022059385,0.000027696398,0.0005271091,0.5416703,0.2873844,0.08928721,0.07932895,0.001147421],"about_ca_topic_score_codex":0.000027425565,"about_ca_topic_score_gemma":0.0000043023992,"teacher_disagreement_score":0.9193555,"about_ca_system_score_codex":0.00009399241,"about_ca_system_score_gemma":0.00008701409,"threshold_uncertainty_score":0.9588876},"labels":[],"label_agreement":null},{"id":"W3197836096","doi":"10.48550/arxiv.2109.00528","title":"Wasserstein GANs with Gradient Penalty Compute Congested Transport","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Limit (mathematics); Flow (mathematics); Mathematical proof; Computer science; Mathematical optimization; Component (thermodynamics); Mathematics; Physics; Geometry; Mathematical analysis","score_opus":0.05043519597761517,"score_gpt":0.16248768112867928,"score_spread":0.11205248515106411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197836096","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21403885,0.00008085623,0.7834538,0.00020323457,0.0005344639,0.0002901008,0.000012858066,0.00017652023,0.0012092779],"genre_scores_gemma":[0.9871233,0.00014918936,0.011444262,0.0001575151,0.00010498713,0.0000015509306,0.00006159917,0.000027571336,0.000929988],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971627,0.00025888544,0.00026101628,0.0016235752,0.00017355921,0.00052025594],"domain_scores_gemma":[0.9975349,0.000090921,0.00027334457,0.0014329964,0.00037321317,0.0002946737],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022491049,0.0005028479,0.0006161611,0.00018493306,0.00024098485,0.00021863838,0.0016408379,0.0002490142,0.000047911675],"category_scores_gemma":[0.000008029372,0.00050064205,0.00030911263,0.0007984843,0.00016974183,0.00052022276,0.00074499915,0.000627345,0.00001865514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050220824,0.00018410553,0.003015038,0.000070511574,0.00040167733,0.0024173837,0.0006090856,0.9814295,0.000080846046,0.011007764,0.00019544637,0.0005383809],"study_design_scores_gemma":[0.001029618,0.00016899774,0.007832754,0.00028570028,0.00025817868,0.000026079979,0.00029393513,0.98654157,0.000917251,0.0008883003,0.0007492078,0.001008384],"about_ca_topic_score_codex":0.00035150137,"about_ca_topic_score_gemma":0.00074074074,"teacher_disagreement_score":0.77308446,"about_ca_system_score_codex":0.00018293751,"about_ca_system_score_gemma":0.00040737886,"threshold_uncertainty_score":0.99974453},"labels":[],"label_agreement":null},{"id":"W3198555495","doi":"10.48550/arxiv.2109.01071","title":"Towards disease-aware image editing of chest X-rays","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Generator (circuit theory); Computer science; Encoder; Generative grammar; Set (abstract data type); Domain (mathematical analysis); Artificial intelligence; Image (mathematics); Computer vision; Programming language","score_opus":0.05145042227913966,"score_gpt":0.18396476800809974,"score_spread":0.1325143457289601,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198555495","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027672935,0.00014454061,0.9685675,0.00023787242,0.0010201983,0.00018648524,0.00004145487,0.000114547016,0.002014493],"genre_scores_gemma":[0.9851338,0.00016162723,0.013900482,0.00006108069,0.00034154244,0.0000010065642,0.000036123696,0.000020150937,0.0003441762],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978519,0.000233818,0.00026500356,0.0011299512,0.00015123097,0.00036809858],"domain_scores_gemma":[0.99755025,0.00008751049,0.00035139036,0.0013052545,0.00044967546,0.0002559147],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024319992,0.00034502073,0.0004741228,0.00015605467,0.00014944324,0.00020278236,0.0016335575,0.00017866246,0.00008966514],"category_scores_gemma":[0.00011409522,0.00039660267,0.00040387583,0.0005588375,0.00016053517,0.0006250819,0.0028569347,0.00042078667,0.000015552892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005744168,0.0005230352,0.004282781,0.0008271308,0.0005790784,0.0029496597,0.001066985,0.94765806,0.0013128887,0.029255837,0.0021503526,0.009336768],"study_design_scores_gemma":[0.00033002373,0.000030661584,0.005778195,0.00031515438,0.00015335083,0.0000018707298,0.00031501747,0.9845839,0.002730314,0.004788153,0.00039404165,0.000579288],"about_ca_topic_score_codex":0.00018030903,"about_ca_topic_score_gemma":0.000027331133,"teacher_disagreement_score":0.9574609,"about_ca_system_score_codex":0.000117241696,"about_ca_system_score_gemma":0.0004464503,"threshold_uncertainty_score":0.9998486},"labels":[],"label_agreement":null},{"id":"W3199806759","doi":"10.1134/s1054661821030123","title":"Identity-Preserved Face Beauty Transformation with Conditional Generative Adversarial Networks","year":2021,"lang":"en","type":"article","venue":"Pattern Recognition and Image Analysis","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Beauty; Normalization (sociology); Computer science; Discriminator; Artificial intelligence; Face (sociological concept); Identity (music); Pattern recognition (psychology); Computer vision; Mathematics; Aesthetics; Art; Linguistics","score_opus":0.02052871819918349,"score_gpt":0.23683214095924168,"score_spread":0.2163034227600582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199806759","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01195053,0.000123647,0.9858862,0.0011953096,0.00009635829,0.00012317132,0.00009601792,0.000052708776,0.00047603957],"genre_scores_gemma":[0.97493106,0.00020049195,0.022099975,0.0010341201,0.0002002069,0.000030890995,0.0014196599,0.000009724379,0.00007388192],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983124,0.00030380732,0.00029929803,0.0004947397,0.00032118728,0.0002685706],"domain_scores_gemma":[0.99894184,0.0000873063,0.00013846596,0.00026172155,0.00043559683,0.00013508146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025543297,0.00020010697,0.00031310652,0.00018208292,0.0003031725,0.0006543467,0.0001984393,0.00007027869,0.0004350072],"category_scores_gemma":[0.000033252,0.00017942242,0.00019120256,0.0010557425,0.0000730074,0.0026697668,0.00008826332,0.00015149263,0.00003706201],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033814544,0.0015450685,0.019357383,0.00020684375,0.021092528,0.0008395128,0.011280925,0.19268467,0.020316407,0.0018426188,0.004029589,0.7264663],"study_design_scores_gemma":[0.0011265404,0.00006732551,0.012198716,0.000021013315,0.0008865902,0.000020568275,0.00038837965,0.9735162,0.009279227,0.0018721159,0.00020669514,0.0004166088],"about_ca_topic_score_codex":0.000099207544,"about_ca_topic_score_gemma":0.0005828916,"teacher_disagreement_score":0.96378624,"about_ca_system_score_codex":0.000029067953,"about_ca_system_score_gemma":0.00004432629,"threshold_uncertainty_score":0.7316634},"labels":[],"label_agreement":null},{"id":"W3201318749","doi":"10.3389/fnins.2021.653213","title":"Longitudinal Prediction of Infant MR Images With Multi-Contrast Perceptual Adversarial Learning","year":2021,"lang":"en","type":"article","venue":"Frontiers in Neuroscience","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Institute of Mental Health; York University; Johns Hopkins University; Washington University in St. Louis; University of Alberta; University of Washington; National Institutes of Health; University of Minnesota; Children's Hospital of Philadelphia; Autism Speaks","keywords":"Computer science; Artificial intelligence; Contrast (vision); Neuroimaging; Perception; Pattern recognition (psychology); Adversarial system; Machine learning; Computer vision; Psychology","score_opus":0.01611834406027478,"score_gpt":0.21938947172695575,"score_spread":0.20327112766668096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201318749","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038063407,0.0001284475,0.95945907,0.00016716089,0.0018425327,0.00011518362,0.0000077123605,0.000044479555,0.00017198657],"genre_scores_gemma":[0.8690658,0.00007081453,0.13052453,0.00006841171,0.00006583036,0.000006846993,0.0000016587425,0.0000074413706,0.0001886345],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998095,0.00020916233,0.00026619143,0.00068393175,0.0003883271,0.00035741657],"domain_scores_gemma":[0.99927473,0.000046959158,0.00012693969,0.00032568898,0.00014023304,0.00008545378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002952986,0.0001608549,0.00025948294,0.00014249791,0.00017755198,0.00012842593,0.0005367694,0.000047722224,0.000006000508],"category_scores_gemma":[0.00032118234,0.00014227467,0.000058474077,0.00090854644,0.0003322593,0.00096939574,0.00021019313,0.00025216828,0.000001001359],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008477288,0.00037399566,0.61797065,0.00002535621,0.000018152034,0.00031108948,0.0019137147,0.16766387,0.1942974,0.00028475988,0.001788057,0.015268178],"study_design_scores_gemma":[0.0011740763,0.00029171945,0.3495625,0.000055566597,0.000013342648,0.000047269197,0.00040091024,0.6175021,0.029789578,0.000031794407,0.00090416154,0.0002269951],"about_ca_topic_score_codex":0.00003882609,"about_ca_topic_score_gemma":0.000017359467,"teacher_disagreement_score":0.8310024,"about_ca_system_score_codex":0.00004117405,"about_ca_system_score_gemma":0.00018109112,"threshold_uncertainty_score":0.5801793},"labels":[],"label_agreement":null},{"id":"W3204276937","doi":"10.1109/icas49788.2021.9551148","title":"Thermal Face Image Generator","year":2021,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Image translation; Image (mathematics); Generator (circuit theory); Face (sociological concept); Computer science; Task (project management); Artificial intelligence; Translation (biology); Computer vision; Thermal; Facial recognition system; Measure (data warehouse); Pattern recognition (psychology); Data mining; Engineering; Power (physics); Geography","score_opus":0.011762941661156623,"score_gpt":0.2201904548640293,"score_spread":0.20842751320287267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204276937","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035119308,0.00017624343,0.95551187,0.0022216171,0.00032427616,0.00003279858,8.6401906e-7,0.00008796314,0.038132448],"genre_scores_gemma":[0.6117807,0.000013598184,0.37793136,0.0016928065,0.0002544554,0.0000046570162,0.0000017525437,0.000007196657,0.008313456],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992261,0.00007877566,0.00009975073,0.00028015854,0.00012361772,0.00019157467],"domain_scores_gemma":[0.9993715,0.000032368032,0.000021002976,0.00040161618,0.000104951985,0.00006855209],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008554761,0.00008687623,0.00009386196,0.0000152359435,0.000095560594,0.00023957276,0.00032267984,0.000027662463,0.00041974528],"category_scores_gemma":[0.000028285638,0.00007074705,0.000059670918,0.00020761174,0.00001999138,0.00042348963,0.00021974687,0.000053363685,0.00023376448],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025962809,0.00012314954,0.00013501139,0.0000053554504,0.00006463492,0.00023518172,0.00047365032,0.0069648526,0.78566265,0.044517584,0.06889918,0.092916146],"study_design_scores_gemma":[0.00017930043,0.000015996357,0.0006499746,0.0000027744502,0.000003968587,0.0000084256735,0.000049048685,0.2277494,0.7416577,0.00028780286,0.029192442,0.00020319596],"about_ca_topic_score_codex":0.0000075918324,"about_ca_topic_score_gemma":0.000011461164,"teacher_disagreement_score":0.6082688,"about_ca_system_score_codex":0.0000101340165,"about_ca_system_score_gemma":0.00006772025,"threshold_uncertainty_score":0.45959166},"labels":[],"label_agreement":null},{"id":"W3204595673","doi":"10.1109/iccv48922.2021.00632","title":"DRB-GAN: A Dynamic ResBlock Generative Adversarial Network for Artistic Style Transfer","year":2021,"lang":"en","type":"article","venue":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":110,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Calgary","funders":"","keywords":"Computer science; Style (visual arts); Generative grammar; Generative adversarial network; Normalization (sociology); Representation (politics); Code (set theory); Artificial intelligence; Programming language; Deep learning; Art","score_opus":0.0257213270317206,"score_gpt":0.28808584121693753,"score_spread":0.26236451418521695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204595673","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015037546,0.00007672293,0.98062557,0.0068298695,0.008258081,0.0004406598,0.00011243273,0.00009341366,0.0020594748],"genre_scores_gemma":[0.78879803,0.00013838109,0.2019786,0.0021672873,0.0033020922,0.000102784456,0.0002225739,0.00004423027,0.0032460277],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996198,0.00037041178,0.00069171755,0.001344114,0.0007795312,0.0006162001],"domain_scores_gemma":[0.9971687,0.00047471854,0.00015948944,0.0007289086,0.0012359974,0.00023217448],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041695934,0.00047933884,0.00053102704,0.00016029697,0.00039421048,0.0009507515,0.0012647463,0.000189245,0.0007474404],"category_scores_gemma":[0.00007675112,0.00046313944,0.00036242075,0.00043152823,0.00008388612,0.00061161985,0.00025784603,0.00036308056,0.00017199748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007553572,0.0011341043,0.000042007654,0.000048112397,0.001019519,0.0005149107,0.0015021248,0.28712988,0.029756155,0.2921972,0.1222451,0.26365554],"study_design_scores_gemma":[0.0014261198,0.00049716927,0.00018083496,0.0001861491,0.000029889974,0.000027392673,0.00003198276,0.9694392,0.0048516165,0.005705496,0.017099377,0.00052478473],"about_ca_topic_score_codex":0.000021499236,"about_ca_topic_score_gemma":0.00013899461,"teacher_disagreement_score":0.78729427,"about_ca_system_score_codex":0.00021611502,"about_ca_system_score_gemma":0.00038476574,"threshold_uncertainty_score":0.999782},"labels":[],"label_agreement":null},{"id":"W3207388056","doi":"10.1007/978-3-030-88942-5_21","title":"Controlling BigGAN Image Generation with a Segmentation Network","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Silhouette; Artificial intelligence; Segmentation; Pattern recognition (psychology); Image segmentation; Pascal (unit); Mixture model; Computer vision; Gaussian; Conditional random field","score_opus":0.014757396378625463,"score_gpt":0.2246717194340237,"score_spread":0.20991432305539823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3207388056","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028383638,0.000725187,0.99484617,0.0005930222,0.0013924537,0.0003862379,0.000002469303,0.00008434846,0.0019417094],"genre_scores_gemma":[0.06794036,0.00007652253,0.9280485,0.001287069,0.0022810851,0.00001528983,0.000022418659,0.000035008947,0.00029377732],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99672425,0.000080726124,0.00043114115,0.0013970239,0.00077503466,0.00059185555],"domain_scores_gemma":[0.99799645,0.00025004052,0.00030815514,0.0008809526,0.000432444,0.00013192996],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00069628534,0.00047595814,0.0005110424,0.00027478303,0.0004081926,0.0012155196,0.0011406633,0.00018547548,0.000029409934],"category_scores_gemma":[0.000041182895,0.0003990783,0.00010583435,0.0006387462,0.00033906917,0.0009103523,0.00045110844,0.00044953582,0.0000138228725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007753764,0.000016693484,0.000018018163,0.000011608628,0.000030649062,0.00014326969,0.00026877705,0.68917656,0.0033896954,0.0076836497,0.00007506164,0.29917827],"study_design_scores_gemma":[0.00040513242,0.00015299015,0.000015304533,0.00023853795,0.000019195817,0.00005626874,3.2113817e-7,0.9828667,0.0085054375,0.006667103,0.00052166934,0.0005513316],"about_ca_topic_score_codex":0.000013510063,"about_ca_topic_score_gemma":0.00018861104,"teacher_disagreement_score":0.29862696,"about_ca_system_score_codex":0.00021381395,"about_ca_system_score_gemma":0.0005007071,"threshold_uncertainty_score":0.9998461},"labels":[],"label_agreement":null},{"id":"W3208331988","doi":"10.1093/mnras/stac130","title":"Realistic galaxy image simulation via score-based generative models","year":2022,"lang":"en","type":"preprint","venue":"Monthly Notices of the Royal Astronomical Society","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Argonne National Laboratory; Science and Technology Facilities Council; Jet Propulsion Laboratory; University of Illinois at Urbana-Champaign; SLAC National Accelerator Laboratory; Queen's University; Chinese Academy of Sciences; U.S. Department of Energy; National Natural Science Foundation of China; Deutsche Forschungsgemeinschaft; University of Portsmouth; University of Hertfordshire; Office of Science; University of Edinburgh; Consejo Superior de Investigaciones Científicas; Center for Cosmology and Astroparticle Physics, Ohio State University; National Research Foundation of Korea; University of Sussex; National Aeronautics and Space Administration; University College London; Eidgenössische Technische Hochschule Zürich; National Centre for Supercomputing Applications; Texas A and M University; University of Chicago; Ohio State University; California Institute of Technology; Higher Education Funding Council for England; Lawrence Berkeley National Laboratory; Division of Astronomical Sciences; Financiadora de Estudos e Projetos; University of Pennsylvania; University of Nottingham; Stanford University; Natural Sciences and Engineering Research Council of Canada; Yonsei University; University of Michigan; Royal Society; National Science Foundation","keywords":"Galaxy; Computer science; Sky; Inference; Artificial intelligence; Similarity (geometry); Ground truth; Physics; Astrophysics; Image (mathematics)","score_opus":0.02104162935031242,"score_gpt":0.2331575025165181,"score_spread":0.21211587316620567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208331988","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07176679,0.0001196164,0.9249099,0.00094041065,0.0009786913,0.00064981304,0.00019048298,0.000073062794,0.00037125542],"genre_scores_gemma":[0.8167166,1.7319209e-7,0.1826469,0.00012013482,0.00028074303,0.00006006194,0.000057291894,0.000026765354,0.00009133247],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969848,0.00050733506,0.0006324707,0.00090186775,0.0005336116,0.0004399367],"domain_scores_gemma":[0.9972427,0.0004109507,0.0007698876,0.001277726,0.00017495634,0.00012380454],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000541854,0.00044885802,0.00060305535,0.000029909263,0.00042975726,0.00025653775,0.002384956,0.0002133054,0.000090815694],"category_scores_gemma":[0.000055674216,0.00036116448,0.0010571396,0.00015598409,0.00027644998,0.00025145375,0.003282162,0.00080919144,0.0000034445327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023939865,0.00009593474,0.00017473918,0.000037486665,0.00013582988,2.505007e-7,0.0003098427,0.99708754,0.000019816065,0.00011799584,0.0007075896,0.0012890517],"study_design_scores_gemma":[0.0002999094,0.000052634,0.0027685552,0.00004087525,0.00010433772,2.5713573e-9,0.000025882051,0.994848,0.00056318304,0.00085419,0.00010761212,0.00033482767],"about_ca_topic_score_codex":0.0006898246,"about_ca_topic_score_gemma":0.000028697448,"teacher_disagreement_score":0.7449498,"about_ca_system_score_codex":0.00040312507,"about_ca_system_score_gemma":0.00027435107,"threshold_uncertainty_score":0.999884},"labels":[],"label_agreement":null},{"id":"W3209917595","doi":"10.1145/3458929","title":"DANCE: Distributed Generative Adversarial Networks with Communication Compression","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Internet Technology","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Upload; Overhead (engineering); Bandwidth (computing); Generative grammar; Cloud computing; Distributed computing; Server; Enhanced Data Rates for GSM Evolution; Artificial intelligence; Theoretical computer science; Computer network; World Wide Web; Operating system","score_opus":0.010650801101825062,"score_gpt":0.2291860601856989,"score_spread":0.21853525908387383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209917595","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018790987,0.00025440037,0.99124026,0.005505406,0.00037977082,0.00015235614,0.000013736187,0.00034794013,0.00022703086],"genre_scores_gemma":[0.83451277,0.00013440906,0.16470917,0.00024616532,0.00003547742,0.00004697909,0.00003783955,0.000013030629,0.00026417326],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860245,0.00018039711,0.00024786167,0.0005185443,0.00016064526,0.00029008588],"domain_scores_gemma":[0.99787015,0.00015842546,0.00011163283,0.0015513216,0.00024831662,0.000060167065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008863382,0.0002130982,0.00025086847,0.00014504998,0.00025710426,0.000115405026,0.0012673836,0.00022362465,0.000099547906],"category_scores_gemma":[0.000040392628,0.00018370544,0.00007288799,0.0008720221,0.00020137441,0.00032940376,0.00010677746,0.00052346365,0.000021558624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028205768,0.00097000605,0.00029018451,0.000012502876,0.00065658265,0.00015642795,0.0007077527,0.60970855,0.0060835825,0.028228251,0.005836401,0.3470677],"study_design_scores_gemma":[0.0018832604,0.00058587984,0.00027862925,0.0002116781,0.00007343244,0.00015520449,0.00033123724,0.72284365,0.25189906,0.005007765,0.016120618,0.00060958427],"about_ca_topic_score_codex":0.00003087857,"about_ca_topic_score_gemma":0.00014879147,"teacher_disagreement_score":0.8326337,"about_ca_system_score_codex":0.00008460003,"about_ca_system_score_gemma":0.000063324405,"threshold_uncertainty_score":0.74912906},"labels":[],"label_agreement":null},{"id":"W3211760555","doi":"10.1109/tip.2021.3125266","title":"A Domain Gap Aware Generative Adversarial Network for Multi-domain Image Translation","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; U.S. Department of Agriculture","keywords":"Consistency (knowledge bases); Constraint (computer-aided design); Domain (mathematical analysis); Generative grammar; Translation (biology); Local consistency; Adversarial system; Unified Model; Structured prediction","score_opus":0.09131428507341252,"score_gpt":0.21289400331955774,"score_spread":0.12157971824614522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211760555","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005166318,0.000111679496,0.99228454,0.00042030818,0.0007069817,0.00039097792,0.00003518916,0.00011256747,0.00077144854],"genre_scores_gemma":[0.50666547,0.000043896413,0.49173623,0.00027377452,0.00051158527,0.000003950308,0.000044597804,0.000020598212,0.0006998997],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978667,0.00037280555,0.00022335676,0.00092054467,0.00009356706,0.0005230507],"domain_scores_gemma":[0.9986857,0.00021378085,0.00013526148,0.00049214426,0.0003034437,0.00016967922],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00033898305,0.00027178778,0.00030843023,0.00007512955,0.00051971636,0.00016052536,0.00051446114,0.00013732027,0.00006339776],"category_scores_gemma":[0.000027300426,0.00030591103,0.0002903386,0.0008603479,0.00010146504,0.00093372975,0.00016432117,0.00015219722,0.000030735508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035626665,0.00044426808,0.0006171098,0.000050750088,0.00047451796,0.00083798234,0.0022337248,0.6414001,0.011898802,0.3254964,0.008726548,0.007463499],"study_design_scores_gemma":[0.002678639,0.000089925205,0.00016938319,0.000024345974,0.00005430915,0.0000069974467,0.00036739052,0.9585154,0.002231973,0.025237085,0.01016529,0.00045925396],"about_ca_topic_score_codex":0.00002635668,"about_ca_topic_score_gemma":0.00019626373,"teacher_disagreement_score":0.5014991,"about_ca_system_score_codex":0.00011093884,"about_ca_system_score_gemma":0.00020388135,"threshold_uncertainty_score":0.9999393},"labels":[],"label_agreement":null},{"id":"W3212438094","doi":"10.1109/tkde.2021.3126642","title":"Constrained Generative Adversarial Learning for Dimensionality Reduction","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dimensionality reduction; Computer science; Artificial intelligence; Feature vector; Diffusion map; Big data; Pattern recognition (psychology); Data mining; Pairwise comparison; Projection (relational algebra); Curse of dimensionality; Reduction (mathematics); Transformation (genetics); Benchmark (surveying); Feature (linguistics); Machine learning; Nonlinear dimensionality reduction; Algorithm; Mathematics","score_opus":0.029209038685555043,"score_gpt":0.2658531333269815,"score_spread":0.23664409464142647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212438094","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00060335785,0.00028011808,0.9971722,0.00020456291,0.0013847426,0.000115493225,0.000049829876,0.00009159432,0.0000981228],"genre_scores_gemma":[0.8817244,0.00008770729,0.11749576,0.000018807497,0.000294209,0.000022526234,0.00005335759,0.000012345326,0.0002908883],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990528,0.000056791705,0.00015762285,0.00048004312,0.00007657201,0.00017615521],"domain_scores_gemma":[0.9991987,0.00018777912,0.000027246371,0.00038611176,0.00012170289,0.00007846877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020737287,0.00013855581,0.00015731978,0.000058632184,0.00029329842,0.00009648638,0.0001905987,0.00005682741,0.000012972701],"category_scores_gemma":[0.000030587784,0.00014235012,0.000049058923,0.00019557538,0.000025594443,0.00053726917,0.00001363803,0.00015749746,0.0000049755913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041901345,0.00022758792,0.0000015456618,0.00006292642,0.00024738326,0.00001033301,0.0006987851,0.72383195,0.11503338,0.0038143324,0.0011488437,0.15488105],"study_design_scores_gemma":[0.00045748765,0.000049757495,0.000010455402,0.000026313735,0.000030405186,0.000022652477,0.000045026885,0.9134038,0.07856859,0.000055992885,0.007160215,0.00016929679],"about_ca_topic_score_codex":0.0000041346507,"about_ca_topic_score_gemma":0.0000069105054,"teacher_disagreement_score":0.88112104,"about_ca_system_score_codex":0.000025102347,"about_ca_system_score_gemma":0.00008530394,"threshold_uncertainty_score":0.58048695},"labels":[],"label_agreement":null},{"id":"W3212516020","doi":"10.1145/3528233.3530757","title":"Palette: Image-to-Image Diffusion Models","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1504,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Google (Canada)","funders":"","keywords":"Computer science; Inpainting; Artificial intelligence; Image (mathematics); Task (project management); Image translation; Translation (biology); Protocol (science); Feature (linguistics); JPEG; Image quality; Sample (material); Machine learning; Pattern recognition (psychology); Computer vision","score_opus":0.021589884938321167,"score_gpt":0.2493163160146387,"score_spread":0.22772643107631751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212516020","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00065062224,0.0000939723,0.94296503,0.0061537996,0.0016757097,0.00057047175,0.000026085943,0.00036365978,0.04750063],"genre_scores_gemma":[0.08579796,0.000119005366,0.9021347,0.004369302,0.00059175486,0.00025434434,0.000044857465,0.00005626174,0.0066317925],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99673027,0.00029435143,0.00041872798,0.0013719157,0.000654804,0.0005299156],"domain_scores_gemma":[0.99741244,0.00010584612,0.00016365455,0.0019128894,0.00016235803,0.00024279873],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004665436,0.00045503525,0.00048243316,0.00022615089,0.00034621308,0.00079886254,0.002786269,0.00014941777,0.0012698617],"category_scores_gemma":[0.000051051724,0.0004147108,0.00029524686,0.0003751624,0.00004775709,0.00057204184,0.0118059255,0.0007457973,0.00017736274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039125902,0.0005172855,0.000035998863,0.00014284134,0.00020440797,0.00030217893,0.003048563,0.50543475,0.03476158,0.025798436,0.35321945,0.07649538],"study_design_scores_gemma":[0.00017220945,0.000055718006,0.00014378023,0.0000309014,0.000018145374,0.000003266482,0.00004490796,0.9616217,0.0019109778,0.019455537,0.01584503,0.0006978343],"about_ca_topic_score_codex":0.00024351219,"about_ca_topic_score_gemma":0.000017539567,"teacher_disagreement_score":0.45618692,"about_ca_system_score_codex":0.00013065459,"about_ca_system_score_gemma":0.00013697812,"threshold_uncertainty_score":0.9998305},"labels":[],"label_agreement":null},{"id":"W3212694181","doi":"","title":"Clockwork Variational Autoencoders","year":2021,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Clockwork; Computer science; Artificial intelligence; Benchmark (surveying); Abstraction; Hierarchy; Machine learning; Term (time); Pattern recognition (psychology)","score_opus":0.013093083608344295,"score_gpt":0.22171116450240272,"score_spread":0.20861808089405842,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212694181","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020706082,0.0002862825,0.9912028,0.0012132549,0.0012524537,0.00008831304,0.0000024654419,0.00017398519,0.0055734026],"genre_scores_gemma":[0.9587415,0.0000057798507,0.039439443,0.0010609102,0.0002687009,0.000024071856,0.000031021773,0.0000050589683,0.00042354225],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883586,0.00008417141,0.0003865886,0.00015393778,0.00034054279,0.00019891736],"domain_scores_gemma":[0.99899924,0.000043187418,0.00021168325,0.00021668497,0.00046371884,0.00006548038],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00021048402,0.00011284018,0.00013202419,0.00006746174,0.0002963244,0.0012761756,0.00028164557,0.00005743345,0.000013627841],"category_scores_gemma":[0.00008784827,0.00010228343,0.000045086217,0.000509565,0.000017712473,0.0047307094,0.00008191619,0.00009876495,0.00007250543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000054240254,0.00003253459,0.00021233421,0.00015671823,0.000027228174,0.000009324499,0.0025164094,0.8169525,0.00030116207,0.03619929,0.011258371,0.13232869],"study_design_scores_gemma":[0.00014307589,0.000009356185,0.00033535855,0.00003544689,0.0000034093669,0.000045333367,0.00015211738,0.9729714,0.00029179238,0.00018678188,0.02570165,0.00012430496],"about_ca_topic_score_codex":0.000012944093,"about_ca_topic_score_gemma":9.786557e-7,"teacher_disagreement_score":0.9585344,"about_ca_system_score_codex":0.00004333365,"about_ca_system_score_gemma":0.00020519468,"threshold_uncertainty_score":0.99976057},"labels":[],"label_agreement":null},{"id":"W3213163682","doi":"10.1609/aaai.v35i2.16250","title":"Exploiting Relationship for Complex-scene Image Generation","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Scene graph; Computer science; Generator (circuit theory); Artificial intelligence; Discriminator; Object (grammar); Generative grammar; Spatial relation; Image (mathematics); Computer vision; Semantics (computer science); Graph; Consistency (knowledge bases); Pattern recognition (psychology); Theoretical computer science","score_opus":0.2131523915101248,"score_gpt":0.3214655293031366,"score_spread":0.1083131377930118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213163682","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016420025,0.000023111053,0.97066385,0.007178877,0.0004852287,0.0003560067,0.0000081438975,0.000058901212,0.0048058466],"genre_scores_gemma":[0.8434662,0.0000121717985,0.15580218,0.00025232934,0.0001907227,0.000038418275,0.0000030803296,0.00001011738,0.00022476967],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984539,0.000032771375,0.00047165228,0.00047140723,0.0002930037,0.0002772709],"domain_scores_gemma":[0.9978101,0.00019851113,0.00030152462,0.00026715698,0.0013599468,0.000062754225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004681661,0.00017176506,0.00021225707,0.00006147972,0.00041687072,0.00040012144,0.000831395,0.00006538102,0.000055097364],"category_scores_gemma":[0.0012094093,0.00014207844,0.00014562879,0.0005049268,0.00012585908,0.0005793144,0.00023080998,0.00015266772,0.000026092555],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001027919,0.000059784423,0.00007282227,0.00001661578,0.000009560836,2.511106e-7,0.00038258336,0.00030199598,0.4072296,0.5659448,0.0006122331,0.025359472],"study_design_scores_gemma":[0.000020463713,0.00004089285,0.00014732072,0.000044535343,0.000008140126,0.0000019932243,0.00021199607,0.3856525,0.55310035,0.060534637,0.00012464021,0.00011254401],"about_ca_topic_score_codex":0.000008250041,"about_ca_topic_score_gemma":0.000012029451,"teacher_disagreement_score":0.8270462,"about_ca_system_score_codex":0.000036769812,"about_ca_system_score_gemma":0.000108843305,"threshold_uncertainty_score":0.5793791},"labels":[],"label_agreement":null},{"id":"W3213716849","doi":"10.1609/aaai.v36i11.21559","title":"Introducing Variational Autoencoders to High School Students","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Generative grammar; Computer science; Artificial intelligence; Deep learning; Metaphor; Curriculum; Field (mathematics); The arts; Mathematics education; Visual arts; Sociology; Psychology; Mathematics; Pedagogy; Art","score_opus":0.037293034625104596,"score_gpt":0.27852846016074256,"score_spread":0.24123542553563798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213716849","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07377626,0.000013558316,0.89523643,0.023522934,0.002414783,0.00093723845,0.000017688995,0.00013496776,0.003946152],"genre_scores_gemma":[0.9671659,0.000003461768,0.031129578,0.0009934795,0.00016918204,0.00008291358,5.9807684e-7,0.000010451155,0.00044442847],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975472,0.00005079753,0.0004507353,0.0005975959,0.0010206993,0.0003329451],"domain_scores_gemma":[0.9987255,0.0000841736,0.00027032843,0.00032503498,0.000465109,0.00012987366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008698668,0.00018856059,0.00021971624,0.0001627009,0.00061082025,0.0003602966,0.0031799052,0.00003154641,0.00047493962],"category_scores_gemma":[0.0005322328,0.00015791455,0.0000944023,0.0009893519,0.00007408145,0.00037433257,0.0016093783,0.00033096728,0.00009083359],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008043658,0.0002778227,0.00056756276,0.000008890807,0.00004317146,6.993223e-7,0.0017899876,0.101754524,0.026723899,0.8441175,0.0024992973,0.022136169],"study_design_scores_gemma":[0.00009270729,0.0007149383,0.003117379,0.000095304524,0.000030011632,0.000007072406,0.001494483,0.578843,0.21119118,0.20266467,0.0011118314,0.00063745136],"about_ca_topic_score_codex":0.000101251084,"about_ca_topic_score_gemma":0.0000055465425,"teacher_disagreement_score":0.89338964,"about_ca_system_score_codex":0.0001421038,"about_ca_system_score_gemma":0.00015267501,"threshold_uncertainty_score":0.64395684},"labels":[],"label_agreement":null},{"id":"W3213924356","doi":"10.1016/j.cjca.2021.11.003","title":"Generative Adversarial Networks in Cardiology","year":2021,"lang":"en","type":"review","venue":"Canadian Journal of Cardiology","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital; Université de Sherbrooke; McGill University Health Centre","funders":"","keywords":"Workflow; Generative grammar; Adversarial system; Medicine; Fidelity; Modality (human–computer interaction); Artificial intelligence; Quality (philosophy); Field (mathematics); Cardiac magnetic resonance; Artificial neural network; Translation (biology); Data science; Computer science; Medical physics; Magnetic resonance imaging; Radiology","score_opus":0.03586957067048093,"score_gpt":0.2720861152216236,"score_spread":0.2362165445511427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213924356","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.2616239e-7,0.6004335,0.39358085,0.000088555134,0.0043085497,0.0001295377,0.000010660895,0.0000032865191,0.0014449069],"genre_scores_gemma":[0.00051191763,0.98784566,0.0035628844,0.00011739863,0.007840734,0.000013534266,0.000021644455,0.000032138923,0.00005410849],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99457234,0.0027394504,0.0011877374,0.0005407705,0.00014268016,0.0008170152],"domain_scores_gemma":[0.9972682,0.00047298396,0.00067163067,0.0006123169,0.0003766477,0.00059823855],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011539552,0.00048373002,0.0043353476,0.0008191805,0.00012406937,0.00013188283,0.0015487839,0.0008011759,0.000013874524],"category_scores_gemma":[0.00038853177,0.000413637,0.001385852,0.0007764534,0.00020635803,0.00024827998,0.00013541714,0.0012298726,0.000010178482],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022341071,0.0000011545923,0.000034945842,0.00009267162,0.0008489205,0.004220131,0.000059353002,0.12120309,1.2696681e-7,0.0017545404,0.023776552,0.8480063],"study_design_scores_gemma":[0.00024535722,0.00009065836,0.000013593425,0.00090775214,0.00024966052,0.0017736682,0.000014875692,0.0006198842,1.9391713e-7,0.00010291573,0.99563116,0.0003502909],"about_ca_topic_score_codex":0.00031732884,"about_ca_topic_score_gemma":0.0013816756,"teacher_disagreement_score":0.9718546,"about_ca_system_score_codex":0.0005372287,"about_ca_system_score_gemma":0.0067084576,"threshold_uncertainty_score":0.99983156},"labels":[],"label_agreement":null},{"id":"W3214044012","doi":"","title":"Efficient Density Ratio-Guided Subsampling of Conditional GANs, With Conditioning on a Class or a Continuous Variable.","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Sampling (signal processing); AKA; Benchmark (surveying); Conditional probability distribution; Artificial intelligence; Margin (machine learning); Pattern recognition (psychology); Statistics; Mathematics; Algorithm; Machine learning; Computer vision","score_opus":0.055541606888207154,"score_gpt":0.19242134418747037,"score_spread":0.13687973729926323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214044012","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27528968,0.000014000605,0.7235847,0.00004794514,0.00025207855,0.0002584108,0.000039004513,0.0000678794,0.00044629618],"genre_scores_gemma":[0.98049617,0.000013112606,0.018786587,0.00017463512,0.00008778493,0.0000025047964,0.00011080874,0.000017999004,0.00031038368],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99772674,0.0002932519,0.00031701656,0.0011099224,0.000209539,0.00034355113],"domain_scores_gemma":[0.997369,0.0004310024,0.00048369195,0.00083281094,0.00074096705,0.00014252633],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000315568,0.00035821553,0.0005869609,0.00020116333,0.00028627663,0.0002025526,0.00072211283,0.0002127276,0.00012061113],"category_scores_gemma":[0.00009901811,0.0003388701,0.00016769391,0.0006779075,0.00020932878,0.0001696471,0.0006185879,0.00044950462,0.000008099142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012860817,0.00016265277,0.0003673577,0.000047332276,0.00020617433,0.00036081616,0.00016673803,0.92841744,0.00053081184,0.06942264,0.00016028,0.000029162591],"study_design_scores_gemma":[0.00099053,0.00016574885,0.0012093611,0.0004101144,0.00013977881,0.000024934307,0.00023599368,0.99063027,0.003835053,0.0018477325,0.000040307285,0.0004701949],"about_ca_topic_score_codex":0.00013218788,"about_ca_topic_score_gemma":0.000057513367,"teacher_disagreement_score":0.7052065,"about_ca_system_score_codex":0.00018741413,"about_ca_system_score_gemma":0.0007171125,"threshold_uncertainty_score":0.99990636},"labels":[],"label_agreement":null},{"id":"W3214459635","doi":"10.1109/iceccme52200.2021.9591087","title":"Facial Animation Using CycleGAN","year":2021,"lang":"en","type":"article","venue":"2021 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"","keywords":"Computer science; Anime; Adversarial system; Artificial intelligence; Generative grammar; Animation; Translation (biology); Image translation; Face (sociological concept); Deep learning; Field (mathematics); Transformation (genetics); Image (mathematics); Natural language processing; Computer vision; Pattern recognition (psychology); Computer graphics (images); Linguistics; Mathematics","score_opus":0.03616989701566346,"score_gpt":0.2700761430426632,"score_spread":0.23390624602699972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214459635","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022311043,0.0006368897,0.99277484,0.0024396637,0.0005581722,0.000111682304,0.000011205884,0.000090367124,0.0011460703],"genre_scores_gemma":[0.6866096,0.0021045124,0.3106964,0.00018613496,0.00021586026,0.000016301608,0.00005340217,0.000016674585,0.00010111111],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985237,0.00011538071,0.00033224086,0.00043442912,0.00029639172,0.0002978457],"domain_scores_gemma":[0.9983094,0.00015568778,0.00011817202,0.0008863323,0.00041391936,0.00011651737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020156591,0.00021961408,0.00022363341,0.00018946455,0.00026391633,0.00056955667,0.001178475,0.000092162874,0.000048457994],"category_scores_gemma":[0.000052900767,0.00024181114,0.00009084773,0.00044205794,0.000031531676,0.00045494369,0.0006672995,0.0003705974,0.000015445778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053091644,0.0001732834,0.00001315685,0.000005900463,0.00013615933,0.000007085703,0.00014938807,0.025879014,0.018839043,0.84580374,0.00019870138,0.10878924],"study_design_scores_gemma":[0.00025748726,0.000073408504,0.00006846767,0.00004733572,0.000010564379,0.000024612953,0.000013376237,0.9819305,0.001323605,0.0012547413,0.014752958,0.00024293699],"about_ca_topic_score_codex":0.000024462639,"about_ca_topic_score_gemma":0.00000969325,"teacher_disagreement_score":0.95605147,"about_ca_system_score_codex":0.00015673898,"about_ca_system_score_gemma":0.00021233842,"threshold_uncertainty_score":0.98607725},"labels":[],"label_agreement":null},{"id":"W3215252183","doi":"10.1177/00405175211059207","title":"Classification of clothing images based on a parallel convolutional neural network and random vector functional link optimized by the grasshopper optimization algorithm","year":2021,"lang":"en","type":"article","venue":"Textile Research Journal","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Lung Association Saskatchewan","funders":"Key Research and Development Program of Zhejiang Province","keywords":"Artificial intelligence; Computer science; Support vector machine; Pattern recognition (psychology); Convolutional neural network; MNIST database; Softmax function; Overfitting; Feature extraction; Normalization (sociology); Histogram of oriented gradients; Histogram; Algorithm; Artificial neural network; Image (mathematics)","score_opus":0.04538331576513266,"score_gpt":0.2989477922639202,"score_spread":0.25356447649878755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215252183","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015484745,0.0011895766,0.9877626,0.010045899,0.0003705174,0.00018266651,0.000010733651,0.000017176208,0.00026603683],"genre_scores_gemma":[0.6670923,0.00092570455,0.32852438,0.0005522263,0.0018774252,0.00006307225,0.0000658441,0.00003168814,0.0008673254],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963745,0.0015610129,0.0003579066,0.00032624026,0.0009749716,0.00040536857],"domain_scores_gemma":[0.99689865,0.0015131433,0.00016926302,0.00028165441,0.0009860432,0.0001512743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027079755,0.00013835116,0.00021677525,0.00010598466,0.0009281214,0.0005093846,0.00036333504,0.00007440084,0.00021469357],"category_scores_gemma":[0.0004968153,0.00009819739,0.00011505672,0.0005354077,0.00025492546,0.00044647467,0.00013256572,0.0006731471,0.0000037178263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014626075,0.00006332646,0.000055501885,0.0000034309728,0.000039332223,0.0000085466945,0.000038974118,0.945513,0.0013537877,0.00038652425,0.023567988,0.028823288],"study_design_scores_gemma":[0.0018846903,0.00009590115,0.0017608994,0.000037520054,0.000009844681,0.00005877597,0.000044880173,0.99427533,0.00025027926,0.00039064742,0.0010940935,0.00009716622],"about_ca_topic_score_codex":0.000007171814,"about_ca_topic_score_gemma":7.8400734e-7,"teacher_disagreement_score":0.6669375,"about_ca_system_score_codex":0.00007627593,"about_ca_system_score_gemma":0.0003731318,"threshold_uncertainty_score":0.7138453},"labels":[],"label_agreement":null},{"id":"W3215977089","doi":"","title":"Exponentially Tilted Gaussian Prior for Variational Autoencoder","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Autoencoder; Gaussian; Divergence (linguistics); Computer science; Artificial intelligence; Kullback–Leibler divergence; Property (philosophy); Prior probability; Generative model; Probabilistic logic; Pattern recognition (psychology); Algorithm; Applied mathematics; Artificial neural network; Mathematics; Generative grammar; Bayesian probability; Physics","score_opus":0.0616887201424651,"score_gpt":0.18944464765617802,"score_spread":0.12775592751371292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215977089","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029465437,0.00005783722,0.99349976,0.0003969838,0.0014541087,0.00043507278,0.000030158211,0.00015458846,0.0010249744],"genre_scores_gemma":[0.8488889,0.000045811426,0.14831702,0.00017786513,0.00031397893,0.00000521814,0.00009095587,0.000021773707,0.0021384996],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99778056,0.00018970751,0.0002454924,0.0012731551,0.00012126389,0.0003898315],"domain_scores_gemma":[0.9980371,0.00016944081,0.00026742826,0.00097247766,0.00039091834,0.00016264229],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002655198,0.00032685552,0.00037138528,0.00016495216,0.00029134352,0.00037885373,0.0013530325,0.00028523317,0.00012821988],"category_scores_gemma":[0.00007832008,0.00037694728,0.00036708257,0.0003955713,0.00006185121,0.00053678214,0.001342531,0.00030483867,0.000021448686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030273097,0.00013722728,0.00010815108,0.00004727893,0.000253571,0.00011001734,0.00029156412,0.9215782,0.00023537675,0.07473005,0.0011098908,0.0013683694],"study_design_scores_gemma":[0.0005146003,0.000031958753,0.0011928529,0.000055622855,0.000089124325,0.0000024292724,0.00003899143,0.9851917,0.0003129783,0.010948426,0.0011988332,0.0004224741],"about_ca_topic_score_codex":0.00007374857,"about_ca_topic_score_gemma":0.000060828188,"teacher_disagreement_score":0.8459423,"about_ca_system_score_codex":0.00015537976,"about_ca_system_score_gemma":0.0006010626,"threshold_uncertainty_score":0.9998683},"labels":[],"label_agreement":null},{"id":"W3216046900","doi":"10.48550/arxiv.2112.01036","title":"GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Compute Canada","keywords":"Artificial intelligence; Computer science; Robustness (evolution); Segmentation; Image (mathematics); Computer vision; Pattern recognition (psychology); Object (grammar); Unsupervised learning; Image segmentation","score_opus":0.04701729669888357,"score_gpt":0.1844635810616375,"score_spread":0.1374462843627539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216046900","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12997533,0.00008503174,0.8677338,0.00045308704,0.000563583,0.00027505547,0.000009399418,0.0001487523,0.00075598096],"genre_scores_gemma":[0.9681568,0.00013669819,0.029337013,0.0005277228,0.00026919483,0.0000031440863,0.00009411038,0.000025971238,0.0014493244],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970357,0.0005560562,0.00025001247,0.0015326637,0.0001656196,0.0004599469],"domain_scores_gemma":[0.9982616,0.000084294006,0.0001337686,0.0009343975,0.0002577824,0.0003282088],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030643286,0.00038693743,0.00039774977,0.0001726863,0.00032995947,0.00056865986,0.0012031081,0.00024335778,0.00014211937],"category_scores_gemma":[0.00007538568,0.00045413178,0.00024219742,0.00061274355,0.000064638814,0.00048523128,0.002041369,0.00072254805,0.00007640607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016561582,0.00012108857,0.00022493492,0.000024908117,0.00011409431,0.0002560683,0.00079460157,0.9680409,0.02068096,0.0014228277,0.004433108,0.0038699878],"study_design_scores_gemma":[0.00031761234,0.000075965334,0.00014424486,0.000050209004,0.00004515719,0.0000025011561,0.0001330965,0.98834574,0.007801374,0.00031882984,0.0022151272,0.0005501294],"about_ca_topic_score_codex":0.00012688324,"about_ca_topic_score_gemma":0.000035230296,"teacher_disagreement_score":0.8383968,"about_ca_system_score_codex":0.00023195364,"about_ca_system_score_gemma":0.00021208875,"threshold_uncertainty_score":0.999791},"labels":[],"label_agreement":null},{"id":"W3216156094","doi":"10.1109/cvpr52688.2022.01753","title":"CLIPstyler: Image Style Transfer with a Single Text Condition","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":233,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Korea Customs Service; National Research Foundation of Korea; Ministry of Science and Technology of the People's Republic of China","keywords":"Computer science; Style (visual arts); Transfer (computing); Image (mathematics); Artificial intelligence; Computer vision; Art; Visual arts","score_opus":0.028173930043407902,"score_gpt":0.240075001331752,"score_spread":0.2119010712883441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216156094","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06632833,0.00002561464,0.9288647,0.0018188113,0.0008222406,0.00045188473,0.00014114715,0.0001785874,0.0013686796],"genre_scores_gemma":[0.9884328,0.000057747897,0.007132184,0.0036289284,0.00025077353,0.000119175005,0.00016795973,0.000031524938,0.00017885433],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970273,0.0005745254,0.0003978165,0.000960556,0.0006172623,0.00042256908],"domain_scores_gemma":[0.998819,0.00017367113,0.00013600019,0.00044876616,0.00021721363,0.00020538308],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00036225579,0.0003849141,0.00040103155,0.0002557956,0.0007005353,0.00068053266,0.00049603806,0.00007331884,0.0020795248],"category_scores_gemma":[0.0000049184473,0.00033830473,0.00011815359,0.0003966214,0.00011213021,0.0007772534,0.00022521512,0.00045749758,0.0001518696],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014831906,0.00056849135,0.00006545786,0.000027040747,0.00006442996,0.00011153789,0.0010253864,0.00028785,0.009140959,0.00022746556,0.006453375,0.9818797],"study_design_scores_gemma":[0.006053494,0.010559851,0.002340107,0.0004253964,0.000099032244,0.00039235782,0.00051020464,0.9291417,0.020534426,0.0021395937,0.025615413,0.0021884206],"about_ca_topic_score_codex":0.000033646145,"about_ca_topic_score_gemma":0.000036688878,"teacher_disagreement_score":0.97969127,"about_ca_system_score_codex":0.00006222598,"about_ca_system_score_gemma":0.000060773502,"threshold_uncertainty_score":0.9999069},"labels":[],"label_agreement":null},{"id":"W3217796336","doi":"10.48550/arxiv.2111.13282","title":"Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Survey","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Autoencoder; Adversarial system; Computer science; Image translation; Feature (linguistics); Matching (statistics); Generative grammar; Image (mathematics); Artificial intelligence; Translation (biology); Interpolation (computer graphics); Algorithm; Pattern recognition (psychology); Deep learning; Theoretical computer science; Mathematics; Statistics; Linguistics; Chemistry","score_opus":0.0570249352263426,"score_gpt":0.18134105138225284,"score_spread":0.12431611615591023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217796336","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045662332,0.0005193751,0.94660807,0.00012370014,0.0060911495,0.00043087653,0.00004600606,0.00015288865,0.00036559516],"genre_scores_gemma":[0.9863219,0.0010631423,0.010290841,0.00015395024,0.0016889138,0.0000023206564,0.0001035508,0.000034646124,0.00034071883],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953054,0.0012315082,0.00038450427,0.0022520486,0.00018275503,0.0006437359],"domain_scores_gemma":[0.99722916,0.00052414037,0.00036927467,0.0010814773,0.00039776164,0.00039819733],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008466647,0.00068132585,0.0008352938,0.00020191728,0.00048634261,0.0008617141,0.0010544657,0.00069314125,0.00003742276],"category_scores_gemma":[0.00023319827,0.00077366544,0.00022601704,0.0005908048,0.00037563292,0.0010225151,0.0038339125,0.0009214209,0.000004664785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020825087,0.00009180154,0.0023673149,0.000031322365,0.00046086928,0.00038555663,0.000693802,0.98435235,0.000040733197,0.00879251,0.0011663754,0.0014090855],"study_design_scores_gemma":[0.0015500288,0.00010182478,0.0041726027,0.000069008696,0.00015751421,0.000009267796,0.00014003042,0.9905598,0.00006231034,0.0019735391,0.00036566498,0.0008383935],"about_ca_topic_score_codex":0.0016130074,"about_ca_topic_score_gemma":0.0009932485,"teacher_disagreement_score":0.9406596,"about_ca_system_score_codex":0.00018343565,"about_ca_system_score_gemma":0.0004891924,"threshold_uncertainty_score":0.9994714},"labels":[],"label_agreement":null},{"id":"W4200441333","doi":"10.1142/s0218126622501146","title":"Generative Image Inpainting with Dilated Deformable Convolution","year":2021,"lang":"en","type":"article","venue":"Journal of Circuits Systems and Computers","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Inpainting; Artificial intelligence; Image (mathematics); Convolution (computer science); Computer science; Computer vision; Generative grammar; Generative adversarial network; Pattern recognition (psychology); Artificial neural network","score_opus":0.009363307520249274,"score_gpt":0.1961051457259329,"score_spread":0.18674183820568363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200441333","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037481617,0.0012571879,0.95963544,0.0003006323,0.00082135154,0.00006953166,8.143415e-7,0.000016373468,0.00041706976],"genre_scores_gemma":[0.97449946,0.00005882184,0.02489787,0.00014317938,0.00032200819,0.0000012067896,7.9637596e-7,0.0000076232204,0.0000690396],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987106,0.00020462414,0.00041343502,0.00019229205,0.00026606838,0.00021300542],"domain_scores_gemma":[0.99852794,0.00008349363,0.00043098978,0.0001647229,0.0006710218,0.000121836834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045360692,0.00013848091,0.00033261735,0.00008977143,0.00017280762,0.0005108486,0.0002155054,0.00004336413,0.0000018733415],"category_scores_gemma":[0.000022401615,0.000101193225,0.000065638815,0.0002959599,0.000043154574,0.0009948614,0.000078032106,0.00015027233,0.0000014507399],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008688913,0.0005563994,0.006781302,0.00055226515,0.0026550465,0.003839215,0.012423806,0.49572402,0.17423767,0.05687765,0.014172276,0.23209345],"study_design_scores_gemma":[0.0014488457,0.0004242014,0.0026985414,0.0005426364,0.00005217687,0.003174829,0.00060729595,0.9797426,0.0074012987,0.00023692215,0.003308206,0.00036243134],"about_ca_topic_score_codex":0.000017554285,"about_ca_topic_score_gemma":0.000003027801,"teacher_disagreement_score":0.93701786,"about_ca_system_score_codex":0.000048071197,"about_ca_system_score_gemma":0.00013853822,"threshold_uncertainty_score":0.49261248},"labels":[],"label_agreement":null},{"id":"W4200632125","doi":"","title":"VampNet : Vampirisation non supervisée de réseaux de convolution","year":2021,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Safran Electronics (Canada)","funders":"","keywords":"Computer science; Convolution (computer science); Artificial intelligence; Artificial neural network","score_opus":0.020151568778279817,"score_gpt":0.22906158429861032,"score_spread":0.2089100155203305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200632125","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06275018,0.0020039235,0.89131826,0.02764721,0.0008615888,0.0004861206,0.000032964526,0.000170536,0.01472922],"genre_scores_gemma":[0.67197335,0.0012486526,0.31754285,0.000400843,0.00015411094,0.00007879995,0.0003742202,0.000049598322,0.008177554],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9816989,0.014370239,0.00084405293,0.0014766776,0.00062899746,0.0009811828],"domain_scores_gemma":[0.99013543,0.0018958015,0.00064551673,0.0028269736,0.0040132315,0.000483041],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.009952685,0.0006069178,0.00063112576,0.00019002245,0.0008532353,0.0019354474,0.002157066,0.0006343043,0.0004439876],"category_scores_gemma":[0.002213037,0.00073652447,0.00046035016,0.00082757295,0.0004187993,0.0008218857,0.0021726538,0.0009937815,0.000098455115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048017995,0.0029775489,0.013372513,0.0006906776,0.0006734357,0.00014362068,0.13405348,0.03412081,0.07984717,0.35358283,0.0120691275,0.36842075],"study_design_scores_gemma":[0.0005894012,0.0000011528377,0.030879863,0.0017714272,0.00011214547,0.000047070076,0.0004430303,0.8551198,0.09194803,0.0048329295,0.013503228,0.0007518803],"about_ca_topic_score_codex":0.010210872,"about_ca_topic_score_gemma":0.004597268,"teacher_disagreement_score":0.820999,"about_ca_system_score_codex":0.000765702,"about_ca_system_score_gemma":0.0019867972,"threshold_uncertainty_score":0.99950856},"labels":[],"label_agreement":null},{"id":"W4205306454","doi":"10.1109/access.2022.3144308","title":"Cross-Spectrum Thermal Face Pattern Generator","year":2022,"lang":"lv","type":"article","venue":"IEEE Access","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Taiwan University of Science and Technology; National Taiwan University; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Artificial intelligence; Computer science; Facial recognition system; Face (sociological concept); Computer vision; Thermal; Task (project management); Generator (circuit theory); Pattern recognition (psychology); Image (mathematics); Thermography; Optics; Infrared; Engineering; Physics","score_opus":0.03301523288086645,"score_gpt":0.2917616735868653,"score_spread":0.25874644070599884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205306454","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33900303,0.001300858,0.64236885,0.0032009212,0.012104931,0.00048116426,0.00017931349,0.00014917013,0.0012117794],"genre_scores_gemma":[0.9913883,0.00004595807,0.00034328576,0.003054724,0.0022231652,0.00010466282,0.000010992531,0.0000567639,0.002772155],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958009,0.0006512841,0.00054254796,0.0011776207,0.0008552171,0.0009724421],"domain_scores_gemma":[0.9979702,0.00013023216,0.00033688135,0.0012161657,0.000107291904,0.0002392139],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00063360354,0.0004645148,0.0004367715,0.0001399362,0.0017216417,0.0027350006,0.0043169716,0.00009927884,0.0035055354],"category_scores_gemma":[0.00002002927,0.00047271422,0.00026900304,0.0008684644,0.00015761485,0.0017258424,0.0024004932,0.00064214715,0.00023848318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000751326,0.0005618445,0.022597767,0.0000477612,0.0003090945,0.00046250562,0.0028092097,0.7733121,0.011736522,0.00029879008,0.027775263,0.16001402],"study_design_scores_gemma":[0.0015083911,0.00043917453,0.028757593,0.000027040018,0.00007238571,0.00005112762,0.00012286835,0.8139513,0.088321075,0.0003526265,0.06474692,0.0016494818],"about_ca_topic_score_codex":0.0007025163,"about_ca_topic_score_gemma":0.000058904818,"teacher_disagreement_score":0.6523853,"about_ca_system_score_codex":0.00019643936,"about_ca_system_score_gemma":0.00025860523,"threshold_uncertainty_score":0.9997724},"labels":[],"label_agreement":null},{"id":"W4205996016","doi":"10.21203/rs.3.rs-1219874/v1","title":"EnGAN: Enhancement Generative Adversarial Network in Medical Image Segmentation","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Adversarial system; Generative grammar; Image (mathematics); Artificial intelligence; Segmentation; Generative adversarial network; Computer science; Image segmentation; Computer vision","score_opus":0.04512820479458916,"score_gpt":0.3795989158309855,"score_spread":0.3344707110363963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205996016","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040019406,0.0015601381,0.9764346,0.005872479,0.0034166672,0.0024433213,0.000041639327,0.00011710636,0.0061121006],"genre_scores_gemma":[0.7124569,0.0038045286,0.26747122,0.0009768938,0.008145842,0.0041310987,0.00084887526,0.00013579582,0.002028887],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9888897,0.004280439,0.0006766141,0.0014275971,0.003543378,0.0011822813],"domain_scores_gemma":[0.99712694,0.0008046625,0.00018550185,0.0011248356,0.00043051637,0.000327522],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006756878,0.00038683758,0.0005322354,0.00044284688,0.00065229763,0.0005562395,0.0023336613,0.00032770404,0.0031992644],"category_scores_gemma":[0.0006320679,0.00038545972,0.00020451605,0.0012434104,0.00019618047,0.00043256645,0.0073758154,0.0030641141,0.000083684405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059202977,0.00237832,0.0019349646,0.00096099376,0.00073856517,0.0031280136,0.019422814,0.50593656,0.0058773444,0.028646324,0.17910336,0.25128073],"study_design_scores_gemma":[0.0024305836,0.00083060935,0.0017930409,0.000792195,0.000020226798,0.000008158258,0.001376777,0.9411575,0.008289935,0.015845584,0.026128555,0.001326844],"about_ca_topic_score_codex":0.0005436111,"about_ca_topic_score_gemma":0.00030973714,"teacher_disagreement_score":0.7089634,"about_ca_system_score_codex":0.0010281695,"about_ca_system_score_gemma":0.0015923977,"threshold_uncertainty_score":0.99985975},"labels":[],"label_agreement":null},{"id":"W4206055806","doi":"10.1109/jbhi.2021.3134004","title":"Guest Editorial Generative Adversarial Networks in Biomedical Image Computing","year":2022,"lang":"en","type":"editorial","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Artificial intelligence; Medical imaging; Segmentation; Deep learning; Image segmentation; Positron emission tomography; Data science; Medical physics; Medicine; Radiology","score_opus":0.01372357525981888,"score_gpt":0.2902843269729673,"score_spread":0.2765607517131484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206055806","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010730367,0.00042965126,0.36479497,0.0014048205,0.63308614,0.00017937648,0.000050248585,0.000018126793,0.000025924612],"genre_scores_gemma":[0.00018257023,0.0022165887,0.04600711,0.0005411348,0.95089394,0.0000046949003,0.000113066315,0.00002577471,0.000015096706],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99135846,0.0005496834,0.0038370984,0.000328584,0.0029911038,0.00093506876],"domain_scores_gemma":[0.9936968,0.0012715232,0.0031853302,0.00036027498,0.000539328,0.00094674854],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0071875937,0.0005207978,0.0015589504,0.00079814275,0.00049186137,0.00037783704,0.0015274602,0.0009402347,0.000029079472],"category_scores_gemma":[0.00078748603,0.00042332694,0.00025158026,0.0008879483,0.00043280338,0.0009553388,0.0006908221,0.0039006525,0.0000043274017],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006341853,0.00017462556,0.000002311747,0.00018191006,0.000082260914,0.0000678293,0.002021898,0.00065606774,0.0000035966914,0.000020366742,0.9839001,0.012825597],"study_design_scores_gemma":[0.0023205613,0.0014423785,0.00000575661,0.0003396949,0.00002643605,0.00004634845,0.00025102275,0.1156397,0.0000027407184,0.0000860818,0.8794925,0.00034677412],"about_ca_topic_score_codex":0.0001298092,"about_ca_topic_score_gemma":0.000017199616,"teacher_disagreement_score":0.31878784,"about_ca_system_score_codex":0.000588525,"about_ca_system_score_gemma":0.003325252,"threshold_uncertainty_score":0.99982184},"labels":[],"label_agreement":null},{"id":"W4210655446","doi":"10.1109/icmla52953.2021.00014","title":"Improved Attribute Manipulation in the Latent Space of StyleGAN for Semantic Face Editing","year":2021,"lang":"en","type":"article","venue":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Face (sociological concept); Generative grammar; Process (computing); Artificial intelligence; Generative model; Space (punctuation); Feature (linguistics); Quality (philosophy); Semantics (computer science); Human–computer interaction","score_opus":0.043570681950924034,"score_gpt":0.3027552039968044,"score_spread":0.2591845220458804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210655446","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009181935,0.000090904934,0.9801221,0.009056719,0.00017028795,0.00031858546,0.000022968445,0.000018747169,0.0010177408],"genre_scores_gemma":[0.99170274,0.00012152347,0.006963106,0.00009612533,0.00021311975,0.00011776062,0.00008582278,0.0000067858896,0.0006930344],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989579,0.00012282918,0.00024395874,0.00033762873,0.00019457692,0.00014311675],"domain_scores_gemma":[0.9991005,0.0002267507,0.00017704765,0.00019711755,0.000268374,0.000030196445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037546753,0.000117502284,0.00014385465,0.00007560526,0.00016276201,0.00018540534,0.00033373095,0.000042646483,0.000018848465],"category_scores_gemma":[0.00010231222,0.00009864619,0.000056195586,0.00023877197,0.000031425545,0.00017915272,0.00006766247,0.00021127186,0.000003373501],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056656285,0.00051661744,0.014987262,0.0001022532,0.00019758815,0.000010689971,0.002058579,0.08747153,0.1245568,0.6288533,0.00041666237,0.14077203],"study_design_scores_gemma":[0.00036976603,0.00005669496,0.002654861,0.000049482136,0.00001131616,0.0000061200467,0.00028187834,0.98313504,0.0059056836,0.0012497085,0.006155786,0.00012363527],"about_ca_topic_score_codex":0.00007663352,"about_ca_topic_score_gemma":0.00008178764,"teacher_disagreement_score":0.98252076,"about_ca_system_score_codex":0.000022204462,"about_ca_system_score_gemma":0.00004313043,"threshold_uncertainty_score":0.4022675},"labels":[],"label_agreement":null},{"id":"W4210807590","doi":"10.1007/s11548-022-02567-6","title":"A systematic comparison of generative models for medical images","year":2022,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Deutsches Forschungszentrum für Künstliche Intelligenz","keywords":"Interpretability; Artificial intelligence; Computer science; Generalization; Locality; Deep learning; Machine learning; Generative model; Statistical model; Artificial neural network; Generative grammar; Pattern recognition (psychology); Mathematics","score_opus":0.02714716624666816,"score_gpt":0.2856747825880661,"score_spread":0.258527616341398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210807590","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007627621,0.0017369945,0.98557395,0.002397948,0.002530764,0.000095809024,0.000008099771,0.0000074831787,0.000021340938],"genre_scores_gemma":[0.9479101,0.00006377982,0.05110864,0.00049907994,0.00038215262,0.000014894538,0.0000045744764,0.000005091007,0.000011742125],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976816,0.0006391572,0.0009084385,0.00015783195,0.0004861599,0.00012677384],"domain_scores_gemma":[0.99611163,0.0024546457,0.00076895405,0.000110441375,0.00047806097,0.000076245495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016499731,0.00010680853,0.00065472495,0.00028212034,0.00011793647,0.000045993056,0.00068835885,0.000050128805,0.000014889603],"category_scores_gemma":[0.0001692522,0.00008583282,0.0002474431,0.00010056992,0.00008654853,0.00027049167,0.00021823563,0.00018424776,1.367039e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012424866,0.0022096229,0.00924398,0.001416302,0.010292299,0.0009507664,0.007488793,0.6048809,0.002524631,0.054928266,0.1402645,0.16455743],"study_design_scores_gemma":[0.00050775695,0.00022178554,0.0007451479,0.00026011647,0.00003666834,0.0015217111,0.000078479585,0.99345696,0.00040168568,0.0024118316,0.00024036971,0.00011746022],"about_ca_topic_score_codex":0.000002472578,"about_ca_topic_score_gemma":6.000254e-7,"teacher_disagreement_score":0.9402824,"about_ca_system_score_codex":0.000040859184,"about_ca_system_score_gemma":0.00018840365,"threshold_uncertainty_score":0.3500161},"labels":[],"label_agreement":null},{"id":"W4213125754","doi":"10.1109/wacv51458.2022.00320","title":"Tailor Me: An Editing Network for Fashion Attribute Shape Manipulation","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Image editing; Computer science; Parsing; RGB color model; Artificial intelligence; Video editing; Pixel; Image (mathematics); Computer vision; Task (project management); Computer graphics (images)","score_opus":0.035258401826002594,"score_gpt":0.2884128643373655,"score_spread":0.2531544625113629,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213125754","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042753117,0.00002691951,0.9907629,0.002030316,0.0011746474,0.0012501146,0.0000788393,0.00016679545,0.00023419144],"genre_scores_gemma":[0.8823728,0.000010077753,0.11440435,0.00069353956,0.0012346663,0.00084726233,0.00023843649,0.00003220377,0.00016668161],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996947,0.00031351962,0.00070934056,0.0009789539,0.0005858711,0.00046534892],"domain_scores_gemma":[0.99751025,0.000250052,0.00051985745,0.0011316352,0.0004287328,0.0001594706],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008140722,0.00032300278,0.0004201868,0.00022980015,0.00085672195,0.0002876958,0.0017576109,0.00008226188,0.00029790754],"category_scores_gemma":[0.000011945085,0.00033725298,0.00021887284,0.00072767655,0.00006931699,0.0006564361,0.00064270024,0.00031648958,0.000030105457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016050151,0.001023607,0.00034840795,0.000062595296,0.0001450231,0.0000047577482,0.0009688334,0.23046607,0.012767947,0.1254786,0.068971545,0.55960214],"study_design_scores_gemma":[0.0005471318,0.0009966077,0.00058753486,0.000037678787,0.00002340935,0.0000074486984,0.00012803513,0.9765975,0.0010562256,0.0040345076,0.015628055,0.00035585076],"about_ca_topic_score_codex":0.000008349212,"about_ca_topic_score_gemma":0.000009845999,"teacher_disagreement_score":0.8780975,"about_ca_system_score_codex":0.000107000575,"about_ca_system_score_gemma":0.000086336084,"threshold_uncertainty_score":0.999908},"labels":[],"label_agreement":null},{"id":"W4224052715","doi":"10.1109/accai53970.2022.9752506","title":"Deep Fakes Image Animation Using Generative Adversarial Networks","year":2022,"lang":"en","type":"article","venue":"2022 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Adversarial system; Face (sociological concept); Animation; Identifier; Idiot; Closeness; Class (philosophy); Computer vision; Computer graphics (images); Psychology","score_opus":0.02139146744812673,"score_gpt":0.285105862677837,"score_spread":0.26371439522971024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224052715","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030056355,0.0002880172,0.96047,0.00048667967,0.0005740967,0.0003382133,0.000008398557,0.000072222974,0.03475671],"genre_scores_gemma":[0.8223271,0.00060879067,0.17609297,0.0007081248,0.00007857053,0.000045026532,0.00009566096,0.00001078876,0.00003301345],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981408,0.00022233356,0.00070558704,0.00028055318,0.00038477074,0.00026594894],"domain_scores_gemma":[0.99840355,0.0002227853,0.0005995044,0.00053478143,0.0001729017,0.000066453904],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007088932,0.00024143596,0.00026156334,0.00026466226,0.0007240388,0.0004236945,0.001502029,0.000051381972,0.00019433323],"category_scores_gemma":[0.00004649815,0.00025903285,0.000052865715,0.00036925712,0.00011904187,0.0012337627,0.001447997,0.0005581956,0.0000065461777],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003365316,0.000063175714,0.00003532248,0.000005363262,0.000016925562,5.904584e-7,0.0019236662,0.59064186,0.00017113818,0.3695249,0.000098329816,0.037485104],"study_design_scores_gemma":[0.0006971372,0.000056915258,0.00008122089,0.000025934904,0.0000049639066,0.000007653058,0.0019052005,0.98476326,0.00015962965,0.008323628,0.0037037523,0.0002707202],"about_ca_topic_score_codex":0.00001858641,"about_ca_topic_score_gemma":0.000023883282,"teacher_disagreement_score":0.81932145,"about_ca_system_score_codex":0.00022660443,"about_ca_system_score_gemma":0.00006820423,"threshold_uncertainty_score":0.9999862},"labels":[],"label_agreement":null},{"id":"W4225277467","doi":"10.1007/s10994-022-06171-2","title":"Arbitrary conditional inference in variational autoencoders via fast prior network training","year":2022,"lang":"en","type":"article","venue":"Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Inference; Computer science; Artificial intelligence; Conditional probability distribution; Machine learning; Approximate inference; Pattern recognition (psychology); Mathematics; Statistics","score_opus":0.015102373214212433,"score_gpt":0.23249925987396183,"score_spread":0.2173968866597494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225277467","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017225542,0.00011150895,0.99440277,0.0011207183,0.00030169464,0.000110143985,0.0000060609077,0.00010805005,0.002116482],"genre_scores_gemma":[0.90975606,0.0000026630942,0.08891719,0.00076047296,0.00020881108,0.00004799942,0.00007720053,0.000011769217,0.00021786323],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980714,0.00050113455,0.00027166202,0.00039556727,0.00038529772,0.00037496633],"domain_scores_gemma":[0.9991441,0.0004671989,0.0001375005,0.0001566707,0.000029116374,0.0000654263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076199445,0.00015206696,0.00018922905,0.00012551525,0.0007506012,0.000109969966,0.0004914668,0.000030669547,0.0006588404],"category_scores_gemma":[0.0001336597,0.00016739192,0.000065173146,0.0005874003,0.00003261171,0.00039728847,0.0004044057,0.00065381813,0.000011681732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000076195884,0.000028974708,0.0058698244,0.0000018720742,0.000014681252,0.000022742093,0.0013349927,0.96087015,0.00009648382,0.011808168,0.000104884384,0.019839607],"study_design_scores_gemma":[0.0003355341,0.00006907348,0.020246528,0.0000069096914,0.00000318993,0.000013239898,0.00007005249,0.9650587,0.0000050297162,0.008650196,0.005355738,0.00018581272],"about_ca_topic_score_codex":0.00010093677,"about_ca_topic_score_gemma":0.00004209761,"teacher_disagreement_score":0.9080335,"about_ca_system_score_codex":0.000088830326,"about_ca_system_score_gemma":0.00016203182,"threshold_uncertainty_score":0.72138405},"labels":[],"label_agreement":null},{"id":"W4225832902","doi":"10.1609/aaai.v36i7.20745","title":"Top-Down Deep Clustering with Multi-Generator GANs","year":2022,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Esri (Canada)","funders":"Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Cluster analysis; Computer science; Generator (circuit theory); Artificial intelligence; Data mining; Hierarchical clustering; Embedding; Classifier (UML); Hierarchy; Brown clustering; Spectral clustering; Tree (set theory); Pattern recognition (psychology); Machine learning; Fuzzy clustering; Canopy clustering algorithm; Power (physics); Mathematics","score_opus":0.07021922864840058,"score_gpt":0.28183157062333425,"score_spread":0.21161234197493367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225832902","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01232518,0.00010746981,0.97529376,0.0030280396,0.0018694202,0.0010746492,0.000025434209,0.00017237026,0.006103689],"genre_scores_gemma":[0.9331552,0.00008333243,0.065573215,0.00031641632,0.00023062991,0.00016490881,0.0000025267368,0.00003799199,0.00043578775],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99663794,0.000065818196,0.0007346149,0.0011988897,0.00080893753,0.0005537963],"domain_scores_gemma":[0.9973688,0.00008889234,0.0008087564,0.0007904896,0.0007970236,0.00014600961],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006095456,0.0005535807,0.00059033965,0.00019253691,0.0004962323,0.0007270395,0.0043475665,0.00018383615,0.00034744779],"category_scores_gemma":[0.00021450523,0.00040424222,0.00025250233,0.00065137306,0.00029868793,0.0003519754,0.0037475675,0.0010763174,0.000027439264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004611719,0.0011996462,0.00077965145,0.0005489883,0.00045808274,0.000017185506,0.012809524,0.27312982,0.050988384,0.35089874,0.0007359116,0.3079729],"study_design_scores_gemma":[0.00004443748,0.00022664519,0.000105011895,0.00023861916,0.00004204952,0.000005385855,0.0007056274,0.7878848,0.1999361,0.009966,0.00027986505,0.0005654708],"about_ca_topic_score_codex":0.0001432363,"about_ca_topic_score_gemma":0.00011169582,"teacher_disagreement_score":0.92083,"about_ca_system_score_codex":0.00013832787,"about_ca_system_score_gemma":0.00029928616,"threshold_uncertainty_score":0.9998409},"labels":[],"label_agreement":null},{"id":"W4232120185","doi":"10.1007/978-1-4899-7687-1_67","title":"Deep Belief Nets","year":2017,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Machine Learning and Data Mining","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Psychology; Computer science; Artificial intelligence","score_opus":0.02275188405138471,"score_gpt":0.2647078751643677,"score_spread":0.24195599111298302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232120185","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010146969,0.008648357,0.16401441,0.00037235662,0.0005855741,0.00011872981,0.000054839198,0.00008230916,0.8261133],"genre_scores_gemma":[0.0053497837,0.021187184,0.23434952,0.00017978031,0.0012763727,0.0000048773327,0.0008893538,0.0001168976,0.73664623],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981112,0.000065929096,0.00038094504,0.00087448605,0.00029839828,0.00026907778],"domain_scores_gemma":[0.99730647,0.00031805265,0.00062870735,0.001553782,0.00006694181,0.00012607826],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006151235,0.00036265768,0.0005447366,0.00012797679,0.00041728877,0.00019880605,0.0018722073,0.00019812041,0.00009226592],"category_scores_gemma":[0.000470703,0.00033667797,0.00006821948,0.000017917446,0.00013492194,0.0006186049,0.0025137584,0.0005666544,0.000022899996],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000921206,0.00001263936,0.0006359454,0.000047800124,0.000119860204,0.000054726424,0.0005789159,0.0003253327,0.000006351843,0.0047233426,0.006219112,0.9872668],"study_design_scores_gemma":[0.00020048518,0.000098963756,0.00010845064,0.0001740517,0.00005673317,0.000015571048,0.000008322707,0.16285267,0.0000024185208,0.0006766303,0.8354381,0.00036762928],"about_ca_topic_score_codex":0.00008672327,"about_ca_topic_score_gemma":0.000057499896,"teacher_disagreement_score":0.98689914,"about_ca_system_score_codex":0.000008924204,"about_ca_system_score_gemma":0.00007322635,"threshold_uncertainty_score":0.9999085},"labels":[],"label_agreement":null},{"id":"W4237136595","doi":"10.1007/978-1-4471-7452-3_24","title":"Deep Learning","year":2019,"lang":"en","type":"book-chapter","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Deep learning; Artificial intelligence; Computer science","score_opus":0.013092554057033029,"score_gpt":0.2008784637070687,"score_spread":0.18778590965003567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237136595","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.4204813e-8,0.00020631604,0.48504615,0.00009714864,0.00030077665,0.000051986142,1.12463354e-7,0.000068021,0.5142295],"genre_scores_gemma":[0.0011446255,0.00012776158,0.031896066,0.00029380928,0.0002633475,9.488364e-7,0.0000038041942,0.000023139057,0.9662465],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99902326,0.000017406524,0.00015666081,0.00042371644,0.00019676366,0.00018218346],"domain_scores_gemma":[0.99923164,0.00007866578,0.000103518534,0.0004585163,0.00007141882,0.000056271165],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00010305289,0.00021678024,0.0002459171,0.000070414826,0.000076575234,0.00014810631,0.0005841816,0.00016301163,0.0011725763],"category_scores_gemma":[0.000011445037,0.00018404453,0.00013962053,0.000019804407,0.000022691138,0.00019603824,0.0003075661,0.00029644434,0.0028626241],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.374899e-7,0.0000026184216,0.0000027796295,0.000006103482,0.000046451754,0.000010559913,0.000042861328,0.0047730035,0.00001998923,0.8268507,0.00449589,0.16374807],"study_design_scores_gemma":[0.00006812403,0.00004837431,0.0000060606267,0.00002606518,0.000009996952,0.0000038217313,0.000001741298,0.16868263,0.00005364578,0.00810585,0.8226836,0.0003101345],"about_ca_topic_score_codex":0.0000048052175,"about_ca_topic_score_gemma":0.0000068966074,"teacher_disagreement_score":0.8187449,"about_ca_system_score_codex":0.000025461166,"about_ca_system_score_gemma":0.000045852375,"threshold_uncertainty_score":0.9997405},"labels":[],"label_agreement":null},{"id":"W4245359331","doi":"10.1007/978-1-4899-7687-1_31","title":"Boltzmann Machines","year":2017,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Machine Learning and Data Mining","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Boltzmann machine; Computer science; Artificial intelligence; Artificial neural network","score_opus":0.025019461061916173,"score_gpt":0.27151708647657136,"score_spread":0.2464976254146552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245359331","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000019097697,0.008333565,0.05350378,0.00040131208,0.00065443973,0.00012669023,0.00014982259,0.000104100465,0.9367072],"genre_scores_gemma":[0.004044976,0.014216818,0.12416327,0.000092036375,0.0011616572,0.000003770026,0.00074999157,0.00009334154,0.8554741],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980187,0.000070636095,0.00041227913,0.0009230055,0.00031078252,0.0002645934],"domain_scores_gemma":[0.99713004,0.00032279416,0.0006853767,0.0016693898,0.00007036949,0.00012201056],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006908937,0.00040681736,0.0006117852,0.0001525141,0.00043737623,0.00022095519,0.0020471034,0.0001965647,0.00009205264],"category_scores_gemma":[0.0005208464,0.00036427146,0.00007984887,0.000018521598,0.0001517107,0.00068833487,0.0027285216,0.0005921523,0.000021759914],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013110831,0.00001406059,0.0011320164,0.00008270665,0.00015140208,0.000060556795,0.00047820839,0.000108244414,0.000010888797,0.0075952136,0.011573711,0.97877985],"study_design_scores_gemma":[0.00021931104,0.00009280995,0.0001509847,0.00021579259,0.00007230575,0.000019669766,0.000006162783,0.104273975,0.000002904672,0.0010287145,0.89349157,0.00042579282],"about_ca_topic_score_codex":0.00012397424,"about_ca_topic_score_gemma":0.000048220933,"teacher_disagreement_score":0.9783541,"about_ca_system_score_codex":0.000008324789,"about_ca_system_score_gemma":0.0000792435,"threshold_uncertainty_score":0.9998809},"labels":[],"label_agreement":null},{"id":"W4247163284","doi":"10.1007/978-1-4471-7452-3_23","title":"Boltzmann Machines","year":2019,"lang":"en","type":"book-chapter","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Boltzmann machine; Restricted Boltzmann machine; Boltzmann constant; Artificial intelligence; Computer science; Artificial neural network; Popularity; Boltzmann equation; Deep learning; Machine learning; Physics; Psychology; Thermodynamics","score_opus":0.014245249133958963,"score_gpt":0.21051112094279098,"score_spread":0.196265871808832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247163284","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.03059e-8,0.00028217924,0.36790243,0.00039176183,0.0006866659,0.000095199845,0.00000279301,0.000083768224,0.63055515],"genre_scores_gemma":[0.00044471739,0.0000927603,0.02849809,0.00078048196,0.0004181838,0.0000013981629,0.0000070586516,0.000025893154,0.9697314],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99889183,0.000012138241,0.00019216354,0.000491725,0.00022260855,0.00018951783],"domain_scores_gemma":[0.99890375,0.000061663675,0.000104552455,0.0007893606,0.00007614976,0.000064516964],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000093752424,0.00028077638,0.00030495613,0.000084923726,0.000060388174,0.00016130632,0.0008336861,0.00017040865,0.0011649122],"category_scores_gemma":[0.000006607391,0.00022005425,0.00017689768,0.000021019414,0.000029836297,0.00023609365,0.0003750978,0.00018464446,0.0027653808],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010235367,0.0000036427355,0.0000015340992,0.000006779631,0.0000430097,0.000009185419,0.000015143174,0.00014662609,0.00001997022,0.88161904,0.058630876,0.05950319],"study_design_scores_gemma":[0.00008866176,0.000040371644,0.000011834134,0.0000337491,0.000013866467,0.0000058847368,3.7728756e-7,0.038129803,0.00007758643,0.034810875,0.9263946,0.0003923847],"about_ca_topic_score_codex":0.000013516241,"about_ca_topic_score_gemma":0.000014292784,"teacher_disagreement_score":0.86776376,"about_ca_system_score_codex":0.000021632497,"about_ca_system_score_gemma":0.00007412824,"threshold_uncertainty_score":0.9997482},"labels":[],"label_agreement":null},{"id":"W4253809711","doi":"10.1109/icpr.2016.7900005","title":"Mutual information-based RBM neural networks","year":2016,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; Nvidia","keywords":"Mutual information; Boltzmann machine; Computer science; Discriminative model; Artificial intelligence; Restricted Boltzmann machine; Artificial neural network; Machine learning; Pattern recognition (psychology)","score_opus":0.0071166385441069485,"score_gpt":0.19136617102709924,"score_spread":0.1842495324829923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253809711","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003668149,0.000011690067,0.9911586,0.0034991626,0.00045945594,0.000069969996,0.0000010020948,0.0001377935,0.0042954986],"genre_scores_gemma":[0.9699361,0.0000022785953,0.027210029,0.0023459296,0.0001487716,0.0000072588005,0.0000013034997,0.0000030245303,0.00034535368],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926955,0.00004767955,0.00016910976,0.00013841291,0.00014167298,0.00023360107],"domain_scores_gemma":[0.9992958,0.00017021048,0.000051885938,0.00031979484,0.00008212447,0.00008022913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012994157,0.00009849624,0.00008717371,0.00005017954,0.00009350692,0.0001514119,0.00043566365,0.00003893659,0.00016554302],"category_scores_gemma":[0.000047628302,0.000056120316,0.000056306955,0.00017810814,0.00003594573,0.0015324046,0.00008969123,0.00003891997,0.00017391711],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012912716,0.000025348932,0.00084876193,0.0000020776617,0.000016181375,0.0000032925343,0.00007526073,0.08824461,0.0002445844,0.021720843,0.03212261,0.8566835],"study_design_scores_gemma":[0.00028745396,0.000036108202,0.00069862464,0.000004340946,0.0000016178927,0.0000010462353,0.0000033198662,0.9849876,0.0010923119,0.00013880039,0.0126313865,0.000117388314],"about_ca_topic_score_codex":0.0000136308345,"about_ca_topic_score_gemma":0.0000064797428,"teacher_disagreement_score":0.9695692,"about_ca_system_score_codex":0.000018124745,"about_ca_system_score_gemma":0.000029263498,"threshold_uncertainty_score":0.228852},"labels":[],"label_agreement":null},{"id":"W4283381280","doi":"10.48550/arxiv.2206.09210","title":"Multi-Modality Image Inpainting using Generative Adversarial Networks","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inpainting; Image (mathematics); Image translation; Translation (biology); Generative grammar; Artificial intelligence; Computer science; Adversarial system; Modality (human–computer interaction); Task (project management); Computer vision; Pattern recognition (psychology); Engineering","score_opus":0.09290140356253535,"score_gpt":0.21729377214380863,"score_spread":0.12439236858127328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283381280","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018898165,0.00010172966,0.9766935,0.00014231575,0.0027009204,0.00054085604,0.00003823108,0.0002801395,0.00060415827],"genre_scores_gemma":[0.8828695,0.00007929476,0.11571105,0.00019155875,0.00063812,0.0000030327699,0.000041963827,0.000042946867,0.00042256023],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952479,0.001228244,0.00044961952,0.0020937284,0.00019215388,0.00078833697],"domain_scores_gemma":[0.996939,0.00021367114,0.00064357714,0.0016433764,0.000299758,0.00026060606],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00096758245,0.0006508849,0.00069615943,0.00027977125,0.0009936757,0.00042753742,0.0025628454,0.00036935895,0.00021798881],"category_scores_gemma":[0.000119588905,0.0007868597,0.00053622253,0.0009622875,0.00023002362,0.0009501834,0.0071542826,0.0014247643,0.000015373811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000324288,0.00011933467,0.00047387788,0.000019604471,0.00019457561,0.00030170573,0.0003028794,0.99273807,0.00041664165,0.0047808867,0.00022688023,0.00039310957],"study_design_scores_gemma":[0.0007360418,0.00003801291,0.0003178551,0.000037377144,0.00012221563,0.0000040311947,0.00016874872,0.99461323,0.00020198403,0.0026635642,0.00028590547,0.00081100763],"about_ca_topic_score_codex":0.00094833557,"about_ca_topic_score_gemma":0.00009203188,"teacher_disagreement_score":0.8639713,"about_ca_system_score_codex":0.0007175248,"about_ca_system_score_gemma":0.00036636484,"threshold_uncertainty_score":0.99945825},"labels":[],"label_agreement":null},{"id":"W4283698083","doi":"10.48550/arxiv.2206.13388","title":"Rotated Digit Recognition by Variational Autoencoders with Fixed Output Distributions","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"MNIST database; Autoencoder; Numerical digit; Dimension (graph theory); Pattern recognition (psychology); Computer science; Artificial intelligence; Representation (politics); Algorithm; Mathematics; Arithmetic; Deep learning; Combinatorics","score_opus":0.05256001007745448,"score_gpt":0.16971899492815623,"score_spread":0.11715898485070175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283698083","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00709212,0.000021412807,0.9889921,0.0003944788,0.0004241751,0.00033516754,0.00063276937,0.00022773299,0.0018800262],"genre_scores_gemma":[0.98419553,0.000087041895,0.011625549,0.000109309,0.0000706035,0.000009258526,0.0015606389,0.000019489664,0.002322586],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997975,0.0002615881,0.000196563,0.0010568975,0.00016633232,0.00034364522],"domain_scores_gemma":[0.99851686,0.00013642425,0.00028552217,0.0006682499,0.00023942352,0.00015354143],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014075368,0.00031192374,0.00027298994,0.00014244135,0.00048822886,0.00023968899,0.0010309849,0.00014438722,0.0002320973],"category_scores_gemma":[0.000041718562,0.00034040815,0.00015412565,0.00073202065,0.00010146165,0.00059247384,0.0010375374,0.0005059731,0.000042776195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045023655,0.00017385074,0.00042434662,0.000011993843,0.00022446591,0.00008269084,0.000103451246,0.9830916,0.000018232658,0.006131737,0.008170936,0.0015216599],"study_design_scores_gemma":[0.00058867503,0.00010303229,0.0008356617,0.000033434033,0.00011206276,0.0000040186633,0.000066410976,0.9791301,0.00014644241,0.010667286,0.0077180406,0.0005948617],"about_ca_topic_score_codex":0.00022406915,"about_ca_topic_score_gemma":0.00003291588,"teacher_disagreement_score":0.97736657,"about_ca_system_score_codex":0.00035979756,"about_ca_system_score_gemma":0.0003374361,"threshold_uncertainty_score":0.9999048},"labels":[],"label_agreement":null},{"id":"W4283800850","doi":"10.1609/aaai.v36i7.20745","title":"Top-Down Deep Clustering with Multi-Generator GANs","year":2022,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Esri (Canada)","funders":"Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Computer science; Cluster analysis; Generator (circuit theory); Artificial intelligence; Data mining; Hierarchical clustering; Embedding; Classifier (UML); Brown clustering; Spectral clustering; Hierarchy; Pattern recognition (psychology); Machine learning; Fuzzy clustering; Canopy clustering algorithm; Power (physics)","score_opus":0.013517863185444377,"score_gpt":0.2105684973677443,"score_spread":0.19705063418229993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283800850","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014949966,0.00007059802,0.99453384,0.0006626541,0.00033455345,0.000118858065,0.0000016515631,0.00011989332,0.0026629618],"genre_scores_gemma":[0.64832693,0.0000025622141,0.34925672,0.0009463525,0.00008865753,0.00004118498,0.00000159525,0.000009551645,0.0013264598],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989308,0.00009968189,0.00012480284,0.00035717283,0.00022546989,0.00026206177],"domain_scores_gemma":[0.99944645,0.000030231606,0.00004243642,0.0003596373,0.00004108709,0.00008012803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016246975,0.00012314382,0.00012201715,0.000053926848,0.00044527964,0.00014135837,0.0005764155,0.000014498758,0.0005395378],"category_scores_gemma":[0.0000071404597,0.00009685402,0.00004261905,0.00032946796,0.000021360489,0.00027941348,0.00054341153,0.00011202016,0.000019393507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003127202,0.00023859156,0.00089444313,0.000008256306,0.000092737675,0.00011612456,0.002116741,0.8722654,0.016116275,0.0046580248,0.0041307695,0.09933135],"study_design_scores_gemma":[0.00035253266,0.00012012943,0.0003679811,0.0000012036888,0.0000045761394,0.000021535592,0.00017355221,0.9805813,0.0064794496,0.000021687523,0.011680803,0.00019523613],"about_ca_topic_score_codex":0.00007288938,"about_ca_topic_score_gemma":0.00018143201,"teacher_disagreement_score":0.6468319,"about_ca_system_score_codex":0.000046327765,"about_ca_system_score_gemma":0.0000448818,"threshold_uncertainty_score":0.59075606},"labels":[],"label_agreement":null},{"id":"W4285192846","doi":"10.1007/978-3-031-06427-2_23","title":"Landmark-Guided Conditional GANs for Face Aging","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Memorial University of Newfoundland","funders":"","keywords":"Discriminative model; Computer science; Landmark; Consistency (knowledge bases); Artificial intelligence; Task (project management); Identity (music); Face (sociological concept); Generative grammar; Computer vision; Scope (computer science); Aesthetics; Art","score_opus":0.024058852724427558,"score_gpt":0.25670236338904157,"score_spread":0.232643510664614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285192846","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000069162434,0.0002668669,0.99205416,0.0019655316,0.0019572838,0.00050177285,0.000046328263,0.000101138074,0.0030999924],"genre_scores_gemma":[0.14267783,0.00006083311,0.8492686,0.004266957,0.0016777613,0.00008501077,0.00009097008,0.000065757304,0.0018062736],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968031,0.000047567977,0.00041416028,0.0013546946,0.00077330257,0.00060714287],"domain_scores_gemma":[0.9977979,0.00079444435,0.00024157143,0.00082476233,0.00020945532,0.00013187891],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008713783,0.0004260974,0.00044766255,0.0004520072,0.0006128498,0.00046198242,0.0024460722,0.00014188814,0.00015617006],"category_scores_gemma":[0.000101474,0.00040909665,0.00019510752,0.00037560408,0.00035561484,0.0006205898,0.0011107721,0.0005014443,0.000014275425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000797503,0.000034089535,0.000032383432,0.00003688106,0.00003846966,0.00005912173,0.0007629509,0.6907572,0.00023964857,0.06533719,0.0014919571,0.24120215],"study_design_scores_gemma":[0.00037030186,0.00012737562,0.000045820427,0.00007823204,0.000011460526,0.000047217123,3.2150518e-7,0.8275111,0.0011312083,0.13207532,0.03796784,0.00063384796],"about_ca_topic_score_codex":0.000015572068,"about_ca_topic_score_gemma":0.000031254618,"teacher_disagreement_score":0.2405683,"about_ca_system_score_codex":0.00028328234,"about_ca_system_score_gemma":0.00046863325,"threshold_uncertainty_score":0.9998361},"labels":[],"label_agreement":null},{"id":"W4285219276","doi":"10.4018/ijssci.300364","title":"A Comparative Study of Generative Adversarial Networks for Text-to-Image Synthesis","year":2022,"lang":"en","type":"article","venue":"International Journal of Software Science and Computational Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Generative grammar; Task (project management); Image (mathematics); Field (mathematics); Image synthesis; Artificial intelligence; Adversarial system; Tree (set theory); Natural language processing; Mathematics","score_opus":0.029652340812840124,"score_gpt":0.31188822673331545,"score_spread":0.2822358859204753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285219276","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030080883,0.00006764713,0.967475,0.0006635201,0.0012794508,0.00035811536,0.000024509185,0.0000122871825,0.000038611102],"genre_scores_gemma":[0.8050304,0.000005514,0.19446744,0.0002693236,0.00016971602,0.000042184034,0.0000011578292,0.0000050869453,0.000009196919],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99689704,0.0001613446,0.0006899878,0.00039957004,0.0016277729,0.00022428078],"domain_scores_gemma":[0.9940681,0.0011985718,0.00058998825,0.00015436966,0.0038386227,0.00015038534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016926972,0.00016430413,0.00034402008,0.0005681187,0.00050590775,0.00024746248,0.0020766119,0.000019351699,0.000030475108],"category_scores_gemma":[0.0007771797,0.00015091595,0.000099427045,0.0009209596,0.000273182,0.0009642082,0.00072247954,0.00018282195,0.0000012766832],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018196044,0.00040517875,0.00016932075,0.0000019841746,0.00012720324,0.000013805303,0.0046463013,0.9555565,0.0003760691,0.003981903,0.00041768976,0.03412207],"study_design_scores_gemma":[0.0005849011,0.002286166,0.0022321353,0.000039999144,0.00004053609,0.00013053887,0.005864534,0.9733706,0.004395912,0.010168396,0.00056200806,0.00032426987],"about_ca_topic_score_codex":0.000026437263,"about_ca_topic_score_gemma":0.0000064246874,"teacher_disagreement_score":0.7749495,"about_ca_system_score_codex":0.00018644329,"about_ca_system_score_gemma":0.0005416461,"threshold_uncertainty_score":0.61541736},"labels":[],"label_agreement":null},{"id":"W4287597924","doi":"10.1109/tpami.2022.3228915","title":"Continuous Conditional Generative Adversarial Networks: Novel Empirical Losses and Label Input Mechanisms","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Discriminator; Computer science; Generator (circuit theory); Regression; Categorical variable; Benchmark (surveying); Artificial intelligence; Scalar (mathematics); Pattern recognition (psychology); Algorithm; Machine learning; Mathematics; Statistics; Power (physics)","score_opus":0.025257020395741264,"score_gpt":0.26777690884055444,"score_spread":0.24251988844481318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287597924","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011874408,0.0001506628,0.9968416,0.00096271787,0.00041671775,0.0001664156,0.00019326607,0.00005577818,0.000025411066],"genre_scores_gemma":[0.98622876,0.0001412143,0.01141838,0.0018831323,0.000070026734,0.00006628549,0.000026223384,0.000012674415,0.0001532865],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799824,0.00023634435,0.00037927704,0.00071955094,0.0003748626,0.0002917276],"domain_scores_gemma":[0.9990241,0.0002733843,0.00013903393,0.0003164649,0.00009139656,0.00015561646],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034021653,0.0002777337,0.00041429375,0.00033559796,0.00084346766,0.00021098187,0.00037035247,0.00005808793,0.00033965532],"category_scores_gemma":[0.000006743738,0.00025712434,0.00018017342,0.0008972268,0.00012046917,0.00027413934,0.000036769332,0.00038656808,0.0000040780087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042100597,0.00042302004,0.00017728607,0.000004078212,0.0009513871,0.000022010972,0.000463875,0.8153574,0.000945817,0.00086709403,0.000096138,0.18064982],"study_design_scores_gemma":[0.00030271144,0.00031622598,0.00024021052,0.0000043115556,0.0003534612,0.00003172764,0.00011698284,0.9848864,0.0123775825,0.0008496242,0.00020029451,0.00032046312],"about_ca_topic_score_codex":0.00042348166,"about_ca_topic_score_gemma":0.0003818518,"teacher_disagreement_score":0.9854232,"about_ca_system_score_codex":0.000050512317,"about_ca_system_score_gemma":0.000037517802,"threshold_uncertainty_score":0.9999881},"labels":[],"label_agreement":null},{"id":"W4288246334","doi":"10.48550/arxiv.1908.11525","title":"Class-Based Styling: Real-time Localized Style Transfer with Semantic\\n Segmentation","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Segmentation; Computer science; Leverage (statistics); Artificial intelligence; Frame (networking); Computer vision; Class (philosophy); Object (grammar); Style (visual arts); Transfer (computing); Geography; Parallel computing","score_opus":0.03497582160052083,"score_gpt":0.18298190466105455,"score_spread":0.1480060830605337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288246334","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060037475,0.000016030459,0.9362038,0.0001519829,0.00027710263,0.0006132731,0.00001880755,0.00022696565,0.0024545875],"genre_scores_gemma":[0.98636246,0.00007649904,0.011391987,0.00014275718,0.00007608977,0.000002220813,0.00005874683,0.00003503485,0.0018542242],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975136,0.00032783404,0.00024201458,0.0013041216,0.00018650829,0.00042595674],"domain_scores_gemma":[0.99807286,0.00016421519,0.00016762457,0.0011911455,0.00023898782,0.0001651686],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002715604,0.00044600666,0.000512364,0.00023017367,0.00016818808,0.00023105276,0.0011194691,0.00026884567,0.000112317415],"category_scores_gemma":[0.0000093500785,0.0004365397,0.00023012332,0.0005359964,0.000120200624,0.0004661151,0.00034305485,0.00038502982,0.00017778038],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015343173,0.00010630288,0.0005304519,0.00005954292,0.00015909919,0.000116872,0.00015402648,0.99378794,0.0012226298,0.0029753936,0.000244075,0.00049024366],"study_design_scores_gemma":[0.0015206261,0.00016500746,0.00020479604,0.00013478748,0.0001597153,0.0000013287035,0.000053955955,0.99102396,0.0053985054,0.00046657695,0.0002993412,0.0005714008],"about_ca_topic_score_codex":0.0002563393,"about_ca_topic_score_gemma":0.000056316392,"teacher_disagreement_score":0.92632496,"about_ca_system_score_codex":0.0002001423,"about_ca_system_score_gemma":0.00037194107,"threshold_uncertainty_score":0.9998086},"labels":[],"label_agreement":null},{"id":"W4289146962","doi":"10.52591/lxai201812036","title":"Generating Videos by Traversing Image Manifolds Learned by GANs","year":2018,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Generator (circuit theory); Discriminator; Computer science; Generative grammar; Artificial intelligence; Traverse; Image (mathematics); Adversarial system; Computer vision; Manifold (fluid mechanics); Sequence (biology); Scheme (mathematics); Generative model; Pattern recognition (psychology); Mathematics","score_opus":0.011881647150019598,"score_gpt":0.2356378222970483,"score_spread":0.2237561751470287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289146962","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003484474,0.00008960235,0.9792085,0.0016334042,0.0003268437,0.00009774085,0.000004358807,0.00015436058,0.015000659],"genre_scores_gemma":[0.6013423,0.000018721632,0.39029902,0.0021253757,0.0005183743,0.000005148707,0.000007870325,0.000020843601,0.0056623197],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985295,0.00011446411,0.00021602424,0.0005036739,0.00022365218,0.0004127159],"domain_scores_gemma":[0.99927145,0.000059799822,0.0000707133,0.0003668449,0.000107649765,0.00012351129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026827093,0.00018265677,0.00016522482,0.000039958824,0.0004251186,0.00046156198,0.0005640256,0.00006573153,0.0003684082],"category_scores_gemma":[0.000035759014,0.00016266335,0.000070272814,0.0002495322,0.00009814859,0.00080404954,0.00015812747,0.00009460572,0.00021577813],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029114549,0.000031244384,0.000014935277,0.0000021199885,0.000018994062,0.0000035228934,0.00032794743,0.00008940841,0.6948884,0.00057282083,0.28064406,0.023403617],"study_design_scores_gemma":[0.00026411976,0.00012488698,0.000012788149,0.000008317587,0.0000078052835,0.000005580068,0.000090970025,0.52545434,0.43748128,0.00017731437,0.036089547,0.00028303088],"about_ca_topic_score_codex":0.00016063814,"about_ca_topic_score_gemma":0.000023517645,"teacher_disagreement_score":0.59785783,"about_ca_system_score_codex":0.000036825375,"about_ca_system_score_gemma":0.000029694773,"threshold_uncertainty_score":0.6633219},"labels":[],"label_agreement":null},{"id":"W4290058690","doi":"10.1016/j.neucom.2022.08.014","title":"Information flow in Deep Restricted Boltzmann Machines: An analysis of mutual information between inputs and outputs","year":2022,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"H2020 Marie Skłodowska-Curie Actions; Universidad de Buenos Aires; Secretaría de Ciencia y Técnica, Universidad de Buenos Aires; Horizon 2020 Framework Programme; Horizon 2020; Consejo Nacional de Investigaciones Científicas y Técnicas","keywords":"Mutual information; Boltzmann machine; Information flow; Computer science; Flow (mathematics); Artificial intelligence; Restricted Boltzmann machine; Mathematics; Deep learning","score_opus":0.00953680857249059,"score_gpt":0.22392151572685606,"score_spread":0.21438470715436547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4290058690","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45362845,0.000008053711,0.5459111,0.00010342305,0.00008625421,0.00012108038,0.000009221066,0.000041559502,0.0000908632],"genre_scores_gemma":[0.98503816,0.0000020497134,0.014504103,0.00032364717,0.000038285638,0.0000065984027,0.000082808736,0.0000033174192,0.0000010172683],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984887,0.0002696595,0.000554515,0.00016062525,0.00032344423,0.00020302754],"domain_scores_gemma":[0.99913895,0.00015546424,0.0003072428,0.00025468264,0.00008253903,0.00006110242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039026391,0.00012511178,0.00026445487,0.0008908973,0.00022666562,0.00015499815,0.0004099233,0.000032481596,0.0000048327393],"category_scores_gemma":[0.00008730941,0.0001325689,0.00005502047,0.0020737394,0.000018578598,0.0023894964,0.0005213618,0.00019774673,0.000001480265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069093735,0.000019979228,0.032597467,0.0000096588865,0.000040656138,0.0000013383426,0.0060110595,0.6652304,0.00005667848,0.00020188082,0.000018721836,0.29580525],"study_design_scores_gemma":[0.00022012238,0.00006973618,0.23113382,0.0000026846633,0.000029495068,0.0000012621779,0.00010244922,0.76776195,0.00004928892,0.00003020025,0.0005077289,0.00009127742],"about_ca_topic_score_codex":0.00013448265,"about_ca_topic_score_gemma":0.000018648929,"teacher_disagreement_score":0.53140974,"about_ca_system_score_codex":0.00003912278,"about_ca_system_score_gemma":0.000031424395,"threshold_uncertainty_score":0.54060024},"labels":[],"label_agreement":null},{"id":"W4297175647","doi":"10.1007/s10845-022-02003-1","title":"Polygon generation and video-to-video translation for time-series prediction","year":2022,"lang":"en","type":"article","venue":"Journal of Intelligent Manufacturing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Hydro-Québec; Polytechnique Montréal","funders":"Natural Resources Canada; Office of Energy Research and Development; Natural Sciences and Engineering Research Council of Canada","keywords":"Translation (biology); Series (stratigraphy); Polygon (computer graphics); Computer science; Computer graphics (images); Production (economics); Artificial intelligence; Telecommunications; Economics; Geology","score_opus":0.023807872301316212,"score_gpt":0.23511998373363557,"score_spread":0.21131211143231937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297175647","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034883264,0.00022246345,0.96207285,0.001741093,0.00079018035,0.00021182309,0.000007994362,0.000015355181,0.000054970602],"genre_scores_gemma":[0.9106042,0.0000979536,0.088038824,0.00023834237,0.0007809051,0.000019229205,0.0000057407838,0.000012349391,0.000202448],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989798,0.00008682136,0.00037627266,0.00016815917,0.00024710083,0.00014185865],"domain_scores_gemma":[0.9994469,0.00008289104,0.00020107054,0.00011722133,0.00007353975,0.00007835202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058519107,0.000103262486,0.00015776156,0.00018779114,0.00031257194,0.00014531735,0.0002284734,0.000022973547,0.00003765337],"category_scores_gemma":[0.000032311742,0.000094401876,0.000090007765,0.000081265076,0.000010300517,0.00068194256,0.00008003869,0.00012225112,0.000002026525],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017683471,0.000045863628,0.00003303693,0.000016818627,0.00008748623,0.00000555625,0.00223637,0.5256984,0.07925653,0.00019776757,0.0057636015,0.38648167],"study_design_scores_gemma":[0.00027611287,0.00072895957,0.00023110081,0.000019288998,0.000030707848,0.00009070261,0.00012895859,0.18897615,0.7312569,0.00061391044,0.0774918,0.00015543314],"about_ca_topic_score_codex":0.000004431386,"about_ca_topic_score_gemma":0.0000027585309,"teacher_disagreement_score":0.8757209,"about_ca_system_score_codex":0.00008205087,"about_ca_system_score_gemma":0.000027426506,"threshold_uncertainty_score":0.38495967},"labels":[],"label_agreement":null},{"id":"W4297690050","doi":"","title":"Image Inpainting Using a Fourth-Order Total Variation Flow","year":2009,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Inpainting; Variation (astronomy); Computer science; Flow (mathematics); Image (mathematics); Order (exchange); Artificial intelligence; Computer vision; Mathematics; Geometry; Physics","score_opus":0.018962099150814978,"score_gpt":0.24811914639674346,"score_spread":0.22915704724592847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297690050","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023258147,0.00005556399,0.9915692,0.0007509438,0.0011656232,0.00028708082,0.000002995167,0.00021844306,0.003624313],"genre_scores_gemma":[0.07053697,0.00000995889,0.92822206,0.00026157583,0.0007730307,0.0000069441494,0.000008977492,0.000017444225,0.00016302025],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978271,0.00020553918,0.0004072031,0.0008223237,0.00032807933,0.00040976255],"domain_scores_gemma":[0.9984143,0.000081237275,0.00026487742,0.00080482,0.0003404829,0.00009431664],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006551655,0.00034874844,0.00036915627,0.00015374737,0.00020788904,0.0009461114,0.00071498955,0.00024230458,0.000090384136],"category_scores_gemma":[0.00017261686,0.00032804007,0.00018439665,0.00032459217,0.000026199526,0.00063389144,0.0013543994,0.00044233308,0.000029366296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000055980713,0.0000886322,0.000021844906,0.000036738205,0.0001031969,0.000032302876,0.0011840935,0.88568914,0.009301741,0.0012451247,0.00086952955,0.101422034],"study_design_scores_gemma":[0.00014197739,0.000018921892,0.00055727124,0.000066705106,0.00002434525,0.000011670128,0.000009664928,0.9938477,0.0007576518,0.0041195317,0.00005669639,0.00038783785],"about_ca_topic_score_codex":0.0002991927,"about_ca_topic_score_gemma":0.000016112856,"teacher_disagreement_score":0.10815856,"about_ca_system_score_codex":0.00011100875,"about_ca_system_score_gemma":0.00019075125,"threshold_uncertainty_score":0.99991715},"labels":[],"label_agreement":null},{"id":"W4298289240","doi":"10.48550/arxiv.1406.2661","title":"Generative Adversarial Networks","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4572,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Compute Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Discriminative model; Minimax; Computer science; Inference; Artificial intelligence; Perceptron; Generative grammar; Machine learning; Sample (material); Generative model; Mistake; Artificial neural network; Mathematical optimization; Mathematics","score_opus":0.045611918411278804,"score_gpt":0.17388367417320086,"score_spread":0.12827175576192207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298289240","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027856298,0.000113843365,0.98897773,0.00023534341,0.0031292401,0.00034163083,0.000010144078,0.00028401578,0.004122399],"genre_scores_gemma":[0.9845417,0.00018434924,0.0119068045,0.00042130158,0.0013551884,0.0000021646977,0.00003060217,0.000031338062,0.0015265415],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967249,0.0005469933,0.0002987216,0.0016945692,0.000121742305,0.00061307655],"domain_scores_gemma":[0.9972146,0.00019553592,0.00037697577,0.0016691182,0.0002631725,0.0002805794],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041416328,0.0005574895,0.00060144806,0.00019747423,0.0003399266,0.00032190562,0.0024177432,0.0005193339,0.00007100924],"category_scores_gemma":[0.000059758353,0.00060813426,0.0004197589,0.0005136099,0.00017256061,0.00048786745,0.002828477,0.00083471055,0.000115931885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002347291,0.000043285912,0.00010984536,0.0000106166535,0.00014229454,0.000098145916,0.00008637579,0.9396876,0.00001697353,0.054846387,0.0034885022,0.001446512],"study_design_scores_gemma":[0.0005059288,0.000061689476,0.00013039599,0.000044422686,0.000085230626,0.0000025137203,0.000016134905,0.9789254,0.00014986879,0.016803497,0.0026200006,0.00065490266],"about_ca_topic_score_codex":0.00013435626,"about_ca_topic_score_gemma":0.000050726278,"teacher_disagreement_score":0.9817561,"about_ca_system_score_codex":0.00020345535,"about_ca_system_score_gemma":0.00021037742,"threshold_uncertainty_score":0.999637},"labels":[],"label_agreement":null},{"id":"W4306404970","doi":"10.1016/j.displa.2022.102321","title":"Generative image inpainting with enhanced gated convolution and Transformers","year":2022,"lang":"en","type":"article","venue":"Displays","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Inpainting; Artificial intelligence; Transformer; Computer science; Convolution (computer science); Generative grammar; Computer vision; Image (mathematics); Engineering; Electrical engineering; Voltage","score_opus":0.0052303292539551795,"score_gpt":0.19425986770559409,"score_spread":0.18902953845163892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306404970","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08043928,0.00006369642,0.9169403,0.0004669118,0.00009542158,0.00014984846,0.0000070996175,0.000043736603,0.0017937125],"genre_scores_gemma":[0.97448313,0.000010087927,0.02507048,0.00024424726,0.000032435928,0.000032593074,0.0000103366665,0.000007465084,0.00010924533],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909174,0.00012234462,0.00011275577,0.00029681143,0.00016613632,0.00021020918],"domain_scores_gemma":[0.99968415,0.00004193216,0.000054926404,0.00012060371,0.000045623652,0.00005278194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019280177,0.000110956695,0.00011881497,0.00004616532,0.00049046776,0.00008840918,0.00016577786,0.000014631114,0.000047075682],"category_scores_gemma":[0.000009550848,0.00009449367,0.000026097256,0.00027474412,0.000064054955,0.00039662368,0.00009287885,0.00011586318,0.0000028793736],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021160433,0.00022230057,0.0007298151,0.000039449023,0.00023252313,0.00007764106,0.017186802,0.031670827,0.8249008,0.024087414,0.0022412024,0.098399624],"study_design_scores_gemma":[0.0012758601,0.00048353247,0.0022801515,0.000016635864,0.000028201253,0.000031803633,0.0013756988,0.8353842,0.1554611,0.00044028033,0.0027205874,0.00050194445],"about_ca_topic_score_codex":0.000035273835,"about_ca_topic_score_gemma":0.000018144428,"teacher_disagreement_score":0.8940438,"about_ca_system_score_codex":0.000037504607,"about_ca_system_score_gemma":0.00003198339,"threshold_uncertainty_score":0.38533399},"labels":[],"label_agreement":null},{"id":"W4311034190","doi":"10.1145/3550469.3555420","title":"StyleBin: Stylizing Video by Example in Stereo","year":2022,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Stylized fact; Computer science; Computer vision; Artificial intelligence; Viewpoints; Set (abstract data type); Stereoscopy; Process (computing); Sequence (biology); Semantics (computer science); Frame (networking); Visualization; Computer graphics (images)","score_opus":0.0149302602315066,"score_gpt":0.20729585580408708,"score_spread":0.19236559557258048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311034190","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010679152,0.00027983607,0.9659769,0.0015603144,0.00040239817,0.00018107085,0.000005100222,0.000112064605,0.0208032],"genre_scores_gemma":[0.97407526,0.0000064285596,0.021725604,0.001976336,0.000038686416,0.000042565,0.0000038725966,0.000008003052,0.002123264],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99877256,0.00020276998,0.00017470682,0.0003569297,0.00022759722,0.0002654333],"domain_scores_gemma":[0.9994385,0.00010133521,0.000041796862,0.00035191528,0.000015412708,0.000051037612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038728627,0.00009673315,0.00012519627,0.00007592639,0.00019819349,0.00011215008,0.00064267725,0.000014698047,0.00042569515],"category_scores_gemma":[0.000011490473,0.000093589544,0.00003783028,0.00044305233,0.000013795223,0.0003913211,0.0006524713,0.00013749226,0.000019889623],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039465685,0.00070977496,0.0045027104,0.000015972595,0.00007251407,0.000123253,0.003974081,0.0517257,0.042596813,0.07611426,0.5069899,0.31313556],"study_design_scores_gemma":[0.0010579403,0.00025973943,0.0016515219,0.0000072891144,0.0000045168244,0.000008890773,0.0008683277,0.374516,0.010944102,0.0023720693,0.6076815,0.0006280455],"about_ca_topic_score_codex":0.00049755594,"about_ca_topic_score_gemma":0.000051353392,"teacher_disagreement_score":0.9633961,"about_ca_system_score_codex":0.00006684435,"about_ca_system_score_gemma":0.000029653756,"threshold_uncertainty_score":0.46610636},"labels":[],"label_agreement":null},{"id":"W4311719620","doi":"10.32985/ijeces.13.9.9","title":"ResViT","year":2022,"lang":"en","type":"article","venue":"International journal of electrical and computer engineering systems","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Extractor; Artificial intelligence; Feature extraction; Pattern recognition (psychology); Feature (linguistics); Machine learning","score_opus":0.005166113242905878,"score_gpt":0.18746513909255239,"score_spread":0.1822990258496465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311719620","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041827494,0.0009268008,0.99130744,0.00043963714,0.0030551446,0.000030028918,8.767486e-7,0.000018746015,0.000038584276],"genre_scores_gemma":[0.98724484,0.000021857159,0.01170319,0.00010082452,0.0008728607,0.0000030408298,3.468885e-7,0.0000046380546,0.00004840965],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990872,0.000053686177,0.0002548128,0.000103541526,0.00039068516,0.00011003209],"domain_scores_gemma":[0.99951446,0.000094453564,0.00011995192,0.000070275644,0.00014071455,0.00006015337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026224952,0.00007008986,0.0001328094,0.0001743067,0.000050835944,0.00016145062,0.0006302048,0.000013164098,0.0000038746343],"category_scores_gemma":[0.000014610324,0.00006116858,0.00005818993,0.00015793425,0.0000047330273,0.0001907436,0.00021166663,0.0001797014,7.614974e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020987723,0.000078158824,0.00020213396,0.0000044544154,0.00023050814,0.00026312645,0.00016365103,0.9050333,0.001161552,0.042171307,0.005423949,0.04524689],"study_design_scores_gemma":[0.00020995106,0.00018569337,0.0004138363,0.000009722856,0.0000031497327,0.0008506034,0.0000024338565,0.9570779,0.00007633811,0.00009186198,0.0410052,0.00007327706],"about_ca_topic_score_codex":0.000006725738,"about_ca_topic_score_gemma":3.3427145e-8,"teacher_disagreement_score":0.9830621,"about_ca_system_score_codex":0.000064152286,"about_ca_system_score_gemma":0.000027210439,"threshold_uncertainty_score":0.24943824},"labels":[],"label_agreement":null},{"id":"W4312602363","doi":"10.1109/cvpr52688.2022.00129","title":"GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Huawei Technologies; Compute Canada; Automotive Research Center","keywords":"Computer science; Artificial intelligence; Robustness (evolution); Segmentation; Code (set theory); Image (mathematics); Unsupervised learning; Computer vision; Pattern recognition (psychology); Image segmentation; Artificial neural network; Set (abstract data type)","score_opus":0.03295431514156284,"score_gpt":0.25568719733899314,"score_spread":0.22273288219743032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312602363","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09235118,0.000028749344,0.90165234,0.003743414,0.0011678303,0.00042631195,0.00006824591,0.00014217594,0.00041972395],"genre_scores_gemma":[0.96941,0.00009101624,0.018846057,0.010340129,0.0005087088,0.00017016842,0.00028856637,0.00003341846,0.0003119106],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99660164,0.0009047272,0.00042628395,0.0010040187,0.000643487,0.0004198637],"domain_scores_gemma":[0.9988883,0.00013979424,0.00013689754,0.00036483625,0.0001714312,0.00029874145],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00053493923,0.0003434849,0.0003452433,0.00023777946,0.00088188774,0.00073307694,0.0005205447,0.0000686335,0.0015135687],"category_scores_gemma":[0.000014335094,0.0003366155,0.00010738223,0.00037258049,0.00004507062,0.0004338252,0.0005122558,0.0005637604,0.00018245839],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004672541,0.00023100153,0.000069603615,0.000012166664,0.000030273472,0.000033654833,0.0010133177,0.0020626737,0.04036746,0.00006153762,0.035576258,0.92049533],"study_design_scores_gemma":[0.0009810686,0.0018177504,0.00034003067,0.00005518332,0.000013694456,0.00003079632,0.00010472515,0.9768371,0.0069630556,0.00026485435,0.011987268,0.0006044931],"about_ca_topic_score_codex":0.000032684475,"about_ca_topic_score_gemma":0.000008568589,"teacher_disagreement_score":0.9747744,"about_ca_system_score_codex":0.000076216646,"about_ca_system_score_gemma":0.000054134987,"threshold_uncertainty_score":0.99990857},"labels":[],"label_agreement":null},{"id":"W4312725636","doi":"10.1109/cvpr52688.2022.01037","title":"Polymorphic-GAN: Generating Aligned Samples across Multiple Domains with Learned Morph Maps","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Leverage (statistics); Computer science; Generative grammar; Artificial intelligence; Image translation; Segmentation; Image (mathematics); Domain (mathematical analysis); Translation (biology); Pattern recognition (psychology); Generative model; Computer vision; Mathematics; Biology","score_opus":0.052366632458381364,"score_gpt":0.26766020803597096,"score_spread":0.2152935755775896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312725636","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1814879,0.0000467398,0.8143302,0.0020484908,0.001006138,0.00042936328,0.00025656683,0.00019098895,0.00020356674],"genre_scores_gemma":[0.9692677,0.000075195356,0.02539579,0.004216788,0.00045410843,0.00012995163,0.00024844153,0.00004111058,0.00017088692],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961485,0.0007432304,0.0005046657,0.001227938,0.0007342643,0.0006413815],"domain_scores_gemma":[0.9982407,0.0003383979,0.00032538455,0.0006120861,0.00022460401,0.00025882502],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0005908732,0.00048445055,0.00050842133,0.00018565959,0.0015146445,0.0009793005,0.00072138355,0.00009264168,0.0005976573],"category_scores_gemma":[0.000017377512,0.0004238679,0.00013413395,0.00044572295,0.00012120967,0.0005816547,0.00055534893,0.00040553382,0.000074974785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019665206,0.00036902845,0.0010293295,0.000032638396,0.00011596065,0.00018531272,0.0020114456,0.0074663702,0.015100801,0.00019381147,0.004976901,0.96832174],"study_design_scores_gemma":[0.0031313475,0.0022158644,0.0017623937,0.00016787252,0.000028661594,0.00019976452,0.0005216205,0.9782516,0.0075719315,0.00090926,0.0041154907,0.0011242394],"about_ca_topic_score_codex":0.00018239599,"about_ca_topic_score_gemma":0.00015340078,"teacher_disagreement_score":0.9707852,"about_ca_system_score_codex":0.00006521931,"about_ca_system_score_gemma":0.00008462252,"threshold_uncertainty_score":0.9998213},"labels":[],"label_agreement":null},{"id":"W4312810855","doi":"10.1109/cvpr52688.2022.00878","title":"Styleformer: Transformer based Generative Adversarial Networks with Style Vector","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Tellabs (Canada)","funders":"","keywords":"Computer science; Transformer; Normalization (sociology); Artificial intelligence; Visualization; Computation; Generative grammar; Generator (circuit theory); Computer vision; Algorithm; Voltage; Engineering","score_opus":0.02206577613607771,"score_gpt":0.22939547177485983,"score_spread":0.20732969563878212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312810855","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011800151,0.00003375915,0.98264134,0.002040839,0.0016541171,0.0006211856,0.00011694571,0.00015103864,0.0009405969],"genre_scores_gemma":[0.9797281,0.00006538083,0.013628982,0.005422028,0.0005966886,0.00018220587,0.00020425224,0.000037701266,0.00013467904],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965936,0.0006552937,0.00044659473,0.0010542927,0.0007039409,0.00054629706],"domain_scores_gemma":[0.9986021,0.00020873165,0.00023732871,0.00046001488,0.00022947676,0.0002623505],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00044146273,0.00048920035,0.000494328,0.0002505191,0.00092920894,0.000536857,0.0005896824,0.0001021668,0.0016380938],"category_scores_gemma":[0.000004563527,0.00040596374,0.00015613137,0.00048028983,0.00010709272,0.0006431531,0.00015556412,0.0006141385,0.000048216833],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004992442,0.0005063318,0.00013836284,0.0000266685,0.00014685038,0.00010459312,0.0008638235,0.035335455,0.0011835792,0.00031776744,0.008113623,0.9527637],"study_design_scores_gemma":[0.0024835593,0.0028759176,0.0006112108,0.0000900457,0.000035866982,0.000035051035,0.00009272334,0.98698145,0.0016778437,0.00014236549,0.0042863055,0.0006876557],"about_ca_topic_score_codex":0.00005564231,"about_ca_topic_score_gemma":0.00005689905,"teacher_disagreement_score":0.9690124,"about_ca_system_score_codex":0.00008837998,"about_ca_system_score_gemma":0.00014591988,"threshold_uncertainty_score":0.99983925},"labels":[],"label_agreement":null},{"id":"W4312969765","doi":"10.1007/978-3-031-20713-6_1","title":"Unsupervised Structure-Consistent Image-to-Image Translation","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Image (mathematics); Translation (biology); Artificial intelligence; Autoencoder; Image translation; Generator (circuit theory); Consistency (knowledge bases); Code (set theory); Constraint (computer-aided design); Pattern recognition (psychology); Computer vision; Deep learning; Mathematics","score_opus":0.017927274307776547,"score_gpt":0.2317983931147251,"score_spread":0.21387111880694856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312969765","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000044516964,0.0003122718,0.9901158,0.0023684858,0.0022089505,0.00068575185,0.0000332348,0.00014607456,0.0040848874],"genre_scores_gemma":[0.082887456,0.000034436056,0.91361916,0.00254618,0.000617757,0.000018176452,0.000021278545,0.00005577538,0.00019977009],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99530894,0.00011070897,0.0006114293,0.0019566098,0.0012464698,0.0007658681],"domain_scores_gemma":[0.99729246,0.00041241033,0.0002217944,0.0015291346,0.00027235286,0.00027185408],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00068995677,0.00065819174,0.00063262146,0.00087055756,0.00054575136,0.0008665989,0.0032536553,0.00020367914,0.00046496384],"category_scores_gemma":[0.00007871288,0.0006268066,0.00022597432,0.00094670494,0.00044626472,0.0010643983,0.0012669825,0.000842659,0.000047653713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017435483,0.000032534175,0.000009252532,0.000031373056,0.000030841056,0.0001203378,0.0015514337,0.17058349,0.007582563,0.0046055885,0.00017424849,0.8152609],"study_design_scores_gemma":[0.00056623545,0.00036482356,0.00015584704,0.00015376807,0.000030937783,0.00006687525,6.42068e-7,0.9156215,0.007970792,0.05613608,0.017455166,0.0014773017],"about_ca_topic_score_codex":0.00003782547,"about_ca_topic_score_gemma":0.00010904909,"teacher_disagreement_score":0.8137836,"about_ca_system_score_codex":0.00036211306,"about_ca_system_score_gemma":0.0004768604,"threshold_uncertainty_score":0.99961835},"labels":[],"label_agreement":null},{"id":"W4313128123","doi":"10.1109/tvcg.2022.3226689","title":"SAC-GAN: Structure-Aware Image Composition","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Visualization and Computer Graphics","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Computer vision; Discriminator; Ground truth; Pattern recognition (psychology)","score_opus":0.010333265478286856,"score_gpt":0.23765253423484645,"score_spread":0.22731926875655958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313128123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029700405,0.000025374913,0.9954729,0.00014780085,0.0009313252,0.00018928882,0.000043886863,0.00018638528,0.000032963344],"genre_scores_gemma":[0.99344105,0.000044626184,0.004657823,0.0016895708,0.00007567252,0.000023462166,0.000022199907,0.000016748952,0.000028860964],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985275,0.0002742234,0.00023194395,0.00043058975,0.00033776005,0.00019794058],"domain_scores_gemma":[0.9993707,0.00006467654,0.00008760852,0.00028009625,0.0001035054,0.00009339089],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012557617,0.00018868232,0.00016818804,0.00027861504,0.0010682027,0.00024674303,0.0003078065,0.000048142232,0.00008975246],"category_scores_gemma":[3.6877347e-7,0.00019972346,0.00008814171,0.0007500911,0.000062803956,0.00041962336,0.000012045255,0.00022164507,0.0000031711977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012778376,0.001289727,0.00007497764,0.00008031646,0.0003264275,0.000049129532,0.0044907182,0.25608927,0.003692722,0.6486161,0.0051341937,0.08002866],"study_design_scores_gemma":[0.00039534218,0.0002470311,0.00012619235,0.000007813815,0.00001762179,0.000032263204,0.00003203263,0.99047005,0.0058638696,0.0008029439,0.0017678392,0.00023697627],"about_ca_topic_score_codex":0.000017390686,"about_ca_topic_score_gemma":0.000008982602,"teacher_disagreement_score":0.9908151,"about_ca_system_score_codex":0.000036722275,"about_ca_system_score_gemma":0.000030773655,"threshold_uncertainty_score":0.82158595},"labels":[],"label_agreement":null},{"id":"W4313591763","doi":"10.1109/access.2022.3233874","title":"Progressive With Purpose: Guiding Progressive Inpainting DNNs Through Context and Structure","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Inpainting; Artificial intelligence; Computer science; Deep learning; Benchmarking; Context (archaeology); Feature (linguistics); Pattern recognition (psychology); Image (mathematics); Convolutional neural network; Feature extraction; Encoder; Pyramid (geometry); Feature learning; Computer vision; Mathematics","score_opus":0.03939070831493946,"score_gpt":0.2947518605369867,"score_spread":0.25536115222204725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313591763","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44620338,0.0013145116,0.54657584,0.002345956,0.001046234,0.0011653779,0.000016340084,0.00062205666,0.0007102951],"genre_scores_gemma":[0.98670906,0.00001859556,0.012376723,0.0004035843,0.00033979246,0.000057460886,0.000004257305,0.000021507345,0.00006899858],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99834186,0.00010647984,0.00020818949,0.0005834216,0.00030500986,0.00045503795],"domain_scores_gemma":[0.9989738,0.00016283241,0.00021146065,0.0003617982,0.00020469402,0.00008540587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017223472,0.00023346781,0.0002547686,0.00008539269,0.00039562743,0.0010280136,0.0008661251,0.0000752126,0.000017407552],"category_scores_gemma":[0.000079692036,0.0001689081,0.000036344853,0.00088572735,0.00015086858,0.0020172037,0.0004236406,0.00013125711,0.0000077706645],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016032056,0.00015126655,0.029310396,0.00034894864,0.00076975685,0.002891258,0.022933196,0.013268398,0.018895455,0.025045736,0.02769967,0.8585256],"study_design_scores_gemma":[0.0047668763,0.0010790696,0.019252697,0.0018442653,0.0002007593,0.0006224826,0.0033033204,0.38251853,0.5364564,0.028098391,0.018306386,0.0035508168],"about_ca_topic_score_codex":0.000035885692,"about_ca_topic_score_gemma":0.000021805557,"teacher_disagreement_score":0.8549748,"about_ca_system_score_codex":0.000022410368,"about_ca_system_score_gemma":0.00006472722,"threshold_uncertainty_score":0.9913159},"labels":[],"label_agreement":null},{"id":"W4317791988","doi":"10.1109/ism55400.2022.00033","title":"Synthesizing ultraviolet skin images via GAN with Gaussian weighted patch blending","year":2022,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Computer vision; Ultraviolet; Pixel; RGB color model; Gaussian; Translation (biology); Image (mathematics); Face (sociological concept); Image resolution; Optics; Physics","score_opus":0.006124617268893698,"score_gpt":0.19429514154950442,"score_spread":0.1881705242806107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317791988","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052122436,0.00007524981,0.98283434,0.0015863908,0.00025851055,0.00019018937,0.000006104818,0.00021259014,0.009624405],"genre_scores_gemma":[0.9151686,0.000009283107,0.0835205,0.00041668778,0.0001156653,0.000048454447,0.0000047860663,0.00002185696,0.0006941883],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99802023,0.00026328623,0.00022752227,0.000587482,0.0004254955,0.00047596893],"domain_scores_gemma":[0.9990161,0.00015542335,0.00011154062,0.00054754165,0.00004752483,0.00012188097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037355468,0.00023103974,0.00023716113,0.00013296907,0.0007787902,0.00023665118,0.0008675861,0.000027268594,0.00047626183],"category_scores_gemma":[0.000009531456,0.00017997366,0.000079615354,0.000625455,0.000052379386,0.0005287132,0.00027381763,0.00023133549,0.000025367233],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017587007,0.0011541499,0.010263421,0.00007132879,0.00068094063,0.0010680651,0.006012588,0.035940707,0.23602483,0.03281984,0.024890358,0.6508979],"study_design_scores_gemma":[0.0010627968,0.00064977433,0.0044013187,0.0000631767,0.00006685425,0.00028377114,0.0014979469,0.47283933,0.49933487,0.0018400395,0.016437395,0.0015227168],"about_ca_topic_score_codex":0.0003058589,"about_ca_topic_score_gemma":0.000029589582,"teacher_disagreement_score":0.90995634,"about_ca_system_score_codex":0.00007732125,"about_ca_system_score_gemma":0.000060086924,"threshold_uncertainty_score":0.7339113},"labels":[],"label_agreement":null},{"id":"W4318977088","doi":"10.1007/978-3-031-10602-6_1","title":"Introduction","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Dimensionality reduction; Subspace topology; Field (mathematics); Computer science; Nonlinear dimensionality reduction; Artificial intelligence; Representation (politics); Curse of dimensionality; Reduction (mathematics); Machine learning; Mathematics","score_opus":0.012400294574442017,"score_gpt":0.19417649493737446,"score_spread":0.18177620036293243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318977088","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.3892471e-8,0.00010496905,0.3542394,0.003209862,0.0011355965,0.00005445828,0.0000012554525,0.000080708785,0.6411737],"genre_scores_gemma":[0.0000717873,0.000106810105,0.022542583,0.00034225854,0.0019829115,0.0000051331476,0.000011397339,0.000015036758,0.97492206],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991146,0.000015329068,0.00013358197,0.00041572395,0.00020867147,0.00011214756],"domain_scores_gemma":[0.99929136,0.000021555554,0.00007603956,0.0005346049,0.00003967716,0.000036753478],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00011396777,0.0001484717,0.00015123573,0.00007584777,0.00012766045,0.00007678122,0.00047363545,0.000059978,0.018866733],"category_scores_gemma":[0.000006703095,0.00013702604,0.00009617878,0.000027929615,0.00002009165,0.00023291526,0.00036854192,0.00019989898,0.00038173984],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.94724e-7,0.0000022976842,3.3017738e-8,0.0000010437968,0.000016604692,0.000004028629,0.00001000011,0.00029492052,0.0000122910715,0.76834774,0.19491735,0.036393095],"study_design_scores_gemma":[0.00002832854,0.00003131512,6.084405e-7,0.0000014050869,0.0000066186476,0.000006571165,7.085945e-7,0.0032908425,0.00006505895,0.019365087,0.9770439,0.00015950558],"about_ca_topic_score_codex":0.0000073648457,"about_ca_topic_score_gemma":0.0000030922158,"teacher_disagreement_score":0.7821266,"about_ca_system_score_codex":0.00005433931,"about_ca_system_score_gemma":0.000036332178,"threshold_uncertainty_score":0.98203015},"labels":[],"label_agreement":null},{"id":"W4318977947","doi":"10.1007/978-3-031-10602-6_18","title":"Restricted Boltzmann Machine and Deep Belief Network","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Boltzmann machine; Ising model; Statistical physics; Boltzmann distribution; Restricted Boltzmann machine; Boltzmann constant; Artificial neural network; Computer science; Spins; Ising spin; Distribution (mathematics); Binary number; Hopfield network; Physics; Boltzmann equation; Artificial intelligence; Mathematics; Thermodynamics; Condensed matter physics; Mathematical analysis","score_opus":0.011202026072532201,"score_gpt":0.1966651783066714,"score_spread":0.1854631522341392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318977947","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.4321598e-7,0.0056399764,0.32165343,0.0007976784,0.00070558814,0.00023277136,0.000009882604,0.00017246144,0.67078775],"genre_scores_gemma":[0.0014811156,0.00453839,0.099071994,0.0023415212,0.0014621369,0.000028663859,0.00009586053,0.00009694365,0.8908834],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981521,0.000059078582,0.00032992667,0.0007480922,0.00035253563,0.0003582843],"domain_scores_gemma":[0.9987137,0.00016208677,0.0001819456,0.00072872586,0.00006382976,0.00014971393],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00018155527,0.00038522092,0.00041762678,0.00011226665,0.0004039452,0.00019519926,0.00075335806,0.00016469702,0.0020060774],"category_scores_gemma":[0.00001640195,0.00034748172,0.00012475571,0.00010721932,0.00006686724,0.00025479778,0.0012326567,0.00045954957,0.000048469916],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010875893,0.000014914161,0.000011185145,0.000009663482,0.0001415724,0.0000956107,0.00006250971,0.0030794349,0.0000069770836,0.8509562,0.043908596,0.10170248],"study_design_scores_gemma":[0.00018096578,0.00012616445,0.00007076311,0.000017700917,0.000035708228,0.000021387514,0.0000013902206,0.061740115,0.0000041158596,0.025724992,0.91161585,0.00046083436],"about_ca_topic_score_codex":0.00007238685,"about_ca_topic_score_gemma":0.00008779163,"teacher_disagreement_score":0.86770725,"about_ca_system_score_codex":0.000047848247,"about_ca_system_score_gemma":0.000053900574,"threshold_uncertainty_score":0.9998977},"labels":[],"label_agreement":null},{"id":"W4318977951","doi":"10.1007/978-3-031-10602-6_16","title":"Stochastic Neighbour Embedding","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Nonlinear dimensionality reduction; Embedding; Dimensionality reduction; Probabilistic logic; Manifold (fluid mechanics); Visualization; Computer science; Curse of dimensionality; Artificial intelligence; Space (punctuation); Mathematics; Pattern recognition (psychology); Engineering","score_opus":0.028073365638479484,"score_gpt":0.24290427627145963,"score_spread":0.21483091063298015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318977951","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.508253e-8,0.000045786528,0.57618076,0.00024376165,0.00077313866,0.00008290184,0.000002972062,0.00025013223,0.42242047],"genre_scores_gemma":[0.0016823505,0.000030928048,0.02221991,0.00028970098,0.0006456632,0.000005953174,0.000006032487,0.00005541281,0.97506404],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985741,0.00001308414,0.00024593493,0.0005707938,0.00030267175,0.00029346027],"domain_scores_gemma":[0.9988771,0.00018199111,0.000120990764,0.0006223862,0.00008739716,0.00011013256],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015245541,0.0003071593,0.0003212009,0.00015793237,0.0001296452,0.00023105054,0.0007932446,0.00018506202,0.000492995],"category_scores_gemma":[0.00003270904,0.00026911893,0.00018257674,0.000058814512,0.000037850863,0.00021894647,0.0004841382,0.00024221657,0.0024975997],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011064037,0.0000031079212,6.530248e-8,0.000006274314,0.00006785512,0.00003443024,0.00004578063,0.011554553,0.000016285068,0.93629116,0.022026239,0.029953131],"study_design_scores_gemma":[0.00017926602,0.00007191938,0.0000055274013,0.00018705007,0.000044646495,0.000012653674,0.0000066933217,0.740575,0.000047515936,0.18679328,0.07116314,0.00091330294],"about_ca_topic_score_codex":0.000010170496,"about_ca_topic_score_gemma":0.00001152775,"teacher_disagreement_score":0.7494979,"about_ca_system_score_codex":0.000039701034,"about_ca_system_score_gemma":0.00006852842,"threshold_uncertainty_score":0.9999761},"labels":[],"label_agreement":null},{"id":"W4319300112","doi":"10.1109/wacv56688.2023.00420","title":"Learning Style Subspaces for Controllable Unpaired Domain Translation","year":2023,"lang":"en","type":"article","venue":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Linear subspace; Translation (biology); Artificial intelligence; Robustness (evolution); Domain (mathematical analysis); Image translation; Theoretical computer science; Algorithm; Pattern recognition (psychology); Image (mathematics); Mathematics","score_opus":0.028954898761440452,"score_gpt":0.28492549276178025,"score_spread":0.2559705940003398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319300112","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028184012,0.000036659352,0.9899947,0.004182615,0.00037575388,0.0011210215,0.00002742342,0.00031039672,0.0011330452],"genre_scores_gemma":[0.8852845,0.00005956988,0.11246337,0.0001904884,0.00031189443,0.00046068657,0.00006715785,0.000029587449,0.0011327667],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99775654,0.0001917213,0.0005448148,0.00073240715,0.00036777853,0.00040671884],"domain_scores_gemma":[0.99786955,0.00057192147,0.0002920201,0.00070499425,0.00043709233,0.00012440424],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006295266,0.00028162057,0.00043655158,0.0003595319,0.00032552867,0.00029571072,0.00097267603,0.00011782268,0.000050495666],"category_scores_gemma":[0.00001667487,0.00026398795,0.00022380093,0.000963839,0.000098737844,0.00042378122,0.0001274143,0.000179203,0.00022612225],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000223228,0.0003855893,0.00007528674,0.00011148791,0.00021548526,0.000004230895,0.0023539034,0.05064696,0.05253722,0.037057623,0.038224358,0.81816465],"study_design_scores_gemma":[0.0011813403,0.0006394607,0.00027236118,0.00010895136,0.000017990666,0.0000014664244,0.00015390693,0.9484852,0.006015702,0.007181824,0.035616912,0.00032491202],"about_ca_topic_score_codex":0.000016123808,"about_ca_topic_score_gemma":0.000017862041,"teacher_disagreement_score":0.89783823,"about_ca_system_score_codex":0.00003300852,"about_ca_system_score_gemma":0.00008555707,"threshold_uncertainty_score":0.9999812},"labels":[],"label_agreement":null},{"id":"W4319300559","doi":"10.1109/wacv56688.2023.00041","title":"RAST: Restorable Arbitrary Style Transfer via Multi-restoration","year":2023,"lang":"en","type":"article","venue":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Stylized fact; Computer science; Style (visual arts); Embedding; Architecture; Perspective (graphical); Image (mathematics); Artificial intelligence; Art","score_opus":0.03313096733209031,"score_gpt":0.28596619007016316,"score_spread":0.25283522273807285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319300559","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003178759,0.000032902983,0.9920304,0.0020386118,0.00067322125,0.00078902184,0.000030471347,0.00035765808,0.00086897356],"genre_scores_gemma":[0.9096485,0.000078089004,0.087761536,0.00050354673,0.000384898,0.00029243686,0.00007192356,0.000039954182,0.0012191407],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971826,0.00022143748,0.00069019303,0.00093160046,0.0005271037,0.00044706426],"domain_scores_gemma":[0.9976653,0.00020977388,0.00017143988,0.0013300139,0.00042791167,0.00019558734],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00046385007,0.0003660301,0.00044361202,0.00048495713,0.00028276662,0.0002922631,0.0014779781,0.00016014796,0.00011756358],"category_scores_gemma":[0.000009285977,0.00034749135,0.0002141823,0.0013428682,0.0001444798,0.00073595473,0.00023325002,0.0003050421,0.0010482306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018931855,0.0018778489,0.00015612863,0.00016881934,0.00029302295,0.00003928526,0.002592348,0.028509831,0.12022848,0.048086546,0.10297479,0.6948836],"study_design_scores_gemma":[0.00075401674,0.00043894292,0.0017720843,0.00014455292,0.000018961611,0.0000051743577,0.00003831328,0.9658422,0.014551795,0.002464702,0.013508021,0.00046124967],"about_ca_topic_score_codex":0.000048817215,"about_ca_topic_score_gemma":0.00003191661,"teacher_disagreement_score":0.93733233,"about_ca_system_score_codex":0.000054936587,"about_ca_system_score_gemma":0.00012881887,"threshold_uncertainty_score":0.9998977},"labels":[],"label_agreement":null},{"id":"W4320490631","doi":"10.1007/s10462-023-10395-6","title":"Games of GANs: game-theoretical models for generative adversarial networks","year":2023,"lang":"en","type":"article","venue":"Artificial Intelligence Review","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Alberta","funders":"","keywords":"Computer science; Generative grammar; Adversarial system; Artificial intelligence; Game theory; Nash equilibrium; Field (mathematics); Machine learning; Zero-sum game; Theoretical computer science; Mathematical economics; Mathematics","score_opus":0.06814399205353684,"score_gpt":0.32021645808620025,"score_spread":0.2520724660326634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320490631","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000033715987,0.011353433,0.9842187,0.0023041621,0.00071826257,0.0008772005,0.000011245661,0.00012198237,0.00036131064],"genre_scores_gemma":[0.816223,0.096676685,0.08323742,0.0019666038,0.0012411152,0.00042664463,0.000044171775,0.00005822833,0.00012610068],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975083,0.0002553575,0.0008418297,0.0005817846,0.0002971356,0.00051557797],"domain_scores_gemma":[0.99802977,0.0006476684,0.00022902386,0.0006063338,0.00035766003,0.00012953977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012733694,0.00025539534,0.00061992084,0.00010171303,0.00012796145,0.00008223234,0.0008548515,0.00009888703,0.00008903019],"category_scores_gemma":[0.0004562601,0.00021580569,0.00035922322,0.0011500615,0.000312551,0.00045680712,0.00021182936,0.0001360902,0.00008084964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013389976,0.000035970403,6.4823143e-7,0.00014204145,0.000035833225,0.000002741563,0.00014559363,0.096961096,0.00017479407,0.624015,0.0019038949,0.27656904],"study_design_scores_gemma":[0.000024772371,0.000107819455,0.0000011159793,0.00050579756,0.000044378878,0.000001673109,0.000031309453,0.80915254,0.007783051,0.18005553,0.0020889263,0.00020307947],"about_ca_topic_score_codex":0.0000106743555,"about_ca_topic_score_gemma":0.000006922333,"teacher_disagreement_score":0.90098125,"about_ca_system_score_codex":0.000027215998,"about_ca_system_score_gemma":0.00009771687,"threshold_uncertainty_score":0.8800301},"labels":[],"label_agreement":null},{"id":"W4320917681","doi":"10.3390/math11040977","title":"AutoGAN: An Automated Human-Out-of-the-Loop Approach for Training Generative Adversarial Networks","year":2023,"lang":"en","type":"article","venue":"Mathematics","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Task (project management); Adversarial system; Artificial intelligence; Oversampling; Set (abstract data type); Process (computing); Machine learning; Generative grammar; Training (meteorology); Point (geometry); Artificial neural network; Modalities; Quality (philosophy); Training set; Mathematics","score_opus":0.0761518601387779,"score_gpt":0.3085738216193072,"score_spread":0.2324219614805293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320917681","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00406082,0.00001274713,0.9926733,0.00012889251,0.0009857789,0.0006220802,0.000010433059,0.0006166739,0.000889286],"genre_scores_gemma":[0.35988113,0.0000027817282,0.6384525,0.000107845444,0.0005693922,0.00011543653,0.00003590133,0.000044305823,0.0007907621],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828404,0.00013116054,0.00046079367,0.00039563715,0.00029163426,0.00043673333],"domain_scores_gemma":[0.9985514,0.00020343991,0.0002838176,0.0007279984,0.00014787562,0.00008542686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077100855,0.00023346969,0.0003908616,0.00008450235,0.00044759858,0.00015175446,0.0010518995,0.00012652129,0.000006513402],"category_scores_gemma":[0.00013450188,0.00017650792,0.00019604896,0.0006432588,0.000103254846,0.00032472258,0.00027602175,0.00012824264,0.0000053538906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014678492,0.00047129847,0.000026751559,0.00019907605,0.0003249568,0.000005271421,0.036320444,0.8124141,0.016323924,0.1049578,0.018172072,0.010769593],"study_design_scores_gemma":[0.00042413332,0.00008323998,0.000048173173,0.000027214981,0.000034492816,0.0000016836938,0.00044198788,0.9921215,0.0026108322,0.003717321,0.00028028,0.00020914992],"about_ca_topic_score_codex":0.000004262875,"about_ca_topic_score_gemma":0.0000067450433,"teacher_disagreement_score":0.3558203,"about_ca_system_score_codex":0.00003123822,"about_ca_system_score_gemma":0.00007894571,"threshold_uncertainty_score":0.7197784},"labels":[],"label_agreement":null},{"id":"W4321353841","doi":"10.2139/ssrn.4364375","title":"Β-Multivariational Autoencoder for Entangled Representation Learning in Video Frames","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Autoencoder; Representation (politics); Computer science; Artificial intelligence; Feature learning; Deep learning; Law; Political science; Politics","score_opus":0.015429290477424034,"score_gpt":0.27463349050715485,"score_spread":0.2592042000297308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321353841","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009641177,0.00016473055,0.9870299,0.002490326,0.00031052224,0.0001500199,5.823536e-7,0.00008349491,0.00012923755],"genre_scores_gemma":[0.9814195,0.00040706218,0.016072785,0.00009084756,0.00038384512,0.00003178699,0.000009304313,0.0000134968595,0.0015713641],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99796283,0.0001664463,0.00024963924,0.0002543402,0.0002247108,0.0011420238],"domain_scores_gemma":[0.99930954,0.00030808782,0.00012807298,0.00011581149,0.000097741446,0.000040766212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015943735,0.000100764184,0.0001332521,0.00020937501,0.00024663127,0.00014869512,0.00032561622,0.00005218688,0.000009730837],"category_scores_gemma":[0.00040335598,0.00009353738,0.00009382795,0.0005820875,0.00001371451,0.00058015704,0.00006159973,0.0006517436,0.000023867082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000081594306,0.000090363006,0.0111715635,0.0000062450868,0.00018762915,0.000011321842,0.0019735026,0.45182884,0.0052905655,0.34607983,0.0010979658,0.1821806],"study_design_scores_gemma":[0.0007591821,0.00011570563,0.005769758,0.000011692942,0.0000059451813,0.00002325453,0.0004981078,0.76522166,0.00039686874,0.22597444,0.0010933602,0.00013003973],"about_ca_topic_score_codex":0.000030270987,"about_ca_topic_score_gemma":0.00012546824,"teacher_disagreement_score":0.97177833,"about_ca_system_score_codex":0.0003380163,"about_ca_system_score_gemma":0.000702096,"threshold_uncertainty_score":0.38143435},"labels":[],"label_agreement":null},{"id":"W4322703855","doi":"10.1109/ipas55744.2022.10053049","title":"A Review of Photorealistic Image Stylization Techniques","year":2022,"lang":"en","type":"review","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Rendering (computer graphics); Artificial intelligence; Convolutional neural network; Similarity (geometry); Computer vision; Convolution (computer science); Image (mathematics); Pattern recognition (psychology); Perception; Task (project management); Artificial neural network","score_opus":0.0492220376709455,"score_gpt":0.3318426398116216,"score_spread":0.2826206021406761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322703855","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.8383255e-11,0.6079886,0.3822034,0.000013527507,0.00008106293,0.0004766723,0.000014753122,0.0000683081,0.009153644],"genre_scores_gemma":[7.967273e-9,0.9276938,0.071395,0.000313208,0.00006083256,0.00020490428,0.000085427135,0.000017748871,0.00022908965],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99814075,0.00041041526,0.00064100296,0.00040474482,0.00024721207,0.00015586877],"domain_scores_gemma":[0.9983389,0.0002192371,0.0005222627,0.0007846469,0.000091374204,0.000043612563],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00059122575,0.00026005847,0.001284246,0.00013424653,0.00006640117,0.000045760604,0.0010952902,0.000064636675,0.0012251524],"category_scores_gemma":[0.00020926328,0.0001944115,0.00042151945,0.00082637614,0.00003451997,0.00020568196,0.00047985316,0.0001548214,0.000008067874],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.855739e-8,0.00001677796,3.3727876e-9,0.044391733,0.000023290382,0.000002438796,0.0000032775163,9.292001e-8,3.6195487e-7,0.0013205792,0.024668284,0.92957306],"study_design_scores_gemma":[0.000010295228,0.000030996893,7.535999e-9,0.03688121,0.00016012699,0.000010091497,5.8973103e-7,0.00021080658,0.000013265254,0.00006622243,0.96243185,0.00018454457],"about_ca_topic_score_codex":0.000037729144,"about_ca_topic_score_gemma":0.0000011096024,"teacher_disagreement_score":0.9377636,"about_ca_system_score_codex":0.000072809504,"about_ca_system_score_gemma":0.00022690024,"threshold_uncertainty_score":0.99968785},"labels":[],"label_agreement":null},{"id":"W4324297696","doi":"10.48550/arxiv.2303.06992","title":"Improving Mutual Information Estimation with Annealed and Energy-Based Bounds","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Mutual information; Marginal distribution; Upper and lower bounds; Joint probability distribution; Computer science; Sample size determination; Density estimation; Sampling (signal processing); Joint (building); Partition (number theory); Algorithm; Sample (material); Mathematics; Applied mathematics; Mathematical optimization; Statistics; Artificial intelligence; Combinatorics; Random variable; Estimator; Mathematical analysis","score_opus":0.03365478930670212,"score_gpt":0.1588642217671323,"score_spread":0.12520943246043018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324297696","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014656046,0.000011774866,0.9842942,0.00012549944,0.000262903,0.00010795078,0.000011330049,0.00024802805,0.00028231568],"genre_scores_gemma":[0.97375005,0.000018697761,0.025685322,0.00010929819,0.00004750835,0.0000020255534,0.000059357964,0.000011457247,0.00031629208],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989015,0.00008685076,0.00016055435,0.00051771716,0.00009641047,0.00023699905],"domain_scores_gemma":[0.9988459,0.00009578041,0.0002637504,0.00052144035,0.00016662451,0.00010653783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018453266,0.00023882599,0.00021165739,0.0002716511,0.00022370432,0.0003898077,0.0004939262,0.00015861854,0.0000036997455],"category_scores_gemma":[0.000035787743,0.00024107484,0.000062223895,0.00044559492,0.0000913131,0.0012671526,0.0005890914,0.00019932081,0.000017232465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032192744,0.000013314197,0.0002509342,0.00005038936,0.00003687476,0.000031338197,0.00013356408,0.9761694,0.000013390426,0.009627714,0.00015963372,0.013481262],"study_design_scores_gemma":[0.0004173569,0.000074804484,0.00069354975,0.000060082748,0.000041818934,0.0000013898729,0.000035922916,0.995422,0.00016574704,0.0025955676,0.00020402335,0.0002877583],"about_ca_topic_score_codex":0.00044547353,"about_ca_topic_score_gemma":0.00010980844,"teacher_disagreement_score":0.959094,"about_ca_system_score_codex":0.00010004811,"about_ca_system_score_gemma":0.00022274032,"threshold_uncertainty_score":0.98307467},"labels":[],"label_agreement":null},{"id":"W4361018823","doi":"10.1007/s00365-023-09635-3","title":"Universal Regular Conditional Distributions via Probabilistic Transformers","year":2023,"lang":"en","type":"article","venue":"Constructive Approximation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Mathematics; Curse of dimensionality; Combinatorics; Probabilistic logic; Discrete mathematics","score_opus":0.011075360324011985,"score_gpt":0.21651596963303138,"score_spread":0.2054406093090194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361018823","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006606959,0.000008459853,0.98984843,0.0010238464,0.0002508284,0.0003349065,0.00006469083,0.00025942767,0.0016024294],"genre_scores_gemma":[0.9717177,0.000004818844,0.027745858,0.000027342843,0.00007248756,0.000046777735,0.00030219537,0.00000701104,0.00007578915],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988871,0.000101018646,0.00019125649,0.00034302587,0.00022691835,0.0002506478],"domain_scores_gemma":[0.9993374,0.00011124404,0.000081348604,0.00019961868,0.00019478683,0.000075602286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019224129,0.00013474321,0.00013872514,0.00013157346,0.00031629656,0.00008714056,0.00024517765,0.00006077239,0.000032986223],"category_scores_gemma":[0.00007043936,0.0001343039,0.00008015939,0.00086570746,0.00025985928,0.00085673964,0.000058401296,0.00009353181,0.000107532],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012473898,0.000043877,0.0001584966,0.000022538288,0.00007641562,0.000009933771,0.00040597102,0.005348555,0.0071446924,0.92052054,0.0014174349,0.06483908],"study_design_scores_gemma":[0.00049996306,0.000046231064,0.0041739116,0.000014687978,0.000023452105,0.000026486437,0.00019339765,0.7519588,0.0064585893,0.23518234,0.0011649162,0.00025725053],"about_ca_topic_score_codex":0.000006919798,"about_ca_topic_score_gemma":0.0000023638136,"teacher_disagreement_score":0.9651108,"about_ca_system_score_codex":0.00010850624,"about_ca_system_score_gemma":0.00009308439,"threshold_uncertainty_score":0.54767543},"labels":[],"label_agreement":null},{"id":"W4362585319","doi":"10.1016/j.bspc.2023.104877","title":"Dynamic-Pix2Pix: Medical image segmentation by injecting noise to cGAN for modeling input and target domain joint distributions with limited training data","year":2023,"lang":"en","type":"article","venue":"Biomedical Signal Processing and Control","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Generalization; Noise (video); Artificial intelligence; Segmentation; Domain (mathematical analysis); Generative model; Deep learning; Pattern recognition (psychology); Generative grammar; Image (mathematics); Mathematics","score_opus":0.024854681892856542,"score_gpt":0.2691240767926921,"score_spread":0.24426939489983557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362585319","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012108216,0.00021946368,0.97855777,0.008490366,0.000046825513,0.00029558348,0.0001508552,0.00012516722,0.0000057858415],"genre_scores_gemma":[0.8888854,0.000009859766,0.1101709,0.0004651604,0.000113559225,0.00005658295,0.00027718674,0.000012632576,0.000008751095],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981971,0.000084564046,0.0003063368,0.00058800454,0.0004230099,0.000400981],"domain_scores_gemma":[0.9990622,0.00020689785,0.000082367835,0.00016035914,0.000097975666,0.00039022474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010976706,0.00017128323,0.00025944697,0.00010090549,0.0005391484,0.00035855127,0.00032361588,0.0000882739,0.0000042571887],"category_scores_gemma":[0.00027628458,0.00013089935,0.000022153636,0.000497359,0.00013641594,0.00048067997,0.00019959096,0.00014467193,0.0000010902585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001563737,0.000117037445,0.00004725687,0.00012935583,0.0001093163,0.000029304412,0.002495765,0.0012834201,0.10660922,0.00009370572,0.0014285253,0.8875007],"study_design_scores_gemma":[0.001361377,0.00018451724,0.000023851351,0.00013905432,0.000024388459,0.0000129336295,0.00053749955,0.9963924,0.00017820968,0.00055021106,0.0004106445,0.00018486188],"about_ca_topic_score_codex":0.000022322285,"about_ca_topic_score_gemma":0.0000070131864,"teacher_disagreement_score":0.995109,"about_ca_system_score_codex":0.000025322473,"about_ca_system_score_gemma":0.00017266496,"threshold_uncertainty_score":0.5337921},"labels":[],"label_agreement":null},{"id":"W4367662933","doi":"10.1109/vrw58643.2023.00244","title":"F2RPC: Fake to Real Portrait Control from a Virtual Character","year":2023,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Research Foundation of Korea","keywords":"Portrait; Computer science; Character (mathematics); Task (project management); Artificial intelligence; Virtual reality; Face (sociological concept); Computer graphics (images); Computer vision; Image (mathematics); Motion (physics); Human–computer interaction; Art; Visual arts; Mathematics; Engineering","score_opus":0.011937175053438717,"score_gpt":0.2255630080263195,"score_spread":0.2136258329728808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367662933","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037950516,0.0000042795955,0.9442914,0.008007853,0.00079083396,0.00020328394,0.000029315794,0.00042657173,0.008295946],"genre_scores_gemma":[0.97926307,0.000008823257,0.011132179,0.0031783236,0.0005380422,0.000025973743,0.000012304089,0.000011106854,0.0058301934],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987429,0.00006548257,0.0001947456,0.00043272844,0.00022751573,0.00033665914],"domain_scores_gemma":[0.9991606,0.0001565447,0.000038765073,0.0004151337,0.00005814956,0.00017083026],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002052535,0.00013794198,0.00019548988,0.00008810991,0.000094376715,0.00018519236,0.00052616384,0.000050184302,0.00025157744],"category_scores_gemma":[0.000039755978,0.0001126009,0.000081859,0.00042882506,0.000016982469,0.00034945633,0.00017745151,0.00007215264,0.0017431118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010896988,0.00018390834,0.0031789774,0.000003788671,0.000350554,0.00033334733,0.0034522838,0.007725859,0.15090255,0.07729077,0.28794804,0.46852094],"study_design_scores_gemma":[0.001791426,0.00043640204,0.3057186,0.000028246213,0.000031942818,0.000004349631,0.00018565639,0.5664133,0.008678591,0.0030325502,0.11269155,0.0009873905],"about_ca_topic_score_codex":0.00046014573,"about_ca_topic_score_gemma":0.00011094403,"teacher_disagreement_score":0.94131255,"about_ca_system_score_codex":0.000015989333,"about_ca_system_score_gemma":0.00004001067,"threshold_uncertainty_score":0.99903417},"labels":[],"label_agreement":null},{"id":"W4376108477","doi":"10.1007/s10489-023-04567-8","title":"Improved α-GAN architecture for generating 3D connected volumes with an application to radiosurgery treatment planning","year":2023,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Toronto","funders":"","keywords":"Computer science; Isocenter; Synthetic data; Domain (mathematical analysis); Voxel; Curse of dimensionality; Artificial intelligence; Machine learning; Radiation therapy","score_opus":0.022424480911225588,"score_gpt":0.26379609952792293,"score_spread":0.24137161861669734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376108477","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015967987,0.000027472448,0.98210573,0.00023448779,0.00011870849,0.0010364004,0.000007092154,0.00036254924,0.00013959334],"genre_scores_gemma":[0.67244786,0.000005159249,0.32612,0.00028376345,0.000248732,0.000762346,0.000040297662,0.000023601597,0.00006827676],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983643,0.000037290676,0.00026397614,0.0007367919,0.00014829154,0.00044932961],"domain_scores_gemma":[0.9987523,0.0003163669,0.000106492414,0.0005666047,0.000095201765,0.00016301622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002476093,0.0002522144,0.00025569403,0.00014880851,0.0003305311,0.00019988533,0.00047173293,0.00006185067,0.00000395462],"category_scores_gemma":[0.000037184604,0.00020090122,0.000049868137,0.00077293057,0.00003711033,0.00015614406,0.000061006875,0.000075519165,0.000026586767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054130873,0.000030247009,0.000027119733,0.0000063969337,0.000033496617,0.0000021488436,0.0016099262,0.3769823,0.066622116,0.0012845095,0.00013762219,0.55320996],"study_design_scores_gemma":[0.00011057867,0.00040251116,0.000059282076,0.000012129643,0.0000113355745,0.0000031106288,0.0002065983,0.87904614,0.11686435,0.00043170186,0.0025765486,0.00027571124],"about_ca_topic_score_codex":0.000051663224,"about_ca_topic_score_gemma":0.00004742499,"teacher_disagreement_score":0.65647984,"about_ca_system_score_codex":0.0000605767,"about_ca_system_score_gemma":0.000068929025,"threshold_uncertainty_score":0.8192514},"labels":[],"label_agreement":null},{"id":"W4379202866","doi":"10.1016/j.compmedimag.2023.102249","title":"DC-cycleGAN: Bidirectional CT-to-MR synthesis from unpaired data","year":2023,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of Windsor","funders":"","keywords":"Computer science; Image synthesis; Artificial intelligence; Similarity (geometry); Image (mathematics); Source code; Contrast (vision); Modality (human–computer interaction); Computer vision; Pattern recognition (psychology)","score_opus":0.03202701701348586,"score_gpt":0.27327719362327857,"score_spread":0.2412501766097927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379202866","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015135967,0.00039335262,0.9561632,0.025445094,0.0018266137,0.00014154075,0.00007378172,0.00072353706,0.000096860604],"genre_scores_gemma":[0.828833,0.0012911778,0.15864444,0.008706159,0.002014142,0.000049451744,0.00026247906,0.000060222985,0.00013891628],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973318,0.00020325171,0.00033934347,0.00096964516,0.00069449685,0.0004614933],"domain_scores_gemma":[0.997261,0.0010327145,0.00007105332,0.00099686,0.000078565805,0.0005597987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009290948,0.00024697525,0.00036529396,0.0002932227,0.00035221368,0.00036917103,0.0016758011,0.000055938268,0.00003840926],"category_scores_gemma":[0.00048284722,0.00022250744,0.0000793619,0.0012678794,0.00020448322,0.0004974014,0.0019716744,0.00026122452,0.00006328862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022292483,0.000109573266,0.0022260786,0.000024202194,0.00019109754,0.00051648787,0.00031366,0.00013615296,0.0013568824,0.003013296,0.1230749,0.8690154],"study_design_scores_gemma":[0.00036820793,0.000010815392,0.0063795946,0.00012674397,0.000022508275,0.000033117452,0.000018999228,0.92638975,0.0003938479,0.0016313201,0.064328335,0.00029675325],"about_ca_topic_score_codex":0.0002662694,"about_ca_topic_score_gemma":0.000020808324,"teacher_disagreement_score":0.9262536,"about_ca_system_score_codex":0.000012751497,"about_ca_system_score_gemma":0.00012083145,"threshold_uncertainty_score":0.907359},"labels":[],"label_agreement":null},{"id":"W4379379910","doi":"10.1016/j.patrec.2023.05.029","title":"Hierarchical supervisions with two-stream network for Deepfake detection","year":2023,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Key Research and Development Program of China","keywords":"Computer science; Face (sociological concept); Quality (philosophy); Task (project management); Domain (mathematical analysis); Artificial intelligence; Machine learning; Binary number; Pattern recognition (psychology); Data mining; Mathematics","score_opus":0.025590922173810156,"score_gpt":0.2392203687236229,"score_spread":0.21362944654981275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379379910","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07040098,0.000006564084,0.9228573,0.0054459088,0.00053739746,0.0003629735,0.000026434702,0.00031116692,0.000051287152],"genre_scores_gemma":[0.9484288,0.000019438055,0.044839587,0.0051160767,0.001088676,0.00027984794,0.00016526865,0.000032766708,0.000029517614],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851847,0.00013150982,0.00020437234,0.0004729054,0.00020451804,0.00046823054],"domain_scores_gemma":[0.9991363,0.0003249245,0.00007086719,0.0002746326,0.00008561022,0.00010762315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027893408,0.00017922945,0.00016478053,0.00013092505,0.00034279338,0.00018161254,0.00026937018,0.00004655485,0.000026278884],"category_scores_gemma":[0.00003054246,0.0001375911,0.00010586463,0.0005859213,0.00004644593,0.00039037736,0.000079275975,0.00013898846,0.00019192132],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028028793,0.000026458085,0.000778454,0.000013243912,0.000052969655,0.000018432456,0.00015986143,0.010191565,0.0050488254,0.000009786364,0.005597269,0.9780751],"study_design_scores_gemma":[0.0028068759,0.00051201275,0.010830048,0.00019190216,0.00008626758,0.000053522606,0.000069353926,0.9552367,0.016207946,0.0029168345,0.010089053,0.0009995361],"about_ca_topic_score_codex":0.000037075486,"about_ca_topic_score_gemma":0.00013642418,"teacher_disagreement_score":0.9770756,"about_ca_system_score_codex":0.000027909704,"about_ca_system_score_gemma":0.000015281974,"threshold_uncertainty_score":0.5610802},"labels":[],"label_agreement":null},{"id":"W4379649695","doi":"10.1007/s13042-023-01871-0","title":"An attentive-based generative model for medical image synthesis","year":2023,"lang":"en","type":"article","venue":"International Journal of Machine Learning and Cybernetics","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of Windsor","funders":"","keywords":"Computer science; Generative model; Artificial intelligence; Image synthesis; Image (mathematics); Code (set theory); Pattern recognition (psychology); Generative grammar; Contrast (vision); Source code; Modality (human–computer interaction); Set (abstract data type)","score_opus":0.014127579276750868,"score_gpt":0.2943054479323201,"score_spread":0.28017786865556926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379649695","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022555782,0.000104309984,0.9714354,0.005399705,0.000331298,0.000043892975,0.000009322694,0.00003420323,0.00008604292],"genre_scores_gemma":[0.89302456,0.00018835666,0.105891675,0.0002900128,0.00036364002,0.000005037691,0.000007486738,0.00001299422,0.00021624379],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986267,0.00015798963,0.0003087142,0.00017955966,0.0005705425,0.00015650937],"domain_scores_gemma":[0.99853384,0.0004903084,0.00022851134,0.00008282879,0.00052150205,0.0001429818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008884354,0.00011678021,0.00017682221,0.00018122303,0.000108563785,0.00022061521,0.00062668667,0.00005716168,0.000023435714],"category_scores_gemma":[0.0007754588,0.00009576265,0.0001054323,0.00010514236,0.000060194478,0.0002710592,0.000088893,0.00022423384,0.000004187166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017700122,0.00023507781,0.0036651301,0.000014554213,0.0003745186,0.0002346077,0.0015048217,0.71378154,0.007481543,0.0046797814,0.0021557254,0.2656957],"study_design_scores_gemma":[0.00047045833,0.0001373837,0.00047006036,0.0000387877,0.00001737766,0.000033028435,0.000029902754,0.994116,0.0021345878,0.0010237657,0.0014240487,0.000104564526],"about_ca_topic_score_codex":0.0000087500375,"about_ca_topic_score_gemma":0.000008111142,"teacher_disagreement_score":0.8704688,"about_ca_system_score_codex":0.000023419045,"about_ca_system_score_gemma":0.00011319437,"threshold_uncertainty_score":0.39050874},"labels":[],"label_agreement":null},{"id":"W4379660313","doi":"10.1007/978-3-031-34048-2_30","title":"SADM: Sequence-Aware Diffusion Model for Longitudinal Medical Image Generation","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Sequence (biology); Artificial intelligence; Autoregressive model; Inference; Image (mathematics); Algorithm; Computer vision; Data mining; Mathematics","score_opus":0.06108082821458336,"score_gpt":0.2881049663729653,"score_spread":0.22702413815838193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379660313","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028916857,0.00008102317,0.9944641,0.0020653328,0.0023324897,0.0005551888,0.000024874182,0.0001914916,0.00025660935],"genre_scores_gemma":[0.10233893,0.00018996235,0.8907545,0.0016656871,0.0029681786,0.00006714071,0.0000682199,0.00009287487,0.0018544714],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952311,0.000043753455,0.00058959704,0.0019013758,0.0014777565,0.0007564074],"domain_scores_gemma":[0.99742204,0.00048797094,0.0002552372,0.0010878473,0.00046436035,0.0002825271],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012808392,0.0005605823,0.00056865934,0.00053662236,0.000525501,0.00067722466,0.0027238934,0.0004594233,0.000027463977],"category_scores_gemma":[0.0003038838,0.0004892689,0.00022221306,0.000498499,0.0005969594,0.0008172301,0.0013254189,0.0005993365,0.000041673567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000977368,0.000038684615,0.000017941147,0.00005131388,0.000022401635,0.00011977507,0.0004925739,0.456915,0.0016042523,0.011690908,0.00085543055,0.52818197],"study_design_scores_gemma":[0.00024348535,0.000096431686,0.000016568634,0.00020539704,0.0000103049915,0.00002270078,8.869424e-8,0.9477289,0.0008441372,0.0501705,0.00014159379,0.0005199235],"about_ca_topic_score_codex":0.000020808668,"about_ca_topic_score_gemma":0.00031004954,"teacher_disagreement_score":0.52766204,"about_ca_system_score_codex":0.00026827623,"about_ca_system_score_gemma":0.0010014278,"threshold_uncertainty_score":0.9997559},"labels":[],"label_agreement":null},{"id":"W4382318270","doi":"10.1609/aaai.v37i8.26145","title":"Diffusing Gaussian Mixtures for Generating Categorical Data","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Categorical variable; Computer science; Generative grammar; Generative model; Probabilistic logic; Domain (mathematical analysis); Artificial intelligence; Gaussian; Mixture model; Machine learning; Focus (optics); Data mining; Mathematics","score_opus":0.16489061443883313,"score_gpt":0.3306756981985165,"score_spread":0.16578508375968337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382318270","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015984848,0.000036550005,0.9686698,0.010815234,0.0012563632,0.0006956856,0.000026224143,0.00022063499,0.0022947034],"genre_scores_gemma":[0.97654736,0.000028703873,0.022611389,0.0002103851,0.00033857676,0.000029613102,0.0000050067,0.000015163512,0.00021379966],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99806273,0.000023259148,0.0004537828,0.0006673791,0.00036632214,0.000426498],"domain_scores_gemma":[0.9984944,0.00021081169,0.00027161065,0.00055009563,0.00039020137,0.000082922175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007478651,0.00020911211,0.00025246915,0.00011469436,0.00043874086,0.00044571064,0.0030661304,0.0000792622,0.000015230179],"category_scores_gemma":[0.00085687626,0.00014835855,0.000099519755,0.0008718351,0.00015412264,0.00054344296,0.001000153,0.00017985239,0.000037195205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003077459,0.00007956962,0.000041098276,0.0000390149,0.00002830693,7.938658e-7,0.0008093071,0.001366745,0.1922827,0.6391856,0.0037713542,0.16236472],"study_design_scores_gemma":[0.00001866046,0.000058190144,0.000034810528,0.00004551258,0.000010361312,0.000001483825,0.0001704862,0.7023173,0.2354046,0.061481263,0.00030606048,0.00015126466],"about_ca_topic_score_codex":0.00003685953,"about_ca_topic_score_gemma":0.000011358504,"teacher_disagreement_score":0.9605625,"about_ca_system_score_codex":0.000025052981,"about_ca_system_score_gemma":0.00008696365,"threshold_uncertainty_score":0.6049886},"labels":[],"label_agreement":null},{"id":"W4384158297","doi":"10.1109/aiiot58121.2023.10174589","title":"A Conditional GAN Architecture for Colorization of Thermal Infrared Images","year":2023,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Chrominance; Artificial intelligence; Computer science; Luminance; Computer vision; RGB color model; Grayscale; Translation (biology); Image (mathematics); Pattern recognition (psychology)","score_opus":0.013706264516226774,"score_gpt":0.23868471589946227,"score_spread":0.2249784513832355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384158297","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023458838,0.000005466154,0.9938232,0.0011841046,0.00011808136,0.00016778463,0.00002466304,0.00008387403,0.002246994],"genre_scores_gemma":[0.9299435,0.0000021202295,0.0685496,0.00016829417,0.00014883018,0.000034828252,0.000053297186,0.000005198788,0.001094327],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995125,0.00002886339,0.00010724081,0.00013657051,0.0000993489,0.00011546367],"domain_scores_gemma":[0.99954844,0.00016251019,0.000045010474,0.00012382687,0.00009619052,0.000024026745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011011167,0.000056462603,0.00008224234,0.000066605506,0.00006551355,0.000032841694,0.00019655879,0.000024954792,0.000038474565],"category_scores_gemma":[0.000056706172,0.000045376175,0.000048876896,0.00028230334,0.000032343927,0.00015432034,0.000043880533,0.000023686875,0.000009115652],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055841505,0.00007136512,0.00039783254,0.00005580241,0.00012153803,0.0000047960316,0.0011897339,0.30346927,0.4136942,0.114824295,0.08467377,0.08144156],"study_design_scores_gemma":[0.00076537655,0.00021883822,0.015286451,0.000012368773,0.000011252865,0.0000019615925,0.00008118946,0.5861948,0.3326898,0.053663876,0.010844322,0.00022974706],"about_ca_topic_score_codex":0.0000045462643,"about_ca_topic_score_gemma":0.0000026356474,"teacher_disagreement_score":0.92759764,"about_ca_system_score_codex":0.000004571128,"about_ca_system_score_gemma":0.00003191821,"threshold_uncertainty_score":0.18503867},"labels":[],"label_agreement":null},{"id":"W4385327769","doi":"10.48550/arxiv.2307.13842","title":"CosSIF: Cosine similarity-based image filtering to overcome low inter-class variation in synthetic medical image datasets","year":2023,"lang":"en","type":"preprint","venue":"PubMed","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Discriminative model; Computer science; Artificial intelligence; Pattern recognition (psychology); Leverage (statistics); Similarity (geometry); Image (mathematics)","score_opus":0.028732506810982404,"score_gpt":0.25779501446609954,"score_spread":0.22906250765511713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385327769","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016968526,0.000026090633,0.981787,0.011328842,0.0022757603,0.0016113777,0.00071528915,0.00032738203,0.00023137382],"genre_scores_gemma":[0.87016994,0.00004241832,0.11961978,0.003354928,0.00092056923,0.004642578,0.00092267955,0.00014360448,0.00018352318],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995177,0.0005575496,0.0008321464,0.0015302314,0.0009347461,0.0009683693],"domain_scores_gemma":[0.99670297,0.000614547,0.0002753459,0.0017441858,0.00014072907,0.0005222028],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0024288394,0.0005334716,0.0007442323,0.00057109114,0.00011971595,0.0009463947,0.0025643336,0.000382432,0.00006585253],"category_scores_gemma":[0.0022348682,0.0005441019,0.00018989926,0.00073372386,0.00011232943,0.00056804426,0.0039885174,0.0009524574,0.00012228341],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076303026,0.0041510044,0.0012756784,0.004161415,0.001110274,0.005453225,0.0037113235,0.1567934,0.014465706,0.0015951338,0.18008071,0.6264391],"study_design_scores_gemma":[0.0011825444,0.000042470754,0.08932116,0.00095724664,0.000048292717,0.000009539852,0.0000103245,0.89712936,0.0046279165,0.0014858482,0.0039248886,0.0012604067],"about_ca_topic_score_codex":0.00049034524,"about_ca_topic_score_gemma":0.00035163696,"teacher_disagreement_score":0.86847305,"about_ca_system_score_codex":0.00041685865,"about_ca_system_score_gemma":0.00026414345,"threshold_uncertainty_score":0.999701},"labels":[],"label_agreement":null},{"id":"W4385424060","doi":"10.3390/make5030045","title":"Efficient Latent Space Compression for Lightning-Fast Fine-Tuning and Inference of Transformer-Based Models","year":2023,"lang":"en","type":"article","venue":"Machine Learning and Knowledge Extraction","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Automatic summarization; Computer science; Inference; Embedding; Encoder; Transformer; Fine-tuning; Artificial intelligence; Pattern recognition (psychology); Voltage","score_opus":0.02609713780614908,"score_gpt":0.2920949468936843,"score_spread":0.26599780908753523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385424060","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06897446,0.0005835943,0.92923516,0.00034671804,0.00018295957,0.0001540424,0.0000026755283,0.00011042945,0.0004099832],"genre_scores_gemma":[0.98962146,0.00006687779,0.009845049,0.0000046202413,0.000051235947,0.00001502597,0.000010400646,0.000010488581,0.00037484753],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912536,0.000108233406,0.00018410086,0.00029262522,0.00010009777,0.0001895647],"domain_scores_gemma":[0.99923354,0.0004056544,0.00010666942,0.000094283714,0.00009457757,0.00006524475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041765315,0.00013499969,0.00018600016,0.00015670632,0.00031867652,0.000069311296,0.00008625551,0.000058154554,0.0000031425077],"category_scores_gemma":[0.00007427021,0.000114776565,0.000048305832,0.00026420478,0.000037032492,0.00013953997,0.000042890624,0.00017593472,0.0000024461672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004806717,0.00007096844,0.0010174504,0.00011181719,0.000015322026,0.0000011099478,0.0016101856,0.7771892,0.044601366,0.0010634778,0.000052827014,0.17421824],"study_design_scores_gemma":[0.00048457697,0.00016223897,0.00119429,0.0001234343,0.000013780556,0.0000017431679,0.000039716626,0.98960954,0.0067134984,0.00016883334,0.0013618505,0.00012651733],"about_ca_topic_score_codex":0.000040499886,"about_ca_topic_score_gemma":0.000022706608,"teacher_disagreement_score":0.920647,"about_ca_system_score_codex":0.00001219749,"about_ca_system_score_gemma":0.000028821034,"threshold_uncertainty_score":0.46804526},"labels":[],"label_agreement":null},{"id":"W4385551668","doi":"10.1111/cgf.14921","title":"Harmonized Portrait‐Background Image Composition","year":2023,"lang":"en","type":"article","venue":"Computer Graphics Forum","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IONICS Mass Spectrometry (Canada)","funders":"Natural Science Foundation of Zhejiang Province","keywords":"Portrait; Computer science; Pipeline (software); Artificial intelligence; Composition (language); Computer vision; Image (mathematics); Style (visual arts); Computer graphics (images); Art; Visual arts","score_opus":0.02275068566771715,"score_gpt":0.24963695967268912,"score_spread":0.22688627400497197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385551668","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006960259,0.00006761048,0.9859298,0.0038792433,0.0015485635,0.00021235058,0.000008155284,0.0007593444,0.0006346582],"genre_scores_gemma":[0.8563027,0.00010761628,0.14022991,0.0025124722,0.000521421,0.000030611027,0.00008607989,0.0000382102,0.0001709697],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99800646,0.00012495235,0.0003237979,0.0005872061,0.0003410169,0.0006165411],"domain_scores_gemma":[0.998768,0.0001344287,0.000115351904,0.0006568948,0.0001662716,0.00015905841],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003752166,0.00025162543,0.00027094173,0.00033266572,0.00041393237,0.00051945256,0.0009210211,0.00009441496,0.000014042761],"category_scores_gemma":[0.0000050492317,0.0002432469,0.00022540688,0.001488425,0.000114944356,0.0008683733,0.0005809773,0.0002044757,0.0002876763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034841665,0.00028459224,0.000982964,0.000053074196,0.0002985986,0.0004227975,0.0006959154,0.0025034097,0.014793655,0.62902486,0.26886418,0.082041115],"study_design_scores_gemma":[0.00062634837,0.00011300262,0.0067515154,0.00002952812,0.000013660451,0.000028599234,0.000021507645,0.9571427,0.0023478235,0.015428071,0.0170661,0.00043114158],"about_ca_topic_score_codex":0.00001899402,"about_ca_topic_score_gemma":0.0000069011076,"teacher_disagreement_score":0.9546393,"about_ca_system_score_codex":0.000023132796,"about_ca_system_score_gemma":0.00004304772,"threshold_uncertainty_score":0.9919321},"labels":[],"label_agreement":null},{"id":"W4385768145","doi":"10.24963/ijcai.2023/196","title":"STS-GAN: Can We Synthesize Solid Texture with High Fidelity from Arbitrary 2D Exemplar?","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Science Foundation of Shandong Province; National Natural Science Foundation of China","keywords":"Texture synthesis; Texture (cosmology); Computer science; Similarity (geometry); Generator (circuit theory); High fidelity; Generative grammar; Artificial intelligence; Fidelity; Scale (ratio); Solid modeling; Computer vision; Image (mathematics); Image texture; Image processing; Power (physics); Physics","score_opus":0.024671920328974122,"score_gpt":0.24160623872678386,"score_spread":0.21693431839780974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385768145","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004175014,0.00056525087,0.97164977,0.016499225,0.0024257703,0.0007662875,0.00041698513,0.0011173883,0.0023842894],"genre_scores_gemma":[0.8056058,0.00036658795,0.1876895,0.0015653365,0.0014252093,0.00013084806,0.00014974625,0.0001011122,0.0029658407],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953741,0.00036052882,0.00063922425,0.002069359,0.00078449264,0.0007723417],"domain_scores_gemma":[0.9958217,0.0006633096,0.00037649565,0.0025587624,0.00025403855,0.00032569416],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042251457,0.0008260888,0.001029894,0.00016895942,0.00029500955,0.00084696966,0.0026679519,0.00055367063,0.000300947],"category_scores_gemma":[0.000100777586,0.0006236089,0.00029116363,0.0004233899,0.00015072728,0.0003451011,0.0021126724,0.0012127,0.00017349061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052290614,0.0014134813,0.0030880177,0.00087716087,0.007393471,0.0036035394,0.0094214445,0.3602818,0.005901813,0.024165668,0.31248352,0.27084717],"study_design_scores_gemma":[0.001994729,0.0004914175,0.033264644,0.0028109814,0.0007580225,0.000035147972,0.0007098036,0.60516864,0.07074781,0.25810826,0.018653728,0.0072568287],"about_ca_topic_score_codex":0.010273967,"about_ca_topic_score_gemma":0.003211859,"teacher_disagreement_score":0.8014308,"about_ca_system_score_codex":0.0001366779,"about_ca_system_score_gemma":0.000628329,"threshold_uncertainty_score":0.9996215},"labels":[],"label_agreement":null},{"id":"W4385804870","doi":"10.1109/cvprw59228.2023.00556","title":"DACNet: A Deep Automated Checkout Network with Selective Deblurring","year":2023,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Deblurring; Computer science; Deep learning; Artificial intelligence; Pipeline (software); Process (computing); Code (set theory); Training set; Tracking (education); Computer vision; Set (abstract data type); Object detection; Machine learning; Image (mathematics); Pattern recognition (psychology); Image restoration; Image processing","score_opus":0.009610696836931533,"score_gpt":0.222666805680246,"score_spread":0.21305610884331447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385804870","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004256426,0.000043790973,0.9785101,0.0004664982,0.00023367033,0.0001853786,3.663294e-7,0.0027543753,0.013549419],"genre_scores_gemma":[0.89032346,0.000009324722,0.1081172,0.00036557554,0.00022479176,0.000029151362,0.0000033463307,0.000018266424,0.0009088766],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861026,0.00008061439,0.00014826907,0.00042641725,0.00021119883,0.0005232186],"domain_scores_gemma":[0.9992785,0.00010894526,0.000054079937,0.00035628205,0.00010205915,0.00010014361],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002481856,0.00016877337,0.00017985771,0.00007714879,0.00024934966,0.00018973238,0.00047030844,0.000048563576,0.000028060378],"category_scores_gemma":[0.00002579681,0.00012314972,0.00004573014,0.0017785555,0.00003349514,0.00041496946,0.0002160724,0.00010104442,0.00023496817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026156586,0.000043342025,0.0038606634,0.000009439819,0.00021624046,0.0001014933,0.0011729167,0.90244687,0.00090073654,0.008969178,0.049656317,0.03259665],"study_design_scores_gemma":[0.00021337777,0.00007858463,0.008314548,0.00001673359,0.0000073123974,0.00000874209,0.000031242555,0.987539,0.0016976723,0.00045923126,0.0014261389,0.0002074311],"about_ca_topic_score_codex":0.00005530403,"about_ca_topic_score_gemma":0.00015437792,"teacher_disagreement_score":0.88606703,"about_ca_system_score_codex":0.00003339103,"about_ca_system_score_gemma":0.000057228106,"threshold_uncertainty_score":0.50218993},"labels":[],"label_agreement":null},{"id":"W4386071545","doi":"10.1109/cvpr52729.2023.02135","title":"Robust Unsupervised StyleGAN Image Restoration","year":2023,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Image restoration; Computer science; Robustness (evolution); Upsampling; Artificial intelligence; Inpainting; Regularization (linguistics); Hyperparameter; Generative grammar; Pattern recognition (psychology); Image (mathematics); Image processing","score_opus":0.03906065924470581,"score_gpt":0.23530916103191427,"score_spread":0.19624850178720846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386071545","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027699354,0.000011568967,0.97993374,0.0032364181,0.00035312164,0.00009359773,8.959613e-7,0.00050374854,0.013096962],"genre_scores_gemma":[0.76115984,0.00003093547,0.23063195,0.0006156661,0.00033337972,0.000018528757,0.000014887168,0.000015349071,0.007179473],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991518,0.000073463794,0.00012589508,0.0002677697,0.0001692252,0.00021179514],"domain_scores_gemma":[0.9994018,0.000056758436,0.000025813635,0.000375829,0.00007732858,0.00006246493],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00025955637,0.00008756248,0.00008677233,0.00009294483,0.00014453176,0.00024383327,0.00039086156,0.000032226635,0.00008347075],"category_scores_gemma":[0.00004895222,0.000073805975,0.000043173826,0.00076486694,0.000022818973,0.00083764584,0.00014597326,0.0000526614,0.0008043698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015812018,0.00012147814,0.00050987204,0.000023696039,0.00006997455,0.00012413906,0.0018501128,0.07724063,0.13863857,0.124262564,0.54488206,0.11226107],"study_design_scores_gemma":[0.0001938314,0.000037302438,0.0030705675,0.000004807296,0.0000029301418,0.0000014388445,0.000073411466,0.9721312,0.0122681735,0.0011338268,0.010910541,0.000171993],"about_ca_topic_score_codex":0.000039182763,"about_ca_topic_score_gemma":0.000025507812,"teacher_disagreement_score":0.89489055,"about_ca_system_score_codex":0.000016391781,"about_ca_system_score_gemma":0.000031060823,"threshold_uncertainty_score":0.9999736},"labels":[],"label_agreement":null},{"id":"W4386071957","doi":"10.1109/cvpr52729.2023.02161","title":"Align Your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","year":2023,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":583,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Waterloo; University of Toronto","funders":"","keywords":"Computer science; Leverage (statistics); Generator (circuit theory); Artificial intelligence; Focus (optics); Computer vision","score_opus":0.030121040886948825,"score_gpt":0.22106269506828347,"score_spread":0.19094165418133463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386071957","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023236552,0.000031330706,0.9715504,0.0025336244,0.00029383213,0.00020153566,0.000004211464,0.0005507968,0.0015977061],"genre_scores_gemma":[0.9564861,0.00011246092,0.04114627,0.00024342399,0.00011008957,0.000049172046,0.000006022635,0.000019429022,0.001827045],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826705,0.0001196711,0.0002231171,0.0005381111,0.00040779464,0.00044426313],"domain_scores_gemma":[0.9990104,0.00012610557,0.00007894898,0.0005436717,0.00011472864,0.00012618164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029700034,0.000209543,0.00022346133,0.00015816343,0.00026053467,0.00019539212,0.0005399992,0.00007339132,0.000053949567],"category_scores_gemma":[0.00003126868,0.00014451572,0.000075927084,0.0007751436,0.000040187606,0.00088654115,0.0003175994,0.00007928845,0.00027907803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006998963,0.00020696192,0.0005010609,0.000020719459,0.00016876959,0.0000969172,0.0005896414,0.86075634,0.010650766,0.05082262,0.019354632,0.056761615],"study_design_scores_gemma":[0.0002540447,0.00006849949,0.0027295998,0.000042024312,0.000019763378,0.000004171159,0.000032843844,0.98646486,0.0061114007,0.0036066107,0.00041399943,0.0002521685],"about_ca_topic_score_codex":0.00042613444,"about_ca_topic_score_gemma":0.00003766291,"teacher_disagreement_score":0.93324953,"about_ca_system_score_codex":0.00004855532,"about_ca_system_score_gemma":0.000033231445,"threshold_uncertainty_score":0.58931804},"labels":[],"label_agreement":null},{"id":"W4386072022","doi":"10.1109/cvpr52729.2023.01367","title":"Fix the Noise: Disentangling Source Feature for Controllable Domain Translation","year":2023,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Controllability; Subspace topology; Translation (biology); Domain (mathematical analysis); Feature (linguistics); Generator (circuit theory); Source code; Artificial intelligence; Noise (video); Transformation (genetics); Code (set theory); Generative model; Quality (philosophy); Pattern recognition (psychology); Algorithm; Image (mathematics); Generative grammar; Mathematics; Set (abstract data type)","score_opus":0.018650600354765554,"score_gpt":0.24178775203711977,"score_spread":0.2231371516823542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386072022","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00074922777,0.00015000514,0.9763086,0.020561768,0.0003097837,0.00036110502,0.00000387944,0.00017211563,0.0013835273],"genre_scores_gemma":[0.8427266,0.000031192616,0.1412316,0.0016803647,0.0008479643,0.00014080646,0.000020936195,0.000024683877,0.013295881],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926215,0.00006277484,0.00009727982,0.00021564221,0.00013037946,0.00023178839],"domain_scores_gemma":[0.9992138,0.0004220551,0.000034317007,0.00024801085,0.0000458456,0.00003593121],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003850874,0.000089322304,0.000102802194,0.000032128974,0.00033292008,0.00019381526,0.0003433722,0.00004231784,0.000011543547],"category_scores_gemma":[0.000030587576,0.000054398817,0.000094116964,0.00038485407,0.000021430595,0.00021468538,0.0000405615,0.000059162612,0.000028410008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011418078,0.000061696,0.00036185436,0.00003599151,0.00019164394,0.000007728845,0.005746313,0.21430445,0.033979967,0.036142685,0.28793225,0.42112124],"study_design_scores_gemma":[0.00048389303,0.0000216284,0.00013129025,0.000004967333,0.000008340814,5.9254955e-7,0.0001886281,0.86982375,0.0018145158,0.0032609978,0.12416535,0.00009605981],"about_ca_topic_score_codex":0.000007545191,"about_ca_topic_score_gemma":0.000023848253,"teacher_disagreement_score":0.84197736,"about_ca_system_score_codex":0.000010044021,"about_ca_system_score_gemma":0.000017616985,"threshold_uncertainty_score":0.25605857},"labels":[],"label_agreement":null},{"id":"W4386160466","doi":"10.1109/csci58124.2022.00280","title":"Deep Learning-based Synthesized Image Attribution Using Frequency Distribution Information","year":2022,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Generalizability theory; Computer science; Deep learning; Artificial intelligence; Categorization; Figuring; Image (mathematics); Pace; Generative grammar; Domain (mathematical analysis); Machine learning; Task (project management); Mathematics; Statistics; Engineering","score_opus":0.010699062603167405,"score_gpt":0.2165932957472945,"score_spread":0.20589423314412708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386160466","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023616364,0.000032027463,0.9959769,0.00053707766,0.00029269845,0.00018605636,0.000014035566,0.00020435707,0.0003952048],"genre_scores_gemma":[0.9131027,0.0000021655374,0.08636633,0.00021923607,0.000045174944,0.00003379399,0.0002006876,0.000005246344,0.000024674307],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984647,0.00038046335,0.00028348932,0.00021771224,0.000370369,0.00028324287],"domain_scores_gemma":[0.9992276,0.00009605267,0.00017978337,0.00027013264,0.00016256663,0.00006390063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006001507,0.00013678487,0.00014270136,0.00008335696,0.0009699108,0.00024428204,0.0003997187,0.000034708017,0.0003553828],"category_scores_gemma":[0.00014871679,0.00013606559,0.00009469692,0.0005775501,0.000034509383,0.001757296,0.00021010962,0.00020670677,0.000040657884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031158776,0.00010464771,0.00054922316,0.000013475102,0.000028099661,0.0000078310295,0.00023523565,0.9312183,0.011152791,0.01697147,0.0006636694,0.03902408],"study_design_scores_gemma":[0.00030388072,0.000073762145,0.00055668864,0.000003152012,0.000010076827,0.000006121931,0.00006426622,0.9869383,0.005535309,0.0003909259,0.0059367055,0.0001808318],"about_ca_topic_score_codex":0.00013446971,"about_ca_topic_score_gemma":0.0000033957333,"teacher_disagreement_score":0.91074103,"about_ca_system_score_codex":0.00031963023,"about_ca_system_score_gemma":0.00009534072,"threshold_uncertainty_score":0.7459868},"labels":[],"label_agreement":null},{"id":"W4386243173","doi":"10.1109/crv60082.2023.00009","title":"LatentKeypointGAN: Controlling Images via Latent Keypoints","year":2023,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence; Computer vision; Image (mathematics); Set (abstract data type); Matching (statistics); Domain (mathematical analysis); Generative grammar; Generative model; Image translation; Pattern recognition (psychology); Mathematics","score_opus":0.016296210850290888,"score_gpt":0.22601230278475634,"score_spread":0.20971609193446544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386243173","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017352428,0.00006549213,0.98800635,0.004027138,0.00073405646,0.0001593715,0.0000015905321,0.00067632826,0.0045944154],"genre_scores_gemma":[0.9559366,0.0000673415,0.037204016,0.00069037627,0.00021004147,0.000016706706,0.000004149516,0.000015568483,0.005855217],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859947,0.00008003523,0.0002387164,0.0004104558,0.00023951718,0.0004317777],"domain_scores_gemma":[0.9991705,0.00013246559,0.00005838823,0.00042692162,0.00009662077,0.00011509281],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00039238745,0.00016202444,0.00021044613,0.00012671792,0.00017935527,0.00022287323,0.00052871206,0.000048259542,0.00011914455],"category_scores_gemma":[0.000042298107,0.00012848934,0.00012247567,0.00047216754,0.00003527523,0.00050529785,0.0002890951,0.00009427408,0.0018315531],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056298053,0.00031755381,0.004844737,0.000051498122,0.00055609434,0.00065925193,0.0017262666,0.12362286,0.23842336,0.03161386,0.20431878,0.39380944],"study_design_scores_gemma":[0.00058361347,0.000054386117,0.004041915,0.00001281698,0.000009777152,0.000009235256,0.000017155007,0.9452188,0.039911807,0.0052841916,0.0045582703,0.00029800876],"about_ca_topic_score_codex":0.000052981002,"about_ca_topic_score_gemma":0.0000072746902,"teacher_disagreement_score":0.95420134,"about_ca_system_score_codex":0.000020230731,"about_ca_system_score_gemma":0.000021167307,"threshold_uncertainty_score":0.99894565},"labels":[],"label_agreement":null},{"id":"W4386597257","doi":"10.1109/icip49359.2023.10221905","title":"Detecting Stable Diffusion Generated Images Using Frequency Artifacts: A Case Study on Disney-Style Art","year":2023,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Realm; Animation; Artificial intelligence; Domain (mathematical analysis); Diffusion; Style (visual arts); Frequency domain; Property (philosophy); Deep learning; Computer vision; Computer graphics (images); Visual arts; Art; Mathematics","score_opus":0.044956447885685945,"score_gpt":0.2816561982229749,"score_spread":0.23669975033728893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386597257","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62748814,0.000013152314,0.3707096,0.00009722734,0.00031302497,0.00028791232,0.0000023149275,0.0003440949,0.00074451795],"genre_scores_gemma":[0.9762129,0.0000055718933,0.022711651,0.00012621227,0.00014926174,0.00002066228,0.0000025652732,0.000023376244,0.0007477886],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99786574,0.00028479172,0.0003355239,0.0006672704,0.0003199812,0.0005266811],"domain_scores_gemma":[0.9988055,0.000190027,0.00010662671,0.0006339223,0.00012232324,0.00014156105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005567298,0.0002540754,0.00024875512,0.00021877549,0.0007037199,0.00048230845,0.00034490714,0.000053069027,0.00008000675],"category_scores_gemma":[0.000116153504,0.00020492601,0.00007443339,0.0013147704,0.000027626224,0.0006938652,0.00034646993,0.00016648686,0.00024904538],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031052743,0.0014148055,0.010403548,0.000027725648,0.00024325227,0.018882344,0.00710812,0.074363805,0.7993614,0.00038070203,0.005623852,0.0821594],"study_design_scores_gemma":[0.0005768533,0.0003545938,0.0012798563,0.000028273105,0.000025413068,0.00022179568,0.0030775573,0.948982,0.04467797,0.00018498833,0.00012497598,0.0004656965],"about_ca_topic_score_codex":0.00096392265,"about_ca_topic_score_gemma":0.00021170487,"teacher_disagreement_score":0.87461823,"about_ca_system_score_codex":0.00007262854,"about_ca_system_score_gemma":0.00005064367,"threshold_uncertainty_score":0.83566403},"labels":[],"label_agreement":null},{"id":"W4386835533","doi":"10.21203/rs.3.rs-3347773/v1","title":"Movie-RNET: Best of Best Movie Recommendation via Deep Learning Networks from Multi-Format Data","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Future Earth","funders":"","keywords":"Offensive; Computer science; Normalization (sociology); Artificial intelligence; Computer vision; Machine learning; Engineering; Operations research","score_opus":0.21358188578940315,"score_gpt":0.404593684235967,"score_spread":0.19101179844656382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386835533","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006525049,0.0017569575,0.9938746,0.0009082989,0.0011278024,0.000903263,0.00024286358,0.00016072123,0.0003730035],"genre_scores_gemma":[0.80820435,0.012429276,0.16516869,0.00007727338,0.0024291447,0.00028291854,0.009694722,0.00020281284,0.0015108191],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9935491,0.0018518958,0.0008395806,0.0016263154,0.001130375,0.0010027158],"domain_scores_gemma":[0.9940182,0.0014268098,0.0004464733,0.0029349322,0.00088807516,0.00028553375],"candidate_categories":["metaepi_narrow","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0037601646,0.00044396514,0.00069212605,0.0004887386,0.00055719045,0.00069536566,0.0045143063,0.0004988247,0.00019250458],"category_scores_gemma":[0.0009683926,0.0004334236,0.00018794418,0.0010191076,0.0001942861,0.0010245877,0.014064038,0.0026209736,0.00041867577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037450525,0.00032313372,0.0020006162,0.00029451953,0.00025853436,0.000034762867,0.0009768088,0.38666418,0.00019285038,0.00006672437,0.0048816237,0.6042688],"study_design_scores_gemma":[0.00032772517,0.00014531623,0.001209702,0.0006771282,0.000025286234,0.0000010743822,0.00038580174,0.9891172,0.00018929309,0.0005399742,0.0069937604,0.00038772434],"about_ca_topic_score_codex":0.005564627,"about_ca_topic_score_gemma":0.0012836766,"teacher_disagreement_score":0.8287059,"about_ca_system_score_codex":0.0001974059,"about_ca_system_score_gemma":0.00025383284,"threshold_uncertainty_score":0.99981177},"labels":[],"label_agreement":null},{"id":"W4386946990","doi":"10.1016/j.compbiomed.2023.107521","title":"Visual attribution using Adversarial Latent Transformations","year":2023,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Artificial intelligence; Adversarial system; Machine learning; Consistency (knowledge bases); Salient; Segmentation; Latent variable; Pattern recognition (psychology)","score_opus":0.03661200231727246,"score_gpt":0.3343487465515937,"score_spread":0.2977367442343212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386946990","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049994644,0.00016288778,0.9455168,0.0027016338,0.0013889638,0.00010243773,0.0000013574388,0.000065425105,0.000065819615],"genre_scores_gemma":[0.98850405,0.00023739274,0.0105628455,0.00035269005,0.00030156525,0.0000035215471,0.00002704856,0.0000026342855,0.000008224021],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924695,0.000103142156,0.0001874356,0.00020523445,0.000051521558,0.00020568629],"domain_scores_gemma":[0.999672,0.0001191381,0.000035632213,0.000094115734,0.000026765314,0.000052371688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037028192,0.000087716464,0.00017023685,0.00018415946,0.00012354186,0.000009763284,0.00014507936,0.000071837865,0.000004923681],"category_scores_gemma":[0.000022493674,0.000068817884,0.00002046011,0.0004512609,0.00013085915,0.00015482675,0.00008258479,0.0000885238,0.000005535764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012321546,0.00017394788,0.024969323,0.000062736,0.00019214503,0.00011067635,0.008816615,0.03338572,0.03858526,0.21215335,0.008617727,0.6728093],"study_design_scores_gemma":[0.0010064217,0.00017266367,0.014845011,0.00005292449,0.000008295314,0.000012417535,0.00003379148,0.9764335,0.00020360813,0.0046818014,0.0024409613,0.00010861187],"about_ca_topic_score_codex":0.000039262275,"about_ca_topic_score_gemma":0.000006615084,"teacher_disagreement_score":0.94304776,"about_ca_system_score_codex":0.000023899007,"about_ca_system_score_gemma":0.000020258183,"threshold_uncertainty_score":0.28063118},"labels":[],"label_agreement":null},{"id":"W4386998133","doi":"10.11591/ijece.v13i6.pp6351-6360","title":"Generative adversarial deep learning in images using Nash equilibrium game theory","year":2023,"lang":"en","type":"article","venue":"International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Adversarial system; Convolutional neural network; Artificial intelligence; Nash equilibrium; Generative grammar; Machine learning; Class (philosophy); Game theory; Process (computing); Deep learning; Mathematical optimization; Mathematics; Mathematical economics","score_opus":0.005621184028618509,"score_gpt":0.2259822067491813,"score_spread":0.2203610227205628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386998133","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09826432,0.0035307598,0.89443654,0.0004887634,0.003165998,0.00006656786,0.0000019000786,0.00001903474,0.000026130992],"genre_scores_gemma":[0.9890193,0.00096756616,0.008343902,0.000073018055,0.0015497592,0.000001055998,0.0000015453404,0.00001816098,0.000025732837],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974961,0.00020349791,0.00090624124,0.00023222525,0.0008101893,0.00035170102],"domain_scores_gemma":[0.99763596,0.00040836204,0.0006632704,0.00007597641,0.0010628186,0.00015362246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011174125,0.00023430541,0.00044726126,0.00096539763,0.00004046972,0.00047808263,0.00084908627,0.000087588545,0.0000034952045],"category_scores_gemma":[0.00017136373,0.00020124254,0.00018083496,0.00035239113,0.00003456932,0.0009052765,0.0002674917,0.0006074017,0.0000010340113],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003049472,0.0001322702,0.0013845979,0.000012677029,0.0014660963,0.0012948557,0.0011919752,0.90314376,0.022112137,0.03111897,0.00022416061,0.03761356],"study_design_scores_gemma":[0.001448441,0.00050482596,0.0018495239,0.00017156581,0.000025371817,0.0017304386,0.00004116067,0.98969585,0.0011098392,0.0014748533,0.0017188317,0.00022930953],"about_ca_topic_score_codex":0.00000774932,"about_ca_topic_score_gemma":0.0000010328598,"teacher_disagreement_score":0.89075494,"about_ca_system_score_codex":0.00026190036,"about_ca_system_score_gemma":0.00017982713,"threshold_uncertainty_score":0.82064325},"labels":[],"label_agreement":null},{"id":"W4387195417","doi":"10.1145/3626235","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","year":2023,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1387,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; HEC Montréal","funders":"","keywords":"Computer science; Data science; Generative grammar; Key (lock); Focus (optics); Generative model; Diffusion; Artificial intelligence; Machine learning","score_opus":0.23377875557158365,"score_gpt":0.422125356263777,"score_spread":0.18834660069219336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387195417","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000011377322,0.469061,0.5302219,0.000004381113,0.00017104748,0.00039327683,0.000029133576,0.000088451816,0.000029693068],"genre_scores_gemma":[0.000051761508,0.81328857,0.18634084,0.000011866715,0.00010219554,0.000029573255,0.000092786744,0.00004538455,0.000037021142],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98905027,0.0085241245,0.00092588505,0.00091613526,0.00021735746,0.00036624735],"domain_scores_gemma":[0.98632133,0.010782168,0.0007429154,0.0016096574,0.0004280883,0.000115813724],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0060388087,0.00045383145,0.0019124969,0.00027313936,0.00023462455,0.00014498047,0.0019242971,0.00023127599,0.0000013771715],"category_scores_gemma":[0.0006638703,0.00038841777,0.00025361817,0.0016513139,0.00012219459,0.00015387392,0.003061478,0.00033318193,0.00001527092],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.762829e-7,0.000024358887,0.00001234732,0.0015022679,0.00012022024,9.91492e-7,0.000045366156,0.00066299073,9.4456936e-7,0.00034158726,0.00013294248,0.9971557],"study_design_scores_gemma":[0.0004190091,0.00012389601,0.004764354,0.008175025,0.00042720986,0.000034760906,0.000021301437,0.70276403,0.00000631624,0.0051184124,0.27627575,0.0018699468],"about_ca_topic_score_codex":0.00096156914,"about_ca_topic_score_gemma":0.000055148546,"teacher_disagreement_score":0.99528575,"about_ca_system_score_codex":0.000034140125,"about_ca_system_score_gemma":0.00017588535,"threshold_uncertainty_score":0.99985677},"labels":[],"label_agreement":null},{"id":"W4387559563","doi":"10.48550/arxiv.2310.04935","title":"Statistical Guarantees for Variational Autoencoders using PAC-Bayesian Theory","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Institut de Valorisation des Données; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Generalization; Bayesian probability; Computer science; Generative grammar; Upper and lower bounds; Posterior probability; Distribution (mathematics); Artificial intelligence; Generative model; Statistical learning theory; Algorithm; Machine learning; Mathematics","score_opus":0.11279118450747692,"score_gpt":0.22275027226860084,"score_spread":0.10995908776112391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387559563","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007218533,0.000020970065,0.9968599,0.00018944663,0.0011955186,0.0003887195,0.00017229334,0.00023051273,0.00022075894],"genre_scores_gemma":[0.7828049,0.000021627227,0.2158769,0.00011421051,0.0002554158,0.0000018347787,0.00005534204,0.000030250512,0.0008394972],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99781936,0.0003050182,0.0002367376,0.0010911988,0.00011775168,0.00042991628],"domain_scores_gemma":[0.99789506,0.0008744521,0.00021447282,0.000686648,0.00019888602,0.00013045374],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005903231,0.00031349328,0.00035089382,0.00021700874,0.0003251769,0.0002062532,0.0011136724,0.00023264684,0.00004649414],"category_scores_gemma":[0.00018683504,0.00034803565,0.00023013838,0.00035775857,0.00014193304,0.00032557713,0.00088652933,0.00029421976,0.000021660042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029890174,0.000027032072,0.000061890845,0.000023238736,0.00011926094,0.00004673475,0.00012448667,0.6055384,0.000016140168,0.39312726,0.000603522,0.0002820925],"study_design_scores_gemma":[0.00023607575,0.00002532662,0.0002616875,0.000032177428,0.00007768413,0.0000012226052,0.000050142386,0.7055178,0.000022932642,0.29334372,0.00015817101,0.0002730215],"about_ca_topic_score_codex":0.00009399339,"about_ca_topic_score_gemma":0.000032615862,"teacher_disagreement_score":0.78208303,"about_ca_system_score_codex":0.0001840784,"about_ca_system_score_gemma":0.0003949096,"threshold_uncertainty_score":0.9998972},"labels":[],"label_agreement":null},{"id":"W4387572923","doi":"10.3390/app132011189","title":"A Review of Image Inpainting Methods Based on Deep Learning","year":2023,"lang":"en","type":"review","venue":"Applied Sciences","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Inpainting; Artificial intelligence; Computer science; Deep learning; Image (mathematics); Computer vision; Field (mathematics); Feature (linguistics); Image restoration; Pattern recognition (psychology); Feature extraction; Image processing; Mathematics","score_opus":0.08770687798474226,"score_gpt":0.399027600227316,"score_spread":0.31132072224257373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387572923","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.6695773e-9,0.5720563,0.42035797,0.00004081465,0.00014049838,0.00033045377,6.7708726e-7,0.000077305594,0.006995998],"genre_scores_gemma":[0.0000010691845,0.692913,0.30660686,0.0002761181,0.00007275132,0.00008004911,0.0000029471594,0.000015691418,0.000031515832],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996367,0.0009805263,0.00077927375,0.00091410696,0.0005193748,0.0004397302],"domain_scores_gemma":[0.9959626,0.0024468317,0.00085288484,0.0005743329,0.00008108828,0.00008222699],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0075817695,0.0003766623,0.0015482795,0.00034933703,0.0003633073,0.00019255785,0.0021272611,0.00010851153,0.000031124473],"category_scores_gemma":[0.0009324864,0.00026694412,0.00043082205,0.0032624349,0.0003056666,0.00016786343,0.00042603532,0.00039229947,0.00010671656],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.8348821e-7,0.0000101680125,5.272946e-8,0.016404808,0.000015251695,0.0000014613486,0.000017936683,0.00031821968,0.000005044952,0.0021332973,0.00022423288,0.98086935],"study_design_scores_gemma":[0.000051742143,0.00008582705,2.7357675e-7,0.07614878,0.00014484958,0.000001968064,0.000016954553,0.07273026,0.00005820405,0.00034343195,0.8499395,0.0004782217],"about_ca_topic_score_codex":0.000007213527,"about_ca_topic_score_gemma":9.312428e-7,"teacher_disagreement_score":0.98039114,"about_ca_system_score_codex":0.000036811307,"about_ca_system_score_gemma":0.00026788053,"threshold_uncertainty_score":0.9999783},"labels":[],"label_agreement":null},{"id":"W4387688000","doi":"10.48550/arxiv.2310.09213","title":"A Sampling-Based Domain Generalization Study with Diffusion Generative Models","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Domain (mathematical analysis); Generalization; Computer science; Artificial intelligence; Generative model; Pattern recognition (psychology); Subspace topology; Gaussian; Representation (politics); Sample (material); Statistical model; Algorithm; Mathematics; Generative grammar","score_opus":0.1104075731901478,"score_gpt":0.2087363050380569,"score_spread":0.0983287318479091,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387688000","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1516445,0.000018185414,0.84649765,0.00014013599,0.00039758827,0.0008026007,0.000017616101,0.00034059584,0.0001411375],"genre_scores_gemma":[0.96175116,0.000033175853,0.03720122,0.00012467304,0.00016405822,0.000009782824,0.000054677275,0.000046160578,0.0006151091],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969347,0.00050669484,0.00025979884,0.0016638046,0.00021550813,0.00041946597],"domain_scores_gemma":[0.99773514,0.00011870364,0.00031594,0.0013279205,0.00033016343,0.00017213785],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003587266,0.00049122033,0.0004690129,0.00035141403,0.00041780004,0.00030586816,0.0013247076,0.00021200269,0.000011624008],"category_scores_gemma":[0.000016528431,0.00046233888,0.00016679491,0.0010153521,0.000092110284,0.00047802832,0.0013276202,0.0003842748,0.00002672224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006147649,0.00025337,0.0010940358,0.000015683421,0.00012761875,0.00017614894,0.0006097823,0.985922,0.00008137227,0.0113752,0.00013957117,0.00014378542],"study_design_scores_gemma":[0.0009403346,0.00026300238,0.000618501,0.000068884816,0.000085329135,6.9630954e-7,0.00021718109,0.96910906,0.000120130426,0.02798372,0.00004359807,0.000549589],"about_ca_topic_score_codex":0.00041908116,"about_ca_topic_score_gemma":0.00061957503,"teacher_disagreement_score":0.81010664,"about_ca_system_score_codex":0.00022222732,"about_ca_system_score_gemma":0.00028989563,"threshold_uncertainty_score":0.99978286},"labels":[],"label_agreement":null},{"id":"W4387801427","doi":"10.1145/3586183.3606725","title":"Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language Models","year":2023,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":160,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; University of Toronto","funders":"","keywords":"Computer science; Workflow; Human–computer interaction; Generative grammar; Generative model; User interface; Image (mathematics); Interface (matter); Quality (philosophy); Cognitive load; Image editing; Artificial intelligence; Multimedia; Cognition; Programming language; Database","score_opus":0.039769651128619,"score_gpt":0.2806497791326361,"score_spread":0.24088012800401712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387801427","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009016239,0.000011758947,0.98151624,0.0028983415,0.00020803708,0.00062702096,0.0000071144154,0.0004636101,0.005251643],"genre_scores_gemma":[0.7816157,0.000009142107,0.2153172,0.0006233311,0.0002826375,0.00019264172,0.000048857004,0.000022374725,0.001888112],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984056,0.000116711395,0.00020314993,0.00057954196,0.00031390548,0.0003811151],"domain_scores_gemma":[0.9991378,0.000046906545,0.00007590212,0.00046809285,0.00018775986,0.00008350184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026371845,0.00020151993,0.00018312313,0.00012528327,0.00022225906,0.00040495285,0.00037670607,0.00004714271,0.000048869068],"category_scores_gemma":[0.000034385273,0.00015023148,0.000045719036,0.0009334486,0.000019938972,0.004486272,0.00023491614,0.00010814096,0.00045575504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014460576,0.00060901686,0.000046857393,0.000051560837,0.00028182036,0.00019020594,0.11584965,0.3433752,0.26824415,0.10790636,0.10216032,0.06114028],"study_design_scores_gemma":[0.00030424885,0.00016485387,0.000058411246,0.000020723697,0.0000072523662,0.0000030746417,0.0009796014,0.9387955,0.056682013,0.0015890585,0.0011409534,0.00025428322],"about_ca_topic_score_codex":0.00006363094,"about_ca_topic_score_gemma":0.00020913509,"teacher_disagreement_score":0.77259946,"about_ca_system_score_codex":0.000048798214,"about_ca_system_score_gemma":0.000055085427,"threshold_uncertainty_score":0.6126262},"labels":[],"label_agreement":null},{"id":"W4388157811","doi":"10.1145/3607540.3617144","title":"Story-to-Images Translation: Leveraging Diffusion Models and Large Language Models for Sequence Image Generation","year":2023,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Fidelity; Scripting language; Consistency (knowledge bases); Context (archaeology); Hollywood; Translation (biology); Language translation; Artificial intelligence; Image (mathematics); Natural language processing; Process (computing); Sequence (biology); Character (mathematics); Machine translation; Programming language; Mathematics; History","score_opus":0.07068339543538582,"score_gpt":0.28893186250516045,"score_spread":0.21824846706977463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388157811","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008532277,0.00014485013,0.9869129,0.0029561943,0.00018283592,0.00040529325,0.000025866902,0.00024983505,0.00058994646],"genre_scores_gemma":[0.7215433,0.000046880665,0.27693492,0.00045351064,0.00017509722,0.000055414497,0.000026281288,0.000014388286,0.00075016933],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873614,0.00008250997,0.00016338771,0.00049214816,0.00019523143,0.00033055837],"domain_scores_gemma":[0.99935395,0.000114910814,0.000038223203,0.00029134555,0.00009691932,0.000104635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005191934,0.00015702102,0.00015769881,0.00013678294,0.00038796602,0.00027100294,0.00024875262,0.00004768065,0.0000087277385],"category_scores_gemma":[0.000021688482,0.00014140162,0.00005603887,0.0003380711,0.000019623554,0.0015964095,0.00012561778,0.0000682903,0.000011996986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000139214435,0.000043500746,0.000007903165,0.000036097146,0.000026599186,0.000014494566,0.0119386995,0.3349223,0.4434363,0.018559137,0.010928786,0.18007226],"study_design_scores_gemma":[0.0003296322,0.00003123119,0.000021903525,0.0000101008345,0.000006236124,0.0000017659949,0.00018009557,0.98423064,0.011067136,0.003363448,0.0005681734,0.00018962576],"about_ca_topic_score_codex":0.000028481525,"about_ca_topic_score_gemma":0.000029299727,"teacher_disagreement_score":0.7130111,"about_ca_system_score_codex":0.000024683723,"about_ca_system_score_gemma":0.000028572744,"threshold_uncertainty_score":0.5766191},"labels":[],"label_agreement":null},{"id":"W4388405509","doi":"10.1109/iccsi58851.2023.10303795","title":"A GAN-based Relative Radiometric Correction Model of Remote Sensing Data","year":2023,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China; Ministry of Natural Resources","keywords":"Computer science; Transfer (computing); Remote sensing; Radiometric dating; Generative adversarial network; Artificial intelligence; Domain (mathematical analysis); Transfer of learning; Feature (linguistics); Data modeling; Feature extraction; Deep learning; Mathematics; Geology; Database","score_opus":0.08145485662136584,"score_gpt":0.2801470876854883,"score_spread":0.19869223106412245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388405509","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004538357,0.000017565348,0.9945738,0.00042795055,0.00048653458,0.000083231076,0.0000038344087,0.00015929357,0.003793971],"genre_scores_gemma":[0.6423798,0.000009239629,0.35661754,0.0000795188,0.000036748046,8.3069956e-8,0.000011603589,0.000005860378,0.0008595901],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990008,0.00008008082,0.00018098438,0.0003563783,0.00021136974,0.00017039487],"domain_scores_gemma":[0.99867684,0.00029219704,0.00009008704,0.0007909928,0.0001063628,0.00004353543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004975033,0.000087437096,0.00014550745,0.0004130508,0.00008670329,0.000043246855,0.00047995316,0.00003979643,0.000004921813],"category_scores_gemma":[0.00033198117,0.0000766391,0.000040297768,0.0029945069,0.000030725812,0.0005193211,0.00013644462,0.00007419021,0.000027608121],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005403964,0.000008235611,0.0000072081257,0.000003912287,0.000018939023,0.0000032337723,0.000121895006,0.63832563,0.0040458175,0.00017192113,0.009065968,0.34822187],"study_design_scores_gemma":[0.0001321337,0.000023551533,0.00006388693,0.00001428954,0.000007923307,0.0000010902907,0.000014803512,0.9841235,0.014537615,0.0008152082,0.00017896482,0.00008700535],"about_ca_topic_score_codex":0.00015524558,"about_ca_topic_score_gemma":0.000017670136,"teacher_disagreement_score":0.641926,"about_ca_system_score_codex":0.000024996549,"about_ca_system_score_gemma":0.000083271516,"threshold_uncertainty_score":0.31252518},"labels":[],"label_agreement":null},{"id":"W4389160135","doi":"10.1109/tip.2023.3335828","title":"KBStyle: Fast Style Transfer Using a 200 KB Network With Symmetric Knowledge Distillation","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Key Technology Research and Development Program of Shandong; National Natural Science Foundation of China","keywords":"Distillation; Computer science; Style (visual arts); Artificial intelligence; Chromatography; Chemistry","score_opus":0.02271592017030391,"score_gpt":0.2579186612356012,"score_spread":0.2352027410652973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389160135","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00463583,0.0002067204,0.9928017,0.00015532326,0.00045174363,0.00026620884,0.00000908548,0.00047396988,0.0009993992],"genre_scores_gemma":[0.9355052,0.000035195942,0.06364851,0.000053090036,0.00022402754,0.000034293244,0.000002910089,0.000046119876,0.00045066982],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99797285,0.00013039967,0.00032180376,0.00063597434,0.00033511518,0.00060388935],"domain_scores_gemma":[0.9990403,0.00014582639,0.00007078725,0.00035699518,0.00024330812,0.00014277345],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003250551,0.00031329974,0.00028574924,0.0004288119,0.000981806,0.0005575016,0.000370087,0.00009182107,0.000027984277],"category_scores_gemma":[0.0000072252874,0.00027315135,0.00011125842,0.0045763846,0.00010644357,0.0014172536,0.000004905219,0.00028698868,0.000083852785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005853533,0.00017286101,0.000025415748,0.000095772884,0.00007041368,0.000025354564,0.0014062856,0.5928323,0.0073484313,0.000072449206,0.0002270705,0.39766508],"study_design_scores_gemma":[0.00049287814,0.00009706197,0.00018311417,0.00019447456,0.00006454513,0.00002035001,0.00012116778,0.9878268,0.010231987,0.00008087221,0.00030408212,0.00038265184],"about_ca_topic_score_codex":0.000021978043,"about_ca_topic_score_gemma":0.000036569003,"teacher_disagreement_score":0.93086934,"about_ca_system_score_codex":0.00010312229,"about_ca_system_score_gemma":0.00018423151,"threshold_uncertainty_score":0.99997205},"labels":[],"label_agreement":null},{"id":"W4389205759","doi":"10.22215/etd/2023-15790","title":"Synthetic Ultrasound Video Generation with Generative Adversarial Networks","year":2023,"lang":"en","type":"dissertation","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Computer science; Modality (human–computer interaction); Generative grammar; Artificial intelligence; Machine learning; Generative adversarial network; Task (project management); Deep learning; Adversarial system; Engineering; Systems engineering","score_opus":0.014039008002464645,"score_gpt":0.23161178883163303,"score_spread":0.21757278082916837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389205759","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020963524,0.00028399588,0.97904235,0.00018137481,0.005826561,0.0007215114,0.000009487425,0.0005585867,0.011279761],"genre_scores_gemma":[0.7817124,0.0007151131,0.11075694,0.0007611341,0.008445538,0.0005559413,0.0032840495,0.0003553804,0.0934135],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964059,0.0002905046,0.0005494869,0.0014168476,0.00067580654,0.00066147157],"domain_scores_gemma":[0.99761844,0.00036642115,0.00038582587,0.001014886,0.0004216085,0.00019279718],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040887835,0.00070779765,0.00063692994,0.00026638588,0.00054118456,0.00083765376,0.0009985465,0.00047189856,0.00016238847],"category_scores_gemma":[0.00013391595,0.0005608739,0.00022070459,0.0009080474,0.000062734594,0.00072592293,0.000083763,0.0004851859,0.00020748212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035916237,0.0003119407,0.000075881304,0.00010473023,0.0017588817,0.00030517793,0.0053729694,0.7592734,0.016751032,0.021132013,0.10980204,0.08475274],"study_design_scores_gemma":[0.0009461559,0.00042648657,0.0005488121,0.00019140748,0.00026541523,0.000040062572,0.0005867842,0.97180635,0.02035339,0.0005932649,0.0024207013,0.001821165],"about_ca_topic_score_codex":0.00021882122,"about_ca_topic_score_gemma":0.0022485952,"teacher_disagreement_score":0.8682854,"about_ca_system_score_codex":0.00012756848,"about_ca_system_score_gemma":0.000322773,"threshold_uncertainty_score":0.9996843},"labels":[],"label_agreement":null},{"id":"W4389394090","doi":"10.54254/2753-7048/29/20231440","title":"Generative AI Processes for 2D Platformer Game Character Design and Animation","year":2023,"lang":"en","type":"article","venue":"Lecture Notes in Education Psychology and Public Media","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Animation; Computer science; Character (mathematics); Skeletal animation; Generative grammar; Multimedia; Character animation; Focus (optics); Process (computing); Software; Video game; Human–computer interaction; Randomness; Computer facial animation; Computer animation; Artificial intelligence; Computer graphics (images); Programming language","score_opus":0.03876720433319492,"score_gpt":0.32200501757632005,"score_spread":0.28323781324312514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389394090","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01489748,0.0007810397,0.9500199,0.03287874,0.0010115446,0.00032904814,0.0000028271108,0.00004301547,0.00003639993],"genre_scores_gemma":[0.9216379,0.00055970764,0.069584854,0.0074261543,0.0004467649,0.0002567119,0.00006014046,0.000009137495,0.000018610768],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990804,0.000102193844,0.00016470235,0.00036632465,0.00006153992,0.00022481015],"domain_scores_gemma":[0.99874234,0.00080696,0.00007246634,0.00015058182,0.00015709964,0.00007057592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038726203,0.00011979146,0.0001362249,0.00023349965,0.00010358551,0.00013868441,0.0001486982,0.00013114442,0.000016599552],"category_scores_gemma":[0.00095363695,0.000100277735,0.000013551527,0.00058244483,0.00007102634,0.0005933877,0.000026428641,0.00011632178,0.000005698821],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041099844,0.00015294156,0.0047954097,0.00006300415,0.00003366741,7.7722655e-7,0.010620888,0.00039348,0.0023061256,0.0057580005,0.00892723,0.9669074],"study_design_scores_gemma":[0.0026742322,0.0005539095,0.24708068,0.000121929304,0.000045285047,0.00009052448,0.000260625,0.18929738,0.009722292,0.47651905,0.072369345,0.0012647563],"about_ca_topic_score_codex":0.0000026410312,"about_ca_topic_score_gemma":0.00002285786,"teacher_disagreement_score":0.96564263,"about_ca_system_score_codex":0.000010127134,"about_ca_system_score_gemma":0.00018804465,"threshold_uncertainty_score":0.40892074},"labels":[],"label_agreement":null},{"id":"W4389471303","doi":"10.48550/arxiv.2312.03540","title":"FoodFusion: A Latent Diffusion Model for Realistic Food Image Generation","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Research Council Canada","keywords":"Computer science; Image (mathematics); Latent image; Field (mathematics); Artificial intelligence; Mathematics","score_opus":0.1818728617298258,"score_gpt":0.20884658350917024,"score_spread":0.02697372177934443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389471303","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020913843,0.000024443028,0.97639894,0.00032951968,0.0010241427,0.00069408346,0.000104636536,0.00029486118,0.00021553821],"genre_scores_gemma":[0.96576786,0.00019109478,0.030975923,0.0000799677,0.00036673236,0.000011794899,0.00010818979,0.00003895024,0.0024595044],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99767977,0.00012873323,0.0002709468,0.0013493805,0.00015179047,0.00041935305],"domain_scores_gemma":[0.99790144,0.00012260255,0.00026240744,0.0011032202,0.0004438173,0.00016649651],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037598412,0.00037197984,0.0003734543,0.0002204056,0.00037298,0.00025276357,0.0011885627,0.0002879432,0.000007633024],"category_scores_gemma":[0.000107767795,0.00039958538,0.00034404645,0.00037572472,0.00006348182,0.00036833753,0.0019092049,0.00028209286,0.000031707106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002092615,0.000059290614,0.000034682776,0.00004725364,0.000067767025,0.000021301588,0.00016420415,0.97440237,0.0012103801,0.02073071,0.0025568993,0.00068424403],"study_design_scores_gemma":[0.0004475398,0.00011030405,0.00012785255,0.000052718024,0.00008498848,8.75663e-7,0.000011443879,0.9563106,0.0003853369,0.041984137,0.00006594873,0.0004182639],"about_ca_topic_score_codex":0.0001133674,"about_ca_topic_score_gemma":0.0002987819,"teacher_disagreement_score":0.945423,"about_ca_system_score_codex":0.00023076069,"about_ca_system_score_gemma":0.00024404815,"threshold_uncertainty_score":0.9998456},"labels":[],"label_agreement":null},{"id":"W4389482528","doi":"10.54254/2753-8818/18/20230364","title":"Unpaired image neural style transfer based on Non-Local-Attention-Cycle-Consistent adversarial network","year":2023,"lang":"en","type":"article","venue":"Theoretical and Natural Science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Focus (optics); Artificial intelligence; Convolutional neural network; Artificial neural network; Image translation; Image (mathematics); Process (computing); Adversarial system; Field (mathematics); Translation (biology); Network architecture; Transfer of learning; Task (project management); Deep learning; Pattern recognition (psychology); Mathematics; Computer security","score_opus":0.004898753031094457,"score_gpt":0.21499793416206248,"score_spread":0.210099181130968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389482528","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14394894,0.00006635152,0.83733,0.010924626,0.0028137972,0.0005568837,0.000010150572,0.00043264768,0.003916597],"genre_scores_gemma":[0.9943075,0.000009315314,0.00438466,0.0009770931,0.00023681595,0.000011103109,0.000003810906,0.000009094443,0.000060617822],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99739957,0.00015419546,0.00024580184,0.0007565637,0.0006597685,0.00078411703],"domain_scores_gemma":[0.9987423,0.00040756768,0.00003144033,0.00040825695,0.00011916103,0.00029130923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011248617,0.00023728092,0.00023678291,0.00013791666,0.0007214339,0.0003364524,0.0008320893,0.00006584567,0.000057001907],"category_scores_gemma":[0.00013547615,0.00016849521,0.00013179104,0.0016596318,0.0024744775,0.0005727636,0.00025937267,0.00026248547,0.00007473311],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042260456,0.00017932963,0.00026628617,0.000029578283,0.000032875974,0.000133222,0.0004139847,0.044551566,0.028138826,0.7897227,0.0021396913,0.13396932],"study_design_scores_gemma":[0.00055795436,0.00017431527,0.007884307,0.00002849972,0.0000125091765,0.0000043580685,0.0000261351,0.9796122,0.0018194511,0.009542103,0.000083631065,0.00025459158],"about_ca_topic_score_codex":0.00001205543,"about_ca_topic_score_gemma":0.0000030146396,"teacher_disagreement_score":0.93506056,"about_ca_system_score_codex":0.000040501734,"about_ca_system_score_gemma":0.00008886347,"threshold_uncertainty_score":0.9117316},"labels":[],"label_agreement":null},{"id":"W4389919193","doi":"10.3390/technologies11060183","title":"Comparing Classical and Quantum Generative Learning Models for High-Fidelity Image Synthesis","year":2023,"lang":"en","type":"article","venue":"Technologies","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of Toronto","funders":"","keywords":"Computer science; Fidelity; Boltzmann machine; Artificial intelligence; Generative grammar; Machine learning; Probabilistic logic; Generative model; Field (mathematics); Trilemma; Representation (politics); Restricted Boltzmann machine; Task (project management); Deep learning; Mathematics","score_opus":0.060169588537285754,"score_gpt":0.2635156842606344,"score_spread":0.2033460957233486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389919193","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04880292,0.00016073073,0.9413343,0.0045513865,0.00012230584,0.00021282416,0.000004237015,0.0046607507,0.00015053865],"genre_scores_gemma":[0.8637215,0.00015203276,0.13588479,0.000021013873,0.00003441317,0.00012984402,0.000002385808,0.000011395216,0.000042617914],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986782,0.00007076732,0.00021164879,0.0005140983,0.00013883559,0.00038646048],"domain_scores_gemma":[0.9988411,0.0005869511,0.00008568312,0.00036109166,0.00009372025,0.000031444808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004082613,0.00018073349,0.00031610488,0.0001645655,0.00039668236,0.00022612832,0.0005507429,0.00012544131,6.7621215e-7],"category_scores_gemma":[0.00069697865,0.00015440733,0.000058137706,0.00043903073,0.00022794168,0.0005591138,0.0006992485,0.0002003286,0.000013565107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003294874,0.00006362612,0.00052706455,0.00006916872,0.00014193526,0.0000253038,0.0006105396,0.06519923,0.045740485,0.68929344,0.01606822,0.18222806],"study_design_scores_gemma":[0.00011775606,0.000052839758,0.00036933197,0.00001830042,0.000009691955,0.0000014648855,0.0004216349,0.8835798,0.039226457,0.0757749,0.00024923176,0.00017859534],"about_ca_topic_score_codex":0.000024983594,"about_ca_topic_score_gemma":0.000009900122,"teacher_disagreement_score":0.8183806,"about_ca_system_score_codex":0.00003062816,"about_ca_system_score_gemma":0.000021821044,"threshold_uncertainty_score":0.6296548},"labels":[],"label_agreement":null},{"id":"W4389952577","doi":"10.2139/ssrn.4668699","title":"Rotated Digit Recognition by Variational Autoencoders with Fixed Output Distributions","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Download; Numerical digit; Computer science; Arithmetic; World Wide Web; Mathematics","score_opus":0.018855934632371636,"score_gpt":0.22493539706457458,"score_spread":0.20607946243220293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389952577","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008783172,0.0003257259,0.9931777,0.003995753,0.0007676015,0.00027715726,0.00018365162,0.0002144089,0.00017965893],"genre_scores_gemma":[0.9200393,0.008362532,0.057178125,0.0003316514,0.0019402726,0.0002346723,0.0030865753,0.00017013443,0.008656721],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99611056,0.00025469981,0.0004628406,0.00065973663,0.0005688572,0.0019433044],"domain_scores_gemma":[0.99838644,0.00013445302,0.00049240387,0.00040700956,0.0004257301,0.00015398467],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00089309126,0.00037545332,0.00034553942,0.00017109573,0.0005107491,0.0007276882,0.0009868387,0.00021562079,0.000015071606],"category_scores_gemma":[0.00013208241,0.00032325048,0.00020011082,0.00044514073,0.00006648687,0.00055793027,0.0003659134,0.0028328446,0.000087295746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029494552,0.00095457473,0.00084518705,0.000067104294,0.006318035,0.00009468979,0.0008408603,0.5870072,0.00041651516,0.06253475,0.06166675,0.2789594],"study_design_scores_gemma":[0.001429596,0.0005737309,0.00095768564,0.00024383276,0.000238902,0.00031537234,0.00021607665,0.32419327,0.00041316618,0.66490674,0.0051861284,0.0013255028],"about_ca_topic_score_codex":0.00013432086,"about_ca_topic_score_gemma":0.00029402456,"teacher_disagreement_score":0.9359996,"about_ca_system_score_codex":0.0012206216,"about_ca_system_score_gemma":0.00440832,"threshold_uncertainty_score":0.999922},"labels":[],"label_agreement":null},{"id":"W4390021790","doi":"10.22214/ijraset.2023.57592","title":"Crafting Expressive Faces: A Comparative Exploration of Facial Animation Techniques in VToonify and AnimeGan","year":2023,"lang":"en","type":"article","venue":"International Journal for Research in Applied Science and Engineering Technology","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Animation; Multimedia; Human–computer interaction; Computer graphics (images)","score_opus":0.12142737945519509,"score_gpt":0.40342858986219715,"score_spread":0.28200121040700205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390021790","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42006776,0.00008388913,0.5752361,0.0035190904,0.00022357487,0.00049174804,0.0000037221637,0.00010189433,0.00027223074],"genre_scores_gemma":[0.9659266,0.000112572336,0.03384628,0.000004944805,0.00003292292,0.000069526104,6.1198705e-7,0.000002954513,0.0000035709854],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988727,0.000016793312,0.00022067456,0.00021959782,0.00041174993,0.00025850485],"domain_scores_gemma":[0.9993511,0.00014459211,0.000058267226,0.00007581541,0.00033394556,0.00003628628],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020222936,0.00006556165,0.000120078825,0.0020342674,0.00011879879,0.00017053574,0.0005644124,0.000054000513,3.4926666e-7],"category_scores_gemma":[0.00029255002,0.000061618826,0.00000949444,0.0015106002,0.00022974635,0.000736148,0.00029621055,0.00024646337,5.066472e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030706127,0.0000302782,0.00032676687,0.000016002134,0.0000119067845,0.000015778858,0.00281095,0.009293234,0.76657,0.09953996,0.00005819376,0.12129623],"study_design_scores_gemma":[0.00041916035,0.00014375236,0.0012617408,0.00014277377,5.9322895e-7,0.00001970214,0.0016574815,0.73762184,0.21766321,0.03969905,0.0012422925,0.00012838806],"about_ca_topic_score_codex":0.000008534623,"about_ca_topic_score_gemma":0.000009418046,"teacher_disagreement_score":0.7283286,"about_ca_system_score_codex":0.000092155424,"about_ca_system_score_gemma":0.00007697668,"threshold_uncertainty_score":0.2512743},"labels":[],"label_agreement":null},{"id":"W4390050574","doi":"10.3204/pubdb-2024-07638","title":"Secondary Vertex Reconstruction with MaskFormers","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Science and Technology Facilities Council; Natural Sciences and Engineering Research Council of Canada; CERN","keywords":"Vertex (graph theory); Physics; Set (abstract data type); Particle physics; Object (grammar); Class (philosophy); Computer science; Artificial intelligence; Combinatorics; Theoretical computer science; Mathematics; Graph; Programming language","score_opus":0.061350123345269576,"score_gpt":0.1659516779602291,"score_spread":0.10460155461495954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390050574","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032426693,0.000026128515,0.95967484,0.00020117218,0.0016890423,0.00024167808,0.000016352249,0.00038774204,0.005336342],"genre_scores_gemma":[0.9881282,0.00016622087,0.008251053,0.000077277924,0.00010927751,0.0000014242092,0.000016308371,0.00002663436,0.0032236318],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981773,0.00011768389,0.00016322877,0.0010893955,0.00008984834,0.00036253355],"domain_scores_gemma":[0.9984941,0.000087532986,0.00020958864,0.00091912015,0.00014190527,0.00014778231],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018158076,0.0003114863,0.00031160077,0.00024086176,0.00021238999,0.00016739413,0.001050542,0.00022069603,0.00006636253],"category_scores_gemma":[0.000016836852,0.00031238148,0.0001621241,0.0006152726,0.00014505806,0.0006350678,0.00095905125,0.0005531354,0.00018473846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007962193,0.00005380114,0.0022214989,0.0000923301,0.00045075093,0.0005733991,0.00028244732,0.93304366,0.0000760402,0.025447175,0.0035873414,0.03409196],"study_design_scores_gemma":[0.0005727505,0.000103395294,0.0026146942,0.00016737528,0.00008961897,0.000023368015,0.0002057344,0.9679582,0.00030837845,0.026256744,0.0010130262,0.0006867046],"about_ca_topic_score_codex":0.00018214896,"about_ca_topic_score_gemma":0.00015212361,"teacher_disagreement_score":0.9557015,"about_ca_system_score_codex":0.00016221132,"about_ca_system_score_gemma":0.00030162232,"threshold_uncertainty_score":0.9999328},"labels":[],"label_agreement":null},{"id":"W4390190371","doi":"10.1109/iccvw60793.2023.00092","title":"TransInpaint: Transformer-based Image Inpainting with Context Adaptation","year":2023,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Inpainting; Artificial intelligence; Computer science; Computer vision; Transformer; Encoder; Image (mathematics); Image texture; Pattern recognition (psychology); Filling-in; Image processing; Engineering","score_opus":0.01752823890312588,"score_gpt":0.21250603025177225,"score_spread":0.19497779134864637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390190371","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027872096,0.0000102821,0.9877165,0.0059799743,0.00008780714,0.00018434563,0.0000015581029,0.00043217847,0.0028001417],"genre_scores_gemma":[0.86511743,0.0000028862842,0.13398391,0.0006299786,0.000042351687,0.000016216136,0.0000059955482,0.000011429886,0.00018979481],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889076,0.000088818764,0.00017451914,0.0003134724,0.00022617586,0.00030625367],"domain_scores_gemma":[0.9993944,0.0001573253,0.000039775718,0.00023108211,0.00010561825,0.00007180313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003818737,0.00014076591,0.0001459712,0.000119900906,0.00022358786,0.00024711905,0.00028192525,0.00003508948,0.000053971344],"category_scores_gemma":[0.000021554637,0.000105401814,0.00006800458,0.00079584715,0.00007558944,0.0006061251,0.000009452499,0.00007872904,0.00009872946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000080689606,0.00011297765,0.00013009514,0.000050962688,0.00009090015,0.000085815955,0.007721614,0.089330874,0.036357965,0.015305137,0.0036721572,0.8470608],"study_design_scores_gemma":[0.0005807112,0.00012699579,0.0003810153,0.000024489062,0.000007709109,0.0000017189446,0.0005355151,0.9524884,0.042083975,0.00024320945,0.0033294694,0.00019674144],"about_ca_topic_score_codex":0.00010706927,"about_ca_topic_score_gemma":0.0002759072,"teacher_disagreement_score":0.8631576,"about_ca_system_score_codex":0.000016940865,"about_ca_system_score_gemma":0.0000826221,"threshold_uncertainty_score":0.42981613},"labels":[],"label_agreement":null},{"id":"W4390344759","doi":"10.1007/978-3-031-50072-5_34","title":"Seeing is No Longer Believing: A Survey on the State of Deepfakes, AI-Generated Humans, and Other Nonveridical Media","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Waterloo","funders":"","keywords":"Field (mathematics); Computer science; Power (physics); Key (lock); Data science; Artificial intelligence; Computer security","score_opus":0.03258205287803422,"score_gpt":0.2454872367028475,"score_spread":0.21290518382481327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390344759","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000816848,0.0003122236,0.99597824,0.0007535703,0.0013790107,0.00031784445,0.0000479905,0.000069505426,0.00032477162],"genre_scores_gemma":[0.8371425,0.00059278833,0.1340735,0.023762306,0.001983628,0.00002965652,0.000033596636,0.0002646474,0.0021173349],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964975,0.00019888251,0.0005287294,0.0012643522,0.0009561412,0.00055439444],"domain_scores_gemma":[0.9963104,0.0018250938,0.0002913062,0.0010477435,0.00038546088,0.00013996028],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002094094,0.0004936845,0.00056833256,0.0003851118,0.00029513356,0.00044835903,0.0019258286,0.0001937913,0.000037148282],"category_scores_gemma":[0.0003577017,0.00034490624,0.000103530394,0.00069700874,0.00091480266,0.00024686242,0.0010034825,0.0006777568,0.00005354695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010759418,0.00014920026,0.0019625926,0.00013147658,0.0002594661,0.00021012167,0.012089074,0.1281298,0.0024980714,0.008924561,0.004682125,0.84085596],"study_design_scores_gemma":[0.00029977658,0.0002620792,0.003114308,0.00062478025,0.000015114877,0.000007201845,3.1471302e-7,0.96642023,0.0070527494,0.019783918,0.0015712879,0.00084825687],"about_ca_topic_score_codex":0.00017537731,"about_ca_topic_score_gemma":0.00061638904,"teacher_disagreement_score":0.86190474,"about_ca_system_score_codex":0.000074082236,"about_ca_system_score_gemma":0.0002847915,"threshold_uncertainty_score":0.9999003},"labels":[],"label_agreement":null},{"id":"W4390450990","doi":"10.1145/3638770","title":"RAST: Restorable Arbitrary Style Transfer","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Multimedia Computing Communications and Applications","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Stylized fact; Style (visual arts); Computer science; Embedding; Content (measure theory); Image (mathematics); Information loss; Artificial intelligence; Mathematics; Art; Visual arts","score_opus":0.032278537162339326,"score_gpt":0.27748872485978454,"score_spread":0.2452101876974452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390450990","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010246908,0.00021402616,0.9905893,0.0060484665,0.00010172317,0.0005255438,0.000026116872,0.000661731,0.0008083895],"genre_scores_gemma":[0.7171478,0.0010517916,0.28084174,0.00030051343,0.0000713015,0.00028714212,0.000039675946,0.000023006616,0.00023698177],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984787,0.00017000077,0.00034619417,0.00048225807,0.00018963731,0.00033320003],"domain_scores_gemma":[0.9955606,0.001232092,0.000054145745,0.0028778508,0.00011250472,0.00016283544],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00036963407,0.00020633904,0.00020565304,0.00027479796,0.0015324666,0.00018793164,0.0019726336,0.000089281806,0.000016218186],"category_scores_gemma":[0.000021768135,0.0002124512,0.00010030492,0.001411907,0.00020961012,0.00030965803,0.00013123512,0.00038174933,0.00019731808],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050770336,0.00035538996,0.00005392103,0.000015619962,0.00007863212,0.0000011862066,0.0012943483,0.0070861178,0.0022311439,0.00885224,0.00055777625,0.9794685],"study_design_scores_gemma":[0.00049345556,0.000060724353,0.0010703012,0.00003893305,0.000034543256,0.000008067538,0.00024846845,0.9323528,0.001239131,0.0031090486,0.060981333,0.000363212],"about_ca_topic_score_codex":0.000055621123,"about_ca_topic_score_gemma":0.000027314647,"teacher_disagreement_score":0.97910535,"about_ca_system_score_codex":0.000031771924,"about_ca_system_score_gemma":0.00006143246,"threshold_uncertainty_score":0.9997674},"labels":[],"label_agreement":null},{"id":"W4390859152","doi":"10.31234/osf.io/zhmy7","title":"Deepfake Detection in Super-Recognizers and Police Officers","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Software deployment; Computer science; Identity (music); Face (sociological concept); Observer (physics); Generative grammar; Artificial intelligence; Computer security; Sociology; Software engineering; Acoustics","score_opus":0.013102421267306628,"score_gpt":0.23455131916560878,"score_spread":0.22144889789830216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390859152","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10708145,0.00096901075,0.86894184,0.0020424188,0.0035053047,0.00055163295,0.000007689216,0.00036213425,0.016538516],"genre_scores_gemma":[0.9792443,0.00014594285,0.019670617,0.00022474602,0.00020433874,0.00002724476,0.0000024645872,0.000016097658,0.0004642358],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985184,0.00010113395,0.00023774232,0.0007402432,0.00014650777,0.00025595934],"domain_scores_gemma":[0.99937135,0.00008373589,0.00004469567,0.00037057174,0.000047318077,0.00008231319],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002800543,0.00024445954,0.00024905638,0.00026901846,0.00004825952,0.00042268896,0.00037022296,0.00020630428,0.000019106094],"category_scores_gemma":[0.000024141416,0.00021244462,0.00008319254,0.00029795125,0.000040133447,0.00015731117,0.0015722463,0.00049363857,0.00004712081],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019059285,0.000060018672,0.0001677387,0.00023969775,0.00013686626,0.00002883178,0.0042355317,0.015128415,0.004074179,0.002000556,0.0018069737,0.9721021],"study_design_scores_gemma":[0.00028360673,0.000062411666,0.0015687993,0.00018204485,0.00003997329,0.000015797992,0.00026069375,0.971636,0.013336573,0.008846916,0.0030753857,0.0006917754],"about_ca_topic_score_codex":0.004481156,"about_ca_topic_score_gemma":0.005526399,"teacher_disagreement_score":0.97141033,"about_ca_system_score_codex":0.000086518245,"about_ca_system_score_gemma":0.00010863512,"threshold_uncertainty_score":0.866324},"labels":[],"label_agreement":null},{"id":"W4390872443","doi":"10.1109/iccv51070.2023.00700","title":"Shortcut-V2V: Compression Framework for Video-to-Video Translation based on Temporal Redundancy Reduction","year":2023,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Korea Creative Content Agency","keywords":"Computer science; Redundancy (engineering); Data compression; Video compression picture types; Block-matching algorithm; Video processing; Translation (biology); Video tracking; Inter frame; Frame (networking); Motion compensation; Computer vision; Block (permutation group theory); Artificial intelligence; Reference frame; Computer network","score_opus":0.0483407705981567,"score_gpt":0.30454541178281025,"score_spread":0.2562046411846535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390872443","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009893669,0.000020932235,0.9868657,0.008791283,0.0013356197,0.000665327,0.0000071664826,0.00044674892,0.00087788363],"genre_scores_gemma":[0.57987463,0.000003599084,0.41872647,0.00064570573,0.0003658183,0.00009228862,0.000025305128,0.000017545352,0.00024860987],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982959,0.00012164933,0.00030038977,0.0006054636,0.000325846,0.0003507434],"domain_scores_gemma":[0.9987516,0.0003667499,0.00007987424,0.00055639417,0.00010607662,0.00013932404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046119187,0.00019524313,0.0002072953,0.0002349459,0.00033248425,0.00019725604,0.0004174843,0.000104902974,0.00004565168],"category_scores_gemma":[0.00011615758,0.00016839612,0.00014043062,0.00094664766,0.000025348992,0.00042439377,0.00005216912,0.00013474927,0.00009008451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033647742,0.00021518949,0.00021389288,0.000057286004,0.000041354204,0.000007716911,0.0009178959,0.44623205,0.018018534,0.021701213,0.09671851,0.41553986],"study_design_scores_gemma":[0.0003268384,0.00027402682,0.00056212884,0.00014622221,0.000009135555,9.2101834e-7,0.00003778773,0.95132744,0.01938824,0.009291315,0.01837468,0.0002612429],"about_ca_topic_score_codex":0.000026168791,"about_ca_topic_score_gemma":0.0000082603165,"teacher_disagreement_score":0.5788853,"about_ca_system_score_codex":0.0000402555,"about_ca_system_score_gemma":0.000055352553,"threshold_uncertainty_score":0.68669945},"labels":[],"label_agreement":null},{"id":"W4390872836","doi":"10.1109/iccv51070.2023.02080","title":"AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networks","year":2023,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Style (visual arts); Computer science; Focus (optics); Metric (unit); Artificial intelligence; Image (mathematics); Perception; Pattern recognition (psychology); Psychology; Engineering","score_opus":0.013729332889720147,"score_gpt":0.2175545032269535,"score_spread":0.20382517033723335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390872836","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024254695,0.00005868872,0.9912918,0.0029355872,0.00054404244,0.00015294696,0.0000019635195,0.0005156401,0.0020738316],"genre_scores_gemma":[0.99478656,0.0000773267,0.0016570042,0.0010822641,0.0001769245,0.000022135917,0.0000074715917,0.000019990166,0.0021703227],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850255,0.000110257235,0.00020734241,0.00045882596,0.00023054598,0.00049047417],"domain_scores_gemma":[0.99919015,0.000063308486,0.000019250372,0.0005409923,0.000057507692,0.00012879247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025229243,0.00018905652,0.00019004312,0.000097953816,0.00017536388,0.00021279075,0.00069856824,0.00007905285,0.0002232895],"category_scores_gemma":[0.000005044581,0.0001558666,0.00012059552,0.00074232806,0.000040094852,0.00036019986,0.00015257677,0.00013105733,0.00051871006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006036068,0.00006991039,0.0006089027,0.0000092240425,0.000037567686,0.00010863638,0.00073924754,0.12304536,0.00024756885,0.0039875205,0.058390096,0.8127499],"study_design_scores_gemma":[0.00024373017,0.00006475235,0.0013621984,0.00001333526,0.000006177898,0.000009006204,0.00004699702,0.9848627,0.0005426032,0.00023611184,0.012353184,0.00025920293],"about_ca_topic_score_codex":0.00006688538,"about_ca_topic_score_gemma":0.000061600025,"teacher_disagreement_score":0.99236107,"about_ca_system_score_codex":0.000017516175,"about_ca_system_score_gemma":0.000024921064,"threshold_uncertainty_score":0.6667142},"labels":[],"label_agreement":null},{"id":"W4390873194","doi":"10.1109/iccv51070.2023.02081","title":"Controllable Person Image Synthesis with Pose-Constrained Latent Diffusion","year":2023,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Surrey Place Centre","funders":"","keywords":"Computer science; Rendering (computer graphics); Pose; Leverage (statistics); Artificial intelligence; Inference; Fidelity; View synthesis; Pixel; Exploit; Computer vision; Source code; Pattern recognition (psychology)","score_opus":0.013768208775007514,"score_gpt":0.20473991174761044,"score_spread":0.19097170297260294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390873194","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03673311,0.000047414782,0.91281635,0.0098484745,0.00045646162,0.00047052497,0.0000091302345,0.0010714306,0.038547125],"genre_scores_gemma":[0.9451482,0.00002227311,0.05095036,0.00028548817,0.0001176447,0.000036875615,0.000002715922,0.00001613562,0.0034202938],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862546,0.00009387849,0.00014431491,0.00043775683,0.00027668066,0.00042189244],"domain_scores_gemma":[0.999025,0.00026089483,0.00006014979,0.00041277442,0.0001199054,0.000121291254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028699927,0.0001863107,0.0002426978,0.000121679084,0.00023087059,0.00030214927,0.0004393529,0.000048406688,0.00024180814],"category_scores_gemma":[0.00008464726,0.00012456017,0.00008274016,0.00064743863,0.00007372197,0.00052005943,0.000115776726,0.00007543922,0.00038251083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023198641,0.00036830682,0.0024815514,0.000057016354,0.0004644703,0.00061669125,0.0021677148,0.0077060307,0.6902472,0.020635877,0.07363208,0.2013911],"study_design_scores_gemma":[0.001161631,0.00020698686,0.0059268926,0.00005397732,0.000038438702,0.000020299167,0.00036839154,0.9463996,0.042783722,0.00029492346,0.0022317243,0.0005133847],"about_ca_topic_score_codex":0.00010100254,"about_ca_topic_score_gemma":0.000021512764,"teacher_disagreement_score":0.9386936,"about_ca_system_score_codex":0.000026640886,"about_ca_system_score_gemma":0.00005111612,"threshold_uncertainty_score":0.50794166},"labels":[],"label_agreement":null},{"id":"W4390873488","doi":"10.59275/j.melba.2024-b87a","title":"Evaluation of pseudo-healthy image reconstruction for anomaly detection with deep generative models: Application to brain FDG PET","year":2024,"lang":"en","type":"article","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; F. Hoffmann-La Roche; Agence Nationale de la Recherche; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; Grand Équipement National De Calcul Intensif; BioClinica; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; Alzheimer's Association","keywords":"Autoencoder; Artificial intelligence; Computer science; Generative model; Anomaly detection; Deep learning; Pattern recognition (psychology); Ground truth; Anomaly (physics); Image (mathematics); Generative grammar; Computer vision","score_opus":0.016223693342653178,"score_gpt":0.29138998094582963,"score_spread":0.27516628760317646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390873488","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012488444,0.0004949546,0.9777557,0.008322995,0.00035849496,0.00052414945,0.0000039311335,0.000027674861,0.000023644161],"genre_scores_gemma":[0.7832595,0.000017713392,0.21616165,0.00014634292,0.0003550623,0.00003253474,0.000004159449,0.000014885792,0.000008134419],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981212,0.00047762034,0.0004386978,0.00021060322,0.00055929675,0.00019257172],"domain_scores_gemma":[0.9979711,0.0005806987,0.00035361046,0.00014378653,0.0008566767,0.00009411866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062662284,0.00012901147,0.00020436014,0.00026423452,0.00024870178,0.000108664,0.00029132765,0.000025404968,0.0000040136474],"category_scores_gemma":[0.00051450374,0.00008211661,0.00010102219,0.00044301053,0.00009359051,0.00062911026,0.000042605538,0.00024825925,8.1407063e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017329153,0.000024966528,0.000009621927,0.000037296126,0.000075672455,8.053549e-7,0.0007390209,0.13178155,0.0727033,0.00018707076,0.0001193962,0.794148],"study_design_scores_gemma":[0.0006084536,0.00063829386,0.000044336502,0.00008159562,0.00016235124,0.00026789843,0.00012562635,0.9878122,0.0052517746,0.004303466,0.00061162043,0.000092363836],"about_ca_topic_score_codex":0.000039421906,"about_ca_topic_score_gemma":0.000018164086,"teacher_disagreement_score":0.85603064,"about_ca_system_score_codex":0.00013064551,"about_ca_system_score_gemma":0.00018378222,"threshold_uncertainty_score":0.33486181},"labels":[],"label_agreement":null},{"id":"W4390874209","doi":"10.1109/iccv51070.2023.00041","title":"DS-Fusion: Artistic Typography via Discriminated and Stylized Diffusion","year":2023,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Typography; Legibility; Generator (circuit theory); Artificial intelligence; Discriminator; Stylized fact; Key (lock); Ground truth; Word (group theory); Character (mathematics); Natural language processing; Font; Semantics (computer science); Task (project management); Computer vision; Linguistics; Programming language; Art","score_opus":0.011453269806368302,"score_gpt":0.2210209749722023,"score_spread":0.209567705165834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390874209","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028418947,0.00008463994,0.96530443,0.0014311897,0.0003631083,0.00014394512,0.0000014878855,0.000378378,0.0038738411],"genre_scores_gemma":[0.98275286,0.00012404704,0.015321383,0.00021844228,0.000060519043,0.000010008321,0.000006005063,0.000007959039,0.0014987545],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990402,0.00007437213,0.00014296893,0.00033943614,0.00016052545,0.0002425377],"domain_scores_gemma":[0.9994215,0.000109112894,0.000035116136,0.00028843555,0.00004472446,0.000101140315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016234703,0.00012227237,0.00014164246,0.00014030996,0.00020997146,0.00013558751,0.0002421996,0.000041272433,0.00010971025],"category_scores_gemma":[0.000033402415,0.000090820235,0.00004887622,0.00079929986,0.000056184865,0.00023493406,0.00035498783,0.000060225484,0.000103724306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048212096,0.00019505355,0.0031028006,0.00004894915,0.00008462343,0.00014762316,0.0013396955,0.00048424632,0.11210527,0.04757738,0.031811945,0.8030542],"study_design_scores_gemma":[0.0006495817,0.00011329891,0.054032113,0.000025730977,0.000018874718,0.000009307681,0.000083596104,0.92466384,0.0034834282,0.010852189,0.005733244,0.000334809],"about_ca_topic_score_codex":0.000056098612,"about_ca_topic_score_gemma":0.000021569651,"teacher_disagreement_score":0.95433396,"about_ca_system_score_codex":0.0000055612627,"about_ca_system_score_gemma":0.000008778239,"threshold_uncertainty_score":0.37035415},"labels":[],"label_agreement":null},{"id":"W4391095530","doi":"10.1109/bigdata59044.2023.10386654","title":"Stabilizing Adversarial Training for Generative Networks","year":2023,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Machine learning; Generative grammar; Artificial intelligence; Classifier (UML); Adversarial system; Disjoint sets; Regularization (linguistics)","score_opus":0.06352876436490246,"score_gpt":0.27808057569914374,"score_spread":0.21455181133424128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391095530","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005907726,0.000034659606,0.9936482,0.0011832832,0.0013705796,0.00031977714,0.0000033122453,0.00043265958,0.0024167893],"genre_scores_gemma":[0.7291205,0.000022047861,0.26759514,0.00063314935,0.001322468,0.00010773395,0.00001707304,0.000021479626,0.0011604319],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859124,0.000080181984,0.00021980313,0.00045484907,0.00015276656,0.000501162],"domain_scores_gemma":[0.9990008,0.0004276022,0.000059450114,0.00031478642,0.00009937836,0.000097972945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056059763,0.00015881073,0.0002046567,0.00009447046,0.0003329302,0.0002051282,0.00046702407,0.00006798513,0.000028917446],"category_scores_gemma":[0.00012824494,0.00013754691,0.0001324872,0.0006230921,0.000036601825,0.00050812465,0.00017674764,0.00008156571,0.00002991211],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003341802,0.000028526598,0.000055535755,0.000008011521,0.00011022828,0.000010923781,0.0036011953,0.6114698,0.0037929032,0.100477204,0.03897975,0.24143252],"study_design_scores_gemma":[0.00040502215,0.00006813837,0.000110004024,0.0000055831806,0.0000064897995,0.0000010511592,0.0003034087,0.9842783,0.0015684316,0.0027903938,0.010267998,0.0001951694],"about_ca_topic_score_codex":0.000010987772,"about_ca_topic_score_gemma":0.000021488806,"teacher_disagreement_score":0.7285297,"about_ca_system_score_codex":0.000028499911,"about_ca_system_score_gemma":0.00006770386,"threshold_uncertainty_score":0.56090003},"labels":[],"label_agreement":null},{"id":"W4391341894","doi":"10.1109/silcon59133.2023.10404316","title":"Text-Conditioned Image Synthesis - A Review","year":2023,"lang":"en","type":"review","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Heritage College","funders":"","keywords":"Computer science; Image synthesis; Generative grammar; Probabilistic logic; Adversarial system; Image (mathematics); Field (mathematics); Task (project management); Artificial intelligence; Mathematics","score_opus":0.06796292178520617,"score_gpt":0.3395449716169356,"score_spread":0.2715820498317294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391341894","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.3535376e-10,0.81857395,0.17259403,0.0004281808,0.00037386204,0.0007800247,0.000029645138,0.00045569206,0.0067646177],"genre_scores_gemma":[1.6047812e-8,0.96905935,0.0256466,0.000462241,0.0003217188,0.00063173356,0.000034254823,0.00006559814,0.003778502],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99674547,0.00056721264,0.000884454,0.0009513976,0.00036935168,0.0004820917],"domain_scores_gemma":[0.99680483,0.0010725142,0.00042951555,0.0014140145,0.00011669109,0.00016241285],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007687606,0.0005923594,0.0023750358,0.0002455784,0.000185943,0.00031697523,0.0019346144,0.00019531931,0.0007006588],"category_scores_gemma":[0.00058217475,0.00042230403,0.0010741459,0.0015385629,0.00007012307,0.00054508046,0.0005960418,0.00028330047,0.007898161],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.152605e-8,0.000013664204,2.818792e-9,0.020790834,0.00012629018,0.00003190908,0.0000020580085,2.6366217e-7,1.2062313e-7,0.0014687666,0.11074548,0.8668205],"study_design_scores_gemma":[0.000020968428,0.0000095047135,1.10181624e-7,0.06057584,0.00052458426,0.000026099835,7.41773e-7,0.00027556275,0.0000027574463,0.00019227351,0.93789476,0.00047680584],"about_ca_topic_score_codex":0.000016115624,"about_ca_topic_score_gemma":0.0000040716905,"teacher_disagreement_score":0.86634374,"about_ca_system_score_codex":0.000079990634,"about_ca_system_score_gemma":0.0002790906,"threshold_uncertainty_score":0.99982285},"labels":[],"label_agreement":null},{"id":"W4391926338","doi":"10.1007/s11227-024-05912-5","title":"Meta generative image and text data augmentation optimization","year":2024,"lang":"en","type":"article","venue":"The Journal of Supercomputing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Discriminator; Computer science; Generator (circuit theory); Generative grammar; Artificial intelligence; Machine learning; Intuition; Domain (mathematical analysis); Generative model; Image (mathematics); Data mining; Pattern recognition (psychology); Mathematics","score_opus":0.06707860647216189,"score_gpt":0.2854487057895803,"score_spread":0.2183700993174184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391926338","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002810393,0.0049257013,0.98889893,0.002789932,0.00039914236,0.000057310997,0.0000026094983,0.00001915944,0.00009683782],"genre_scores_gemma":[0.50223565,0.00039742532,0.49664542,0.00019271573,0.00049062254,2.800676e-7,0.0000031199872,0.00000845441,0.00002633175],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989856,0.0002688233,0.0002858285,0.00015261966,0.00019247632,0.000114691386],"domain_scores_gemma":[0.9991358,0.0003664262,0.00008661206,0.00025959525,0.00011162099,0.00003998064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016212751,0.000097249875,0.00016194489,0.00007490035,0.00018710448,0.00045745188,0.0006422242,0.000019398962,0.000020133519],"category_scores_gemma":[0.000048783466,0.000055768538,0.000047405196,0.00023079096,0.0000470692,0.0018836211,0.00036780408,0.00014983575,0.0000028342488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014685616,0.000035972927,0.000018363931,0.000033824497,0.0016849088,0.000050213617,0.008347887,0.79996467,0.021493556,0.0019526668,0.0068218126,0.15958144],"study_design_scores_gemma":[0.000085789485,0.000039282113,0.000031042666,0.000029802082,0.0003131103,0.00014062873,0.0002006096,0.99667907,0.0017549708,0.00030415232,0.0003566392,0.00006487877],"about_ca_topic_score_codex":0.000015808084,"about_ca_topic_score_gemma":0.0000018008986,"teacher_disagreement_score":0.49942523,"about_ca_system_score_codex":0.00001833002,"about_ca_system_score_gemma":0.000049181468,"threshold_uncertainty_score":0.4411219},"labels":[],"label_agreement":null},{"id":"W4392619076","doi":"10.1145/3613904.3642803","title":"PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Usability; Modal; Field (mathematics); Image editing; Inpainting; Quality (philosophy); Image (mathematics); Human–computer interaction; Generative grammar; Artificial intelligence","score_opus":0.05568774798347245,"score_gpt":0.30236544286513256,"score_spread":0.2466776948816601,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392619076","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0070969,0.0005446758,0.9798252,0.0068834857,0.0015330301,0.0011438096,0.000010692117,0.00032532445,0.0026368997],"genre_scores_gemma":[0.23821187,0.000060707465,0.7578327,0.00064747734,0.00086972123,0.00023471238,0.00002021943,0.000033613698,0.0020889407],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99717075,0.00012479875,0.00046824053,0.0014734844,0.00034762057,0.00041509134],"domain_scores_gemma":[0.99877685,0.00003272266,0.00012880616,0.0007472063,0.00017548782,0.00013892057],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00044631315,0.00044782483,0.00039083706,0.00012589499,0.00020453305,0.001375137,0.0006470738,0.0001800555,0.00005051821],"category_scores_gemma":[0.000058402326,0.0003708725,0.00011244261,0.00022889859,0.00004446368,0.00030842025,0.0047738315,0.0005052833,0.00012736021],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026983884,0.000658851,0.0000775314,0.0014293011,0.0008163901,0.00018522989,0.021567296,0.06064341,0.29314643,0.030374514,0.091572694,0.49950135],"study_design_scores_gemma":[0.00019767923,0.00006864912,0.00013859481,0.00017581334,0.00003802517,0.000006843199,0.000049152608,0.9701791,0.021733008,0.0022186642,0.0046320558,0.00056245713],"about_ca_topic_score_codex":0.00024675735,"about_ca_topic_score_gemma":0.00007859006,"teacher_disagreement_score":0.90953565,"about_ca_system_score_codex":0.00009484207,"about_ca_system_score_gemma":0.0001446312,"threshold_uncertainty_score":0.9998743},"labels":[],"label_agreement":null},{"id":"W4392657315","doi":"10.1016/j.forsciint.2024.111986","title":"Empirical investigation of passive blood drop trajectory and first point of contact on inclined surfaces","year":2024,"lang":"en","type":"article","venue":"Forensic Science International","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University; Advantage Forensics (Canada)","funders":"","keywords":"Ellipse; Drop (telecommunication); Trajectory; Contact angle; Point (geometry); Geometry; Mechanics; Geodesy; Physics; Materials science; Mathematics; Geology; Engineering; Composite material; Mechanical engineering","score_opus":0.020210598331138942,"score_gpt":0.27130675482951777,"score_spread":0.25109615649837885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392657315","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95284295,0.00007003751,0.042486746,0.0028387145,0.0010806865,0.00009104187,0.0000131889365,0.0000272301,0.0005494321],"genre_scores_gemma":[0.98933256,0.000012815703,0.010439633,0.00010749679,0.00007503633,0.000003097299,0.0000020602665,0.000003062415,0.000024259514],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987957,0.000029872417,0.00023984577,0.000321461,0.0004966887,0.0001164199],"domain_scores_gemma":[0.9991462,0.00031626297,0.000097651115,0.00014462332,0.00023550616,0.00005976109],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040159922,0.00008656566,0.0001235716,0.00021805064,0.00007013793,0.00010763459,0.00043502968,0.000027432052,0.000017969194],"category_scores_gemma":[0.00023595412,0.00006740707,0.000045687364,0.0004187127,0.0004997666,0.00060960057,0.00014377685,0.000070239395,0.0000026546795],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015685643,0.00038362516,0.075929455,0.00016226093,0.00046350632,0.00008396793,0.019089308,0.017024476,0.6205561,0.20565335,0.0056680213,0.054829035],"study_design_scores_gemma":[0.00027845424,0.000437802,0.10767373,0.00022345848,0.000014507078,0.00001364031,0.00007871535,0.55250955,0.33045045,0.007976013,0.00020388237,0.00013978651],"about_ca_topic_score_codex":0.000047378428,"about_ca_topic_score_gemma":0.000029342742,"teacher_disagreement_score":0.5354851,"about_ca_system_score_codex":0.000028529716,"about_ca_system_score_gemma":0.00016796432,"threshold_uncertainty_score":0.27487803},"labels":[],"label_agreement":null},{"id":"W4392890134","doi":"10.1016/j.compbiomed.2024.108296","title":"DSG-GAN:A dual-stage-generator-based GAN for cross-modality synthesis from PET to CT","year":2024,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg; Research Manitoba; Western University","funders":"","keywords":"Discriminator; Computer science; Artificial intelligence; Leverage (statistics); Context (archaeology); Computer vision; Generator (circuit theory); Pattern recognition (psychology); Attenuation; Detector; Optics","score_opus":0.02628887715150982,"score_gpt":0.3379311576683566,"score_spread":0.3116422805168467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392890134","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07552953,0.0012246039,0.9092064,0.0107248435,0.0027068672,0.0003049169,0.000057965866,0.00010732038,0.00013754852],"genre_scores_gemma":[0.93586344,0.000049053855,0.060280524,0.0028300514,0.00081136083,0.00006149236,0.000032229083,0.000012094051,0.000059731432],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998218,0.00019728071,0.00034067486,0.00079272775,0.000090012225,0.0003612846],"domain_scores_gemma":[0.9977538,0.0015706017,0.00004773114,0.00039744092,0.000059985414,0.00017041336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007448469,0.00023564084,0.000432593,0.0001931771,0.00014763714,0.00009184148,0.00039344747,0.00006744423,0.000029606601],"category_scores_gemma":[0.00024737223,0.0001786746,0.00006576272,0.00032139232,0.00026258576,0.00012992189,0.00011478556,0.0001444626,0.000007502825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005611383,0.00044589743,0.030182373,0.00058266637,0.0008191279,0.0014683028,0.0039595296,0.037558343,0.08876236,0.11663723,0.06482996,0.6541931],"study_design_scores_gemma":[0.0014725133,0.0006538091,0.012342235,0.0005242346,0.000052511466,0.000024172505,0.000048523398,0.89355254,0.014304461,0.011916347,0.06448429,0.00062435895],"about_ca_topic_score_codex":0.00021065024,"about_ca_topic_score_gemma":0.000055722703,"teacher_disagreement_score":0.8603339,"about_ca_system_score_codex":0.000047134483,"about_ca_system_score_gemma":0.00007847305,"threshold_uncertainty_score":0.7286139},"labels":[],"label_agreement":null},{"id":"W4393156675","doi":"10.1609/aaai.v38i10.29065","title":"Turning Waste into Wealth: Leveraging Low-Quality Samples for Enhancing Continuous Conditional Generative Adversarial Networks","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Generative grammar; Adversarial system; Generative adversarial network; Quality (philosophy); Environmental economics; Computer science; Environmental science; Economics; Artificial intelligence; Deep learning","score_opus":0.06579381498993259,"score_gpt":0.3122054445825523,"score_spread":0.2464116295926197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393156675","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01759104,0.00015738205,0.9759016,0.003056958,0.0019238408,0.0006286022,0.000018626864,0.00012575975,0.00059620873],"genre_scores_gemma":[0.9778515,0.00004154424,0.02050527,0.00035958836,0.0009966101,0.00008438726,0.000006441595,0.000023188597,0.00013148252],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99717104,0.00007555312,0.00087909517,0.00084802706,0.00049261795,0.0005336534],"domain_scores_gemma":[0.9975387,0.00081259006,0.0004097405,0.00025366084,0.0008618289,0.0001234701],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013755449,0.0003509589,0.0004611446,0.0001482299,0.00059294305,0.00082933763,0.00126175,0.0001323904,0.000048964055],"category_scores_gemma":[0.0007876348,0.00027547436,0.0002830442,0.0005771585,0.00029029005,0.00081110286,0.00035856562,0.0004175214,0.000016959491],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010345567,0.000068711764,0.000022220513,0.00013493004,0.00009163142,0.000001024358,0.0034438404,0.02360352,0.1480099,0.7662811,0.00060442474,0.057635225],"study_design_scores_gemma":[0.000038966686,0.0001075424,0.000014697692,0.00037546988,0.000019407224,0.0000020037658,0.00076451735,0.5216597,0.37775332,0.098855674,0.00016871885,0.00024003207],"about_ca_topic_score_codex":0.000094991316,"about_ca_topic_score_gemma":0.00005219167,"teacher_disagreement_score":0.96026045,"about_ca_system_score_codex":0.000121799305,"about_ca_system_score_gemma":0.00025288964,"threshold_uncertainty_score":0.9999697},"labels":[],"label_agreement":null},{"id":"W4393218562","doi":"10.3390/e26040290","title":"A Unifying Generator Loss Function for Generative Adversarial Networks","year":2024,"lang":"en","type":"article","venue":"Entropy","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Discriminator; MNIST database; Divergence (linguistics); Generator (circuit theory); Function (biology); Mathematics; Applied mathematics; Computer science; Algorithm; Topology (electrical circuits); Artificial neural network; Artificial intelligence; Combinatorics; Power (physics); Physics; Quantum mechanics; Telecommunications","score_opus":0.013217087501533779,"score_gpt":0.2373218435313356,"score_spread":0.22410475602980182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393218562","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00052764785,0.0016952305,0.989551,0.0010479725,0.0063359733,0.00034087402,0.0000091195625,0.0002685497,0.00022360517],"genre_scores_gemma":[0.8790448,0.00007763262,0.11269366,0.00071798,0.006477814,0.00012106297,0.000026514881,0.000035023175,0.0008055574],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984842,0.00011118111,0.00023257872,0.00058243645,0.00018167608,0.0004079156],"domain_scores_gemma":[0.99925053,0.00017450911,0.00004947006,0.00031392917,0.00010333495,0.00010820701],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028330635,0.00021373686,0.00019311988,0.00009303709,0.00029072835,0.0005944169,0.0003416676,0.00009654149,0.000054122404],"category_scores_gemma":[0.0000394507,0.00018425351,0.00018306964,0.0003792829,0.0000420863,0.0006676103,0.00011351037,0.00015166948,0.00004731833],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013401474,0.00007110121,0.00005416874,0.00003912,0.00042759517,0.000065267006,0.0007014287,0.21447112,0.015936334,0.60199577,0.07646897,0.089635156],"study_design_scores_gemma":[0.0003562657,0.0001328952,0.000026749754,0.000020923708,0.000037175283,0.000004979895,0.000014481362,0.9002447,0.0038356732,0.0032525072,0.09185704,0.00021662623],"about_ca_topic_score_codex":0.000010892802,"about_ca_topic_score_gemma":0.000006198359,"teacher_disagreement_score":0.8785171,"about_ca_system_score_codex":0.000087970286,"about_ca_system_score_gemma":0.00010231684,"threshold_uncertainty_score":0.751364},"labels":[],"label_agreement":null},{"id":"W4393561234","doi":"10.1117/12.3006482","title":"MACAW 3D: A masked causal normalizing flow method for counterfactual 3D brain image generation","year":2024,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Children's Hospital; Ontario Brain Institute; University of Calgary","funders":"","keywords":"Counterfactual thinking; Generative grammar; Computer science; Artificial intelligence; Deep learning; Biobank; Generative model; Machine learning; Image (mathematics); Perspective (graphical); Psychology; Bioinformatics","score_opus":0.025487416838933873,"score_gpt":0.29895321946930403,"score_spread":0.2734658026303702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393561234","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012343173,0.00020858429,0.9927921,0.0029718475,0.001394439,0.00032998828,0.000024757997,0.0002634334,0.0018913848],"genre_scores_gemma":[0.03114243,0.000010176549,0.9642975,0.0013870983,0.0009850153,0.000060194972,0.000027267737,0.000025141426,0.002065224],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983246,0.00016269811,0.00028819148,0.00060498883,0.00023043327,0.0003891233],"domain_scores_gemma":[0.9989954,0.00042707208,0.000040901876,0.00032571823,0.00012057967,0.000090329275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083955505,0.00022123141,0.00021018696,0.000115770905,0.00021620344,0.0010136314,0.00037464756,0.00008145973,0.00016639329],"category_scores_gemma":[0.00008958943,0.00018401122,0.00011896587,0.00027494796,0.00002868652,0.0012057319,0.00015004534,0.00011831325,0.00007396087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020900889,0.000046372028,0.0000032803491,0.000072587056,0.00016946722,0.000039249993,0.002025589,0.019660685,0.2845042,0.015414831,0.21360148,0.46444136],"study_design_scores_gemma":[0.00019803533,0.00007997512,0.000005327434,0.000015672575,0.000019456182,0.000015513688,0.000025236315,0.9224764,0.03289218,0.00037350002,0.04366754,0.000231145],"about_ca_topic_score_codex":0.00010550867,"about_ca_topic_score_gemma":0.00008986452,"teacher_disagreement_score":0.90281576,"about_ca_system_score_codex":0.000065144784,"about_ca_system_score_gemma":0.00010358595,"threshold_uncertainty_score":0.9774471},"labels":[],"label_agreement":null},{"id":"W4394597431","doi":"10.1109/csce60160.2023.00315","title":"Multi-Modality Image Inpainting Using Generative Adversarial Networks","year":2023,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inpainting; Adversarial system; Modality (human–computer interaction); Computer science; Artificial intelligence; Generative grammar; Image (mathematics); Computer vision; Generative adversarial network","score_opus":0.0424320420686888,"score_gpt":0.28742323972737605,"score_spread":0.24499119765868724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394597431","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042699696,0.00002419479,0.99200267,0.00090295624,0.0012209755,0.00021513918,0.0000025223621,0.0005284339,0.00083312026],"genre_scores_gemma":[0.51426935,0.000012142379,0.4842786,0.00036192426,0.00068930024,0.000008799987,0.000006860629,0.000017457525,0.00035558827],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978011,0.00032064592,0.00034719176,0.00064466766,0.00026187827,0.0006244956],"domain_scores_gemma":[0.99884224,0.00018188504,0.00012487445,0.00053891604,0.00017135325,0.00014075257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092799147,0.0002473705,0.0002755127,0.0001366929,0.00048477584,0.00038983615,0.0006699646,0.00010540964,0.00005643172],"category_scores_gemma":[0.00016666985,0.00022016295,0.00015270454,0.0011534789,0.00009025032,0.0010321562,0.0006771832,0.00019642568,0.000102534126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014746216,0.00009233896,0.0005639264,0.000009562485,0.00012684437,0.00008429546,0.0009815048,0.90985847,0.05619056,0.005364954,0.0066758543,0.020036964],"study_design_scores_gemma":[0.0004156118,0.000018469678,0.0010702135,0.000009519094,0.000009592792,0.0000031974039,0.000083023246,0.9928208,0.0045580617,0.00036336895,0.0003662428,0.00028187816],"about_ca_topic_score_codex":0.00026039418,"about_ca_topic_score_gemma":0.000049176506,"teacher_disagreement_score":0.5099994,"about_ca_system_score_codex":0.00006966133,"about_ca_system_score_gemma":0.00006654209,"threshold_uncertainty_score":0.8977985},"labels":[],"label_agreement":null},{"id":"W4396512602","doi":"10.1111/cgf.15063","title":"State of the Art on Diffusion Models for Visual Computing","year":2024,"lang":"en","type":"article","venue":"Computer Graphics Forum","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Samsung; Deutsche Forschungsgemeinschaft; Stanford Institute for Human-Centered Artificial Intelligence, Stanford University","keywords":"Computer science; Computer graphics; Field (mathematics); Generative grammar; Personalization; Artificial intelligence; Graphics; Data science; Generative model; Human–computer interaction; Computer graphics (images); World Wide Web","score_opus":0.015263880359530402,"score_gpt":0.2468639245447087,"score_spread":0.2316000441851783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396512602","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052088574,0.00015076263,0.9902776,0.0015472502,0.0022439014,0.00031432798,0.000008779053,0.00010733233,0.0001411882],"genre_scores_gemma":[0.9725551,0.000020244013,0.02621802,0.0008806065,0.00019263856,0.0000070331507,0.0000033060815,0.000018032553,0.000105046754],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865794,0.00007530039,0.00027215623,0.00041319264,0.00026019875,0.00032122896],"domain_scores_gemma":[0.9990394,0.00031926768,0.00007910294,0.00040673665,0.00010270727,0.000052779516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029369618,0.00017399939,0.0001917553,0.00013695707,0.00023331895,0.00021653225,0.0007067694,0.000044663757,7.6893e-7],"category_scores_gemma":[0.0000074662967,0.00011747967,0.0002758495,0.00051664934,0.00007565529,0.00027138225,0.0005061012,0.00015786242,0.000004754279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017830358,0.00014354671,0.00008874695,0.00008748891,0.00011125367,0.0000045439388,0.00067302573,0.16989636,0.0005351642,0.5251051,0.024453389,0.27888352],"study_design_scores_gemma":[0.0001435654,0.00017173376,0.00018238975,0.00014739642,0.0000075572607,0.0000023245257,0.0000028075833,0.94519866,0.0015751662,0.046779424,0.005656776,0.000132181],"about_ca_topic_score_codex":0.0000042249044,"about_ca_topic_score_gemma":0.0000062623653,"teacher_disagreement_score":0.9673462,"about_ca_system_score_codex":0.000015967236,"about_ca_system_score_gemma":0.0000445813,"threshold_uncertainty_score":0.4790682},"labels":[],"label_agreement":null},{"id":"W4399086070","doi":"10.1111/exsy.13618","title":"Efficient integration of perceptual variational autoencoder into dynamic latent scale generative adversarial network","year":2024,"lang":"en","type":"article","venue":"Expert Systems","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Discriminator; Computer science; Latent variable; Autoencoder; Encoder; Backpropagation; Artificial intelligence; Probabilistic latent semantic analysis; Feature (linguistics); Pattern recognition (psychology); Artificial neural network; Algorithm; Telecommunications","score_opus":0.011806014668047086,"score_gpt":0.2510093352804046,"score_spread":0.2392033206123575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399086070","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002502699,0.002072676,0.9867558,0.0006001684,0.007184567,0.0003400901,0.000008650785,0.00014890888,0.00038646834],"genre_scores_gemma":[0.8989999,0.000023463428,0.09904353,0.00009109343,0.0012944707,0.000067570036,0.000020877684,0.000017886568,0.00044118895],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978244,0.00032258878,0.00050665974,0.0005571502,0.000498957,0.00029027183],"domain_scores_gemma":[0.9990889,0.00016367673,0.00011174197,0.00035880855,0.00018914611,0.00008771355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005395747,0.00023024657,0.00031248791,0.00011757833,0.00020052784,0.00029457436,0.0004058773,0.0001162444,0.000046324716],"category_scores_gemma":[0.000030687956,0.00018280336,0.00015665506,0.00044936186,0.00007529807,0.00027161016,0.00014985274,0.00014157813,0.000059617196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016977949,0.000054188346,0.0000088486,0.000019444493,0.0000918044,0.0000070216956,0.013762157,0.9334022,0.019044532,0.022976378,0.0055792443,0.005037226],"study_design_scores_gemma":[0.00016569847,0.000076492164,0.00021253755,0.00014489987,0.000010395118,0.000008607373,0.00027934072,0.9962027,0.0006809972,0.000185517,0.0018330482,0.00019977022],"about_ca_topic_score_codex":0.0004532071,"about_ca_topic_score_gemma":0.00004504872,"teacher_disagreement_score":0.8964972,"about_ca_system_score_codex":0.00021806902,"about_ca_system_score_gemma":0.000167431,"threshold_uncertainty_score":0.74545044},"labels":[],"label_agreement":null},{"id":"W4399353100","doi":"10.48550/arxiv.2405.20448","title":"Knockout: A simple way to handle missing inputs","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; University of Southern California; Biogen; BioClinica; Meso Scale Diagnostics; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Association; Canadian Institutes of Health Research; National Science Foundation","keywords":"Simple (philosophy); Computer science; Set (abstract data type); Epistemology; Philosophy","score_opus":0.059712189534217204,"score_gpt":0.19686707884902352,"score_spread":0.13715488931480632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399353100","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034392845,0.00016959645,0.9577919,0.0010073239,0.0013001525,0.0002995533,0.000020952957,0.00031948162,0.0046981513],"genre_scores_gemma":[0.98809916,0.000032799588,0.0078091314,0.00043641042,0.00030691348,0.0000014151574,0.000008502059,0.000028939075,0.0032767255],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997592,0.00014836715,0.00022177558,0.0014437407,0.00011167295,0.0004824687],"domain_scores_gemma":[0.9981364,0.0000981442,0.00011522425,0.0011802323,0.00014713856,0.0003228385],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025346567,0.0003879928,0.00040784213,0.00033980983,0.00022905067,0.00053195364,0.0016095723,0.0002310701,0.000059667214],"category_scores_gemma":[0.00005572477,0.0004155641,0.00028670544,0.0008730152,0.000058103586,0.00024702595,0.0049062558,0.00055812555,0.0005464411],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003142439,0.000106863146,0.00012731992,0.0001578399,0.0002652873,0.0008918452,0.0012222845,0.9166131,0.0011604156,0.037094653,0.0150172245,0.02731172],"study_design_scores_gemma":[0.00021378387,0.00006730803,0.00022881849,0.00023688083,0.00009831656,0.000004606954,0.000032448417,0.88981116,0.0029430527,0.08931161,0.016316017,0.00073599635],"about_ca_topic_score_codex":0.00019964168,"about_ca_topic_score_gemma":0.00010004045,"teacher_disagreement_score":0.9537063,"about_ca_system_score_codex":0.00021090817,"about_ca_system_score_gemma":0.00018481047,"threshold_uncertainty_score":0.9998296},"labels":[],"label_agreement":null},{"id":"W4399620502","doi":"10.1109/isas61044.2024.10552390","title":"Text-guided image generation based on ternary attention mechanism generative adversarial network","year":2024,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"National Natural Science Foundation of China","keywords":"Adversarial system; Computer science; Mechanism (biology); Generative grammar; Ternary operation; Generative adversarial network; Image (mathematics); Artificial intelligence; Theoretical computer science; Programming language; Physics","score_opus":0.021350484245696372,"score_gpt":0.2507202156398528,"score_spread":0.22936973139415642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399620502","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005978457,0.00008690272,0.9830648,0.0032702629,0.004382224,0.00036640436,0.0000065781983,0.00046477836,0.0077602463],"genre_scores_gemma":[0.6311183,0.000020850666,0.3595933,0.0022308885,0.0046087713,0.000062600055,0.000056383393,0.000038050028,0.0022708185],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974739,0.00032139148,0.0003845433,0.0009004365,0.00046419486,0.00045554765],"domain_scores_gemma":[0.99896073,0.00013571035,0.00007522077,0.0005693107,0.00012963581,0.00012938106],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00058566825,0.00033058124,0.00024033817,0.0001684641,0.00035120302,0.00094789674,0.00049763947,0.0001270894,0.0003022712],"category_scores_gemma":[0.000036808917,0.00027366288,0.00022451911,0.0005630742,0.000042735857,0.001070924,0.00015242361,0.00021039067,0.00037470323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034679786,0.00015848436,0.000020319532,0.000025110086,0.00016440396,0.00020947683,0.00019554974,0.29173785,0.17701773,0.265482,0.22733675,0.03761764],"study_design_scores_gemma":[0.00032938863,0.00017523563,0.00006272421,0.000044676402,0.000024949217,0.000006781828,0.0000062283048,0.968903,0.022648154,0.0042810687,0.003190489,0.00032729335],"about_ca_topic_score_codex":0.000046131812,"about_ca_topic_score_gemma":0.000020652076,"teacher_disagreement_score":0.67716515,"about_ca_system_score_codex":0.0001272769,"about_ca_system_score_gemma":0.00013566838,"threshold_uncertainty_score":0.99997157},"labels":[],"label_agreement":null},{"id":"W4399817052","doi":"10.1002/cjce.25370","title":"Gnireteet","year":2024,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science","score_opus":0.0074232510996741045,"score_gpt":0.17987014068018106,"score_spread":0.17244688958050697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399817052","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020946458,0.0055893813,0.9578276,0.0115968445,0.0027913922,0.000057523386,0.0000021719045,0.000053917585,0.0011346574],"genre_scores_gemma":[0.9940683,0.0000016758452,0.0054033934,0.00008747275,0.00040610795,3.8473763e-7,8.3340396e-8,0.0000059142126,0.000026648691],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99955887,0.000008454382,0.00012375829,0.000058406207,0.00009030915,0.0001601998],"domain_scores_gemma":[0.99955916,0.000079416204,0.000017019804,0.00010776013,0.000039656083,0.00019699546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021509884,0.000059558955,0.00007773657,0.00007056315,0.000032296546,0.00023758509,0.00046196254,0.000025924597,0.000015571655],"category_scores_gemma":[0.000079045385,0.000038985225,0.00007025957,0.00019623512,0.000021249432,0.00019211456,0.000015720258,0.00020113248,0.000007979253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004919341,0.000009405983,0.00003475624,0.0000970859,0.0004615634,0.0014632195,0.0033572472,0.2987593,0.33129767,0.17871599,0.048892908,0.13690594],"study_design_scores_gemma":[0.000063332016,0.000018580407,0.000020414866,0.00012999274,0.00001622943,0.00032542777,0.0000029062041,0.8414683,0.108321354,0.0014304364,0.048062183,0.00014088576],"about_ca_topic_score_codex":0.00015197962,"about_ca_topic_score_gemma":0.000026503465,"teacher_disagreement_score":0.9731219,"about_ca_system_score_codex":0.000069478425,"about_ca_system_score_gemma":0.0002606926,"threshold_uncertainty_score":0.22910385},"labels":[],"label_agreement":null},{"id":"W4399828306","doi":"10.32920/26052700.v1","title":"Novel Generative Adversarial Network Architectures for Generating image Data","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Adversarial system; Generative grammar; Image (mathematics); Computer science; Generative adversarial network; Artificial intelligence","score_opus":0.051716472949168375,"score_gpt":0.2978354787237932,"score_spread":0.2461190057746248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399828306","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013659055,0.0014123007,0.98211014,0.0028429881,0.008671012,0.001356629,0.000715475,0.00047054418,0.0022843368],"genre_scores_gemma":[0.014609979,0.000024131796,0.9677226,0.0011276017,0.014649121,0.00021846447,0.00053129357,0.00008756247,0.0010292706],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99498594,0.00019501043,0.0007553597,0.002695925,0.00046629907,0.0009014616],"domain_scores_gemma":[0.99544084,0.0005086024,0.00031398455,0.003249748,0.0002847611,0.0002020632],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0012072348,0.00079455366,0.0007866441,0.00015787347,0.00047390832,0.002013463,0.004647953,0.00039917737,0.00004602472],"category_scores_gemma":[0.00029696224,0.0006630593,0.00038558242,0.0003339476,0.00012600094,0.00018961987,0.01734435,0.0010290626,0.00003682597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027919756,0.00006601816,0.0000016241058,0.00015922227,0.00061124633,0.00001643065,0.00045693817,0.7840834,0.008137557,0.012666657,0.15687291,0.036900025],"study_design_scores_gemma":[0.00036453985,0.000056429493,0.0000047905896,0.00012640723,0.00013563939,0.000010174578,0.000014873064,0.9584584,0.0025695942,0.030045137,0.0074421978,0.0007717872],"about_ca_topic_score_codex":0.00021214307,"about_ca_topic_score_gemma":0.00030485302,"teacher_disagreement_score":0.17437498,"about_ca_system_score_codex":0.0000923386,"about_ca_system_score_gemma":0.00068267976,"threshold_uncertainty_score":0.99958205},"labels":[],"label_agreement":null},{"id":"W4399828421","doi":"10.32920/26052700","title":"Novel Generative Adversarial Network Architectures for Generating image Data","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Adversarial system; Generative grammar; Image (mathematics); Computer science; Generative adversarial network; Artificial intelligence","score_opus":0.051716472949168375,"score_gpt":0.2978354787237932,"score_spread":0.2461190057746248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399828421","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013659055,0.0014123007,0.98211014,0.0028429881,0.008671012,0.001356629,0.000715475,0.00047054418,0.0022843368],"genre_scores_gemma":[0.014609979,0.000024131796,0.9677226,0.0011276017,0.014649121,0.00021846447,0.00053129357,0.00008756247,0.0010292706],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99498594,0.00019501043,0.0007553597,0.002695925,0.00046629907,0.0009014616],"domain_scores_gemma":[0.99544084,0.0005086024,0.00031398455,0.003249748,0.0002847611,0.0002020632],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0012072348,0.00079455366,0.0007866441,0.00015787347,0.00047390832,0.002013463,0.004647953,0.00039917737,0.00004602472],"category_scores_gemma":[0.00029696224,0.0006630593,0.00038558242,0.0003339476,0.00012600094,0.00018961987,0.01734435,0.0010290626,0.00003682597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027919756,0.00006601816,0.0000016241058,0.00015922227,0.00061124633,0.00001643065,0.00045693817,0.7840834,0.008137557,0.012666657,0.15687291,0.036900025],"study_design_scores_gemma":[0.00036453985,0.000056429493,0.0000047905896,0.00012640723,0.00013563939,0.000010174578,0.000014873064,0.9584584,0.0025695942,0.030045137,0.0074421978,0.0007717872],"about_ca_topic_score_codex":0.00021214307,"about_ca_topic_score_gemma":0.00030485302,"teacher_disagreement_score":0.17437498,"about_ca_system_score_codex":0.0000923386,"about_ca_system_score_gemma":0.00068267976,"threshold_uncertainty_score":0.99958205},"labels":[],"label_agreement":null},{"id":"W4400335279","doi":"10.1007/s11042-024-19365-8","title":"SFI-Swin: symmetric face inpainting with swin transformer by distinctly learning face components distributions","year":2024,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Inpainting; Transformer; Face (sociological concept); Artificial intelligence; Computer vision; Pattern recognition (psychology); Image (mathematics); Electrical engineering","score_opus":0.014710464365952837,"score_gpt":0.22998917090018614,"score_spread":0.2152787065342333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400335279","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034956299,0.0009317057,0.992117,0.0015673887,0.00006105734,0.00050331745,0.00016510738,0.00019931326,0.0009595092],"genre_scores_gemma":[0.9756012,0.000122016376,0.022981137,0.00004674855,0.00011820227,0.00030097621,0.00025656153,0.000016511642,0.0005566381],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986769,0.00005750942,0.00023044924,0.0005168726,0.0001996543,0.00031859873],"domain_scores_gemma":[0.99908096,0.00042432678,0.000052563697,0.00023189385,0.00005796301,0.00015229534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018851165,0.00019938716,0.00018293948,0.00007814453,0.0005303292,0.0006054659,0.00030280542,0.00006091917,0.000020201802],"category_scores_gemma":[0.000040160536,0.00016101486,0.000057227215,0.0008916889,0.000101483274,0.0005157314,0.00006536184,0.0002652756,0.000057063116],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000056528297,0.00016429099,0.001166999,0.00006395863,0.00011392331,0.0000060175194,0.0010203789,0.0027448423,0.017705685,0.008017237,0.0023971123,0.9665939],"study_design_scores_gemma":[0.00032962576,0.000057704354,0.0032712196,0.00006684564,0.00004603642,0.000016607792,0.00020512212,0.786716,0.0032041932,0.00014428103,0.20553936,0.00040301352],"about_ca_topic_score_codex":0.000050804952,"about_ca_topic_score_gemma":0.0000063331463,"teacher_disagreement_score":0.97210556,"about_ca_system_score_codex":0.00003708432,"about_ca_system_score_gemma":0.00003436066,"threshold_uncertainty_score":0.6565995},"labels":[],"label_agreement":null},{"id":"W4400410106","doi":"10.1109/ipdps57955.2024.00042","title":"Optimized GPU Implementation of Grid Refinement in Lattice Boltzmann Method","year":2024,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Autodesk (Canada)","funders":"","keywords":"Computer science; Lattice Boltzmann methods; Computational science; Parallel computing; Grid; CUDA; General-purpose computing on graphics processing units; Computer graphics (images); Physics; Geometry; Mathematics; Graphics; Mechanics","score_opus":0.020238071837683627,"score_gpt":0.3263173900843002,"score_spread":0.3060793182466166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400410106","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00048123114,0.00020803667,0.9936075,0.0019270094,0.00043197838,0.00013578073,0.000002701737,0.000049891503,0.003155841],"genre_scores_gemma":[0.10346832,0.00004248268,0.8958667,0.00018523731,0.00008253223,0.000018298611,0.0000036996412,0.0000054541883,0.00032730147],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990386,0.00012827106,0.00027282376,0.000259207,0.00015078776,0.0001503541],"domain_scores_gemma":[0.9995482,0.00014384191,0.000036291873,0.00020404525,0.000039439583,0.000028210961],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000619054,0.000083042985,0.00013934558,0.00011842381,0.000022429746,0.00008539674,0.00022893952,0.000021526363,0.00027134616],"category_scores_gemma":[0.000011587705,0.00006688393,0.000053127533,0.00039574524,0.000009468651,0.00034636454,0.000120139426,0.00005434998,0.000015413674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000211169,0.00010944444,0.00018599747,0.00009462227,0.00014649938,0.000037354308,0.0027378183,0.041978586,0.013846941,0.15487672,0.022501806,0.7634631],"study_design_scores_gemma":[0.0006379272,0.00009535677,0.0013175728,0.000041065654,0.000019936046,0.0000028923291,0.00033033054,0.9082338,0.07131937,0.001925275,0.015890691,0.00018573836],"about_ca_topic_score_codex":0.00046768598,"about_ca_topic_score_gemma":0.00009610764,"teacher_disagreement_score":0.8662553,"about_ca_system_score_codex":0.000029839648,"about_ca_system_score_gemma":0.00004833959,"threshold_uncertainty_score":0.297105},"labels":[],"label_agreement":null},{"id":"W4400573524","doi":"10.1145/3641519.3657458","title":"Diffusion Texture Painting","year":2024,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Texture (cosmology); Painting; Diffusion; Computer science; Computer graphics (images); Artificial intelligence; Art; Visual arts; Image (mathematics); Physics; Thermodynamics","score_opus":0.006906408330993501,"score_gpt":0.2164133634336968,"score_spread":0.20950695510270329,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400573524","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003929965,0.0003650493,0.9740007,0.0022197932,0.0005551057,0.000033316184,1.6017547e-7,0.00027476676,0.022158137],"genre_scores_gemma":[0.9459227,0.000013706534,0.04937477,0.00041167162,0.00024841013,0.0000020490834,4.0646586e-7,0.0000042503116,0.0040220744],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99948174,0.000028601946,0.00006846206,0.00020844763,0.00008832341,0.0001244569],"domain_scores_gemma":[0.99971074,0.00006868833,0.0000067704987,0.00016527982,0.000016051808,0.000032497246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014513233,0.000059703634,0.000050024435,0.000035875826,0.0000692225,0.00033350088,0.00021994369,0.000024361672,0.00011437731],"category_scores_gemma":[0.000017898421,0.00004044475,0.00004409485,0.00021701619,0.000009317313,0.00030566775,0.00013397454,0.000063236024,0.00015386773],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.302861e-7,0.000009949326,0.000043017895,0.000008697856,0.000010786804,0.0000259719,0.0002697975,0.0002907871,0.008527554,0.102643505,0.026996352,0.8611733],"study_design_scores_gemma":[0.000020828906,0.000010117258,0.00016104981,0.000019771709,0.0000017328462,0.000003965386,0.000014648014,0.9105583,0.0021364496,0.0022915567,0.08470702,0.000074598785],"about_ca_topic_score_codex":0.000012274145,"about_ca_topic_score_gemma":0.0000032602863,"teacher_disagreement_score":0.94552964,"about_ca_system_score_codex":0.000008679094,"about_ca_system_score_gemma":0.000014178896,"threshold_uncertainty_score":0.32159567},"labels":[],"label_agreement":null},{"id":"W4400702583","doi":"10.52202/079017-3256","title":"Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences","year":2024,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Generative model; Computer science; Generative grammar; Retraining; Pairwise comparison; Upload; Artificial intelligence; Function (biology); Machine learning; Stability (learning theory); Synthetic data","score_opus":0.06929622210286662,"score_gpt":0.2768607772941121,"score_spread":0.2075645551912455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400702583","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00094040926,0.0005340831,0.98169976,0.00056995975,0.00019737256,0.0002988458,0.000012733314,0.0006017889,0.015145034],"genre_scores_gemma":[0.45118782,0.000034946963,0.5476406,0.0000902305,0.00011680415,0.000022677028,0.000026621266,0.000012639337,0.00086768164],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982018,0.00012059578,0.00022006068,0.00089242804,0.0002577259,0.0003073801],"domain_scores_gemma":[0.9987318,0.0000918364,0.00004629104,0.0009155894,0.00012512808,0.00008937386],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00028717556,0.00022766886,0.00020487362,0.00008791383,0.00025611222,0.0011433857,0.0013228393,0.00005170332,0.000052181374],"category_scores_gemma":[0.000008862331,0.00014644007,0.000028798793,0.0004922612,0.000060156588,0.0031633645,0.0005568769,0.00015551664,0.000028343176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004243676,0.0004892877,0.000098698074,0.00026159562,0.0020278583,0.00032854697,0.008879102,0.31375653,0.010705613,0.5200646,0.03961308,0.10373262],"study_design_scores_gemma":[0.0001359067,0.00008411772,0.000006516761,0.000051775874,0.000029838784,0.000009704943,0.00005978267,0.9905244,0.004170831,0.0028087352,0.0018623463,0.00025603094],"about_ca_topic_score_codex":0.00009330042,"about_ca_topic_score_gemma":0.000081816266,"teacher_disagreement_score":0.6767679,"about_ca_system_score_codex":0.00002754718,"about_ca_system_score_gemma":0.00020932012,"threshold_uncertainty_score":0.99989355},"labels":[],"label_agreement":null},{"id":"W4400768355","doi":"10.1016/j.media.2024.103278","title":"Generating multi-pathological and multi-modal images and labels for brain MRI","year":2024,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"EPSRC Centre for Doctoral Training in Medical Imaging; Engineering and Physical Sciences Research Council; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Avid Radiopharmaceuticals; Genentech; Royal Academy of Engineering; IXICO; H. Lundbeck A/S; Centre For Medical Engineering, King’s College London; Servier; Eisai; King's College London; National Institutes of Health; National Institute on Aging; National Institute for Health and Care Research; Northern California Institute for Research and Education; Nvidia; Wellcome Trust; University of Southern California; Pfizer; BioClinica; Biogen; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; European Commission; National Center for Advancing Translational Sciences; Medical Research Council; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Alzheimer's Association","keywords":"Computer science; Segmentation; Artificial intelligence; Categorical variable; Generative model; Synthetic data; Modal; Pattern recognition (psychology); Machine learning; Generative grammar","score_opus":0.018465209063195195,"score_gpt":0.3049406073021934,"score_spread":0.2864753982389982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400768355","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054202615,0.0026147407,0.98233426,0.009182288,0.00012335855,0.00015137091,0.00002064507,0.000128371,0.000024696476],"genre_scores_gemma":[0.23457286,0.00024345536,0.762898,0.0013679548,0.00026812212,0.000044654826,0.000015832402,0.000014364282,0.0005747359],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997921,0.00022539932,0.00033710105,0.0008222208,0.00032482686,0.0003694423],"domain_scores_gemma":[0.99855775,0.00072375435,0.00004801772,0.00027924083,0.000094200834,0.0002970671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012948052,0.00022134403,0.000431143,0.00021682472,0.00024943738,0.0007180195,0.00034137405,0.00013507016,0.0000767398],"category_scores_gemma":[0.0010693473,0.00016307938,0.00020643258,0.00072295923,0.00027081644,0.00049748964,0.00036633664,0.0002119572,0.0000073992037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018052015,0.00040628327,0.0032549102,0.00021621885,0.0025542404,0.0013225646,0.0021296842,0.0018735959,0.08108975,0.001898779,0.012513239,0.89272267],"study_design_scores_gemma":[0.00037697854,0.000048288402,0.0012664596,0.00002091717,0.00027178793,0.00001846759,0.00003822243,0.9954867,0.001173311,0.00011191898,0.0009786828,0.00020829691],"about_ca_topic_score_codex":0.00004893562,"about_ca_topic_score_gemma":0.000075443175,"teacher_disagreement_score":0.99361306,"about_ca_system_score_codex":0.000015817239,"about_ca_system_score_gemma":0.000047173336,"threshold_uncertainty_score":0.6923879},"labels":[],"label_agreement":null},{"id":"W4400814077","doi":"10.1145/3664210","title":"Unveiling New Artistic Dimensions in Calligraphic Arabic Script with Generative Adversarial Networks","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on Computer Graphics and Interactive Techniques","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario College of Art and Design; Simon Fraser University","funders":"","keywords":"Calligraphy; Representation (politics); Computer science; Cursive; Generative grammar; Style (visual arts); Perspective (graphical); Mode (computer interface); Art; Artificial intelligence; Visual arts; Painting; Human–computer interaction","score_opus":0.011862773147804748,"score_gpt":0.23622738218628814,"score_spread":0.22436460903848338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400814077","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055761915,0.00061355095,0.93859607,0.0029835007,0.00074074924,0.000654663,0.000003884392,0.00027376472,0.0003718985],"genre_scores_gemma":[0.90630776,0.00024607405,0.09253724,0.0005524868,0.0002727934,0.00002691304,7.4315517e-7,0.000019599634,0.0000363863],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984484,0.000037077603,0.00033632544,0.0006360219,0.00025312768,0.00028909443],"domain_scores_gemma":[0.9988597,0.00028688772,0.00015845033,0.00037456205,0.0002285606,0.000091811984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031764977,0.0002998869,0.00032994515,0.00040313535,0.00015212942,0.00038092164,0.0011188256,0.00010021135,0.0000027164854],"category_scores_gemma":[0.000097928336,0.00019245055,0.00012687525,0.0010731558,0.00017646789,0.0007867097,0.0008343057,0.0005726236,5.4086695e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005658292,0.00056459114,0.0066800616,0.00019995653,0.00086255674,0.000054070442,0.0047733802,0.0030776483,0.021869238,0.7891933,0.051170386,0.120989],"study_design_scores_gemma":[0.00033474318,0.0010846211,0.0032810085,0.0020502536,0.00005551469,0.000040821196,0.000048540765,0.90059066,0.04284299,0.046981927,0.0021782503,0.0005106449],"about_ca_topic_score_codex":0.00009650298,"about_ca_topic_score_gemma":0.00003135018,"teacher_disagreement_score":0.89751303,"about_ca_system_score_codex":0.00004387578,"about_ca_system_score_gemma":0.000056716453,"threshold_uncertainty_score":0.7847906},"labels":[],"label_agreement":null},{"id":"W4400971967","doi":"10.2316/j.2024.206-1048","title":"IMAGE STYLE MIGRATION BASED ON CYCLEGAN WITH SAME MAPPING LOSS","year":2024,"lang":"en","type":"article","venue":"International Journal of Robotics and Automation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Style (visual arts); Image (mathematics); Computer science; Artificial intelligence; Computer vision; Art; Visual arts","score_opus":0.008594740710790716,"score_gpt":0.2349604466331488,"score_spread":0.22636570592235808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400971967","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009560812,0.000068308844,0.97811306,0.011379056,0.00064390997,0.00003816525,0.0000019363806,0.00002861003,0.00016616749],"genre_scores_gemma":[0.8180741,0.000027244887,0.18142508,0.0002035807,0.0002365267,6.433894e-7,0.0000027531316,0.0000050688145,0.000024980396],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991946,0.00003884416,0.00021570873,0.000115371346,0.00036350772,0.000071955204],"domain_scores_gemma":[0.99938345,0.000100856094,0.00013589175,0.000069507354,0.0002709464,0.000039323542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023696125,0.00008019223,0.000087838336,0.00022211211,0.0000439711,0.00060890726,0.00020471508,0.000024269055,0.000006971277],"category_scores_gemma":[0.000030847255,0.000058741276,0.000044357683,0.00012655836,0.000023572598,0.0007840716,0.000022753966,0.00009493641,0.000004594026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005507465,0.00013639478,0.0005502185,0.000041686457,0.00023961514,0.00038097176,0.0012944974,0.8086085,0.009367802,0.023408402,0.0015705501,0.15434633],"study_design_scores_gemma":[0.00020741353,0.00011629428,0.002423754,0.00024023252,0.000008661794,0.00006535229,0.000023396477,0.9943098,0.0009030783,0.0007728706,0.00085804326,0.000071103335],"about_ca_topic_score_codex":0.0000056246968,"about_ca_topic_score_gemma":0.0000038985113,"teacher_disagreement_score":0.8085133,"about_ca_system_score_codex":0.000048705097,"about_ca_system_score_gemma":0.00006124597,"threshold_uncertainty_score":0.58717066},"labels":[],"label_agreement":null},{"id":"W4401017512","doi":"10.1109/tvcg.2024.3434386","title":"FACEMUG: A Multimodal Generative and Fusion Framework for Local Facial Editing","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Visualization and Computer Graphics","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Image editing; Artificial intelligence; Feature (linguistics); Generative grammar; Generative model; Image (mathematics)","score_opus":0.01948815635380958,"score_gpt":0.2846601965708095,"score_spread":0.2651720402169999,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401017512","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013910622,0.00018710647,0.9962558,0.00021391908,0.0014598176,0.00027374463,0.000022179398,0.00019039393,0.0000059429817],"genre_scores_gemma":[0.94530773,0.00022316996,0.053358264,0.00063924113,0.00038228283,0.000043033124,0.000006015032,0.0000180561,0.00002219767],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886554,0.00008754351,0.000205786,0.00048425185,0.00016490194,0.00019197635],"domain_scores_gemma":[0.99941,0.00023946157,0.000037099686,0.000118065305,0.00009763682,0.000097787684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001517214,0.00019105812,0.0001617409,0.0002099893,0.00048101414,0.00044796208,0.000113257316,0.00013203254,0.0000054248094],"category_scores_gemma":[0.0000031536622,0.00017606985,0.000082225015,0.00040796754,0.00008109944,0.0004000485,0.0000071185127,0.00016626115,0.0000019358108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001837024,0.00006851181,0.000005976614,0.00006039918,0.00007704929,0.0000039038964,0.0024317843,0.013510248,0.000084842926,0.7357171,0.00019353733,0.24782825],"study_design_scores_gemma":[0.00023050976,0.00018841504,0.000027299553,0.000090421985,0.000021781092,0.000007361763,0.00005009163,0.990232,0.0023886906,0.0053953826,0.0011789149,0.00018914654],"about_ca_topic_score_codex":0.000008951857,"about_ca_topic_score_gemma":0.000010911132,"teacher_disagreement_score":0.97672176,"about_ca_system_score_codex":0.000016012247,"about_ca_system_score_gemma":0.00002964295,"threshold_uncertainty_score":0.717992},"labels":[],"label_agreement":null},{"id":"W4401077477","doi":"10.1007/978-981-97-5600-1_39","title":"Harmonizing Stable Diffusion and GPT-4 for Mural Expansion with ArtExtend","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Mural; Computer science; Diffusion; Computer graphics (images); Art history; History; Thermodynamics; Physics","score_opus":0.020916618015842697,"score_gpt":0.22536291085428753,"score_spread":0.20444629283844484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401077477","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017426042,0.0016609541,0.9949316,0.0008264187,0.0010879176,0.00046759285,0.000006720756,0.000096059455,0.0007484916],"genre_scores_gemma":[0.2770696,0.00015730674,0.7196556,0.00075616373,0.00074881583,0.000024508154,0.0000063007487,0.000057326837,0.0015243895],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99726593,0.000016148948,0.00028448406,0.0014136685,0.00048997207,0.0005297991],"domain_scores_gemma":[0.99859077,0.0003443147,0.00012685396,0.0006282068,0.00017074977,0.00013909373],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000446563,0.00043880296,0.00041421465,0.00038468477,0.00035605812,0.0009324275,0.0009237988,0.00016116782,0.00000675664],"category_scores_gemma":[0.000024598705,0.00032142486,0.000076911914,0.00031861415,0.0004016792,0.00063534273,0.0008381336,0.00039126354,0.000007195913],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002183782,0.00001962778,0.000015319963,0.000092228634,0.000021883914,0.0000715354,0.0010176637,0.028580735,0.0018574665,0.013846052,0.00009845073,0.9543572],"study_design_scores_gemma":[0.0002663763,0.00029159506,0.000038689737,0.00061609485,0.000018833007,0.00004829532,6.1837545e-7,0.9192001,0.0024259156,0.07304241,0.003536998,0.0005140557],"about_ca_topic_score_codex":0.000017159655,"about_ca_topic_score_gemma":0.000061542,"teacher_disagreement_score":0.9538431,"about_ca_system_score_codex":0.00010856703,"about_ca_system_score_gemma":0.00019924497,"threshold_uncertainty_score":0.99992377},"labels":[],"label_agreement":null},{"id":"W4401110445","doi":"10.1109/cai59869.2024.00207","title":"Query-Selected Global Attention for Text guided Image Style Transfer using Diffusion Model","year":2024,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Style (visual arts); Image (mathematics); Diffusion; Transfer (computing); Information retrieval; Artificial intelligence; Computer vision; Parallel computing; Physics; Geography","score_opus":0.02741260345477258,"score_gpt":0.2824362380260376,"score_spread":0.25502363457126503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401110445","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024101768,0.00010932399,0.97318584,0.0006421859,0.00037501604,0.00030530398,0.000016092428,0.00024567408,0.0010187953],"genre_scores_gemma":[0.69088304,0.0000096663125,0.30815372,0.00012745096,0.00012101711,0.000013519443,0.000008090225,0.000011326345,0.00067217514],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876344,0.000049769253,0.0002321954,0.00047302828,0.00017938038,0.00030218659],"domain_scores_gemma":[0.9994522,0.000042620002,0.000014176516,0.00023851226,0.00018221755,0.00007031353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018145255,0.00016383223,0.00015288549,0.000054423275,0.00017298509,0.0004547369,0.00028811384,0.00006826927,0.00003129771],"category_scores_gemma":[0.000022863223,0.00013327654,0.0001454096,0.00052840245,0.000026164756,0.0008059529,0.00007232022,0.000057020046,0.000017317312],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000293234,0.00014073287,0.000048937967,0.00008350525,0.000103592436,0.000011409822,0.0003014739,0.044320136,0.81995493,0.056453884,0.017569244,0.060982857],"study_design_scores_gemma":[0.00023851798,0.00003330607,0.000119857155,0.000031473486,0.00002497444,0.000006673015,0.000009804447,0.99005663,0.006669691,0.002182554,0.00044783182,0.00017866159],"about_ca_topic_score_codex":0.000095488336,"about_ca_topic_score_gemma":0.00003841786,"teacher_disagreement_score":0.9457365,"about_ca_system_score_codex":0.000098222474,"about_ca_system_score_gemma":0.000105393745,"threshold_uncertainty_score":0.54348594},"labels":[],"label_agreement":null},{"id":"W4401448657","doi":"10.4018/979-8-3693-5298-4.ch021","title":"Approaching Deepfake Detection Models","year":2024,"lang":"en","type":"book-chapter","venue":"Advances in information security, privacy, and ethics book series","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Yorkville University","funders":"","keywords":"Computer science","score_opus":0.0216073341146957,"score_gpt":0.25197819382512204,"score_spread":0.23037085971042634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401448657","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00000923654,0.013451292,0.6629284,0.0010649057,0.00090899254,0.00033927217,0.000014777079,0.00019680939,0.32108632],"genre_scores_gemma":[0.5216006,0.35836968,0.08258553,0.0053847353,0.0012091366,0.00025625524,0.00020390603,0.00016698014,0.030223168],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982134,0.000048803682,0.0006381165,0.000384842,0.00044470525,0.00027011434],"domain_scores_gemma":[0.99881244,0.00018047255,0.00029056476,0.00044355786,0.00018995874,0.00008301022],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007609647,0.00038552016,0.00035254963,0.00031956585,0.00031387745,0.00073626114,0.0005084656,0.0005260641,0.000006802617],"category_scores_gemma":[0.00007876033,0.00037749548,0.00009534985,0.00008878059,0.00021397998,0.01861985,0.000923804,0.0016061876,0.000024113528],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014165537,0.0000036964195,7.8746575e-7,0.00038153015,0.000018977084,0.000002792999,0.014802332,0.00947188,0.0000017797429,0.94831395,0.000028896136,0.026959196],"study_design_scores_gemma":[0.00008692997,0.000039952443,0.0000011574156,0.00021671176,0.000011915507,0.000015951937,0.00012243123,0.13690019,0.00010630494,0.60028285,0.26191545,0.0003001577],"about_ca_topic_score_codex":0.000015169826,"about_ca_topic_score_gemma":0.00014106475,"teacher_disagreement_score":0.5803429,"about_ca_system_score_codex":0.00008321954,"about_ca_system_score_gemma":0.00010381485,"threshold_uncertainty_score":0.9998677},"labels":[],"label_agreement":null},{"id":"W4401662101","doi":"10.1016/j.knosys.2024.112394","title":"Unified bi-encoder bispace-discriminator disentanglement for cross-domain echocardiography segmentation","year":2024,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Artificial Intelligence in Medicine (Canada)","funders":"Natural Science Foundation of Shandong Province","keywords":"Discriminator; Encoder; Segmentation; Computer science; Domain (mathematical analysis); Artificial intelligence; Mathematics; Telecommunications; Mathematical analysis","score_opus":0.023405421730478247,"score_gpt":0.29893466524370144,"score_spread":0.27552924351322317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401662101","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023051961,0.004192448,0.9836797,0.0004147547,0.006067704,0.001280449,0.00007302116,0.00037155225,0.0016151825],"genre_scores_gemma":[0.97725016,0.000014951775,0.020110484,0.000060299022,0.00078627013,0.00067570334,0.000055278186,0.00004554779,0.0010012807],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976139,0.00031148465,0.00047536456,0.0007882507,0.00032614573,0.00048484196],"domain_scores_gemma":[0.99852794,0.00033614095,0.000100896184,0.00060516177,0.00025480875,0.00017502859],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009071678,0.00032655665,0.00034352732,0.0004139437,0.00033712972,0.0013119022,0.00054188014,0.00010478336,0.000012540492],"category_scores_gemma":[0.000027214353,0.0002759614,0.000412107,0.00096048974,0.00008483655,0.00052554323,0.000088021436,0.000109867644,0.00008339608],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004150458,0.0019735058,0.013057018,0.009315924,0.0032711076,0.00025889976,0.015913308,0.15709378,0.09083683,0.24524255,0.3430441,0.11957793],"study_design_scores_gemma":[0.0012887185,0.00025884778,0.00038810715,0.00046144528,0.000096722135,0.000004025663,0.0005445236,0.8829376,0.01836852,0.0011515705,0.09384369,0.0006562091],"about_ca_topic_score_codex":0.000040319188,"about_ca_topic_score_gemma":0.000023023222,"teacher_disagreement_score":0.974945,"about_ca_system_score_codex":0.00020541243,"about_ca_system_score_gemma":0.00020594281,"threshold_uncertainty_score":0.99996924},"labels":[],"label_agreement":null},{"id":"W4402474921","doi":"10.1109/ispds62779.2024.10667597","title":"Classification Assistance Based Image Inpainting for BR code","year":2024,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"La Cité Collégiale","funders":"","keywords":"Inpainting; Computer science; Artificial intelligence; Code (set theory); Computer vision; Image (mathematics); Computer graphics (images); Pattern recognition (psychology); Programming language; Set (abstract data type)","score_opus":0.030009294897632793,"score_gpt":0.2780721495027125,"score_spread":0.24806285460507968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402474921","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012258666,0.00009143424,0.9889844,0.005027997,0.00044337288,0.00015782799,0.0000053952704,0.0002712768,0.0048956927],"genre_scores_gemma":[0.5034073,0.000002383768,0.49508634,0.0003727304,0.00014100487,0.000033919576,0.0000036624303,0.000007602063,0.0009450675],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991495,0.000043500717,0.0001531149,0.00036009197,0.000110294095,0.00018349827],"domain_scores_gemma":[0.9992818,0.0002870855,0.000030260377,0.00026963267,0.000090994195,0.000040220468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041511873,0.000089426314,0.000086601096,0.00005537409,0.000117358184,0.00052650715,0.00029889634,0.000032391727,0.000030401878],"category_scores_gemma":[0.00008787601,0.00007455285,0.00007803347,0.0002669467,0.000026129652,0.00051247934,0.000036146746,0.00005408552,0.0000376094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016346907,0.00008616509,0.00020924964,0.00017191611,0.000060187238,0.000010739524,0.000274969,0.0020220885,0.23938566,0.41135737,0.093495436,0.25290987],"study_design_scores_gemma":[0.00007764145,0.00001625748,0.000641798,0.000024418061,0.000004807711,4.3576827e-7,0.0000102370705,0.93936265,0.018338151,0.0013255873,0.04009616,0.000101857484],"about_ca_topic_score_codex":0.0000068406734,"about_ca_topic_score_gemma":0.000019954217,"teacher_disagreement_score":0.93734056,"about_ca_system_score_codex":0.000034911638,"about_ca_system_score_gemma":0.000057132984,"threshold_uncertainty_score":0.50771207},"labels":[],"label_agreement":null},{"id":"W4402703012","doi":"10.1109/cvpr52733.2024.01031","title":"Training Diffusion Models Towards Diverse Image Generation with Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Advanced Micro Devices (Canada)","funders":"","keywords":"Reinforcement learning; Computer science; Training (meteorology); Artificial intelligence; Image (mathematics); Diffusion; Reinforcement; Machine learning; Engineering","score_opus":0.05010947563397056,"score_gpt":0.2503338376741902,"score_spread":0.20022436204021965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402703012","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019294716,0.00007400672,0.96861565,0.00036051852,0.0002772672,0.000112947084,2.691204e-7,0.000263353,0.028366525],"genre_scores_gemma":[0.86489666,0.000040376144,0.13191015,0.00012628488,0.00022227329,0.000011075165,0.0000066425637,0.000009912375,0.0027766586],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989221,0.000054282045,0.00014583494,0.00037284754,0.00027495343,0.00022998136],"domain_scores_gemma":[0.9996269,0.00002023758,0.000027916552,0.00019011644,0.00006393829,0.00007092542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022228745,0.00014216512,0.00011542531,0.00008290775,0.00022614014,0.0005805611,0.00021466849,0.000033742064,0.000103305254],"category_scores_gemma":[0.000009458857,0.00009882121,0.00005260036,0.00025518876,0.00002746884,0.0014682503,0.00015717857,0.00012628423,0.00003330971],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004967393,0.000010582626,0.0000023251098,0.000009748537,0.00003627978,0.000047978232,0.004200261,0.7101874,0.018243365,0.03179214,0.00089409796,0.23457086],"study_design_scores_gemma":[0.00012112453,0.00010902046,0.0000069012513,0.000029196557,0.000010305162,0.000009019576,0.00022322846,0.99185485,0.0051533123,0.00025374658,0.002070849,0.0001584775],"about_ca_topic_score_codex":0.00007890679,"about_ca_topic_score_gemma":0.000012364732,"teacher_disagreement_score":0.86296713,"about_ca_system_score_codex":0.000045243552,"about_ca_system_score_gemma":0.00007666127,"threshold_uncertainty_score":0.55983645},"labels":[],"label_agreement":null},{"id":"W4402715899","doi":"10.1109/cvpr52733.2024.00650","title":"Prompting Hard or Hardly Prompting: Prompt Inversion for Text-to-Image Diffusion Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Inversion (geology); Diffusion; Image (mathematics); Artificial intelligence; Computer vision; Geology; Physics; Geomorphology","score_opus":0.045524645211830535,"score_gpt":0.27271766044084733,"score_spread":0.2271930152290168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402715899","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005449721,0.000077178105,0.9844538,0.0044625364,0.00075141183,0.0015708259,0.000008210357,0.0006530795,0.002573225],"genre_scores_gemma":[0.3026422,0.000011490317,0.6850858,0.0006189242,0.0004538949,0.00023695077,0.000007822244,0.00004437175,0.010898564],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99754745,0.00007644629,0.00038148926,0.0010311744,0.00037043943,0.0005930297],"domain_scores_gemma":[0.99878913,0.00022160061,0.00006546262,0.0005027439,0.00019542167,0.00022561153],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000590745,0.00030903355,0.00029943266,0.00021294686,0.00037941794,0.0010744255,0.0007790271,0.00009536548,0.00008322341],"category_scores_gemma":[0.0001530024,0.00021372922,0.00016964017,0.0006383205,0.000036425554,0.0017061916,0.000602126,0.00016129452,0.00016403823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023353788,0.00035761215,0.000033058663,0.00078623445,0.00017924876,0.00009189646,0.007018358,0.016077047,0.30561447,0.025289461,0.16374058,0.48057848],"study_design_scores_gemma":[0.00027571237,0.00026249167,0.00003380373,0.00023547524,0.00001823244,0.000007474698,0.00007819305,0.9577847,0.019004136,0.0024277167,0.019520506,0.00035152756],"about_ca_topic_score_codex":0.000032418393,"about_ca_topic_score_gemma":0.000014562004,"teacher_disagreement_score":0.9417077,"about_ca_system_score_codex":0.00008906704,"about_ca_system_score_gemma":0.00016284121,"threshold_uncertainty_score":0.99996257},"labels":[],"label_agreement":null},{"id":"W4402716110","doi":"10.1109/cvpr52733.2024.00752","title":"StyleCineGAN: Landscape Cinemagraph Generation Using a Pre-trained StyleGAN","year":2024,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.022359051505886584,"score_gpt":0.26180648118772804,"score_spread":0.23944742968184146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402716110","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019405682,0.00068935147,0.97411156,0.0009386396,0.0008297378,0.00015710724,0.000002042337,0.0003448976,0.0035209958],"genre_scores_gemma":[0.89339167,0.000021004314,0.1036827,0.00028395522,0.0008717697,0.000007107615,0.0000059791882,0.000014290862,0.001721509],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874675,0.00008021377,0.00021695012,0.00047518263,0.00021491155,0.00026596978],"domain_scores_gemma":[0.9994087,0.000057756435,0.000028384238,0.00035565568,0.00006242948,0.000087027474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025699005,0.0001711492,0.00015280308,0.0001748161,0.00014258848,0.00072540774,0.00032047622,0.000056514073,0.00018502717],"category_scores_gemma":[0.000021033402,0.00013170904,0.000099656354,0.0007214782,0.000021655778,0.0008751573,0.00009817677,0.00009857676,0.000028945957],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013346252,0.00012438578,0.0002540441,0.000070580245,0.0002531965,0.000121454505,0.0019617851,0.05839686,0.6720124,0.10872709,0.0594573,0.09860758],"study_design_scores_gemma":[0.0001263691,0.000048396672,0.00021976593,0.000020916237,0.000015534188,0.000018468123,0.000019432597,0.98170465,0.013417405,0.00032042965,0.0039028365,0.00018579632],"about_ca_topic_score_codex":0.000051991912,"about_ca_topic_score_gemma":0.000040587875,"teacher_disagreement_score":0.9233078,"about_ca_system_score_codex":0.000020995818,"about_ca_system_score_gemma":0.00008243791,"threshold_uncertainty_score":0.69951236},"labels":[],"label_agreement":null},{"id":"W4402753715","doi":"10.1109/cvpr52733.2024.00848","title":"Concept Weaver: Enabling Multi-Concept Fusion in Text-to-Image Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Image fusion; Fusion; Artificial intelligence; Image (mathematics); Natural language processing; Linguistics","score_opus":0.024387412372857763,"score_gpt":0.26118209965032807,"score_spread":0.2367946872774703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402753715","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000806321,0.0007731273,0.991308,0.0016084095,0.0007075461,0.00025209,0.0000037922325,0.00025418977,0.0042865607],"genre_scores_gemma":[0.7868654,0.000035949524,0.20958197,0.0007004433,0.00018095462,0.000010805293,0.000002164504,0.000015804842,0.0026065118],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983049,0.00009973876,0.00028461695,0.0006734427,0.00022927496,0.0004080467],"domain_scores_gemma":[0.99923617,0.0001401472,0.000023811332,0.00039870158,0.00006472346,0.0001364679],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027482316,0.00019973263,0.00021261063,0.00021306724,0.00009654148,0.0005148347,0.0006030499,0.000072825984,0.00017081476],"category_scores_gemma":[0.000040305564,0.00016460635,0.00009124667,0.00078747934,0.000045114553,0.0013594837,0.00041266347,0.00018192001,0.00022445213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001188384,0.00018383744,0.000018531362,0.000026253854,0.000044604785,0.0002364389,0.016504617,0.39844227,0.053279467,0.045896962,0.018994948,0.46636018],"study_design_scores_gemma":[0.0002318667,0.000037587797,0.000033645836,0.0000738266,0.000003226947,0.0000029460173,0.00016901467,0.96746147,0.026259346,0.0009952586,0.0044943932,0.00023744788],"about_ca_topic_score_codex":0.00026030632,"about_ca_topic_score_gemma":0.000075077536,"teacher_disagreement_score":0.7860591,"about_ca_system_score_codex":0.00006963351,"about_ca_system_score_gemma":0.00007317125,"threshold_uncertainty_score":0.67124516},"labels":[],"label_agreement":null},{"id":"W4402754275","doi":"10.1109/cvpr52733.2024.00131","title":"SCE-MAE: Selective Correspondence Enhancement with Masked Autoencoder for Self-Supervised Landmark Estimation","year":2024,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Landmark; Autoencoder; Artificial intelligence; Computer science; Pattern recognition (psychology); Estimation; Computer vision; Artificial neural network; Engineering","score_opus":0.008781674077387029,"score_gpt":0.23910229577278286,"score_spread":0.23032062169539583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402754275","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00069056463,0.000119895616,0.9943532,0.0010022188,0.00041828278,0.00054656586,0.0000029465166,0.00036452015,0.0025018293],"genre_scores_gemma":[0.38384277,0.000009558652,0.6132753,0.00020813596,0.00007885655,0.00013207983,0.000005222831,0.000011272334,0.0024368314],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987083,0.00006490199,0.00017288877,0.00051842997,0.0002446261,0.0002908516],"domain_scores_gemma":[0.99918795,0.0002735618,0.000034601213,0.00026873732,0.00016372532,0.0000714146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029589623,0.00017735179,0.00015830636,0.00009218467,0.00016369346,0.0004159396,0.00032568205,0.00004550883,0.000079807876],"category_scores_gemma":[0.000031806616,0.00012522022,0.0000575039,0.00049374026,0.000024621182,0.0007615459,0.000066452936,0.00008166342,0.00006792414],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005899197,0.0006265164,0.00022383881,0.00050111004,0.0010297177,0.0000917437,0.012168745,0.16278975,0.019695036,0.08961406,0.10856499,0.6041046],"study_design_scores_gemma":[0.0002849537,0.0002788644,0.0000909525,0.000060000413,0.000025568901,0.0000067787755,0.000024809979,0.9792274,0.015530726,0.0010770493,0.003192661,0.00020020005],"about_ca_topic_score_codex":0.000019910913,"about_ca_topic_score_gemma":0.000019633999,"teacher_disagreement_score":0.81643766,"about_ca_system_score_codex":0.00008992727,"about_ca_system_score_gemma":0.00017781835,"threshold_uncertainty_score":0.51063323},"labels":[],"label_agreement":null},{"id":"W4402904749","doi":"10.1167/jov.24.10.640","title":"Mapping neural similarity spaces for scenes with generative adversarial networks","year":2024,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Generative grammar; Adversarial system; Similarity (geometry); Computer science; Artificial intelligence; Artificial neural network; Pattern recognition (psychology); Image (mathematics)","score_opus":0.01729367106015438,"score_gpt":0.26858504233644337,"score_spread":0.251291371276289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402904749","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007839592,0.0016412124,0.98512834,0.003069811,0.0020913077,0.00013978414,0.0000018856928,0.000028425968,0.000059626866],"genre_scores_gemma":[0.84507173,0.00007603285,0.15287562,0.00018821578,0.0017160932,0.000002261352,0.0000011411893,0.000012361329,0.00005655709],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883175,0.00010876278,0.0003141483,0.00023537493,0.00028247928,0.00022748679],"domain_scores_gemma":[0.9990087,0.00027299483,0.00018875377,0.0001524511,0.00027960117,0.000097506694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006033801,0.00015630462,0.00025589878,0.00015160203,0.0001826526,0.0006150512,0.0003680124,0.000064506,0.000008961439],"category_scores_gemma":[0.000050509974,0.00010007027,0.00017193185,0.00033794064,0.000043757733,0.0012024386,0.00008468687,0.00022162726,0.0000011249565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043512406,0.00013493486,0.00023542321,0.000071819384,0.00038715333,0.0002634914,0.0019996995,0.6979234,0.009934791,0.002864978,0.028392313,0.25735685],"study_design_scores_gemma":[0.0004475516,0.0007220381,0.00082955154,0.00020759525,0.000026041465,0.000050839724,0.00007547665,0.98554236,0.0008670108,0.00056434755,0.010523142,0.0001440766],"about_ca_topic_score_codex":0.000004321695,"about_ca_topic_score_gemma":0.0000069353605,"teacher_disagreement_score":0.8372321,"about_ca_system_score_codex":0.000045026263,"about_ca_system_score_gemma":0.000102885744,"threshold_uncertainty_score":0.59309524},"labels":[],"label_agreement":null},{"id":"W4402915476","doi":"10.1109/icip51287.2024.10647939","title":"A Dataset for Understanding Open UGC Video Datasets","year":2024,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Google (Canada)","funders":"","keywords":"Computer science; World Wide Web; Data science","score_opus":0.11620419609502121,"score_gpt":0.34325194367160866,"score_spread":0.22704774757658747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402915476","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000011851077,0.0001322584,0.99003065,0.0032943806,0.0005329399,0.00032605894,0.0039429814,0.00005748557,0.0016820431],"genre_scores_gemma":[0.28137386,0.000047438723,0.70154953,0.004186483,0.00058965886,0.00015053542,0.010424369,0.000037469883,0.0016406297],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99905664,0.000035373232,0.00013373636,0.00045404263,0.00010113086,0.00021907986],"domain_scores_gemma":[0.99911773,0.0002670671,0.000017564636,0.00051663857,0.000011339751,0.000069682654],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00042939172,0.00010255999,0.000114250666,0.0000543263,0.00016570871,0.0018466773,0.0012621504,0.000026249154,0.00011034537],"category_scores_gemma":[0.00003851482,0.00007945833,0.0000356412,0.0002360925,0.000022287788,0.0017032451,0.00081559207,0.000048982503,0.00007787966],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032387682,0.000009099301,7.0798217e-7,0.000010852312,0.000026753682,0.000008957685,0.000039992872,0.000117521384,0.0001981589,0.18653688,0.805927,0.007120895],"study_design_scores_gemma":[0.00013043,0.000035535548,0.000001733686,0.000023335757,0.000009566003,0.0000047295493,0.00003363414,0.38464117,0.00074872177,0.028302692,0.58594185,0.00012659034],"about_ca_topic_score_codex":0.00007486205,"about_ca_topic_score_gemma":0.00006904962,"teacher_disagreement_score":0.38452363,"about_ca_system_score_codex":0.00005298426,"about_ca_system_score_gemma":0.00006680637,"threshold_uncertainty_score":0.9991895},"labels":[],"label_agreement":null},{"id":"W4402951630","doi":"10.1007/978-3-031-73235-5_5","title":"AFreeCA: Annotation-Free Counting for All","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Annotation; Artificial intelligence","score_opus":0.018501839513415053,"score_gpt":0.24661791583381779,"score_spread":0.22811607632040273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402951630","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003626875,0.0009877466,0.9860839,0.002604459,0.0032002442,0.0005051846,0.00002297382,0.00016719992,0.006424628],"genre_scores_gemma":[0.024762133,0.0000436559,0.96913326,0.0022348831,0.0017386449,0.000035369485,0.00001333089,0.00006291871,0.0019758074],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99657923,0.000017346661,0.00047649635,0.0015582858,0.00071126997,0.0006573947],"domain_scores_gemma":[0.99722433,0.00075841,0.00020782136,0.0013368672,0.0003507513,0.00012181283],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009555238,0.00048647114,0.00045418052,0.0005509473,0.0002572194,0.0011618794,0.0033815217,0.00024252912,0.000013968923],"category_scores_gemma":[0.00019435066,0.00043618123,0.00019984013,0.00046136882,0.00037939678,0.00070177944,0.0013852409,0.0004829185,0.00004691122],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008404768,0.00002474567,0.000009568824,0.00012950704,0.000065459346,0.00007515676,0.0010918514,0.14122228,0.0002875614,0.17844918,0.0018740313,0.6767622],"study_design_scores_gemma":[0.00014472094,0.000077455275,0.0000070984634,0.00019621378,0.000014535062,0.000012211479,1.03723735e-7,0.6387646,0.00055619323,0.3436649,0.016170427,0.00039151972],"about_ca_topic_score_codex":0.000016693284,"about_ca_topic_score_gemma":0.000108662425,"teacher_disagreement_score":0.67637074,"about_ca_system_score_codex":0.0002086037,"about_ca_system_score_gemma":0.00035672623,"threshold_uncertainty_score":0.999875},"labels":[],"label_agreement":null},{"id":"W4402996526","doi":"10.1007/978-3-031-72920-1_20","title":"TexGen: Text-Guided 3D Texture Generation with Multi-view Sampling and Resampling","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Huawei Technologies (Canada); University of Alberta","funders":"","keywords":"Computer science; Resampling; Artificial intelligence; Texture (cosmology); Computer vision; Sampling (signal processing); Texture synthesis; Computer graphics (images); Pattern recognition (psychology); Image texture; Image (mathematics); Image processing","score_opus":0.048450876575010855,"score_gpt":0.2751053607190412,"score_spread":0.22665448414403033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402996526","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000026629375,0.0044714995,0.99191254,0.00080893625,0.0012278878,0.00047262374,0.0000063886323,0.00015410097,0.0009193789],"genre_scores_gemma":[0.05732396,0.0002773531,0.9392601,0.0010562458,0.0013130378,0.00001379806,0.00000937734,0.00005938417,0.0006866981],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99609923,0.000040654868,0.00051268935,0.0020345962,0.00069473445,0.00061807147],"domain_scores_gemma":[0.9980259,0.00029436784,0.0002162472,0.0010003198,0.00027701206,0.00018615938],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00080929097,0.00066300033,0.00058587507,0.0005618245,0.00044968154,0.0015546668,0.001342522,0.00030569427,0.000015972902],"category_scores_gemma":[0.00006629,0.0005075979,0.00009191073,0.00062617235,0.0005145474,0.00070576096,0.0010148155,0.00082060695,0.000026206031],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000041427634,0.000017333123,0.000031941985,0.00008373262,0.000038260983,0.000093073,0.000712608,0.29146463,0.0009546449,0.0058613615,0.00004441237,0.70069385],"study_design_scores_gemma":[0.00021171155,0.000112916576,0.000042413954,0.00073895,0.0000273183,0.00016243961,2.6930977e-7,0.98484975,0.00074884633,0.00870127,0.0037033593,0.000700768],"about_ca_topic_score_codex":0.000029730338,"about_ca_topic_score_gemma":0.00020142112,"teacher_disagreement_score":0.69999313,"about_ca_system_score_codex":0.00018584191,"about_ca_system_score_gemma":0.00034270703,"threshold_uncertainty_score":0.99973756},"labels":[],"label_agreement":null},{"id":"W4403090349","doi":"10.1007/978-3-031-72069-7_26","title":"Masked Residual Diffusion Probabilistic Model with Regional Asymmetry Prior for Generating Perfusion Maps from Multi-phase CTA","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Residual; Diffusion; Asymmetry; Probabilistic logic; Perfusion; Algorithm; Artificial intelligence; Radiology; Thermodynamics; Physics; Medicine","score_opus":0.028880539993555727,"score_gpt":0.26267657411804013,"score_spread":0.2337960341244844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403090349","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006200054,0.0005982375,0.9952186,0.0011089159,0.0010180682,0.0010539064,0.00007660489,0.00015674415,0.00014892565],"genre_scores_gemma":[0.033118516,0.000027878043,0.9638096,0.000748331,0.0012146346,0.000047058933,0.00006649376,0.000070742164,0.00089673384],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99519616,0.000049728744,0.00061111175,0.002443066,0.0009958977,0.0007040253],"domain_scores_gemma":[0.9972444,0.00068982696,0.00030231517,0.001173308,0.0003799703,0.00021018958],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00068303256,0.0007340391,0.00064825243,0.0005174261,0.00060314784,0.00095996633,0.0019958466,0.00035336148,0.000007860545],"category_scores_gemma":[0.00012774473,0.00056017406,0.00017529906,0.00044668958,0.00053168216,0.00054645434,0.0012632627,0.00071583193,0.000011246021],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008299781,0.00013840708,0.0000067458636,0.00008041004,0.000033099474,0.000077146535,0.0011156079,0.65850866,0.0042186202,0.008115998,0.00022825599,0.32739407],"study_design_scores_gemma":[0.00094073464,0.0003281113,0.000006262394,0.00068522047,0.00003830321,0.00001826732,5.869588e-7,0.9379345,0.0011474732,0.057837557,0.00036912184,0.00069385424],"about_ca_topic_score_codex":0.000037592097,"about_ca_topic_score_gemma":0.00023603292,"teacher_disagreement_score":0.3267002,"about_ca_system_score_codex":0.00030160317,"about_ca_system_score_gemma":0.0007300128,"threshold_uncertainty_score":0.999685},"labels":[],"label_agreement":null},{"id":"W4403140677","doi":"10.1016/j.cag.2024.104099","title":"Diverse non-homogeneous texture synthesis from a single exemplar","year":2024,"lang":"en","type":"article","venue":"Computers & Graphics","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Homogeneous; Texture (cosmology); Texture synthesis; Computer science; Artificial intelligence; Mathematics; Image texture; Image (mathematics); Combinatorics; Image processing","score_opus":0.015353404427712793,"score_gpt":0.2167690850646488,"score_spread":0.201415680636936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403140677","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0081779165,0.00196149,0.9848729,0.0009665498,0.0029180902,0.00017532895,0.000037422124,0.00047719502,0.00041315128],"genre_scores_gemma":[0.91351414,0.00015526134,0.08469391,0.0007881031,0.0007291594,0.000017136488,0.000011600102,0.00003435204,0.00005634627],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978174,0.00013509461,0.0002899216,0.0009076142,0.00037804616,0.0004719213],"domain_scores_gemma":[0.99814916,0.00069935655,0.000066534114,0.00079102727,0.000092114744,0.00020179404],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002067971,0.0003549962,0.00034251847,0.00026575517,0.0002858943,0.0008982558,0.001257385,0.00016996077,0.000046719993],"category_scores_gemma":[0.0000307016,0.00032216802,0.00032167867,0.00095744955,0.00013076958,0.00058698107,0.00054626697,0.00029147,0.0001405663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001707233,0.00022502129,0.00023057483,0.00005771461,0.0005572639,0.0013355539,0.0020267465,0.004918222,0.006876613,0.0101592885,0.05474395,0.918852],"study_design_scores_gemma":[0.0001715705,0.00011053658,0.00066315633,0.0002736416,0.00009690934,0.000039529885,0.000050780323,0.9375415,0.006206779,0.0040186015,0.05017315,0.00065383606],"about_ca_topic_score_codex":0.00016820033,"about_ca_topic_score_gemma":0.000047513273,"teacher_disagreement_score":0.93262327,"about_ca_system_score_codex":0.000053831453,"about_ca_system_score_gemma":0.00007232274,"threshold_uncertainty_score":0.99992305},"labels":[],"label_agreement":null},{"id":"W4403243319","doi":"10.1162/neco_a_01715","title":"Sparse-Coding Variational Autoencoders","year":2024,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Eye Institute; National Institute of Neurological Disorders and Stroke; National Institute of Mental Health; National Institute on Drug Abuse; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Neural coding; Artificial intelligence; Computer science; Coding (social sciences); Autoencoder; Pattern recognition (psychology); Algorithm; Psychology; Mathematics; Artificial neural network; Statistics","score_opus":0.025608850249368542,"score_gpt":0.2609490435763236,"score_spread":0.23534019332695505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403243319","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010286268,0.00012140935,0.99299693,0.0023868424,0.0016281477,0.0000776326,0.0000012579666,0.00032646258,0.001432687],"genre_scores_gemma":[0.89786077,0.0000037208724,0.10147374,0.00027760657,0.0002598879,0.000004629287,0.0000082953975,0.000006775751,0.000104578365],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991264,0.00007298708,0.00014712753,0.0002968494,0.00020454325,0.00015210034],"domain_scores_gemma":[0.99961054,0.0001680997,0.000028835952,0.000095466276,0.000053331896,0.00004372586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014775828,0.000094711526,0.00007747074,0.000095926975,0.00012372562,0.00046914513,0.0001878528,0.000029885581,0.00002165856],"category_scores_gemma":[0.000023452336,0.00008671751,0.000056720888,0.000357431,0.00001573028,0.0008001996,0.000061025334,0.000095174946,0.00008880002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020789055,0.000011926937,0.00002645017,0.000013023201,0.000020127769,0.000022721819,0.0004447085,0.8041611,0.0011568387,0.05721721,0.005048186,0.13187568],"study_design_scores_gemma":[0.000059876405,0.000025286743,0.001156031,0.000013806028,0.0000049489427,0.000011145745,0.000005202389,0.9893596,0.0002520885,0.0077849114,0.0012302411,0.000096863],"about_ca_topic_score_codex":0.000011645568,"about_ca_topic_score_gemma":0.0000018405585,"teacher_disagreement_score":0.89683217,"about_ca_system_score_codex":0.0000384922,"about_ca_system_score_gemma":0.00004454695,"threshold_uncertainty_score":0.45239773},"labels":[],"label_agreement":null},{"id":"W4403536393","doi":"10.1145/3691620.3695067","title":"Bridging the Gap between Real-world and Synthetic Images for Testing Autonomous Driving Systems","year":2024,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bridging (networking); Computer science; Computer vision; Artificial intelligence; Computer security","score_opus":0.03919739003894227,"score_gpt":0.27066266700843555,"score_spread":0.2314652769694933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403536393","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001408719,0.0006743644,0.9891525,0.0020940334,0.0005308969,0.00033674497,0.00000484666,0.00033552558,0.0054623815],"genre_scores_gemma":[0.9595321,0.000014021754,0.03746374,0.000045867906,0.0007183559,0.000041953015,8.0856904e-7,0.000017521854,0.0021656645],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988083,0.00008816203,0.00023133578,0.0004375035,0.00012232825,0.00031233553],"domain_scores_gemma":[0.9976153,0.0018974982,0.000048530266,0.00031359025,0.000060700066,0.00006438601],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007688606,0.00015279166,0.0001871325,0.00009056946,0.00037478213,0.0014401812,0.00037702796,0.000025350435,0.0000025155389],"category_scores_gemma":[0.000140704,0.00009856546,0.00005676019,0.00035270533,0.000060306458,0.0004170366,0.00021936312,0.00009989201,0.000007677584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018113531,0.000017297416,0.0046557896,0.00031416083,0.00022001764,0.00002994286,0.0009042371,0.0117826145,0.0074824784,0.070349194,0.015324032,0.8889184],"study_design_scores_gemma":[0.000044739543,0.000026246738,0.001942151,0.00018861172,0.00003372833,0.000011272653,0.000035941273,0.9912683,0.0015702512,0.00071557047,0.003996091,0.0001671291],"about_ca_topic_score_codex":0.00037328133,"about_ca_topic_score_gemma":0.000020578787,"teacher_disagreement_score":0.97948563,"about_ca_system_score_codex":0.00003738076,"about_ca_system_score_gemma":0.000053012544,"threshold_uncertainty_score":0.9995964},"labels":[],"label_agreement":null},{"id":"W4403706727","doi":"10.1007/978-3-031-73229-4_20","title":"Salience-Based Adaptive Masking: Revisiting Token Dynamics for Enhanced Pre-training","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Salience (neuroscience); Security token; Masking (illustration); Artificial intelligence; Speech recognition; Computer security","score_opus":0.023276721237876063,"score_gpt":0.25412994406511824,"score_spread":0.2308532228272422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403706727","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012346006,0.0004546142,0.98968136,0.0009670207,0.0023518344,0.0007707299,0.000022644139,0.00021598549,0.00552347],"genre_scores_gemma":[0.3524255,0.00001247631,0.6450028,0.0007021665,0.0012097372,0.00003675435,0.000011258238,0.00005200494,0.00054731744],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99555045,0.00004189441,0.0006373578,0.0020628127,0.00079140655,0.00091609935],"domain_scores_gemma":[0.9969329,0.0011524337,0.00035877302,0.0010084781,0.00037070914,0.00017669472],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012213386,0.0006644103,0.00069783017,0.0006315112,0.00041109,0.0010680528,0.0026632186,0.00030343645,0.0000106584575],"category_scores_gemma":[0.00018092542,0.0006083322,0.00028603766,0.00070568395,0.0005291902,0.0006387909,0.00088767195,0.00069840724,0.000015588741],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012521336,0.000007797999,0.0000019282309,0.00006563115,0.000020995005,0.000026902839,0.00085298624,0.35888472,0.00024575574,0.05117932,0.000012426831,0.588689],"study_design_scores_gemma":[0.00017327373,0.00019304732,0.0000050548024,0.0011388628,0.000020259782,0.000008781768,0.0000015011434,0.89575434,0.00355906,0.09792063,0.00058491976,0.0006402524],"about_ca_topic_score_codex":0.000015098199,"about_ca_topic_score_gemma":0.00009697635,"teacher_disagreement_score":0.58804876,"about_ca_system_score_codex":0.00074673974,"about_ca_system_score_gemma":0.0008089184,"threshold_uncertainty_score":0.99996895},"labels":[],"label_agreement":null},{"id":"W4403791098","doi":"10.1145/3664647.3681509","title":"Improving the Training of the GANs with Limited Data via Dual Adaptive Noise Injection","year":2024,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Queen's University; Queen's University Belfast; Department for the Economy","keywords":"Dual (grammatical number); Computer science; Training (meteorology); Noise (video); Training set; Noise measurement; Artificial intelligence; Noise reduction; Physics","score_opus":0.041651528792579315,"score_gpt":0.22790638911318414,"score_spread":0.18625486032060484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403791098","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025322398,0.00009070628,0.9944769,0.0011306471,0.00039266486,0.0001412989,0.0000054993147,0.00006217743,0.0011678779],"genre_scores_gemma":[0.97978044,0.0000024103572,0.019656286,0.0001523076,0.00015092903,0.0000041952967,0.0000014502357,0.0000068765376,0.00024510222],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991475,0.00010320793,0.00012193374,0.00030298388,0.00018397182,0.00014044065],"domain_scores_gemma":[0.9989779,0.00018354238,0.000048892958,0.00071593915,0.000052754935,0.000020990017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003527807,0.00009105316,0.00008320749,0.00002999183,0.0001627003,0.00015950097,0.0007437886,0.000023539098,0.00000990288],"category_scores_gemma":[0.00003599597,0.000039532977,0.000033721422,0.00053063285,0.000082736355,0.0005843859,0.00042782776,0.00013302441,0.0000030496371],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048371454,0.00006441204,0.00010559913,0.000028509785,0.0003275419,0.000019644938,0.013429282,0.036916956,0.045161907,0.018824978,0.004181322,0.8808915],"study_design_scores_gemma":[0.000059973117,0.000088222034,0.00041995177,0.000031326144,0.000023831726,0.00001917169,0.0005547212,0.9929671,0.0052332706,0.00013930745,0.00039217994,0.00007093467],"about_ca_topic_score_codex":0.0002964839,"about_ca_topic_score_gemma":0.00024260723,"teacher_disagreement_score":0.9772482,"about_ca_system_score_codex":0.000013592611,"about_ca_system_score_gemma":0.000104627965,"threshold_uncertainty_score":0.1612108},"labels":[],"label_agreement":null},{"id":"W4403885263","doi":"10.1145/3680528.3687682","title":"Robust Symmetry Detection via Riemannian Langevin Dynamics","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Army Research Laboratory; Azrieli Foundation","keywords":"Homogeneous space; Robustness (evolution); Computer science; Symmetrization; Rotational symmetry; Symmetry (geometry); Noise (video); Artificial intelligence; Statistical physics; Mathematics; Physics; Geometry; Image (mathematics); Mathematical analysis","score_opus":0.018223005597863943,"score_gpt":0.22167401666434206,"score_spread":0.20345101106647812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403885263","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00036593262,0.00049301225,0.97391343,0.0014771331,0.0053478233,0.0002328352,0.000008585762,0.0005034211,0.01765781],"genre_scores_gemma":[0.86559,0.000058178342,0.12715197,0.0003179903,0.0009598041,0.00004538271,0.000024584127,0.000043122218,0.0058089686],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981799,0.00011101014,0.00028167787,0.0008617122,0.00026154728,0.0003041475],"domain_scores_gemma":[0.99874544,0.000058517933,0.000100373785,0.0008903889,0.000101241625,0.00010403628],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030513637,0.00032264914,0.00030357367,0.00020731267,0.00010706996,0.0006648077,0.00091029116,0.00030632896,0.000044262048],"category_scores_gemma":[0.000028350547,0.0002797229,0.00022082173,0.00035803273,0.000035903788,0.00014638991,0.0028109597,0.00074197917,0.00033205107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000084209605,0.000105014675,0.00006132181,0.0004408556,0.00040845326,0.0001222586,0.00036876596,0.07640496,0.0005818158,0.029481169,0.011028586,0.88098836],"study_design_scores_gemma":[0.000042580406,0.000024810577,0.00011562769,0.00007264666,0.000035826393,0.000009725404,0.000016146087,0.9741167,0.0013609616,0.022436168,0.0014294381,0.00033940532],"about_ca_topic_score_codex":0.00045527038,"about_ca_topic_score_gemma":0.0010144803,"teacher_disagreement_score":0.8977117,"about_ca_system_score_codex":0.00022166442,"about_ca_system_score_gemma":0.00007873103,"threshold_uncertainty_score":0.9999655},"labels":[],"label_agreement":null},{"id":"W4403886702","doi":"10.1088/1742-5468/ad363c","title":"Learning to sample better","year":2024,"lang":"en","type":"article","venue":"Journal of Statistical Mechanics Theory and Experiment","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Particle Physics","funders":"","keywords":"Sample (material); Computer science; Statistical physics; Physics; Thermodynamics","score_opus":0.010457312915782448,"score_gpt":0.27089477442741705,"score_spread":0.2604374615116346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403886702","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015002227,0.0006505024,0.9964421,0.0007031131,0.00058121094,0.00003946984,0.000003185539,0.000014430493,0.00006578617],"genre_scores_gemma":[0.71042585,0.00003655885,0.28898245,0.0003549404,0.00016663667,0.0000020137902,2.6656988e-7,0.0000058695673,0.000025441852],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991316,0.00019458229,0.00021685708,0.00014329229,0.00017001222,0.00014363926],"domain_scores_gemma":[0.9988093,0.0008762149,0.000036571688,0.00007645388,0.000048535952,0.00015294059],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000891613,0.00008500696,0.00014425605,0.000068748166,0.0000769879,0.00021380502,0.00015869089,0.000024285693,0.00009686733],"category_scores_gemma":[0.000265032,0.00006204532,0.000037950886,0.000090246096,0.00001211987,0.00018857302,0.00010663589,0.0001575197,0.000012202003],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044765533,0.000017281696,3.4699835e-7,0.000006405761,0.000034902667,0.000053665364,0.0013501208,0.00024604803,0.008608257,0.88149273,0.00051442254,0.10763107],"study_design_scores_gemma":[0.00017648876,0.0015858235,0.000006085428,0.00010853975,0.00002716716,0.00007534376,0.00050103787,0.110539325,0.028010687,0.8374739,0.021305623,0.00018994979],"about_ca_topic_score_codex":0.0000013056579,"about_ca_topic_score_gemma":9.364047e-8,"teacher_disagreement_score":0.7089256,"about_ca_system_score_codex":0.000024668927,"about_ca_system_score_gemma":0.000025610874,"threshold_uncertainty_score":0.2530135},"labels":[],"label_agreement":null},{"id":"W4404037313","doi":"10.1109/mlsp58920.2024.10734764","title":"Enhancing Supervised Visualization Through Autoencoder and Random Forest Proximities for Out-of-Sample Extension","year":2024,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Autoencoder; Extension (predicate logic); Visualization; Random forest; Computer science; Sample (material); Artificial intelligence; Pattern recognition (psychology); Data mining; Artificial neural network","score_opus":0.0309943730052248,"score_gpt":0.28390935702502296,"score_spread":0.2529149840197982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404037313","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021041622,0.00055243314,0.9957033,0.00034203858,0.00061497185,0.0003588606,0.000004313401,0.00011490366,0.00020501722],"genre_scores_gemma":[0.5875651,0.0000797457,0.4117778,0.00014485001,0.00013253136,0.000036002737,0.000008316522,0.00001175679,0.00024384499],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991671,0.00004429757,0.00021237283,0.0003033811,0.000116035175,0.00015683426],"domain_scores_gemma":[0.9991008,0.00056440494,0.000030105517,0.00016270956,0.00011496072,0.000026993299],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025970358,0.000107373286,0.00017230712,0.00004734465,0.00010715716,0.0001987412,0.000120196164,0.000040376093,0.000014283057],"category_scores_gemma":[0.00014936543,0.00008011952,0.00006220139,0.00013367692,0.000038691716,0.00073902204,0.00008220837,0.000028577084,0.0000016066559],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019898811,0.00017678617,0.0005192722,0.0012457363,0.0002737936,0.000008761078,0.030670198,0.018570147,0.09038641,0.73089993,0.009004651,0.11804529],"study_design_scores_gemma":[0.00038380377,0.00007739502,0.00004879302,0.00007819747,0.000015058907,8.490559e-7,0.00015276646,0.9413396,0.04020007,0.015052975,0.0025415018,0.00010894941],"about_ca_topic_score_codex":0.00007941238,"about_ca_topic_score_gemma":0.00014798959,"teacher_disagreement_score":0.9227695,"about_ca_system_score_codex":0.000010060031,"about_ca_system_score_gemma":0.000043074022,"threshold_uncertainty_score":0.32671794},"labels":[],"label_agreement":null},{"id":"W4404361444","doi":"10.1111/cgf.15246","title":"DiffPop: Plausibility‐Guided Object Placement Diffusion for Image Composition","year":2024,"lang":"en","type":"article","venue":"Computer Graphics Forum","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Composition (language); Object (grammar); Computer vision; Image (mathematics); Artificial intelligence; Computer graphics (images); Art","score_opus":0.015839737829143864,"score_gpt":0.2601809198382708,"score_spread":0.24434118200912694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404361444","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041786884,0.000288535,0.98861736,0.002713218,0.0028585743,0.0006990643,0.000028733906,0.00043499,0.00018083284],"genre_scores_gemma":[0.7484656,0.0000694536,0.24908781,0.0013271939,0.00068883615,0.000109572095,0.0000853783,0.00004012921,0.00012603178],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777126,0.000108882225,0.0004093732,0.00084770506,0.00032208452,0.00054071716],"domain_scores_gemma":[0.99865985,0.000320586,0.000073850366,0.0006496267,0.00016077123,0.0001353451],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004423202,0.00030652428,0.00028813691,0.00026069602,0.00040357505,0.0008038463,0.00069343316,0.000106959655,0.000010663257],"category_scores_gemma":[0.000011119629,0.00026739982,0.00033177345,0.00054304604,0.00008997701,0.00068952393,0.0005173861,0.00018851958,0.000025677775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008805395,0.00061744975,0.0003504911,0.0004456863,0.0004097646,0.0001081736,0.0013905814,0.0032023336,0.020373806,0.6135167,0.28567806,0.073818885],"study_design_scores_gemma":[0.00046872275,0.00026089218,0.00031593174,0.000113765826,0.000026094775,0.000021202739,0.000010665799,0.9670711,0.0040067188,0.011241251,0.016121497,0.00034212356],"about_ca_topic_score_codex":0.00001893628,"about_ca_topic_score_gemma":0.00001477942,"teacher_disagreement_score":0.9638688,"about_ca_system_score_codex":0.00007505308,"about_ca_system_score_gemma":0.000061414736,"threshold_uncertainty_score":0.9999778},"labels":[],"label_agreement":null},{"id":"W4404397123","doi":"","title":"Boosting Latent Diffusion with Perceptual Objectives","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University; Canadian Institute for Advanced Research","funders":"","keywords":"Computer science; Artificial intelligence; Generative model; Boosting (machine learning); Autoencoder; Pattern recognition (psychology); Margin (machine learning); Generative grammar; Machine learning; Artificial neural network","score_opus":0.044911763197878624,"score_gpt":0.17261055764425914,"score_spread":0.12769879444638052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404397123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.230912,0.00014688411,0.76419485,0.00015911488,0.00064872263,0.00023624081,0.000010364675,0.0002759543,0.003415869],"genre_scores_gemma":[0.99261117,0.00010911239,0.0045633563,0.00006338489,0.00020304839,0.0000011433484,0.000008562414,0.00002595116,0.0024142559],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979075,0.00015491924,0.00015191721,0.0013032444,0.00011705271,0.0003653474],"domain_scores_gemma":[0.99871147,0.00009115252,0.00013231729,0.0007784556,0.00014164348,0.00014499361],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016037704,0.0003710754,0.000320837,0.0002012323,0.00022399994,0.00029294382,0.001005618,0.00019099576,0.000041919593],"category_scores_gemma":[0.00001980109,0.00032660252,0.00018967416,0.0004940912,0.00013092298,0.00026306062,0.0032456033,0.0006795884,0.000115910596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051942137,0.00011272892,0.0013552724,0.00010218372,0.00026445498,0.00090403896,0.002053084,0.95866853,0.000304988,0.031431243,0.00061893405,0.004132609],"study_design_scores_gemma":[0.00024983194,0.00010681665,0.0016415615,0.0002873689,0.00011103695,0.00000862569,0.00022208942,0.9809771,0.00021227048,0.015415847,0.00023819569,0.0005292425],"about_ca_topic_score_codex":0.00023103436,"about_ca_topic_score_gemma":0.000104035345,"teacher_disagreement_score":0.7616992,"about_ca_system_score_codex":0.00017485955,"about_ca_system_score_gemma":0.00018089752,"threshold_uncertainty_score":0.9999186},"labels":[],"label_agreement":null},{"id":"W4404654748","doi":"10.1007/978-3-031-72995-9_10","title":"PanGu-Draw: Advancing Resource-Efficient Text-to-Image Synthesis with Time-Decoupled Training and Reusable Coop-Diffusion","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Diffusion; Image (mathematics); Resource (disambiguation); Training (meteorology); Multimedia; Computer graphics (images); Artificial intelligence; Computer vision; Computer network","score_opus":0.008880837916798421,"score_gpt":0.21454081047762943,"score_spread":0.20565997256083102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404654748","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000436549,0.00062484137,0.9903388,0.001579666,0.0005921973,0.00058960944,0.000009828184,0.0002344984,0.005594034],"genre_scores_gemma":[0.12695065,0.000054211112,0.868175,0.0014743223,0.0008471632,0.000040541006,0.0000043640866,0.00013605373,0.0023176682],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949856,0.00006440689,0.000547274,0.00234833,0.0010213882,0.0010330245],"domain_scores_gemma":[0.9965479,0.0013375038,0.00022708035,0.0012638059,0.000230716,0.00039299423],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0013917453,0.0007630912,0.0008507864,0.00095307396,0.000541919,0.001309108,0.001900764,0.00024854956,0.000053776566],"category_scores_gemma":[0.00031993698,0.0006035894,0.0001192388,0.0010775015,0.00063666847,0.00044164248,0.001829199,0.00072371843,0.000108777866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032443553,0.000043014727,0.00000799293,0.00009166584,0.00004500842,0.00032206593,0.0037135766,0.37047887,0.0039753816,0.0014982007,0.00029703797,0.61949474],"study_design_scores_gemma":[0.00018340453,0.00027293456,0.000024593532,0.0019070427,0.00003836524,0.000107018284,0.0000037354334,0.9835278,0.0029143868,0.004322313,0.005804046,0.0008943819],"about_ca_topic_score_codex":0.000025822617,"about_ca_topic_score_gemma":0.00007342706,"teacher_disagreement_score":0.61860037,"about_ca_system_score_codex":0.00028835578,"about_ca_system_score_gemma":0.00039973907,"threshold_uncertainty_score":0.9997276},"labels":[],"label_agreement":null},{"id":"W4404838560","doi":"10.1016/j.neucom.2024.128996","title":"Do inpainting yourself: Generative facial inpainting guided by exemplars","year":2024,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Science Foundation of Zhejiang Province; Engineering and Physical Sciences Research Council; Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Government of Canada","keywords":"Inpainting; Generative grammar; Artificial intelligence; Computer science; Generative model; Computer vision; Pattern recognition (psychology); Image (mathematics)","score_opus":0.020345967911891704,"score_gpt":0.264153361177595,"score_spread":0.24380739326570333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404838560","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058951717,0.00057840557,0.93319327,0.0020724423,0.0019659323,0.0002650259,0.0000045065785,0.00078894483,0.0021797735],"genre_scores_gemma":[0.91684186,0.000014848954,0.08048393,0.0010996136,0.0012844543,0.000011916528,0.000005639165,0.000046841607,0.00021090807],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99679214,0.00038093506,0.00055220997,0.0010978581,0.00042733687,0.0007495357],"domain_scores_gemma":[0.99871606,0.00044272598,0.00014462444,0.0004236053,0.00012208211,0.00015091061],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009993961,0.00037067558,0.00032278185,0.00019250513,0.00075127435,0.001723066,0.00089000195,0.00010425797,0.000021924508],"category_scores_gemma":[0.00023750987,0.00035647114,0.0001879339,0.0008841281,0.000060872248,0.0007944369,0.0006954972,0.00048226162,0.000077345314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040385057,0.0000673133,0.00048286788,0.000068411355,0.000115414194,0.00024410935,0.005292037,0.033789035,0.10333462,0.0077001415,0.04779586,0.80110615],"study_design_scores_gemma":[0.00018953416,0.00005312286,0.000078129655,0.00012414574,0.000014944065,0.000048960148,0.00008141158,0.9370525,0.018825645,0.0007015722,0.04237605,0.00045399636],"about_ca_topic_score_codex":0.000029204997,"about_ca_topic_score_gemma":0.0000022542108,"teacher_disagreement_score":0.90326345,"about_ca_system_score_codex":0.00008539666,"about_ca_system_score_gemma":0.00009311391,"threshold_uncertainty_score":0.9998887},"labels":[],"label_agreement":null},{"id":"W4404943058","doi":"10.1007/978-3-031-78305-0_15","title":"Diffusion Models as a Representation Learner for Deepfake Image Detection","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Representation (politics); Diffusion; Image (mathematics); Artificial intelligence; Computer vision; Thermodynamics","score_opus":0.02050881456786294,"score_gpt":0.260682528575783,"score_spread":0.24017371400792006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404943058","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000044749733,0.00036696758,0.99177796,0.0007690259,0.0025026859,0.0006763104,0.000004758076,0.00017868765,0.0036788837],"genre_scores_gemma":[0.3129029,0.00013240644,0.68076175,0.00087489665,0.001688435,0.00007335412,0.0000138839405,0.00008709832,0.0034652879],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966796,0.000034320517,0.00042720124,0.0016896335,0.0006646869,0.00050454034],"domain_scores_gemma":[0.9980761,0.00039082335,0.00019498217,0.0009031517,0.00031217886,0.00012278005],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00060416025,0.00044282054,0.00039967362,0.0006294306,0.00033149114,0.0010069164,0.0013127414,0.00027679658,0.000013253213],"category_scores_gemma":[0.00010167057,0.00038921088,0.00022614884,0.000533057,0.000308106,0.0011861206,0.00083758007,0.0004915468,0.000060637372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016539849,0.000018364502,8.623268e-7,0.000039611714,0.000016949672,0.000030799813,0.0006491184,0.21597143,0.004729487,0.017009754,0.000046312733,0.7614708],"study_design_scores_gemma":[0.00012581768,0.00011373834,0.0000030883593,0.00012026824,0.000012191341,0.000019930912,2.529576e-7,0.6370198,0.008151933,0.35347942,0.00067036547,0.00028317684],"about_ca_topic_score_codex":0.000047924703,"about_ca_topic_score_gemma":0.00011764163,"teacher_disagreement_score":0.7611876,"about_ca_system_score_codex":0.00023781479,"about_ca_system_score_gemma":0.00020084037,"threshold_uncertainty_score":0.999856},"labels":[],"label_agreement":null},{"id":"W4404965856","doi":"10.1007/978-3-031-78312-8_6","title":"An Edge-Assisted Mural Image Inpainting Approach Leveraging Aggregated Contextual Transformations","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Inpainting; Mural; Computer science; Computer vision; Artificial intelligence; Enhanced Data Rates for GSM Evolution; Image (mathematics); Computer graphics (images); Art history; Art; Painting","score_opus":0.020243813079816837,"score_gpt":0.24279359178788376,"score_spread":0.22254977870806691,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404965856","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000087548,0.00054694986,0.98734117,0.000626048,0.0015768501,0.00047820926,0.000011551472,0.00037414755,0.008957534],"genre_scores_gemma":[0.4848644,0.000021059595,0.51346415,0.00062019064,0.00063793594,0.000014749776,0.000028355218,0.000048593578,0.00030054385],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958551,0.000091611466,0.00071720965,0.0016924047,0.0008226016,0.00082105765],"domain_scores_gemma":[0.9977394,0.00028394,0.0002446688,0.0011402584,0.00035112258,0.00024064208],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001152326,0.0006741185,0.0006234441,0.000908068,0.00056315167,0.0021554974,0.0027881993,0.00029454773,0.000022149876],"category_scores_gemma":[0.000059451337,0.00059964607,0.00022588979,0.0010000268,0.00071455445,0.0021301706,0.0005809641,0.0010960222,0.000047215643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006437063,0.00006338918,0.000005775822,0.00008114743,0.00004836227,0.00010063224,0.00576363,0.10383298,0.0016224226,0.011921038,0.00007465164,0.8764795],"study_design_scores_gemma":[0.00023239166,0.00009640988,0.000035856436,0.00035038983,0.00002204342,0.000094379815,0.0000038828966,0.9746117,0.0016126944,0.021572007,0.0006524094,0.000715816],"about_ca_topic_score_codex":0.00003620448,"about_ca_topic_score_gemma":0.00004795837,"teacher_disagreement_score":0.8757637,"about_ca_system_score_codex":0.0002884422,"about_ca_system_score_gemma":0.00037494246,"threshold_uncertainty_score":0.9996455},"labels":[],"label_agreement":null},{"id":"W4405010156","doi":"10.1016/j.neunet.2024.106979","title":"Deep clustering analysis via variational autoencoder with Gamma mixture latent embeddings","year":2024,"lang":"en","type":"article","venue":"Neural Networks","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Autoencoder; Cluster analysis; Artificial intelligence; Pattern recognition (psychology); Computer science; Mixture model; Mathematics; Deep learning","score_opus":0.007475380848434619,"score_gpt":0.21597499433510495,"score_spread":0.20849961348667032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405010156","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022083038,0.0007031077,0.9961342,0.0013480927,0.00087330036,0.00013157363,0.0000013051011,0.0002862232,0.00030135844],"genre_scores_gemma":[0.870762,0.000022409677,0.12748316,0.00061248423,0.0007444707,0.000020727502,0.000019376916,0.000022630165,0.00031274735],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99816465,0.00010380673,0.00026322316,0.00067278306,0.0003456335,0.00044988786],"domain_scores_gemma":[0.9991511,0.00015802194,0.000071422655,0.00038625268,0.00009677567,0.00013641501],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002038272,0.0002650851,0.00028261082,0.00018694894,0.00020237091,0.00070383865,0.0004927563,0.000112445414,0.0001149597],"category_scores_gemma":[0.000007461461,0.00019651522,0.00021099388,0.0017069554,0.00004184368,0.00070783944,0.00020293491,0.00032794627,0.000015189376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010590587,0.000013287347,0.00031184315,0.0000062972645,0.0003773293,0.00007475344,0.00018480283,0.9697415,0.000026634918,0.00060697284,0.0006060592,0.028039921],"study_design_scores_gemma":[0.00010963312,0.00005816933,0.0025295168,0.000020939045,0.00020506677,0.000031901487,0.000003407935,0.9958879,0.000011857766,0.00017957707,0.0007044948,0.00025756145],"about_ca_topic_score_codex":0.000034674365,"about_ca_topic_score_gemma":0.00012726273,"teacher_disagreement_score":0.87054116,"about_ca_system_score_codex":0.00005426113,"about_ca_system_score_gemma":0.000024843053,"threshold_uncertainty_score":0.8013658},"labels":[],"label_agreement":null},{"id":"W4405033076","doi":"10.1109/iccv51701.2025.00974","title":"VISION-XL: High Definition Video Inverse Problem Solver using Latent Image Diffusion Models","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Research Foundation of Korea","keywords":"Solver; Problem solver; Computer vision; Computer science; Diffusion; Inverse; Image (mathematics); Computer graphics (images); Artificial intelligence; Inverse problem; Mathematics; Computational science; Geometry; Mathematical analysis; Physics","score_opus":0.03997770058442579,"score_gpt":0.2576535222003682,"score_spread":0.2176758216159424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405033076","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031505965,0.00008202263,0.9849393,0.00093269645,0.001176592,0.00069043925,0.000031261345,0.00028633222,0.008710772],"genre_scores_gemma":[0.11297708,0.0002582475,0.8846329,0.00077549793,0.00021115928,0.00004924807,0.00005766307,0.000024101277,0.0010140945],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968393,0.0002608656,0.00060586457,0.0012743192,0.00053065486,0.000489004],"domain_scores_gemma":[0.997827,0.00012215745,0.0003055772,0.0011896999,0.00040135832,0.00015421334],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044156553,0.00052227924,0.00055840996,0.00029766117,0.00032664268,0.00073308835,0.0011217733,0.00038421547,0.00010732236],"category_scores_gemma":[0.000029428322,0.0004503678,0.00030544857,0.00034726656,0.000080063204,0.0011131797,0.004562477,0.00054171577,0.000042167907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003892185,0.00057410577,0.000043411666,0.000346693,0.0002318989,0.000049793387,0.00071835687,0.90174294,0.013096934,0.05294931,0.014568863,0.015638748],"study_design_scores_gemma":[0.00029593782,0.000031164687,0.000043182103,0.00045381414,0.00006323616,0.0000018399662,0.000009754528,0.8722632,0.0024075476,0.123872735,0.00010956576,0.0004480428],"about_ca_topic_score_codex":0.0014698992,"about_ca_topic_score_gemma":0.00008115565,"teacher_disagreement_score":0.10982648,"about_ca_system_score_codex":0.00022257767,"about_ca_system_score_gemma":0.0003184019,"threshold_uncertainty_score":0.9997948},"labels":[],"label_agreement":null},{"id":"W4406091633","doi":"10.7717/peerj-cs.2553","title":"GAN inversion and shifting: recommending product modifications to sellers for better user preference","year":2025,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Waterloo","funders":"","keywords":"Computer science; Recommender system; Preference; Bridging (networking); Product (mathematics); Similarity (geometry); Customer needs; Human–computer interaction; Information retrieval; Artificial intelligence; Marketing; Business; Image (mathematics)","score_opus":0.03963277696433789,"score_gpt":0.27094593178592397,"score_spread":0.23131315482158607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406091633","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016089844,0.000029945008,0.9609633,0.021103017,0.00092859636,0.00046153142,0.000002163427,0.000089305024,0.00033229875],"genre_scores_gemma":[0.5668636,0.0000037614861,0.43103337,0.0017812937,0.0000890616,0.000029878454,7.879081e-7,0.0000033933231,0.00019487142],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817187,0.00004964506,0.00020731195,0.00092787103,0.00023804422,0.0004052606],"domain_scores_gemma":[0.9987253,0.00017710995,0.000062627005,0.00060814415,0.0002737498,0.00015305946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007984784,0.00015553457,0.00015912075,0.0003177252,0.0007383323,0.0006713938,0.0012857977,0.000025834415,0.0000021050564],"category_scores_gemma":[0.00012858653,0.00014174373,0.0000381335,0.0012869322,0.00014665518,0.0009320399,0.00067769,0.00008684991,0.000007472544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021636672,0.00015502406,0.005489865,0.00007697061,0.000044420984,0.0000018229526,0.0048949267,0.040979322,0.026540669,0.03393434,0.09150873,0.79635227],"study_design_scores_gemma":[0.0001939932,0.00006553181,0.006566003,0.000057096848,0.0000075586004,0.0000014127847,0.000016945169,0.9474314,0.02550156,0.0015590467,0.018368606,0.00023087661],"about_ca_topic_score_codex":0.000015812728,"about_ca_topic_score_gemma":0.00000592998,"teacher_disagreement_score":0.90645206,"about_ca_system_score_codex":0.00006543976,"about_ca_system_score_gemma":0.00014243368,"threshold_uncertainty_score":0.6474266},"labels":[],"label_agreement":null},{"id":"W4406499795","doi":"10.1109/cascon62161.2024.10837875","title":"On Sarcasm Detection with OpenAI GPT-Based Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Sarcasm; Computer science; Artificial intelligence; Philosophy; Irony; Linguistics","score_opus":0.014505884042636794,"score_gpt":0.2152418864123628,"score_spread":0.200736002369726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406499795","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010045763,0.000052992465,0.9820979,0.00077782583,0.0002732559,0.000103285805,5.795094e-7,0.00022768478,0.015461868],"genre_scores_gemma":[0.9559924,0.0000021726607,0.042537678,0.00058425905,0.00006459549,0.000013193361,4.896116e-7,0.000008669679,0.0007965526],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992236,0.000041841333,0.000077919634,0.0003336547,0.0001678281,0.00015514165],"domain_scores_gemma":[0.9995372,0.00009145467,0.000011898698,0.00027396268,0.000035181765,0.00005025129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012148276,0.000103570994,0.00007849917,0.00007855333,0.0000876049,0.00036787364,0.00023470275,0.000028165785,0.000045105782],"category_scores_gemma":[0.000005417042,0.00006676644,0.00003899421,0.00031544807,0.0000188467,0.0005179128,0.000038361322,0.000083790146,0.00010019941],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002977153,0.00004932346,0.0000014688508,0.000014194821,0.00003800677,0.000041943094,0.00012724062,0.6826068,0.004389891,0.091174215,0.0029977565,0.21852939],"study_design_scores_gemma":[0.000100301935,0.00017728242,0.0000068757495,0.000029820385,0.00000409703,0.0000033313574,0.000003452199,0.93613225,0.056728516,0.0053223316,0.0013851115,0.00010664049],"about_ca_topic_score_codex":0.000053891174,"about_ca_topic_score_gemma":0.000048832608,"teacher_disagreement_score":0.9549878,"about_ca_system_score_codex":0.000030900177,"about_ca_system_score_gemma":0.00005215033,"threshold_uncertainty_score":0.3547414},"labels":[],"label_agreement":null},{"id":"W4406539358","doi":"10.3390/e27010080","title":"Bidimensional Increment Entropy for Texture Analysis: Theoretical Validation and Application to Colon Cancer Images","year":2025,"lang":"en","type":"article","venue":"Entropy","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Centre for Addiction and Mental Health","funders":"","keywords":"Entropy (arrow of time); Computer science; Pattern recognition (psychology); Sample entropy; Artificial intelligence; Support vector machine; Approximate entropy; Mathematics; Physics","score_opus":0.004542515419490102,"score_gpt":0.2674616003757908,"score_spread":0.26291908495630073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406539358","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0065610157,0.00020517738,0.9857875,0.0067528817,0.00013923636,0.0004426019,0.000013804443,0.000030492476,0.0000672785],"genre_scores_gemma":[0.95576113,0.000033086493,0.042937282,0.00083442096,0.00010256754,0.00021479516,0.000015762078,0.0000035570915,0.00009742279],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99911416,0.00006984501,0.0001513776,0.00035943306,0.00013832947,0.00016688016],"domain_scores_gemma":[0.9994406,0.00011890386,0.000036229623,0.00022047939,0.00012256554,0.000061207604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020471538,0.00010229894,0.0001572633,0.00012920011,0.00014784702,0.0001143493,0.00018567109,0.000039400114,0.000025497573],"category_scores_gemma":[0.000047912738,0.000085045736,0.00006369144,0.0004746239,0.000042331536,0.000110577625,0.00011775274,0.000043381166,0.000004008245],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007790844,0.00007097001,0.0018702022,0.000011897706,0.00036442047,4.435418e-7,0.00014397278,0.010887,0.12990871,0.8096967,0.008982224,0.03798559],"study_design_scores_gemma":[0.00049396435,0.00009402488,0.0076163886,0.000020355568,0.0003675252,3.0657162e-7,0.000024804416,0.7942209,0.16971031,0.016345927,0.010889412,0.00021605713],"about_ca_topic_score_codex":0.00003141401,"about_ca_topic_score_gemma":0.0000069702064,"teacher_disagreement_score":0.9492001,"about_ca_system_score_codex":0.00005516327,"about_ca_system_score_gemma":0.000035258556,"threshold_uncertainty_score":0.34680647},"labels":[],"label_agreement":null},{"id":"W4406771711","doi":"10.1051/itmconf/20257004009","title":"Advances in Image Generation Technology: Exploring GANs and MirrorGANs","year":2025,"lang":"en","type":"article","venue":"ITM Web of Conferences","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Image (mathematics); Computer science; Artificial intelligence","score_opus":0.028632086419774296,"score_gpt":0.26286138631933004,"score_spread":0.23422929989955574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406771711","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23322472,0.0041576433,0.7348844,0.0059539643,0.0006509306,0.00023005846,0.000002764104,0.00009842933,0.020797081],"genre_scores_gemma":[0.98068553,0.0017000509,0.01749412,0.000034852026,0.000020411706,0.000021977155,6.0014986e-7,0.000001827751,0.000040638042],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993158,0.00004020129,0.00018963909,0.00024056542,0.000080783066,0.00013302766],"domain_scores_gemma":[0.99960977,0.000055939345,0.000057796697,0.0001739644,0.00008508186,0.000017428143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013444883,0.00009018435,0.0001682286,0.00026480624,0.000055493092,0.000066968,0.00029586672,0.000042922777,0.000009877761],"category_scores_gemma":[0.000060408423,0.000079829486,0.000017536415,0.00049736997,0.0001248043,0.0007728175,0.00010402453,0.00006826656,0.0000012989573],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000711803,0.00006472354,0.027767995,0.000042215925,0.000019726644,0.0000062585823,0.0004683096,0.0002862057,0.16451412,0.36319652,0.00013688,0.4434899],"study_design_scores_gemma":[0.0008724523,0.00016870731,0.012970279,0.00032173368,0.000019409055,0.0000025852373,0.0012385995,0.22860427,0.690617,0.043055743,0.021693083,0.00043611508],"about_ca_topic_score_codex":0.000031241972,"about_ca_topic_score_gemma":0.0003959793,"teacher_disagreement_score":0.7474608,"about_ca_system_score_codex":0.000008073754,"about_ca_system_score_gemma":0.0002490938,"threshold_uncertainty_score":0.3255352},"labels":[],"label_agreement":null},{"id":"W4407027944","doi":"10.1016/j.dib.2025.111352","title":"A dataset of drip patterns for teaching and research purposes in forensic bloodstain pattern analysis","year":2025,"lang":"en","type":"article","venue":"Data in Brief","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"University of Ontario Institute of Technology","keywords":"Forensic science; Data science; Computer science; Archaeology; Geography","score_opus":0.0540798712795852,"score_gpt":0.3653242377729824,"score_spread":0.3112443664933972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407027944","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04384759,0.0001622352,0.94944656,0.0009405306,0.00005146199,0.00031498214,0.00519791,0.0000059938025,0.000032726362],"genre_scores_gemma":[0.9718864,0.00003634181,0.024681734,0.0002297664,0.000026822489,0.000027399252,0.003089964,0.0000041136236,0.000017468199],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982819,0.00040572713,0.0003167854,0.0005488953,0.0001732493,0.00027345464],"domain_scores_gemma":[0.9978368,0.0007814721,0.000057787933,0.0012450413,0.000048255173,0.00003061489],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029992661,0.000089716224,0.00026229877,0.00057370897,0.00008497644,0.00013274876,0.0011969937,0.000040148836,0.0000033460756],"category_scores_gemma":[0.00057831686,0.000084397434,0.000024162473,0.00087656983,0.000077349156,0.0005415035,0.0014621224,0.00021014099,2.6966205e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003102114,0.0002957138,0.2156752,0.00017753875,0.00030368895,0.00003080494,0.0010792463,0.0008488637,0.0004143895,0.00251411,0.029018436,0.74961096],"study_design_scores_gemma":[0.0010464144,0.000080475445,0.11184397,0.00018692431,0.00008753382,9.2597725e-7,0.00040868614,0.8622234,0.0011095944,0.0018525933,0.020934764,0.00022474896],"about_ca_topic_score_codex":0.0068935845,"about_ca_topic_score_gemma":0.0100819785,"teacher_disagreement_score":0.9280388,"about_ca_system_score_codex":0.00002018587,"about_ca_system_score_gemma":0.00004694928,"threshold_uncertainty_score":0.9997196},"labels":[],"label_agreement":null},{"id":"W4407568385","doi":"10.1117/12.3047788","title":"Ultrasound image generation using latent diffusion models","year":2025,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Artificial intelligence; Image (mathematics); Computer vision; Diffusion; Physics","score_opus":0.03178186559234559,"score_gpt":0.25475852207999233,"score_spread":0.22297665648764675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407568385","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0182915,0.00007611821,0.9740688,0.0004039951,0.00046696822,0.000104733845,5.8645355e-7,0.00007357609,0.00651369],"genre_scores_gemma":[0.72011286,0.000027585369,0.27822143,0.00045553088,0.00009232148,0.0000030756983,0.0000021917722,0.0000034344193,0.0010815621],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991954,0.00006405918,0.00015723892,0.00029127693,0.00012064585,0.00017137334],"domain_scores_gemma":[0.9994837,0.00004288979,0.000033755055,0.00031213244,0.000090886104,0.00003661734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013976727,0.00010361603,0.000104239894,0.00007469245,0.00021061015,0.00027715295,0.00027393864,0.00004068672,0.000029451201],"category_scores_gemma":[0.000018992285,0.00008480805,0.00005397265,0.00027427427,0.000022028522,0.0007709947,0.00014557535,0.000051077903,0.000009677274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022884378,0.00006181071,0.00008584417,0.0000042652878,0.000022834316,0.000002978913,0.00013345479,0.13236415,0.78586555,0.06530275,0.005186743,0.010967346],"study_design_scores_gemma":[0.0001148699,0.000006861411,0.00013869136,0.0000073542174,0.0000065411145,0.000002125726,0.0000063746043,0.94829124,0.046153378,0.005016818,0.00016339343,0.00009236095],"about_ca_topic_score_codex":0.000106650594,"about_ca_topic_score_gemma":0.000017405104,"teacher_disagreement_score":0.8159271,"about_ca_system_score_codex":0.000044172684,"about_ca_system_score_gemma":0.000043703603,"threshold_uncertainty_score":0.3458372},"labels":[],"label_agreement":null},{"id":"W4408075062","doi":"10.1007/978-3-658-47422-5_60","title":"Abstract: Würstchen","year":2025,"lang":"de","type":"book-chapter","venue":"Informatik aktuell","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Medicine","score_opus":0.015462444479195897,"score_gpt":0.21917700775872492,"score_spread":0.20371456327952903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408075062","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000049629566,0.0018203852,0.15301012,0.0008231453,0.0037994557,0.00059098226,0.00011846945,0.00017515029,0.83965737],"genre_scores_gemma":[0.07479912,0.0075401333,0.062192366,0.011379545,0.0047251186,0.00007662661,0.00053459586,0.00019339878,0.8385591],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960295,0.000033349545,0.0015703145,0.00070436875,0.00081765326,0.00084483915],"domain_scores_gemma":[0.9962154,0.00036846587,0.00091248815,0.0016863197,0.0004911695,0.00032612905],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000609977,0.0010007224,0.00097201177,0.00045100783,0.00048629084,0.0009937894,0.002242719,0.0007587483,0.0042121317],"category_scores_gemma":[0.000097991644,0.00096401136,0.00060571654,0.00019209457,0.00025950317,0.0018167506,0.0011602413,0.0010743778,0.019678129],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004533983,0.00006886489,0.000015302177,0.0006137793,0.0007410617,0.00009319269,0.0019346728,0.0035698263,0.000043998105,0.30190644,0.17417826,0.51678926],"study_design_scores_gemma":[0.00044969216,0.0000748462,0.00011027498,0.00078965566,0.000129256,0.000008647616,0.000037212234,0.043224365,0.00043718296,0.0058816453,0.9477936,0.0010636296],"about_ca_topic_score_codex":0.00010949334,"about_ca_topic_score_gemma":0.000021187883,"teacher_disagreement_score":0.77361536,"about_ca_system_score_codex":0.00016737342,"about_ca_system_score_gemma":0.000484824,"threshold_uncertainty_score":0.99928105},"labels":[],"label_agreement":null},{"id":"W4408133719","doi":"10.18280/mmep.120219","title":"Behavior of Visual Content in Deepfake Generated Based on Conditional Generative Adversarial Networks","year":2025,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Generative grammar; Adversarial system; Content (measure theory); Computer science; Generative adversarial network; Artificial intelligence; Machine learning; Econometrics; Mathematics; Image (mathematics)","score_opus":0.025244255038779133,"score_gpt":0.2270222837456355,"score_spread":0.20177802870685635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408133719","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01366683,0.00008765338,0.98557234,0.000107370935,0.00013758139,0.00024214765,0.0000024976607,0.000045823257,0.00013775488],"genre_scores_gemma":[0.88952327,0.000008039245,0.11024727,0.000065667926,0.000034968485,0.000066442895,0.00000749441,0.000008408937,0.000038464466],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989444,0.000042613374,0.0003599587,0.0002817002,0.00014743004,0.00022390719],"domain_scores_gemma":[0.9994684,0.00020741872,0.00004959064,0.0001493965,0.000068154564,0.00005704653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027309565,0.00017169003,0.00028542682,0.0001508371,0.00005100687,0.000060913306,0.00014534403,0.00009164187,0.0000062752874],"category_scores_gemma":[0.000030443383,0.00015212354,0.000054761473,0.0002362797,0.00003597721,0.000083395884,0.000048659225,0.0001604792,0.0000010286523],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009011985,0.00014660478,0.000024682531,0.00004589704,0.000015623666,0.0000026771675,0.00006616118,0.9673823,0.00088670646,0.03090905,0.000013597561,0.0004977022],"study_design_scores_gemma":[0.0005188627,0.000078651625,0.00006379655,0.00020915273,0.00001514016,8.133632e-7,0.0000047912026,0.9951944,0.0018953006,0.0018618284,0.000019354231,0.0001379527],"about_ca_topic_score_codex":0.000012080579,"about_ca_topic_score_gemma":0.0000013416109,"teacher_disagreement_score":0.8758564,"about_ca_system_score_codex":0.000031386433,"about_ca_system_score_gemma":0.000028401993,"threshold_uncertainty_score":0.6203418},"labels":[],"label_agreement":null},{"id":"W4408181558","doi":"10.1109/jiot.2025.3549038","title":"Generative-Diffusion-Model-Based Deep-Learning Framework for Remaining Useful Life Prediction","year":2025,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Institute for Information and Communications Technology Promotion","keywords":"Computer science; Artificial intelligence; Generative grammar; Generative model; Machine learning; Data modeling; Diffusion; Deep learning","score_opus":0.017412362220706752,"score_gpt":0.2649268801844142,"score_spread":0.24751451796370744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408181558","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012472012,0.00023156394,0.9834719,0.0011383188,0.0021494762,0.00014381637,0.0000013706119,0.00006042753,0.00033116384],"genre_scores_gemma":[0.56988376,0.00001891807,0.42864627,0.00089838356,0.00027554636,0.0000074788913,9.542659e-7,0.000010237565,0.0002584397],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982959,0.00018625392,0.00057742983,0.0003339215,0.00029873793,0.00030774545],"domain_scores_gemma":[0.99822444,0.0005030149,0.00048139069,0.00023787918,0.0004212703,0.00013198586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009820287,0.00019693929,0.00031826415,0.0002580185,0.00030492962,0.0003647942,0.00080072304,0.00014965821,0.000019391005],"category_scores_gemma":[0.0010318995,0.0001744885,0.00025116952,0.00024733087,0.000060810973,0.00072061195,0.00011213859,0.0006230991,0.0000019773565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022330937,0.00016609188,0.0022331534,0.00006822705,0.00032853324,0.000010258725,0.005513643,0.9018386,0.020877616,0.015236642,0.0059133642,0.04759057],"study_design_scores_gemma":[0.00046526798,0.00018394078,0.00012786136,0.0004786933,0.00003228907,0.000007615684,0.00006946581,0.9636699,0.019959603,0.013880899,0.0009900498,0.00013443915],"about_ca_topic_score_codex":0.000006887875,"about_ca_topic_score_gemma":0.0000010442362,"teacher_disagreement_score":0.55741173,"about_ca_system_score_codex":0.00008981836,"about_ca_system_score_gemma":0.0002037338,"threshold_uncertainty_score":0.7115434},"labels":[],"label_agreement":null},{"id":"W4408237370","doi":"10.23977/acss.2025.090106","title":"PGGAN: Probability Guided Generative Adversarial Network for Image Inpainting","year":2025,"lang":"en","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Inpainting; Adversarial system; Image (mathematics); Generative grammar; Artificial intelligence; Computer science; Generative adversarial network; Pattern recognition (psychology); Computer vision","score_opus":0.019326625240915177,"score_gpt":0.2775767608863517,"score_spread":0.25825013564543653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408237370","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012077736,0.005032396,0.9885594,0.0004098027,0.0030991673,0.0010586261,0.0000059785034,0.000074237985,0.00055261515],"genre_scores_gemma":[0.38184464,0.00020775372,0.6154402,0.00055161247,0.0015896055,0.00024069805,0.000006491861,0.000013578941,0.000105458996],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975047,0.00040460564,0.00066643144,0.000773997,0.00016508563,0.00048514418],"domain_scores_gemma":[0.9983332,0.00074514985,0.00020149059,0.0004117961,0.00023859818,0.00006977269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014008989,0.00026846965,0.0005370207,0.00010176468,0.00029022654,0.00043700406,0.0005303237,0.000092338116,0.0000016395528],"category_scores_gemma":[0.00008404288,0.00023464476,0.000100811274,0.0004816089,0.00009244514,0.0010310111,0.00031803266,0.00012609895,0.0000012528205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041762683,0.00008586384,0.0018786759,0.00028350498,0.0000849773,0.000011708836,0.00056821783,0.8107559,0.00053702015,0.069468215,0.006514191,0.10976994],"study_design_scores_gemma":[0.000765594,0.00009964614,0.00018916136,0.00024151523,0.000009182384,0.000004112508,0.000020891448,0.9638809,0.00034504465,0.020313447,0.013868992,0.00026149984],"about_ca_topic_score_codex":0.000049411614,"about_ca_topic_score_gemma":0.000044829147,"teacher_disagreement_score":0.38063687,"about_ca_system_score_codex":0.000062121115,"about_ca_system_score_gemma":0.00007018019,"threshold_uncertainty_score":0.95685357},"labels":[],"label_agreement":null},{"id":"W4408251546","doi":"10.1016/j.asoc.2025.112964","title":"Art style classification via self-supervised dual-teacher knowledge distillation","year":2025,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Science Foundation of Jiangxi Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Distillation; Dual (grammatical number); Style (visual arts); Computer science; Artificial intelligence; Machine learning; Chromatography; Chemistry; Art; Visual arts","score_opus":0.013267341453817997,"score_gpt":0.24454083378105848,"score_spread":0.23127349232724048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408251546","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047709933,0.000086161584,0.94906,0.0003711356,0.0004330006,0.00027616307,3.76954e-7,0.00043896947,0.044563193],"genre_scores_gemma":[0.8955033,0.000002840718,0.1035737,0.00017277057,0.00021257508,0.000012754803,0.000011947889,0.000011876912,0.0004982674],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985099,0.00010877789,0.00034540673,0.00056176574,0.00015880061,0.0003153568],"domain_scores_gemma":[0.9989483,0.00025547712,0.0001241692,0.0004946254,0.000112386726,0.00006506663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046334398,0.00020304523,0.00022237186,0.00011715022,0.00040502465,0.00022557547,0.00040123414,0.000097461976,0.000014442702],"category_scores_gemma":[0.000032854885,0.00020482922,0.00007173473,0.0006614187,0.000035724104,0.00018465503,0.00030712364,0.00017169307,0.00021120414],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000135408145,0.0003370716,0.0010934987,0.00006058184,0.00013920382,0.0000021790397,0.002815328,0.010245724,0.017337393,0.07924994,0.011657846,0.8770477],"study_design_scores_gemma":[0.00031173084,0.000010004538,0.0057237027,0.000020558999,0.000017906817,9.567214e-7,0.00005715968,0.9808037,0.00089024525,0.0013346925,0.01062094,0.00020839163],"about_ca_topic_score_codex":0.00000463358,"about_ca_topic_score_gemma":0.000003928914,"teacher_disagreement_score":0.970558,"about_ca_system_score_codex":0.000095031595,"about_ca_system_score_gemma":0.00007358035,"threshold_uncertainty_score":0.83526933},"labels":[],"label_agreement":null},{"id":"W4408530997","doi":"10.1007/s00521-025-11137-1","title":"Cycle generative adversarial Transformer network for MRI brain tumor segmentation","year":2025,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"National Natural Science Foundation of China","keywords":"Computational Science and Engineering; Computer science; Adversarial system; Transformer; Generative grammar; Generative adversarial network; Artificial intelligence; Segmentation; Pattern recognition (psychology); Machine learning; Deep learning; Physics","score_opus":0.00967681207318998,"score_gpt":0.2702672205187858,"score_spread":0.26059040844559583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408530997","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019280798,0.00014881807,0.9901658,0.006119705,0.00025234406,0.0007337743,0.00000849969,0.00009780992,0.0005451423],"genre_scores_gemma":[0.7002482,0.000012553021,0.29326513,0.0049219676,0.00095298025,0.0002522738,0.000032691143,0.000011183335,0.00030304954],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990166,0.00006399231,0.00021596263,0.0003877245,0.00007487556,0.00024087976],"domain_scores_gemma":[0.9992735,0.00033932575,0.0000706182,0.00018730013,0.00007760409,0.000051653733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019034212,0.00013188455,0.0001489836,0.00004434181,0.00070901983,0.000167106,0.00023338132,0.000033838573,0.0000018808274],"category_scores_gemma":[0.000013834689,0.00012494191,0.00006577814,0.00034618584,0.000046524154,0.00017406237,0.000053633285,0.00008345451,0.0000019846143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003162487,0.0000880316,0.00023282618,0.00004295103,0.00008805805,6.909971e-7,0.0006335415,0.34793788,0.009422192,0.15167867,0.031364556,0.45847896],"study_design_scores_gemma":[0.00057185674,0.000047976922,0.0003870218,0.000012171282,0.0000215677,0.0000021536482,0.000044960772,0.96025765,0.003426125,0.009066888,0.0260012,0.00016045455],"about_ca_topic_score_codex":0.000018944931,"about_ca_topic_score_gemma":0.0000131826555,"teacher_disagreement_score":0.6983201,"about_ca_system_score_codex":0.000020372052,"about_ca_system_score_gemma":0.00003634756,"threshold_uncertainty_score":0.5453279},"labels":[],"label_agreement":null},{"id":"W4409137672","doi":"10.1016/j.ijmedinf.2025.105903","title":"A systematic review of generative AI approaches for medical image enhancement: Comparing GANs, transformers, and diffusion models","year":2025,"lang":"en","type":"review","venue":"International Journal of Medical Informatics","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"Luonnontieteiden ja Tekniikan Tutkimuksen Toimikunta; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Generative grammar; Generative model; Transformer; Artificial intelligence; Engineering; Electrical engineering","score_opus":0.045585322837716574,"score_gpt":0.33782283335414376,"score_spread":0.2922375105164272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409137672","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.630868e-8,0.48282456,0.515483,0.00073940115,0.00034795492,0.00044667878,0.000010501932,0.0000033957306,0.00014441139],"genre_scores_gemma":[0.000013128843,0.9649677,0.033656023,0.0010583537,0.00019218803,0.00005082336,0.000030538664,0.000008754292,0.000022472093],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9931517,0.0002695465,0.003537594,0.00014045947,0.00270047,0.00020021104],"domain_scores_gemma":[0.99580544,0.00097346306,0.0020327668,0.00019629058,0.00073810614,0.00025390685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036234376,0.00032167992,0.0025022556,0.000323512,0.00005669568,0.00014957617,0.0021943669,0.00026051962,0.000028186003],"category_scores_gemma":[0.0014905941,0.00020618395,0.00062843505,0.00020319129,0.00013253596,0.0008327399,0.00035950722,0.00054381124,0.0000010324125],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005587171,0.000092891016,3.502817e-8,0.65312105,0.0009386747,0.000010075069,0.00044095374,0.000016776474,8.5396714e-8,0.0050972044,0.0014412777,0.3388354],"study_design_scores_gemma":[0.00042385745,0.00006279257,8.451206e-9,0.62737453,0.00058275554,0.00015493314,0.0000527941,0.36257842,0.0000059149975,0.00033150904,0.008285438,0.00014700925],"about_ca_topic_score_codex":0.0000023388259,"about_ca_topic_score_gemma":0.0000014655109,"teacher_disagreement_score":0.48214316,"about_ca_system_score_codex":0.00010200765,"about_ca_system_score_gemma":0.0011771813,"threshold_uncertainty_score":0.8407937},"labels":[],"label_agreement":null},{"id":"W4409374101","doi":"10.1016/b978-0-443-15888-9.00012-1","title":"Advanced deep learning methods","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Artificial intelligence; Computer science","score_opus":0.01283156315366462,"score_gpt":0.2738736451801055,"score_spread":0.26104208202644086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409374101","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.4679066e-8,0.0019524023,0.38216886,0.000071560025,0.0006801902,0.00019114252,9.981721e-7,0.00012259814,0.6148122],"genre_scores_gemma":[0.00002811547,0.00014872916,0.3202444,0.00031828645,0.00019633958,0.00001905286,0.0000036095835,0.00002812524,0.6790133],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979103,0.00020154861,0.00042759764,0.0008208355,0.00026156058,0.00037811455],"domain_scores_gemma":[0.99824095,0.00032695069,0.00027549115,0.00086345576,0.0001725989,0.00012054612],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000541728,0.0004777601,0.0006356185,0.00019394835,0.00026997784,0.0001871571,0.0010460508,0.0002845679,0.000108206405],"category_scores_gemma":[0.000095217874,0.00045262504,0.00033911175,0.00003816815,0.000083289575,0.00014885321,0.0006641119,0.00071777805,0.000099185076],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003093971,0.0000023949704,2.2234687e-7,0.000021357546,0.0000840396,0.000014168087,0.000111172376,0.00026000492,0.00007908881,0.027369289,0.00010326001,0.9719519],"study_design_scores_gemma":[0.00014189987,0.00004704232,0.0000017019561,0.00021683307,0.000052917338,0.0000038950366,0.000003363474,0.009912557,0.00040739472,0.017922696,0.9708441,0.0004455893],"about_ca_topic_score_codex":2.789358e-7,"about_ca_topic_score_gemma":0.0000052358223,"teacher_disagreement_score":0.9715063,"about_ca_system_score_codex":0.00008043853,"about_ca_system_score_gemma":0.00012479047,"threshold_uncertainty_score":0.9997926},"labels":[],"label_agreement":null},{"id":"W4410204823","doi":"10.1016/j.imavis.2025.105545","title":"A landmarks-assisted diffusion model with heatmap-guided denoising loss for high-fidelity and controllable facial image generation","year":2025,"lang":"en","type":"article","venue":"Image and Vision Computing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of Education and Child Care","funders":"National Natural Science Foundation of China","keywords":"Image denoising; Image (mathematics); Noise reduction; Fidelity; High fidelity; Computer science; Artificial intelligence; Computer vision; Diffusion; Pattern recognition (psychology); Algorithm; Physics; Acoustics; Telecommunications","score_opus":0.015803938746721445,"score_gpt":0.2928081992466695,"score_spread":0.2770042604999481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410204823","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2037329,0.00021869084,0.794377,0.0010126717,0.00013053839,0.0003355636,0.000005915185,0.000060163242,0.00012650444],"genre_scores_gemma":[0.70860046,0.000021598538,0.29079837,0.00034955784,0.00011892882,0.0000059779036,0.000010131204,0.000008223341,0.0000867378],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984688,0.000116299445,0.00034362564,0.00060087704,0.00015989353,0.00031048025],"domain_scores_gemma":[0.9989885,0.00022398026,0.0001279294,0.0002655588,0.00031008897,0.00008390759],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005285413,0.00022278525,0.00034504765,0.00010338638,0.0008355331,0.00079846254,0.00017773209,0.00007375616,0.0000014322121],"category_scores_gemma":[0.00008983763,0.00017661153,0.00004666048,0.00021762318,0.00008461625,0.0006277955,0.0002968891,0.000102916594,6.046558e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025590012,0.00018230185,0.0009034714,0.00014480678,0.000103299695,0.000022574699,0.00059864856,0.015102118,0.4512093,0.0030894522,0.005050083,0.523338],"study_design_scores_gemma":[0.0022218197,0.0001085986,0.0019839103,0.000111664354,0.000031401632,0.0000084858575,0.000017963595,0.98619115,0.007869961,0.001096655,0.00015470335,0.00020366996],"about_ca_topic_score_codex":0.00009776979,"about_ca_topic_score_gemma":0.00003967167,"teacher_disagreement_score":0.97108907,"about_ca_system_score_codex":0.00003408101,"about_ca_system_score_gemma":0.00007096857,"threshold_uncertainty_score":0.7699593},"labels":[],"label_agreement":null},{"id":"W4410719643","doi":"10.1007/978-3-031-91838-4_14","title":"QSD: Query-Selection Denoising Score for Image Editing in Latent Diffusion Model","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Selection (genetic algorithm); Image denoising; Noise reduction; Artificial intelligence; Image editing; Image (mathematics); Computer vision; Pattern recognition (psychology)","score_opus":0.01806262709527675,"score_gpt":0.24312162780143012,"score_spread":0.22505900070615337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410719643","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014964798,0.00020523659,0.9960419,0.0006064639,0.0015932862,0.0006323064,0.0000055924224,0.00008712774,0.00067842554],"genre_scores_gemma":[0.13393727,0.00004553335,0.8636895,0.0008618954,0.0009018282,0.000028471793,0.000008032629,0.000032326818,0.00049513724],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99661833,0.000042167245,0.0005694628,0.00151032,0.00055391,0.00070578826],"domain_scores_gemma":[0.99824536,0.0004475196,0.00026847774,0.00060902676,0.00033092857,0.000098665834],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00092215004,0.00048531432,0.000529561,0.00094335363,0.00039682214,0.00065303646,0.0015706402,0.00029742424,0.0000042434444],"category_scores_gemma":[0.00019738537,0.00045852314,0.00016507911,0.00068334106,0.00024418053,0.0008580437,0.0009442798,0.0006186474,0.0000031453521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009088594,0.00002832984,0.000086996595,0.000050723378,0.0000067203723,0.000014577364,0.00035879738,0.5963121,0.0017883212,0.0041900356,0.00010136835,0.3970529],"study_design_scores_gemma":[0.00026890228,0.00006713792,0.00005600874,0.0007011863,0.000007872953,0.0000078442135,1.8092878e-7,0.9355928,0.0037506013,0.05901114,0.00013618666,0.00040017563],"about_ca_topic_score_codex":0.00005308482,"about_ca_topic_score_gemma":0.00038441524,"teacher_disagreement_score":0.39665276,"about_ca_system_score_codex":0.0004781367,"about_ca_system_score_gemma":0.0005151926,"threshold_uncertainty_score":0.9997867},"labels":[],"label_agreement":null},{"id":"W4411014113","doi":"10.20944/preprints202506.0198.v1","title":"Markov Observation Models and Deepfakes","year":2025,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Markov chain; Econometrics; Computer science; Statistical physics; Geography; Mathematics; Machine learning; Physics","score_opus":0.13989079778686392,"score_gpt":0.3188212364318213,"score_spread":0.1789304386449574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411014113","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.080271214,0.00044955194,0.90415347,0.0016052374,0.001044495,0.00050503697,0.000011894719,0.00022971244,0.011729398],"genre_scores_gemma":[0.9296926,0.00053336204,0.06669694,0.00043518218,0.00017937174,0.00010601062,0.000016381142,0.000013095756,0.0023270044],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997645,0.00022031784,0.00038692524,0.0011856491,0.00026532589,0.0002967349],"domain_scores_gemma":[0.997952,0.00012810656,0.00021166563,0.0013974294,0.00020856797,0.000102220125],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00061857805,0.00032741317,0.000379651,0.00013532602,0.00015695913,0.00013904084,0.0011439106,0.00026852492,0.00004018312],"category_scores_gemma":[0.00014058784,0.00033525855,0.00012880612,0.0001978436,0.00006202115,0.0005306398,0.004580028,0.0004688772,0.000046489466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000094370545,0.00042569527,0.29417193,0.0009836513,0.0008717135,0.00004246267,0.006215302,0.4342543,0.008627193,0.08045818,0.001780247,0.17207497],"study_design_scores_gemma":[0.00022416424,0.000009644781,0.09990837,0.0002330011,0.000048701942,0.0000022244608,0.000020985566,0.8270211,0.011592836,0.058469392,0.0019526201,0.0005169556],"about_ca_topic_score_codex":0.00019039665,"about_ca_topic_score_gemma":0.000021875474,"teacher_disagreement_score":0.84942144,"about_ca_system_score_codex":0.00007025432,"about_ca_system_score_gemma":0.00016309007,"threshold_uncertainty_score":0.99990994},"labels":[],"label_agreement":null},{"id":"W4411114763","doi":"10.1016/j.cmpb.2025.108869","title":"echoGAN: Extending the field of view in Transthoracic Echocardiography through conditional GAN-based outpainting","year":2025,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Agentúra na Podporu Výskumu a Vývoja","keywords":"Field (mathematics); Computer science; Cardiology; Internal medicine; Medicine; Mathematics","score_opus":0.033116231603481074,"score_gpt":0.3842782037554532,"score_spread":0.3511619721519721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411114763","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010889508,0.0032473186,0.9902662,0.0043755355,0.00045018937,0.0003372619,8.216346e-7,0.000028088365,0.00020565683],"genre_scores_gemma":[0.4241412,0.00015766615,0.57429796,0.0012993504,0.000070283,0.000024296798,0.0000037034624,0.000003415536,0.000002117405],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99810904,0.0006904353,0.00044401994,0.00036505086,0.00014568218,0.00024578132],"domain_scores_gemma":[0.9981162,0.0013989848,0.00009406169,0.0003021206,0.00005697551,0.00003167464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025112496,0.00015944774,0.00038714518,0.00031181023,0.00008314226,0.00006391438,0.000425298,0.00007525959,0.0000034649615],"category_scores_gemma":[0.00006263817,0.000108745924,0.00010541999,0.001848522,0.00020856447,0.00014197867,0.0000682509,0.0002108979,1.3086847e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010397776,0.00006370233,0.00505053,0.00008840713,0.000030020676,0.0000076114998,0.00039590712,0.00045144357,0.00026395897,0.0032318202,0.0000779084,0.9903283],"study_design_scores_gemma":[0.0024377303,0.0007587071,0.03389755,0.0023005311,0.00006849041,0.000008575715,0.0002187964,0.8690742,0.009052803,0.049343128,0.03236278,0.0004766648],"about_ca_topic_score_codex":0.00006662603,"about_ca_topic_score_gemma":0.0000065355125,"teacher_disagreement_score":0.98985165,"about_ca_system_score_codex":0.000013128904,"about_ca_system_score_gemma":0.00003545463,"threshold_uncertainty_score":0.443453},"labels":[],"label_agreement":null},{"id":"W4411162860","doi":"10.1016/j.egyr.2025.05.062","title":"Generative AI applied for synthetic data in PMU","year":2025,"lang":"en","type":"article","venue":"Energy Reports","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Total; Agência Nacional do Petróleo, Gás Natural e Biocombustíveis; Fundação de Amparo à Pesquisa do Estado de São Paulo; Research Centre for Gas Innovation","keywords":"Computer science; Generative grammar; Artificial intelligence","score_opus":0.015613218940903674,"score_gpt":0.26380150078751213,"score_spread":0.24818828184660846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411162860","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018418637,0.00026017803,0.9859541,0.0016054335,0.0007871419,0.0001509691,0.0000032117146,0.000053951986,0.011000799],"genre_scores_gemma":[0.934476,0.000018340848,0.061615165,0.0016343395,0.00011798787,0.000116080504,0.0000376592,0.0000093977515,0.0019749945],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983882,0.000054475782,0.00037045236,0.00079059444,0.00013071256,0.00026558462],"domain_scores_gemma":[0.9981091,0.00012932172,0.00011445324,0.0015324149,0.0000706138,0.00004411473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000477152,0.00015012734,0.00023724674,0.00012687553,0.000112420654,0.00014228084,0.0006235653,0.00006554607,0.000010639383],"category_scores_gemma":[0.00014618898,0.000136374,0.000044557608,0.00038973018,0.00003652664,0.0003418275,0.0005055346,0.00006676309,0.0000011709534],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005883693,0.00038596886,0.00050494587,0.00004014307,0.0002330308,0.0004668242,0.0004829112,0.05118127,0.012467226,0.45004126,0.11510583,0.36903176],"study_design_scores_gemma":[0.00041637645,0.000041977386,0.00048679375,0.000056666227,0.000026211492,0.000031192103,0.000020568848,0.59077024,0.057276674,0.053196795,0.29724258,0.0004338925],"about_ca_topic_score_codex":0.00011302626,"about_ca_topic_score_gemma":0.00025419547,"teacher_disagreement_score":0.93429184,"about_ca_system_score_codex":0.000037513204,"about_ca_system_score_gemma":0.00017117224,"threshold_uncertainty_score":0.55611706},"labels":[],"label_agreement":null},{"id":"W4411823757","doi":"10.3390/math13132128","title":"Markov Observation Models and Deepfakes","year":2025,"lang":"en","type":"article","venue":"Mathematics","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Markov chain; Computer science; Machine learning","score_opus":0.024921546614744793,"score_gpt":0.23916587669481548,"score_spread":0.21424433008007068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411823757","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004447408,0.00013903988,0.9876779,0.0008338004,0.00009735175,0.00007982407,3.6675968e-7,0.00004758654,0.0066767456],"genre_scores_gemma":[0.2595315,0.000033901186,0.73918235,0.0003010175,0.000019181258,0.0000075669077,5.3044647e-7,0.0000032030396,0.00092073606],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995596,0.000019205956,0.00012260777,0.00013017392,0.00007481938,0.00009359748],"domain_scores_gemma":[0.9995799,0.00009682271,0.0000352877,0.00022414442,0.000043982534,0.000019876832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015448613,0.000066631386,0.000096058095,0.000037816804,0.00007627457,0.000120546785,0.00018382355,0.000028121407,0.0000027983954],"category_scores_gemma":[0.00004115673,0.000056582016,0.000019447774,0.00016082983,0.000018194114,0.00030690114,0.00011198563,0.000033211865,0.0000034018942],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015368323,0.00007256583,0.00015361745,0.000104991625,0.000035216828,0.0000019444667,0.0013716662,0.0040850304,0.0012736312,0.9058076,0.0038374232,0.08325474],"study_design_scores_gemma":[0.000059953636,0.0000052060477,0.0002210574,0.000025446161,0.000005502814,6.9090476e-7,0.000028429375,0.81059897,0.0010159909,0.18763185,0.0003573091,0.000049622475],"about_ca_topic_score_codex":0.000003272821,"about_ca_topic_score_gemma":0.000003105935,"teacher_disagreement_score":0.8065139,"about_ca_system_score_codex":0.000009452009,"about_ca_system_score_gemma":0.000014898995,"threshold_uncertainty_score":0.23073475},"labels":[],"label_agreement":null},{"id":"W4411968859","doi":"10.1016/j.patrec.2025.06.011","title":"Text optimization with latent inversion for non-rigid image editing","year":2025,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Inversion (geology); Computer science; Artificial intelligence; Image (mathematics); Computer vision; Algorithm; Pattern recognition (psychology); Geology","score_opus":0.01216039675966703,"score_gpt":0.21769538524601184,"score_spread":0.2055349884863448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411968859","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00627375,0.0000040808045,0.98251057,0.009843027,0.00054009474,0.00038552532,0.000012273518,0.00007646492,0.00035424586],"genre_scores_gemma":[0.57639366,0.00001334489,0.40663436,0.016122548,0.00044372602,0.00015288044,0.00014326413,0.000020904985,0.00007530124],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990175,0.000052290867,0.0001855005,0.0003736728,0.0001316918,0.00023936748],"domain_scores_gemma":[0.9993957,0.00010132807,0.00011059991,0.00019164667,0.00015609975,0.000044615415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015354529,0.00014824314,0.00013605323,0.00014334281,0.00020988965,0.00021606541,0.00022577023,0.000040382853,0.0000332676],"category_scores_gemma":[0.000026749909,0.00013114983,0.00006705018,0.00025456326,0.00003622694,0.00064675196,0.00006911079,0.00007975899,0.000030435847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008506105,0.00016189854,0.003021126,0.00021211794,0.00021693876,0.000026378406,0.0006159552,0.08952902,0.030894993,0.000024264093,0.07220804,0.8030042],"study_design_scores_gemma":[0.0010085875,0.000068018446,0.00054213323,0.0002204603,0.000037144047,0.0000023950881,0.00003740115,0.97019136,0.026900008,0.00007401852,0.0006715869,0.00024691425],"about_ca_topic_score_codex":0.000022457989,"about_ca_topic_score_gemma":0.000005396583,"teacher_disagreement_score":0.8806623,"about_ca_system_score_codex":0.00004866051,"about_ca_system_score_gemma":0.00002052294,"threshold_uncertainty_score":0.5348135},"labels":[],"label_agreement":null},{"id":"W4412450822","doi":"10.1016/j.rcim.2025.103086","title":"Grid-to-Robot: Deep Wasserstein generative modeling of robot/power grid interaction using hybrid adversarial Residual Networks","year":2025,"lang":"en","type":"article","venue":"Robotics and Computer-Integrated Manufacturing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Grid; Residual; Computer science; Robot; Generative grammar; Power grid; Adversarial system; Artificial intelligence; Power (physics); Mathematics; Algorithm; Physics","score_opus":0.014858110059176153,"score_gpt":0.23813159870415115,"score_spread":0.223273488644975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412450822","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017924124,0.00017571406,0.9765971,0.00033456748,0.004355439,0.0003743153,0.000009598075,0.00011128933,0.00011786874],"genre_scores_gemma":[0.71276975,0.00006888805,0.2862205,0.0002691843,0.00059414015,0.0000062193462,0.000024270323,0.000023995288,0.000023040653],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99714917,0.0002467969,0.00077399274,0.0009259527,0.00029723338,0.00060688343],"domain_scores_gemma":[0.99848,0.00018078722,0.00025913058,0.0005894793,0.00029163278,0.00019894482],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003530104,0.00052083534,0.00068250287,0.00044896489,0.00042399726,0.0005069993,0.00069501443,0.00015795161,0.000008228081],"category_scores_gemma":[0.000027728593,0.00048315298,0.0001780318,0.0004387308,0.00006288316,0.0006760722,0.0007489242,0.00048741125,0.0000025213935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000637,0.000060658745,0.000019199526,0.000019809848,0.00023644001,0.000023480992,0.00019992195,0.98457587,0.0009874088,0.00097082986,0.00028979182,0.012552866],"study_design_scores_gemma":[0.0005355641,0.00015257958,0.00007906237,0.00028385167,0.00008716723,0.000019351892,0.00011603088,0.9710595,0.026809162,0.00028469757,0.00014328733,0.00042975083],"about_ca_topic_score_codex":0.00037229448,"about_ca_topic_score_gemma":0.000083328356,"teacher_disagreement_score":0.6948456,"about_ca_system_score_codex":0.0001861888,"about_ca_system_score_gemma":0.00011903731,"threshold_uncertainty_score":0.999762},"labels":[],"label_agreement":null},{"id":"W4412762215","doi":"10.54254/2755-2721/2025.po25557","title":"Literature Review on Attention Based Image Enhancement Techniques","year":2025,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Image enhancement; Computer science; Image (mathematics); Artificial intelligence","score_opus":0.0038590473140243673,"score_gpt":0.21067523921039005,"score_spread":0.2068161918963657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412762215","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007129692,0.0018082852,0.9952085,0.0011070067,0.00006733706,0.00016276781,0.0000012382654,0.00008877414,0.0014848141],"genre_scores_gemma":[0.34747693,0.000811425,0.64757943,0.003829006,0.00007172445,0.00011456614,0.000040178977,0.000007813759,0.00006890211],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99947625,0.000009299411,0.000118915676,0.000202461,0.000101681224,0.00009135946],"domain_scores_gemma":[0.9997373,0.00006407267,0.00002468924,0.00010409772,0.000046528672,0.000023280812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010453382,0.00010079984,0.000106336694,0.0000771524,0.000057840592,0.00009169435,0.00011248292,0.000022853488,0.0000028936893],"category_scores_gemma":[0.000007972828,0.00009186234,0.000029391005,0.0002567335,0.0000078280145,0.00008978139,0.0000419263,0.000070978516,0.000003342622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012279753,0.000118944336,0.000006651097,0.0014108126,0.00007597955,0.000010362324,0.00004825687,0.11640959,0.031308867,0.5595275,0.004550313,0.28652045],"study_design_scores_gemma":[0.0002379813,0.000037396378,0.00055937655,0.0029015115,0.000014024617,0.0000017116432,0.0000013821167,0.96853685,0.015039902,0.004293287,0.008142983,0.00023356706],"about_ca_topic_score_codex":2.7210783e-7,"about_ca_topic_score_gemma":2.5952184e-8,"teacher_disagreement_score":0.8521273,"about_ca_system_score_codex":0.000016768732,"about_ca_system_score_gemma":0.000015077885,"threshold_uncertainty_score":0.37460375},"labels":[],"label_agreement":null},{"id":"W4412762357","doi":"10.54254/2755-2721/2025.ast25502","title":"A Comparative Study on the Integration of Attention Mechanisms in GAN Architectures","year":2025,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Earl Haig Secondary School","funders":"","keywords":"Materials science; Computer science; Psychology","score_opus":0.013437579954688634,"score_gpt":0.23527173698444248,"score_spread":0.22183415702975384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412762357","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17493452,0.000009630635,0.82429475,0.00015893758,0.00003819915,0.00017692964,3.6662908e-7,0.000012928879,0.0003737414],"genre_scores_gemma":[0.98705673,3.0326058e-7,0.0128468685,0.000052804306,0.0000075185003,0.000028246895,0.0000011519348,0.0000015692666,0.0000047851704],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999574,0.000023988961,0.000121033365,0.0001305963,0.00009126518,0.000059102284],"domain_scores_gemma":[0.99964964,0.00022090369,0.000027270711,0.000071406386,0.00002171521,0.00000904199],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013276795,0.00006955849,0.00010240021,0.00010193795,0.000040358715,0.0000309749,0.00010880959,0.0000123805185,6.254839e-7],"category_scores_gemma":[0.0000077274535,0.000050200604,0.000014941808,0.0002381386,0.000010483433,0.000025335687,0.000032718566,0.00006988549,4.858398e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000043108594,0.00003666743,0.000015673952,0.0000021333133,0.000014063938,2.005089e-7,0.00069344277,0.66277266,0.0053972984,0.3287401,0.000004688101,0.0023187941],"study_design_scores_gemma":[0.00019895635,0.00004035038,0.044135075,0.000024428473,0.00000319241,2.3632944e-7,0.00040821408,0.9262864,0.0030265988,0.025822626,0.00000337824,0.000050560444],"about_ca_topic_score_codex":0.0000064783076,"about_ca_topic_score_gemma":0.000003949569,"teacher_disagreement_score":0.8121222,"about_ca_system_score_codex":0.000009564151,"about_ca_system_score_gemma":0.0000102629865,"threshold_uncertainty_score":0.20471212},"labels":[],"label_agreement":null},{"id":"W4413032606","doi":"10.32388/poy29b","title":"VSF: Simple, Efficient, and Effective Negative Guidance in Few-Step Image Generation Models By Value Sign Flip","year":2025,"lang":"en","type":"preprint","venue":"Qeios","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Sign (mathematics); Simple (philosophy); Image (mathematics); Value (mathematics); Computer science; Algorithm; Artificial intelligence; Computer vision; Mathematics; Machine learning; Mathematical analysis; Philosophy; Epistemology","score_opus":0.012906796100016351,"score_gpt":0.25003717338028814,"score_spread":0.23713037728027178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413032606","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008867996,0.0009602543,0.98535323,0.00047344912,0.00069282006,0.0016086688,0.00012545266,0.00009525028,0.001822882],"genre_scores_gemma":[0.89225304,0.00009324968,0.10602929,0.0004500367,0.00031284595,0.0004275707,0.000054603297,0.00002542178,0.00035394155],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964772,0.00081195444,0.00049622334,0.0014040492,0.00034093426,0.0004696804],"domain_scores_gemma":[0.9980908,0.0004661912,0.00027256226,0.0008153295,0.0002407239,0.00011436304],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006928814,0.000512812,0.0006129356,0.00022267475,0.00020508352,0.00047096153,0.0008226531,0.0002998918,0.000007050234],"category_scores_gemma":[0.00022253171,0.0005067278,0.00013374163,0.0003980121,0.00011828055,0.00042393766,0.0014365666,0.00056633947,0.000008443363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027380032,0.00014617974,0.000044954002,0.00009856038,0.00010027576,0.000016964936,0.00151825,0.93059057,0.009590811,0.0069852998,0.014258387,0.036622364],"study_design_scores_gemma":[0.0005249709,0.000055863,0.0002962618,0.00015787987,0.000025081079,0.0000010883772,0.00001724691,0.972196,0.01981103,0.0062223016,0.0002286014,0.00046367862],"about_ca_topic_score_codex":0.0006692213,"about_ca_topic_score_gemma":0.00006819518,"teacher_disagreement_score":0.88338506,"about_ca_system_score_codex":0.00022556707,"about_ca_system_score_gemma":0.00017938484,"threshold_uncertainty_score":0.99973845},"labels":[],"label_agreement":null},{"id":"W4413278267","doi":"10.1109/icip55913.2025.11084656","title":"In2Out: Fine-Tuning Video Inpainting Model for Video Outpainting Using Hierarchical Discriminator","year":2025,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Discriminator; Inpainting; Computer science; Artificial intelligence; Computer vision; Computer graphics (images); Image (mathematics); Telecommunications","score_opus":0.034954105245384566,"score_gpt":0.2881649543437927,"score_spread":0.25321084909840813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413278267","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062105814,0.00006107161,0.98863745,0.0020198082,0.0004025264,0.00031740338,0.0000022742504,0.00018109172,0.0021678184],"genre_scores_gemma":[0.5458684,8.155105e-7,0.4524296,0.0009528214,0.00010471243,0.00001941372,0.0000012276113,0.000011407684,0.00061163655],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979422,0.00012798104,0.00046828654,0.0006643131,0.00020029303,0.00059691264],"domain_scores_gemma":[0.99846447,0.00063610723,0.0001256842,0.00048550413,0.0001844297,0.000103839186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010092314,0.0002526069,0.00032893108,0.00022469275,0.0006010749,0.00047420064,0.00076341344,0.000080011014,0.0000070505994],"category_scores_gemma":[0.0009175409,0.00022476685,0.00019735338,0.00048425494,0.00007042666,0.0007859162,0.00069107855,0.00023941038,0.0000025682443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038853825,0.00012944816,0.0010627956,0.00016853386,0.00015328676,0.000008704678,0.0021991655,0.45697653,0.027461557,0.3262452,0.0034277008,0.1821282],"study_design_scores_gemma":[0.00032468018,0.000017210863,0.000044014007,0.00011473458,0.000026675452,0.0000014554536,0.00008923389,0.9790275,0.0039572045,0.015560843,0.0005824046,0.00025405193],"about_ca_topic_score_codex":0.000070916125,"about_ca_topic_score_gemma":0.000038793827,"teacher_disagreement_score":0.5396578,"about_ca_system_score_codex":0.00008413562,"about_ca_system_score_gemma":0.00020456039,"threshold_uncertainty_score":0.91657263},"labels":[],"label_agreement":null},{"id":"W4414043767","doi":"10.1016/j.neucom.2025.131488","title":"A first look at temporal bias in industrial image datasets","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Fundamental Research Funds for the Central Universities","keywords":"Generalization; Convolutional neural network; Inference; Feature (linguistics); Visualization; Pattern recognition (psychology); Image (mathematics); Industrial production","score_opus":0.04401281046675237,"score_gpt":0.2662948994455904,"score_spread":0.22228208897883805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414043767","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14089501,0.00014727295,0.8443649,0.005560701,0.0026983093,0.0008246423,0.000027615606,0.00034159087,0.005139991],"genre_scores_gemma":[0.9740895,0.000004153242,0.0244953,0.0009552082,0.0002757994,0.0000079954125,0.00001675678,0.000010158686,0.0001450997],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830323,0.0001932012,0.00035912218,0.00058442086,0.00017198992,0.00038804984],"domain_scores_gemma":[0.9989331,0.00036692037,0.00010941537,0.00049824186,0.000029541146,0.000062803425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004132658,0.00018229136,0.00022980406,0.00019123181,0.00026534504,0.00023887643,0.00078416715,0.000073771815,0.000015606342],"category_scores_gemma":[0.00022801218,0.000178545,0.00006489639,0.0007933523,0.000044923127,0.00037199096,0.0012418592,0.00026162583,0.000039633847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001447119,0.0007751745,0.18743241,0.00015430931,0.000121109275,0.0013617374,0.0014813393,0.110091366,0.008628568,0.0065646595,0.40154716,0.28169745],"study_design_scores_gemma":[0.0015574197,0.00005185137,0.011517511,0.00017280008,0.000008665346,0.000012616265,0.000021225369,0.90642774,0.004646638,0.0003739564,0.07485508,0.00035450753],"about_ca_topic_score_codex":0.00014846565,"about_ca_topic_score_gemma":0.0001382976,"teacher_disagreement_score":0.8331945,"about_ca_system_score_codex":0.00007436676,"about_ca_system_score_gemma":0.00007936391,"threshold_uncertainty_score":0.72808534},"labels":[],"label_agreement":null},{"id":"W4414170207","doi":"10.1109/avss65446.2025.11149915","title":"Self-Conditioned Generative Data Augmentation for Image Classification","year":2025,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nexen (Canada)","funders":"","keywords":"Generalization; Generative grammar; Pattern recognition (psychology); Pipeline (software); Generative model; Image (mathematics); Dependency (UML)","score_opus":0.04274270401852803,"score_gpt":0.31746077602406236,"score_spread":0.27471807200553433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414170207","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000066201974,0.00003098449,0.9870292,0.0049713347,0.00037287106,0.00040534438,0.000026339922,0.00013762663,0.0069600972],"genre_scores_gemma":[0.09796558,0.000017273751,0.89917994,0.0009879293,0.00011421918,0.000089533365,0.00028160194,0.0000042316915,0.0013596694],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991101,0.00006816442,0.00017577106,0.0004264192,0.0000876838,0.00013185355],"domain_scores_gemma":[0.9989454,0.00013422519,0.00006340861,0.00066873536,0.00016123592,0.000026986325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025016218,0.00008957647,0.00009316689,0.00007258162,0.00023120783,0.00024479307,0.0006679315,0.000033794407,0.000022793301],"category_scores_gemma":[0.00005779713,0.0000798943,0.000029833383,0.00025697617,0.000021227102,0.0012481427,0.00017998024,0.00003248547,0.000020274345],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018670198,0.00021549764,0.00005159502,0.000039767474,0.0001917344,0.0000010590552,0.00039994088,0.00035122273,0.056047037,0.6307187,0.23736876,0.07459599],"study_design_scores_gemma":[0.0003961739,0.000021759184,0.000532671,0.000004580673,0.000020646912,3.3272357e-7,0.00007279435,0.94532764,0.030754384,0.007488817,0.015279994,0.00010019278],"about_ca_topic_score_codex":0.000007535925,"about_ca_topic_score_gemma":0.00001159815,"teacher_disagreement_score":0.94497645,"about_ca_system_score_codex":0.000042975782,"about_ca_system_score_gemma":0.00008606465,"threshold_uncertainty_score":0.3257995},"labels":[],"label_agreement":null},{"id":"W4414359203","doi":"10.24963/ijcai.2025/1162","title":"Generative AI for Immersive Video: Recent Advances and Future Opportunities","year":2025,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; McGill University","funders":"","keywords":"Categorization; Key (lock); Component (thermodynamics); Virtual reality; Pipeline (software); Scalability; Generative grammar","score_opus":0.02195010834225365,"score_gpt":0.2699430495987455,"score_spread":0.24799294125649185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414359203","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000022697834,0.0070214937,0.9298293,0.054760087,0.00080897403,0.00022230251,0.00000569045,0.000022495036,0.0073069776],"genre_scores_gemma":[0.04662671,0.09686209,0.74219096,0.07603698,0.0029670133,0.00045141875,0.0000386161,0.000034664314,0.034791533],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99926144,0.00005088092,0.0001334611,0.00030208845,0.00007172311,0.00018038033],"domain_scores_gemma":[0.99940246,0.00011329948,0.000040968443,0.00018296261,0.00020769941,0.00005259867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000118919175,0.00012358572,0.000151824,0.0000639695,0.00022924223,0.00014698207,0.00021524301,0.000040299936,0.000028900664],"category_scores_gemma":[0.00002123736,0.00009600444,0.000041474206,0.00014985677,0.000054776665,0.00061890256,0.00011931398,0.00005034143,0.000001074491],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017077857,0.000019894658,0.000018829245,0.000019219293,0.000056126108,0.0000020724465,0.00037864476,0.0002060596,0.0006536717,0.20488325,0.044467248,0.7492779],"study_design_scores_gemma":[0.00026379008,0.00006486993,0.00004393684,0.00000960698,0.00001149737,9.745121e-7,0.0009892976,0.027561551,0.018064495,0.010090338,0.94276327,0.00013637263],"about_ca_topic_score_codex":0.000004484377,"about_ca_topic_score_gemma":0.000020073127,"teacher_disagreement_score":0.898296,"about_ca_system_score_codex":0.000018656341,"about_ca_system_score_gemma":0.00008268812,"threshold_uncertainty_score":0.39149475},"labels":[],"label_agreement":null},{"id":"W4414360939","doi":"10.24963/ijcai.2024/1162","title":"Generative AI for Immersive Video: Recent Advances and Future Opportunities","year":2024,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; McGill University","funders":"","keywords":"Categorization; Key (lock); Component (thermodynamics); Virtual reality; Pipeline (software); Scalability; Generative grammar","score_opus":0.028986239629853992,"score_gpt":0.2715159588318652,"score_spread":0.2425297192020112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414360939","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018993176,0.025525708,0.923488,0.046572533,0.0013202045,0.00018698527,0.0000111338895,0.00005165372,0.0028247747],"genre_scores_gemma":[0.07663405,0.19254263,0.6672897,0.029837776,0.010586174,0.0004641806,0.000060423004,0.00008730152,0.022497796],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99920166,0.00004181934,0.00012256435,0.00035073917,0.00009584842,0.00018738676],"domain_scores_gemma":[0.9995121,0.00012293726,0.00002180196,0.00014581849,0.00012221973,0.00007515145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013345294,0.0001311345,0.00012866584,0.00005775007,0.00015610569,0.00034880202,0.00016972564,0.000037932186,0.00006335181],"category_scores_gemma":[0.0000109247185,0.00009574203,0.000049766015,0.00013285634,0.000049283684,0.0010082804,0.00008640566,0.00006238151,0.000004727273],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000068053573,0.000009051944,0.000001980698,0.00003184212,0.00005111133,0.000010875029,0.0008488181,0.00014819177,0.00074016384,0.13882394,0.040893544,0.81843364],"study_design_scores_gemma":[0.000085601285,0.00008458233,0.000005767536,0.000012338418,0.000010121621,0.0000055210403,0.00069445604,0.093498066,0.009128233,0.0062987427,0.890035,0.00014161803],"about_ca_topic_score_codex":0.0000032928222,"about_ca_topic_score_gemma":0.000011559061,"teacher_disagreement_score":0.8491414,"about_ca_system_score_codex":0.000018624034,"about_ca_system_score_gemma":0.000071306014,"threshold_uncertainty_score":0.39042467},"labels":[],"label_agreement":null},{"id":"W4414704369","doi":"10.1038/s41598-025-16257-1","title":"High-resolution conditional MR image synthesis through the PACGAN framework","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; European Commission; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National Institute on Aging; Alzheimer's Association","keywords":"Discriminator; Overfitting; Image synthesis; Classifier (UML); A priori and a posteriori; Synthetic data; Generator (circuit theory); Pattern recognition (psychology)","score_opus":0.010656089894071097,"score_gpt":0.24639695918483298,"score_spread":0.23574086929076188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414704369","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025200217,0.00021332159,0.97397345,0.007368714,0.01168435,0.0002591411,0.000004789016,0.00013177328,0.0038444123],"genre_scores_gemma":[0.8886621,0.000006739742,0.108063444,0.00047736612,0.00021426217,0.000067286455,0.00001495402,0.00000748492,0.0024863775],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974696,0.00020584217,0.00045665022,0.000909957,0.0005625969,0.00039536136],"domain_scores_gemma":[0.99734914,0.00045734443,0.00024599716,0.0016098111,0.00027831577,0.000059418206],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001323911,0.00018395548,0.00020652448,0.00010583855,0.001331953,0.0012829015,0.00069887144,0.00009107823,0.00016553294],"category_scores_gemma":[0.0008998465,0.00012874164,0.0001566029,0.0011818147,0.0005513858,0.000861937,0.0003355819,0.0001949059,0.00006796846],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009140897,0.00019764718,0.00026963765,0.000025159903,0.00015480568,0.00027764033,0.0008452262,0.012209197,0.015437741,0.41827357,0.54099214,0.011308089],"study_design_scores_gemma":[0.000064430096,0.00001224909,0.001180634,0.000099887795,0.000042704993,0.000053780568,0.000097311524,0.017050715,0.07632826,0.7915336,0.11326297,0.00027345057],"about_ca_topic_score_codex":0.00007911834,"about_ca_topic_score_gemma":0.000010322025,"teacher_disagreement_score":0.8861421,"about_ca_system_score_codex":0.00006734288,"about_ca_system_score_gemma":0.00022849327,"threshold_uncertainty_score":0.9999682},"labels":[],"label_agreement":null},{"id":"W4414824699","doi":"10.1016/j.neucom.2025.131706","title":"FaceDisentGAN: Disentangled facial editing with targeted semantic alignment","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Information Technology Research Centre; Ministry of Science and ICT, South Korea","keywords":"Feature (linguistics); Generative grammar; Semantic feature; Fidelity; Semantics (computer science); Feature learning; Pattern recognition (psychology); Face (sociological concept)","score_opus":0.006767194165782982,"score_gpt":0.2184473230320968,"score_spread":0.21168012886631382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414824699","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030061021,0.000044677796,0.9624678,0.001753052,0.0011894318,0.00030958772,0.0000012024764,0.00026065068,0.003912599],"genre_scores_gemma":[0.9739395,0.0000028749769,0.024603331,0.0008700101,0.00040218778,0.000009628126,0.0000026342213,0.000012102488,0.00015774416],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982881,0.000121126766,0.0002788122,0.00057853694,0.00028611245,0.0004473014],"domain_scores_gemma":[0.99923927,0.0001306591,0.00012239962,0.00035050046,0.000073258634,0.000083902596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015423089,0.00022427281,0.00023687116,0.00012629734,0.00040879255,0.00027709638,0.00055195123,0.00003956467,0.000007163897],"category_scores_gemma":[0.000046051307,0.00018949661,0.000076882294,0.0006568665,0.000041699124,0.00025688167,0.0004074767,0.00015925369,0.000014107334],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009950782,0.00066553743,0.035752837,0.00024674577,0.00053023215,0.0005965774,0.0035170736,0.25438198,0.053154256,0.019514449,0.016321994,0.6152188],"study_design_scores_gemma":[0.0010098061,0.0001079968,0.0070808353,0.00016617616,0.000038436763,0.000012888107,0.0001486316,0.95458144,0.026184171,0.00032524974,0.009942162,0.00040222247],"about_ca_topic_score_codex":0.000020628699,"about_ca_topic_score_gemma":0.000007924399,"teacher_disagreement_score":0.9438785,"about_ca_system_score_codex":0.00004028316,"about_ca_system_score_gemma":0.000054814314,"threshold_uncertainty_score":0.7727447},"labels":[],"label_agreement":null},{"id":"W4415077465","doi":"10.1007/978-3-032-07502-4_10","title":"Imagining Alternatives: Towards High-Resolution 3D Counterfactual Medical Image Generation via Language Guidance","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Counterfactual thinking; Medical imaging; Fidelity; Image (mathematics); Natural language; Natural language generation; Limiting; Visualization","score_opus":0.011620716915066718,"score_gpt":0.2573483645142772,"score_spread":0.24572764759921045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415077465","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006024211,0.0009991807,0.989562,0.0017880257,0.003540032,0.0003240839,0.000016602038,0.00015934858,0.003550481],"genre_scores_gemma":[0.24298511,0.00012481867,0.75088394,0.0027237195,0.002537912,0.00001848727,0.000032250766,0.000038271144,0.00065548584],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949797,0.00013198935,0.00070160505,0.0017699761,0.0016912557,0.0007255004],"domain_scores_gemma":[0.9974853,0.00034884483,0.0003514488,0.0011624628,0.00044072184,0.00021126682],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013995656,0.0006382633,0.0006331063,0.0006365422,0.0003716077,0.0008027024,0.003161073,0.00034765806,0.00012488723],"category_scores_gemma":[0.00037227725,0.00058207003,0.00014314865,0.00053400174,0.0008052797,0.0012190219,0.0015536005,0.000884224,0.000042095788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008046147,0.000034798697,0.0000061110013,0.000029743243,0.000034547476,0.00017408734,0.0013566798,0.050963886,0.0020593053,0.0036156084,0.0004034981,0.9413137],"study_design_scores_gemma":[0.0003185531,0.000095145755,0.000037503843,0.00039432372,0.000012830049,0.00003059796,5.2045715e-7,0.9837058,0.009228781,0.0047712135,0.0008323458,0.00057237817],"about_ca_topic_score_codex":0.0002709664,"about_ca_topic_score_gemma":0.00022182763,"teacher_disagreement_score":0.9407413,"about_ca_system_score_codex":0.00047903493,"about_ca_system_score_gemma":0.0010313223,"threshold_uncertainty_score":0.99966305},"labels":[],"label_agreement":null},{"id":"W4415092886","doi":"10.1007/978-3-032-07884-1_21","title":"SecureT2I: No More Unauthorized Manipulation on AI Generated Images from Prompts","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Image editing; Vagueness; Set (abstract data type); Generalization; Block (permutation group theory); Quality (philosophy)","score_opus":0.014580527221166463,"score_gpt":0.2490164141492142,"score_spread":0.23443588692804773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415092886","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000052982305,0.00030483064,0.98880726,0.0022858554,0.0036666957,0.0005973203,0.000030838313,0.00020106859,0.004053119],"genre_scores_gemma":[0.1933763,0.00008440538,0.79335755,0.007095446,0.002865771,0.000036524692,0.0001226624,0.00007727214,0.0029840907],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99550974,0.00010754433,0.0005995022,0.0021363345,0.0009977123,0.00064914284],"domain_scores_gemma":[0.99701965,0.0004262467,0.0003117839,0.0014973943,0.0005835297,0.00016139033],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000512501,0.0007415239,0.0007050554,0.0007072432,0.00042071342,0.0009456669,0.0025356493,0.00043619183,0.000065871165],"category_scores_gemma":[0.00016281806,0.00065261463,0.00018365211,0.0007458522,0.000391135,0.00070248335,0.0009833594,0.0009198413,0.00009304578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054098848,0.00008309511,0.0000377391,0.000040656807,0.00008108454,0.00019630832,0.00059455045,0.4242779,0.003055971,0.012875042,0.0026100916,0.55609345],"study_design_scores_gemma":[0.00037757287,0.00014804422,0.00014359185,0.0004942578,0.000019440587,0.0000045837223,1.1446238e-7,0.94962454,0.009436961,0.03672892,0.0023010208,0.0007209388],"about_ca_topic_score_codex":0.0000672495,"about_ca_topic_score_gemma":0.000037909733,"teacher_disagreement_score":0.55537254,"about_ca_system_score_codex":0.00030080674,"about_ca_system_score_gemma":0.00058256317,"threshold_uncertainty_score":0.9995925},"labels":[],"label_agreement":null},{"id":"W4415600217","doi":"10.20944/preprints202510.2064.v1","title":"Monosemantic Feature Neurons: A Sparse Autoencoding Layer for Interpretable, Steerable Transformer Features","year":2025,"lang":"","type":"preprint","venue":"Preprints.org","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Interpretability; Transformer; Heuristics; Bottleneck; Computation; Residual; ENCODE; Pattern recognition (psychology)","score_opus":0.09834803971921124,"score_gpt":0.3331170462294064,"score_spread":0.23476900651019517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415600217","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016571498,0.002599278,0.92927456,0.008591649,0.011332097,0.006933949,0.00030887328,0.0005351203,0.023852983],"genre_scores_gemma":[0.9086381,0.0020046758,0.030200467,0.0014730473,0.0009573063,0.0012491053,0.000059646394,0.000120425015,0.05529721],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9896308,0.0009153557,0.0016444918,0.0047526355,0.0009003056,0.0021563806],"domain_scores_gemma":[0.992612,0.0010298355,0.0008874121,0.004012774,0.0009125677,0.00054542173],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0022153987,0.0018989849,0.002228273,0.0006792006,0.001220165,0.00083800184,0.004909407,0.0012926575,0.00060924946],"category_scores_gemma":[0.00093415123,0.0019164933,0.0017768622,0.0010645984,0.0003092558,0.0014348939,0.0032392398,0.0030488113,0.0003378467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028761206,0.003058508,0.039463986,0.00780534,0.0072222347,0.0002302834,0.031158691,0.6602193,0.10064846,0.015651044,0.025370624,0.10629542],"study_design_scores_gemma":[0.0029934808,0.00030345246,0.036432855,0.004976316,0.0015759196,0.00006429694,0.00042345165,0.6281726,0.19607729,0.0062419362,0.11883368,0.003904775],"about_ca_topic_score_codex":0.00041737664,"about_ca_topic_score_gemma":0.00013918421,"teacher_disagreement_score":0.8990741,"about_ca_system_score_codex":0.00040130864,"about_ca_system_score_gemma":0.0011880298,"threshold_uncertainty_score":0.9993754},"labels":[],"label_agreement":null},{"id":"W4415708102","doi":"10.1109/icme59968.2025.11209358","title":"Enhancing Object-Attribute Alignment in Diffusion Models via Training-Free Contrastive Parallel Denoising","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Noise reduction; Image denoising; Pattern recognition (psychology); Noise (video); Code (set theory); Object (grammar)","score_opus":0.02160311897150091,"score_gpt":0.24209317584253387,"score_spread":0.22049005687103296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415708102","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005862806,0.0015750002,0.98123753,0.0029098121,0.0017374991,0.0009867899,0.000012249119,0.00009255343,0.0055857706],"genre_scores_gemma":[0.9305052,0.00032750398,0.0654737,0.0014646834,0.00020187821,0.000053709435,0.0000051529896,0.000025255651,0.0019429225],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99419606,0.0006822197,0.0013883112,0.0016058354,0.00066664227,0.0014609282],"domain_scores_gemma":[0.997216,0.0007234695,0.00032076653,0.0011904583,0.0002735611,0.00027574683],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014369957,0.00074069813,0.0010839918,0.00047213526,0.000624101,0.0006492225,0.0016261458,0.0003166959,0.00011795258],"category_scores_gemma":[0.0002587213,0.00071749167,0.00031027527,0.0014382496,0.00020056847,0.0014074526,0.0015755399,0.00051804126,0.000021792544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000278497,0.00093853706,0.00044387407,0.000103010665,0.0005349559,0.00017778113,0.02123211,0.6687559,0.048786268,0.02887365,0.0019047037,0.22797073],"study_design_scores_gemma":[0.0028545342,0.0001756416,0.00094714225,0.00073259603,0.00007803713,0.0000050268977,0.0013720006,0.9496018,0.022848342,0.02049565,0.00018463915,0.00070453965],"about_ca_topic_score_codex":0.0007646107,"about_ca_topic_score_gemma":0.0016755776,"teacher_disagreement_score":0.9246424,"about_ca_system_score_codex":0.0005452334,"about_ca_system_score_gemma":0.00058159465,"threshold_uncertainty_score":0.99952763},"labels":[],"label_agreement":null},{"id":"W4415720123","doi":"10.18280/ts.420541","title":"Advanced Image Domain Adaptation and Multi-Angle Reconstruction in Medical Imaging Using Deep Neural Models","year":2025,"lang":"","type":"article","venue":"Traitement du signal","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medical imaging; Domain adaptation; Domain (mathematical analysis); Adaptation (eye); Image (mathematics); Artificial neural network; Pattern recognition (psychology)","score_opus":0.023943383637995374,"score_gpt":0.26089276834313463,"score_spread":0.23694938470513927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415720123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08612022,0.0014306791,0.9096548,0.0012201439,0.0008486884,0.0005174304,0.000005199298,0.000036056525,0.00016681463],"genre_scores_gemma":[0.7746087,0.0000969423,0.22477591,0.00034191643,0.00012834593,0.000019971454,0.0000037693744,0.000013119207,0.000011369528],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966454,0.0005311653,0.000859634,0.0008792667,0.0004983816,0.0005861777],"domain_scores_gemma":[0.99901813,0.0001613363,0.00022899878,0.00023729904,0.00016800655,0.00018623006],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009652187,0.00037427427,0.00042339854,0.0003671397,0.0003785993,0.00038862723,0.000377169,0.00011663901,0.00013412503],"category_scores_gemma":[0.0000560292,0.00039901954,0.00011054872,0.00066386216,0.00029716437,0.0023123852,0.00026146497,0.00033079117,0.0000017722492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007864691,0.00015070595,0.00056388124,0.000037750036,0.00003745574,0.00005163083,0.0018097224,0.24906026,0.008789928,0.0008090534,0.0000063673647,0.7386046],"study_design_scores_gemma":[0.0028890264,0.000045493416,0.002042627,0.0003259394,0.00004089948,0.000038858292,0.0012360717,0.9899703,0.0006611457,0.002394792,0.000015829579,0.0003389798],"about_ca_topic_score_codex":0.00019265461,"about_ca_topic_score_gemma":0.00024365875,"teacher_disagreement_score":0.74091005,"about_ca_system_score_codex":0.00021368821,"about_ca_system_score_gemma":0.00020891729,"threshold_uncertainty_score":0.99984616},"labels":[],"label_agreement":null},{"id":"W4415742469","doi":"10.36227/techrxiv.176192897.74591053/v1","title":"BDN: Blaschke Decomposition Networks","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Artificial neural network; Decomposition; Blaschke product; Algebra over a field; Matrix decomposition","score_opus":0.007135226548780838,"score_gpt":0.25900091442796946,"score_spread":0.2518656878791886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415742469","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014531112,0.002313425,0.8805279,0.006084018,0.004956645,0.0003359791,0.00000157783,0.00012662912,0.105508484],"genre_scores_gemma":[0.9300425,0.00061812287,0.046525374,0.0048391717,0.0006892413,0.000018294646,0.0000053592557,0.000014369316,0.017247546],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99696726,0.00038102202,0.00063290715,0.000979973,0.00028687587,0.0007519804],"domain_scores_gemma":[0.99802995,0.00027141496,0.00014806808,0.0009952649,0.0003688478,0.00018647179],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00055131566,0.00042030876,0.00044677296,0.00023264742,0.0006683861,0.0018481689,0.0011864164,0.0002711987,0.0006607962],"category_scores_gemma":[0.000057657573,0.0004045283,0.00029333495,0.0015088805,0.00016216139,0.0015885192,0.00080487726,0.0003764642,0.00019815101],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046201458,0.00027287766,0.0003174759,0.000026782063,0.00029396833,0.000021834012,0.00013539045,0.24981335,0.00056610967,0.117626026,0.09325995,0.53762007],"study_design_scores_gemma":[0.0004684084,0.00009308621,0.0014233341,0.00014714699,0.000076652395,0.000003703289,0.000026951582,0.9664799,0.0032599822,0.002328548,0.025309397,0.00038288077],"about_ca_topic_score_codex":0.00009979001,"about_ca_topic_score_gemma":0.000055142034,"teacher_disagreement_score":0.9298972,"about_ca_system_score_codex":0.0001173174,"about_ca_system_score_gemma":0.00022593311,"threshold_uncertainty_score":0.9998407},"labels":[],"label_agreement":null},{"id":"W4415820784","doi":"10.1109/tip.2025.3624614","title":"Multi-Energy Quasi-Symplectic Langevin Inference for Latent Disentangled Learning","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Workplace Health, Safety and Compensation Commission","funders":"Agence Nationale de la Recherche","keywords":"Inference; Information bottleneck method; Bottleneck; Encoding (memory); Integrator; Code (set theory); Approximate inference; Source code","score_opus":0.021635771357034345,"score_gpt":0.2862701222859848,"score_spread":0.2646343509289505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415820784","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020997369,0.00018839148,0.9978896,0.00065128895,0.00042923566,0.00016998193,0.0000036129918,0.00022026619,0.00023766112],"genre_scores_gemma":[0.8488368,0.00003408186,0.14910412,0.00026658332,0.000037008565,0.00012302052,0.0000016627513,0.0000145640415,0.0015821691],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873215,0.000096700394,0.00024649387,0.00045954128,0.00013881049,0.00032630388],"domain_scores_gemma":[0.9991961,0.0002246017,0.00008777779,0.00022902183,0.0001965677,0.00006592175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015910901,0.00019901471,0.00021132441,0.0001975609,0.0006930776,0.0004297527,0.0003522813,0.00006375128,0.000011180849],"category_scores_gemma":[0.000040761846,0.00018673018,0.00012457462,0.0005813027,0.000055128563,0.0006846884,0.0000057666794,0.00019020979,0.0000075376493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056551304,0.0005290612,0.000047286783,0.00014009532,0.00008223657,0.0000061597616,0.00061398704,0.050685957,0.04092636,0.00039200665,0.00016789326,0.9063524],"study_design_scores_gemma":[0.00061001943,0.000096670025,0.00006495695,0.00014774458,0.000042051506,0.000001760404,0.00005853565,0.9403966,0.057243403,0.00043244145,0.000686759,0.0002190428],"about_ca_topic_score_codex":0.00004354379,"about_ca_topic_score_gemma":0.00008035783,"teacher_disagreement_score":0.90613335,"about_ca_system_score_codex":0.000082881554,"about_ca_system_score_gemma":0.00014343554,"threshold_uncertainty_score":0.7614636},"labels":[],"label_agreement":null},{"id":"W4416028058","doi":"10.1038/s40494-025-02100-3","title":"Hierarchical symmetric GAN for Thangka image generation","year":2025,"lang":"en","type":"article","venue":"npj Heritage Science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Overfitting; Discriminator; Feature (linguistics); Pattern recognition (psychology); Image (mathematics); Generalization; Object (grammar); Differentiable function; Generator (circuit theory)","score_opus":0.019522244265698964,"score_gpt":0.2767312467106408,"score_spread":0.2572090024449418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416028058","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034954115,0.00015610243,0.978995,0.0021367194,0.0012010634,0.00034127777,0.0000041981643,0.00010237434,0.013567848],"genre_scores_gemma":[0.74553937,0.000012103413,0.25256217,0.00074290996,0.00020458584,0.00004650844,0.0000017892062,0.000005163199,0.00088542164],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981067,0.00006557853,0.0002295326,0.0007264331,0.00037142957,0.0005003161],"domain_scores_gemma":[0.9987663,0.00016058733,0.000060818456,0.00059780787,0.00029197687,0.00012249153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010576607,0.000153603,0.00017063985,0.00038462228,0.000722399,0.0007362644,0.0014240048,0.0000522164,0.0000138232435],"category_scores_gemma":[0.00058026594,0.0001360701,0.00008873158,0.0028389667,0.0003721422,0.0013202459,0.00025713904,0.00011115485,0.000018958604],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010189549,0.00014736985,0.00016968645,0.000027764481,0.000016874605,0.000008350518,0.0004572072,0.00077456445,0.59095126,0.2229131,0.013383452,0.17114018],"study_design_scores_gemma":[0.00035110663,0.00011374327,0.0014038294,0.000018201385,0.000008764316,0.0000029015728,0.00004674639,0.85177493,0.13278973,0.004969349,0.008263947,0.0002567317],"about_ca_topic_score_codex":0.000010565745,"about_ca_topic_score_gemma":0.0000118765265,"teacher_disagreement_score":0.85100037,"about_ca_system_score_codex":0.00008774376,"about_ca_system_score_gemma":0.00032891883,"threshold_uncertainty_score":0.70998144},"labels":[],"label_agreement":null},{"id":"W4416052719","doi":"10.48550/arxiv.2504.11389","title":"VideoPanda: Video Panoramic Diffusion with Multi-view Attention","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Virtual reality; Diffusion; Duration (music); Video processing; Autoregressive model; Video camera; Frame (networking)","score_opus":0.03211679802509091,"score_gpt":0.259287849487547,"score_spread":0.22717105146245611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416052719","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17388798,0.0009497225,0.821475,0.0010677059,0.0014484483,0.0005648213,0.000017230903,0.00022028324,0.00036875036],"genre_scores_gemma":[0.9505726,0.00067595294,0.044237863,0.000617019,0.00031341772,0.000106388376,0.000062850326,0.000026458963,0.0033874465],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99724793,0.00028237992,0.00045588758,0.001232831,0.00033579973,0.00044515834],"domain_scores_gemma":[0.99777883,0.000111702575,0.00033089085,0.0013900319,0.00026679056,0.00012174775],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032761003,0.0004933648,0.0005858535,0.00017019644,0.00028608568,0.00029133933,0.0012817469,0.00026805114,0.000033784607],"category_scores_gemma":[0.00007224768,0.00039184187,0.00023858993,0.00041070438,0.00008983897,0.000375883,0.002081144,0.00060297066,0.00011332952],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014268942,0.0013434582,0.7113182,0.001307147,0.0010587731,0.00020826781,0.0014223933,0.02714252,0.016061326,0.0014936819,0.0053348094,0.23316671],"study_design_scores_gemma":[0.0021074621,0.00023813725,0.66699797,0.0031586986,0.00034197446,0.000014214275,0.000057658843,0.30253255,0.004204064,0.00062236196,0.017849771,0.0018751649],"about_ca_topic_score_codex":0.0003747227,"about_ca_topic_score_gemma":0.00020728887,"teacher_disagreement_score":0.7772372,"about_ca_system_score_codex":0.000119893164,"about_ca_system_score_gemma":0.00023886019,"threshold_uncertainty_score":0.9998534},"labels":[],"label_agreement":null},{"id":"W4416085958","doi":"","title":"GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Camera auto-calibration; Leverage (statistics); Camera resectioning; Focus (optics); Trajectory; Pinhole camera model; Monocular; Smart camera","score_opus":0.03480100332103325,"score_gpt":0.2540751055821305,"score_spread":0.21927410226109723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416085958","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03131356,0.0008887818,0.9534765,0.0026516486,0.0026797361,0.0013828767,0.000048651586,0.00027650973,0.0072817453],"genre_scores_gemma":[0.9372739,0.0001637876,0.052645363,0.0019870002,0.0010007826,0.0002736347,0.000067915236,0.000028535163,0.0065590446],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99684435,0.0002546622,0.000670762,0.0011933361,0.00046166795,0.0005752193],"domain_scores_gemma":[0.9969766,0.00026058845,0.0004552211,0.0016434388,0.00046845202,0.00019569248],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00038122231,0.00059444696,0.0007262208,0.0003054721,0.0002986006,0.0005296289,0.0012528562,0.00023044279,0.000071246985],"category_scores_gemma":[0.0001400747,0.00049181446,0.00025755318,0.00048577585,0.000114943505,0.0005745359,0.0008794942,0.0006095913,0.00010173847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004293795,0.0006790381,0.112200245,0.0005467276,0.0032267366,0.00026159195,0.0034458158,0.64708334,0.0052456916,0.003252609,0.06136353,0.16226527],"study_design_scores_gemma":[0.003084831,0.00026439768,0.03144174,0.00081401516,0.0005392276,0.000021186064,0.000047538437,0.90566826,0.014381763,0.00026967336,0.04139379,0.0020735955],"about_ca_topic_score_codex":0.00023518362,"about_ca_topic_score_gemma":0.0008359082,"teacher_disagreement_score":0.9059604,"about_ca_system_score_codex":0.00024373776,"about_ca_system_score_gemma":0.00094181113,"threshold_uncertainty_score":0.99975336},"labels":[],"label_agreement":null},{"id":"W4416091725","doi":"10.48550/arxiv.2505.05409","title":"Hide &amp; Seek: Transformer Symmetries Obscure Sharpness &amp; Riemannian Geometry Finds It","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Geodesic; Homogeneous space; Quotient; Diagonal; Transformer; Manifold (fluid mechanics); Robustness (evolution)","score_opus":0.0570234197663034,"score_gpt":0.290597072295874,"score_spread":0.2335736525295706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416091725","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.076986946,0.0023209283,0.89555854,0.009252817,0.0061626993,0.0008122396,0.00019181437,0.00041589278,0.008298147],"genre_scores_gemma":[0.8683477,0.0018177391,0.06592339,0.005370302,0.0022388906,0.00025128436,0.00042029933,0.00010641741,0.055524],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9948976,0.00040338206,0.0010717148,0.0019417895,0.00066592835,0.0010195846],"domain_scores_gemma":[0.9955895,0.0004686791,0.0004197143,0.002584715,0.0006126698,0.000324704],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011010469,0.000916533,0.0011921248,0.00067075033,0.000511679,0.0006267026,0.0032468296,0.00082230335,0.0003204215],"category_scores_gemma":[0.0005526804,0.0008611183,0.00073799235,0.0016838127,0.0002452085,0.000747039,0.0015413065,0.0015685539,0.00064808293],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018124236,0.0013925132,0.41656202,0.0023940203,0.004215744,0.00017234722,0.01008583,0.026361046,0.0018261261,0.0055744895,0.38812652,0.14310811],"study_design_scores_gemma":[0.0011582271,0.000094301366,0.12474337,0.0012823023,0.00043482185,0.000015950442,0.00015062426,0.0044033565,0.005454649,0.0030209906,0.8563074,0.0029339937],"about_ca_topic_score_codex":0.00037176517,"about_ca_topic_score_gemma":0.00046001023,"teacher_disagreement_score":0.82963514,"about_ca_system_score_codex":0.0001576871,"about_ca_system_score_gemma":0.0006042712,"threshold_uncertainty_score":0.9993839},"labels":[],"label_agreement":null},{"id":"W4416176516","doi":"10.2139/ssrn.5743746","title":"Ill-Posedness Evolved in the Deep: Adaptive Evolutionary Latent Optimization, An Application to Recovering Volatility","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Volatility (finance); Prior probability; Generative grammar; Evolutionary algorithm; Gaussian; Inverse problem; Optimization problem","score_opus":0.013411703326838035,"score_gpt":0.24652590663243548,"score_spread":0.23311420330559746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416176516","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033887632,0.0026212893,0.9881595,0.002423259,0.0012292484,0.001826271,0.00001789798,0.000043405515,0.00029037287],"genre_scores_gemma":[0.93939644,0.0039328975,0.054504406,0.00060414895,0.00094161904,0.0002377309,0.000045957568,0.000034068904,0.00030274366],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9907454,0.0021885228,0.001403775,0.0016077994,0.00092864677,0.0031258122],"domain_scores_gemma":[0.99571204,0.00030189104,0.0008068249,0.0015190551,0.0014132231,0.0002469676],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006904316,0.0007524975,0.0007336159,0.000510037,0.0011793968,0.0006635577,0.0035750815,0.00042067832,0.000032777],"category_scores_gemma":[0.00029468854,0.0006516683,0.00037317045,0.0017452968,0.00011651373,0.001314008,0.00097079587,0.004886182,0.00001427434],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00021514817,0.00032140792,0.0007837235,0.000014067696,0.0001902228,0.0000029320188,0.0023358064,0.90578717,0.000030653442,0.010374738,0.000023714745,0.079920426],"study_design_scores_gemma":[0.000495392,0.00045595187,0.0047201086,0.00016950055,0.00009657548,0.000061809,0.0016754325,0.9362198,0.00001839249,0.055207934,0.00028267363,0.0005964174],"about_ca_topic_score_codex":0.00071090355,"about_ca_topic_score_gemma":0.0030617483,"teacher_disagreement_score":0.9360077,"about_ca_system_score_codex":0.004968918,"about_ca_system_score_gemma":0.0071066376,"threshold_uncertainty_score":0.99959344},"labels":[],"label_agreement":null},{"id":"W4416177895","doi":"10.26599/cvm.2025.9450408","title":"GRIG: Data-Efficient Generative Residual Image Inpainting","year":2025,"lang":"en","type":"article","venue":"Computational Visual Media","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Memorial University of Newfoundland","funders":"Natural Science Foundation of Zhejiang Province","keywords":"Inpainting; Generative grammar; Residual; Pattern recognition (psychology); Image (mathematics); Computer graphics; Convolutional neural network; Feature (linguistics)","score_opus":0.029204268568780566,"score_gpt":0.3178622097112278,"score_spread":0.28865794114244725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416177895","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005988532,0.00019697576,0.9887702,0.0021823451,0.0011697263,0.00017060392,0.000023813654,0.00012279753,0.0013750164],"genre_scores_gemma":[0.61441815,0.0000041083254,0.3837645,0.0009965757,0.0005186994,0.0000121443245,0.00017839688,0.0000090038,0.00009839528],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99793535,0.0002550125,0.00037017866,0.00068688055,0.00044215814,0.0003103992],"domain_scores_gemma":[0.9979684,0.0010365818,0.00011291788,0.00045885853,0.00032778268,0.00009546252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064187805,0.00019661683,0.00022740429,0.00019127231,0.00032353617,0.00032306713,0.0011211568,0.00005777971,0.00002998469],"category_scores_gemma":[0.00065463374,0.00018222482,0.000047685422,0.00066750956,0.00013098538,0.0004576921,0.0010682559,0.00017346398,0.00007558609],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002989619,0.00044166748,0.00027742863,0.000033455584,0.00020603927,0.000057790054,0.0019545697,0.67183113,0.0024037396,0.13953522,0.061610542,0.121618524],"study_design_scores_gemma":[0.00032758914,0.000024216743,0.0042736623,0.000031584783,0.000012843211,0.0000024427839,0.00006962358,0.98640037,0.0012819289,0.006062368,0.0013277351,0.00018562571],"about_ca_topic_score_codex":0.000014549487,"about_ca_topic_score_gemma":0.000008717029,"teacher_disagreement_score":0.6084296,"about_ca_system_score_codex":0.000056032983,"about_ca_system_score_gemma":0.0002642129,"threshold_uncertainty_score":0.7430912},"labels":[],"label_agreement":null},{"id":"W4416252349","doi":"10.1109/ijcnn64981.2025.11228442","title":"Pyramid Hierarchical Masked Diffusion Model for Imaging Synthesis","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Pyramid (geometry); Fidelity; Consistency (knowledge bases); Code (set theory); Similarity (geometry); Image (mathematics); Process (computing); Source code; Feature (linguistics)","score_opus":0.015156900958323163,"score_gpt":0.25737099703126926,"score_spread":0.24221409607294608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416252349","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039176704,0.00056043296,0.96636266,0.019023344,0.0016214857,0.00094504055,0.000029064244,0.0001543099,0.010911896],"genre_scores_gemma":[0.7590256,0.00017531363,0.22279976,0.0022897436,0.00026783862,0.00016716769,0.0000033250524,0.00003069463,0.015240603],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99585885,0.00025954432,0.0008426672,0.0015154026,0.0004068832,0.0011166689],"domain_scores_gemma":[0.9966619,0.0013467101,0.00017353386,0.0011923157,0.00035934083,0.0002661826],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008441359,0.00059794873,0.00072469213,0.00037678026,0.001053789,0.00093065976,0.0015726616,0.00019985715,0.00014335228],"category_scores_gemma":[0.0006751582,0.0005393437,0.00058276625,0.00078387535,0.00034672295,0.00078639685,0.0011738013,0.00032704012,0.00003059226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001814629,0.00045575917,0.00020766084,0.00014347772,0.00017410166,0.0000075279086,0.0005674068,0.07510014,0.007194648,0.10600928,0.017748052,0.79221046],"study_design_scores_gemma":[0.0006766719,0.00003216362,0.00019746285,0.00022942545,0.00014466513,0.0000017834312,0.000056089713,0.96342885,0.008406103,0.023123622,0.0031567407,0.00054641697],"about_ca_topic_score_codex":0.00005777093,"about_ca_topic_score_gemma":0.000023474093,"teacher_disagreement_score":0.88832873,"about_ca_system_score_codex":0.0001528457,"about_ca_system_score_gemma":0.0005021854,"threshold_uncertainty_score":0.9997058},"labels":[],"label_agreement":null},{"id":"W4416260735","doi":"10.1109/iccv51701.2025.02439","title":"UnMix-NeRF: Spectral Unmixing Meets Neural Radiance Fields","year":2025,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"King Abdullah University of Science and Technology","keywords":"Radiance; Hyperspectral imaging; Segmentation; Focus (optics); RGB color model; Spectral signature; Endmember; Pattern recognition (psychology); Image segmentation","score_opus":0.007944722907442825,"score_gpt":0.23078862184514276,"score_spread":0.22284389893769993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416260735","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00144998,0.0002936686,0.93147135,0.012654952,0.0011216196,0.000092075075,4.2344726e-7,0.0001414345,0.052774478],"genre_scores_gemma":[0.89747137,0.00002240095,0.09357077,0.0026293057,0.00017454638,0.0000057366865,5.882705e-7,0.0000042059437,0.006121103],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894625,0.00006810971,0.00017446736,0.00036802486,0.00011983067,0.0003233456],"domain_scores_gemma":[0.99932075,0.00010797113,0.000033801865,0.00042632202,0.000043766428,0.00006738138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013913689,0.00013697926,0.00015689674,0.00008072637,0.00016929221,0.00021816885,0.00066192745,0.000056922185,0.000081651764],"category_scores_gemma":[0.000043286625,0.00011634819,0.000086445005,0.00045771594,0.000036970996,0.00044770777,0.00018394516,0.00012912633,0.000033156786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019953104,0.00011427619,0.0011773373,0.000028167988,0.00013337958,0.00008069047,0.00056477846,0.036582477,0.0055184206,0.45792568,0.10810218,0.38975266],"study_design_scores_gemma":[0.00035398235,0.00004775167,0.0033376326,0.000026794702,0.000010450848,0.0000053547583,0.000024533269,0.9360438,0.029419785,0.005988657,0.02444973,0.00029151578],"about_ca_topic_score_codex":0.00010579743,"about_ca_topic_score_gemma":0.00008347344,"teacher_disagreement_score":0.8994613,"about_ca_system_score_codex":0.000028380353,"about_ca_system_score_gemma":0.000052924468,"threshold_uncertainty_score":0.47445413},"labels":[],"label_agreement":null},{"id":"W4416371824","doi":"10.2316/j.2026.206-1289","title":"STYLE TRANSFER AND PERSONALISED DESIGN OF VISUAL ELEMENTS BASED ON CLIP CONTRASTIVE LANGUAGE IMAGE MODEL. 254-264","year":2025,"lang":"en","type":"article","venue":"International Journal of Robotics and Automation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Style (visual arts); Visual language; Bridge (graph theory); Contrastive analysis; Image (mathematics); Visualization","score_opus":0.009868304675649349,"score_gpt":0.2735447946368721,"score_spread":0.2636764899612227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416371824","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0186021,0.000060314465,0.97989285,0.001102082,0.00017338603,0.000075107906,0.00000647541,0.00000614791,0.00008150977],"genre_scores_gemma":[0.88414574,0.000028353415,0.11554218,0.00022205517,0.00003562444,8.9270947e-7,0.0000019346467,0.0000028039076,0.000020423953],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918944,0.00007417376,0.00029219664,0.00010132237,0.00027282172,0.000070064976],"domain_scores_gemma":[0.99929696,0.00015755904,0.00013756426,0.00004537942,0.0003306379,0.000031903546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032439383,0.000079996375,0.00013874954,0.0001721042,0.000037605507,0.00010617004,0.00016783706,0.000029217716,0.0000050898047],"category_scores_gemma":[0.00006469968,0.000067385896,0.000043751013,0.000069439215,0.0000351522,0.0003019497,0.00002361679,0.00006834397,2.2185229e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015915022,0.0002220328,0.0002645531,0.00001845092,0.00019697196,0.000016222444,0.0009370975,0.9153781,0.036107104,0.0077942433,0.0002150636,0.038691],"study_design_scores_gemma":[0.0009969962,0.00013400338,0.0014685746,0.00010782467,0.000022169363,0.000002920888,0.000067349436,0.9898367,0.0068038492,0.00049963576,0.0000057060984,0.000054252803],"about_ca_topic_score_codex":0.0000035125065,"about_ca_topic_score_gemma":7.341921e-7,"teacher_disagreement_score":0.8655436,"about_ca_system_score_codex":0.000028904326,"about_ca_system_score_gemma":0.00006931795,"threshold_uncertainty_score":0.27479172},"labels":[],"label_agreement":null},{"id":"W4416736648","doi":"10.1145/3757371.3763259","title":"CGAI: How generative AI is reshaping digital media and artists practices","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Digital media; Natural (archaeology); Style (visual arts); Generative grammar; Visual language; Digital photography; Natural language; Visual media; Mimicry","score_opus":0.028672282070021947,"score_gpt":0.281748968248567,"score_spread":0.25307668617854506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416736648","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014554822,0.005634944,0.8443032,0.13263075,0.0016515701,0.00036143925,0.00003834579,0.00007096842,0.013853294],"genre_scores_gemma":[0.94231254,0.0007653454,0.028965423,0.014090624,0.0007231504,0.00001605698,0.000006477165,0.00001862501,0.013101766],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967517,0.0002977225,0.0004694488,0.0013470136,0.00045831216,0.000675782],"domain_scores_gemma":[0.9971184,0.0009011457,0.00052940374,0.0007115474,0.00047528394,0.00026419866],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004707582,0.0005004338,0.0005276047,0.00022794912,0.0007153571,0.0067784847,0.0006970097,0.00020326927,0.00017826167],"category_scores_gemma":[0.0013875505,0.00044542475,0.00014331075,0.00091381755,0.00045882293,0.005396801,0.0010868559,0.00041064178,0.000048462978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009419532,0.00029926898,0.0021493882,0.00009999637,0.0007980035,0.000107060914,0.009118131,0.00039761318,0.0034264023,0.038263075,0.31327692,0.63197],"study_design_scores_gemma":[0.00092013535,0.00019586862,0.001871719,0.00029990525,0.00014272817,0.000020055386,0.0007595227,0.8630544,0.031947333,0.008634983,0.09121979,0.0009335332],"about_ca_topic_score_codex":0.00007803672,"about_ca_topic_score_gemma":0.0001247591,"teacher_disagreement_score":0.94085705,"about_ca_system_score_codex":0.00006676201,"about_ca_system_score_gemma":0.00037950283,"threshold_uncertainty_score":0.9997997},"labels":[],"label_agreement":null},{"id":"W4416740373","doi":"10.48550/arxiv.2506.08065","title":"Dynamic Diffusion Schrödinger Bridge in Astrophysical Observational Inversions","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Discriminative model; Context (archaeology); Probabilistic logic; Generative grammar; Bridge (graph theory); Generative model; Pairwise comparison; Bayesian probability; Domain (mathematical analysis)","score_opus":0.056210611787668494,"score_gpt":0.28008786422930715,"score_spread":0.22387725244163864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416740373","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6503582,0.000075139855,0.3452976,0.0024713022,0.0011674712,0.00022794543,0.000020547135,0.00007695959,0.00030483052],"genre_scores_gemma":[0.9698499,0.00007253028,0.028305717,0.0006262213,0.00016832592,0.000043260126,0.00006856683,0.000010895448,0.0008546084],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979708,0.00017248809,0.00036073243,0.0008473317,0.00029720034,0.00035144624],"domain_scores_gemma":[0.99866885,0.00017621822,0.00014958938,0.00078346865,0.00012895459,0.00009291272],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018286661,0.00030237756,0.00037286262,0.0002042519,0.00016247663,0.00012298289,0.0011489893,0.00021773292,0.000028595034],"category_scores_gemma":[0.00012688665,0.00029950406,0.00019324903,0.00047103592,0.00007031693,0.00031710084,0.0027957957,0.00071948126,0.00007710082],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055049994,0.000997522,0.83291495,0.00019356007,0.0002200081,0.00011252655,0.0010943344,0.1023476,0.017679788,0.010043814,0.009709833,0.024631036],"study_design_scores_gemma":[0.00019841794,0.000014880831,0.6429223,0.00018531494,0.000010624666,3.9491823e-7,0.000005356175,0.35477322,0.00018892405,0.00082617934,0.0006553597,0.00021905545],"about_ca_topic_score_codex":0.00022834212,"about_ca_topic_score_gemma":0.00007412419,"teacher_disagreement_score":0.31949168,"about_ca_system_score_codex":0.00018755108,"about_ca_system_score_gemma":0.00030786684,"threshold_uncertainty_score":0.9999457},"labels":[],"label_agreement":null},{"id":"W4416774226","doi":"10.3847/1538-4357/ae0d83","title":"Galaxy Model Subtraction with a Convolutional Denoising Autoencoder","year":2025,"lang":"en","type":"article","venue":"The Astrophysical Journal","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Herzberg Institute of Astrophysics","funders":"","keywords":"Galaxy; Convolutional neural network; Residual; Pattern recognition (psychology); Spiral galaxy; Ellipse; Subtraction; Background subtraction","score_opus":0.009253971442445804,"score_gpt":0.2236433382282354,"score_spread":0.2143893667857896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416774226","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013447152,0.000031793126,0.9828215,0.003053499,0.00018319282,0.00005084823,5.2055515e-7,0.000026439035,0.0003850193],"genre_scores_gemma":[0.82514304,0.0000045322113,0.17401013,0.00027028567,0.00025719177,0.0000026098903,2.5460884e-7,0.000003932267,0.00030802193],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999096,0.00010434446,0.00014313754,0.00016030195,0.00026674604,0.00022948654],"domain_scores_gemma":[0.99941546,0.000080611484,0.000086847635,0.00021023091,0.00014610201,0.000060778053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016613134,0.00010789045,0.000119326294,0.000044244207,0.0005106109,0.00030634474,0.0004638037,0.000022550998,0.0000062951553],"category_scores_gemma":[0.000015333531,0.000061650135,0.0000791463,0.00024460803,0.00009682613,0.0005074493,0.000086674314,0.00034725596,0.000012155276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060422666,0.00007370725,0.00008885197,0.0000015844814,0.00009028473,0.000010215969,0.00012359094,0.8936898,0.020922128,0.06370709,0.0017455063,0.019486826],"study_design_scores_gemma":[0.0002549557,0.000057148183,0.0061124386,0.000027477174,0.00002320971,0.000051896888,0.000018545417,0.975762,0.001199445,0.016273886,0.00014204078,0.00007696245],"about_ca_topic_score_codex":0.0000044285234,"about_ca_topic_score_gemma":0.0000011457331,"teacher_disagreement_score":0.8116959,"about_ca_system_score_codex":0.0000643338,"about_ca_system_score_gemma":0.00021358073,"threshold_uncertainty_score":0.39272577},"labels":[],"label_agreement":null},{"id":"W4416873480","doi":"10.1109/inc465408.2025.11256489","title":"Enhancing Text-to-Image Generation Using Ensemble Vision Transformers","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Optech (Canada)","funders":"","keywords":"Bridging (networking); Transformer; Modalities; Consistency (knowledge bases); Metric (unit); Representation (politics)","score_opus":0.02009932331468428,"score_gpt":0.28497380428842095,"score_spread":0.26487448097373667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416873480","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008849993,0.0003612249,0.9661947,0.0032939883,0.00316579,0.0007468671,0.0000033492165,0.00008299799,0.017301094],"genre_scores_gemma":[0.6953767,0.00008547174,0.29850557,0.001889067,0.00046268638,0.000009907307,0.0000028477596,0.000020243566,0.0036474897],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99617416,0.00033931315,0.0008810367,0.0012571594,0.00046545925,0.0008828601],"domain_scores_gemma":[0.998412,0.0001317455,0.00013005867,0.00064484414,0.00040615906,0.00027516292],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009320161,0.00050905545,0.0005271204,0.0004985397,0.0010638045,0.0013573003,0.0006610688,0.00021372968,0.00033148716],"category_scores_gemma":[0.00010921533,0.0004969288,0.00027591942,0.0019593674,0.00009469046,0.0018894428,0.00031563765,0.00025652,0.00016716686],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018043987,0.00008020259,0.000005819523,0.000030446246,0.00005596592,0.0000054789143,0.00065260235,0.023228385,0.74676347,0.001492845,0.0023668983,0.22529982],"study_design_scores_gemma":[0.00026269752,0.00010764131,0.00004152627,0.00014782124,0.00005073382,0.0000021071091,0.00009949455,0.5637617,0.4323189,0.0001041321,0.002791985,0.00031125263],"about_ca_topic_score_codex":0.00033279747,"about_ca_topic_score_gemma":0.0004989989,"teacher_disagreement_score":0.6865267,"about_ca_system_score_codex":0.0002798304,"about_ca_system_score_gemma":0.00050436385,"threshold_uncertainty_score":0.99974823},"labels":[],"label_agreement":null},{"id":"W4416874509","doi":"10.1109/inc465408.2025.11256440","title":"Leveraging Attention U-Net in Generative Adversarial Networks for Satellite to Map Image Translation","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Image translation; Salient; Translation (biology); Task (project management); Generative grammar; Focus (optics); Image (mathematics); Satellite; Baseline (sea); Key (lock)","score_opus":0.02154300316581643,"score_gpt":0.26933754512767066,"score_spread":0.24779454196185424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416874509","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00070656545,0.0014351637,0.97592616,0.010933947,0.0056270654,0.0026138122,0.000014389824,0.0000740427,0.002668871],"genre_scores_gemma":[0.6574269,0.00026888654,0.3348974,0.002374907,0.0012161832,0.00020837925,0.000060811337,0.000036431986,0.0035101243],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953516,0.0005590275,0.0011492113,0.0015441308,0.00032894645,0.0010670573],"domain_scores_gemma":[0.99809015,0.0004831333,0.00019946095,0.000647193,0.00037708075,0.0002029838],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013844535,0.0006031441,0.00069848145,0.00060389255,0.0005119537,0.00095734245,0.00076613436,0.0003037951,0.000094162904],"category_scores_gemma":[0.000081404636,0.0006400242,0.00038275207,0.0014819503,0.00009754357,0.0014038895,0.00025981673,0.00033846364,0.000040350107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005244403,0.00022931262,0.0004972464,0.00008883137,0.00019840738,0.000010389022,0.0023484854,0.375445,0.010015279,0.0064447946,0.006488694,0.5977091],"study_design_scores_gemma":[0.0024063734,0.0001909276,0.0030060667,0.000296574,0.00008605892,6.9583194e-7,0.00023760292,0.9719319,0.0033716115,0.001633705,0.01619859,0.0006399232],"about_ca_topic_score_codex":0.00021057276,"about_ca_topic_score_gemma":0.0005636368,"teacher_disagreement_score":0.65672034,"about_ca_system_score_codex":0.00030489673,"about_ca_system_score_gemma":0.00025188466,"threshold_uncertainty_score":0.9996051},"labels":[],"label_agreement":null},{"id":"W4416909503","doi":"10.65521/ijacect.v14i1.560","title":"AI-Based Approach using Generative Adversarial Network for Interior Design System","year":2025,"lang":"","type":"article","venue":"International Journal on Advanced Computer Engineering and Communication Technology","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Workflow; Interior design; Generative grammar; Adversarial system; Generative Design; Generative adversarial network","score_opus":0.01455885830667766,"score_gpt":0.26047163307071974,"score_spread":0.24591277476404208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416909503","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019791258,0.0021299091,0.9859971,0.005691732,0.0051257475,0.0005972053,0.000011662038,0.00021170556,0.000037044632],"genre_scores_gemma":[0.3506302,0.00019606468,0.6477735,0.0007641228,0.00051615894,0.000064338405,0.000008159782,0.000024239269,0.00002320473],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973413,0.00035581068,0.00088235905,0.0006232788,0.0002963892,0.0005008919],"domain_scores_gemma":[0.9969727,0.0005815544,0.00051088183,0.0007944204,0.0010278873,0.000112564856],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008839884,0.0004796146,0.00058264006,0.0009465003,0.00063275313,0.00074731297,0.002195048,0.0003264213,0.0000021656435],"category_scores_gemma":[0.00012171,0.00049873843,0.0002082235,0.0006633577,0.0001576042,0.00047678527,0.00068239076,0.0009058749,0.0000015454001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019785174,0.00007171419,0.0000066111543,0.000027976936,0.000404467,0.0000065679515,0.000058097983,0.82769585,0.00053775293,0.057423845,0.00034503939,0.11322425],"study_design_scores_gemma":[0.0021269368,0.00033344948,0.000010496559,0.0012288805,0.00006515469,0.000099573335,0.000045665776,0.9836036,0.0023331163,0.0016095818,0.008159103,0.00038445165],"about_ca_topic_score_codex":0.0000033475862,"about_ca_topic_score_gemma":5.200493e-7,"teacher_disagreement_score":0.35043228,"about_ca_system_score_codex":0.000603562,"about_ca_system_score_gemma":0.00027299824,"threshold_uncertainty_score":0.99974644},"labels":[],"label_agreement":null},{"id":"W4416958388","doi":"10.1016/j.cag.2025.104490","title":"Adaptive multiresolution exemplar-based texture synthesis on animated fluids","year":2025,"lang":"en","type":"article","venue":"Computers & Graphics","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Texture synthesis; Distortion (music); Texture (cosmology); View synthesis; Orientation (vector space); Animation; Consistency (knowledge bases); Displacement mapping","score_opus":0.01547145698300355,"score_gpt":0.23739022463819312,"score_spread":0.22191876765518956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416958388","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009418621,0.00024778015,0.9934339,0.0026440737,0.0009648314,0.00028692192,0.0000089016385,0.00035928324,0.0011124401],"genre_scores_gemma":[0.9104166,0.00002570934,0.08670896,0.0026362424,0.0001056565,0.000037166865,0.0000063331604,0.000016228083,0.00004708868],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978854,0.00030279421,0.0003123319,0.0007294606,0.0003194847,0.00045050716],"domain_scores_gemma":[0.99816716,0.0006285786,0.000109196255,0.00076883496,0.0002114722,0.00011476859],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003213365,0.00034049322,0.00034096334,0.00045976002,0.00044803892,0.00024108055,0.0010194314,0.00018561589,0.000006392814],"category_scores_gemma":[0.000081226906,0.0003159295,0.00022733262,0.0014336408,0.000116044546,0.0002855664,0.00021894643,0.00029939463,0.000022773238],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039262598,0.0011058719,0.0009114585,0.00010470707,0.00061708054,0.0001373025,0.00058514666,0.10440345,0.0083234515,0.36313966,0.12426967,0.39600956],"study_design_scores_gemma":[0.0004220488,0.00015696607,0.0027191155,0.00022321707,0.000032967,0.0000015033869,0.000014079395,0.97892874,0.0077368165,0.0012753791,0.008160383,0.00032878865],"about_ca_topic_score_codex":0.000039270297,"about_ca_topic_score_gemma":0.000013603778,"teacher_disagreement_score":0.90947473,"about_ca_system_score_codex":0.00008461932,"about_ca_system_score_gemma":0.0001192211,"threshold_uncertainty_score":0.99992925},"labels":[],"label_agreement":null},{"id":"W4416962096","doi":"10.1109/pst65910.2025.11268852","title":"Detecting Deepfakes using Temporal Consistency of Facial Expression Transitions","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Robustness (evolution); Facial expression; Consistency (knowledge bases); Scalability; Pattern recognition (psychology); Expression (computer science); Face (sociological concept)","score_opus":0.02833198900675852,"score_gpt":0.2704117443076745,"score_spread":0.242079755300916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416962096","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03660594,0.0006998412,0.9550141,0.00039066578,0.001338841,0.000303057,0.000011391867,0.000044523214,0.0055916253],"genre_scores_gemma":[0.8430158,0.000018707175,0.15647018,0.000109985456,0.00010848224,0.0000037637067,0.0000011432352,0.000007891404,0.00026407343],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99750763,0.0003665396,0.0008222269,0.00060680526,0.0002738299,0.0004229654],"domain_scores_gemma":[0.99861324,0.00018317631,0.0002633857,0.0004987786,0.0003458875,0.00009553257],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041346814,0.0002964525,0.0004944874,0.00027039018,0.00079146965,0.00019407964,0.0004758469,0.00017612304,0.00017132134],"category_scores_gemma":[0.00013284742,0.00028108992,0.0003040394,0.00096421596,0.00027399062,0.0006930312,0.00023241318,0.00020606861,0.0000036192753],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000076448945,0.00034283698,0.001564289,0.00018504728,0.00017483855,0.000014007911,0.0029919825,0.03399622,0.7147782,0.004187673,0.00024843952,0.24144003],"study_design_scores_gemma":[0.000444729,0.000072990064,0.0002971065,0.00046396954,0.00008847827,0.0000037085663,0.0007844747,0.6521904,0.34432283,0.00083936466,0.00023871553,0.0002532591],"about_ca_topic_score_codex":0.00030681354,"about_ca_topic_score_gemma":0.00011030573,"teacher_disagreement_score":0.80640984,"about_ca_system_score_codex":0.000053758602,"about_ca_system_score_gemma":0.00043975934,"threshold_uncertainty_score":0.9999641},"labels":[],"label_agreement":null},{"id":"W4416965660","doi":"10.1109/ojcs.2025.3639606","title":"H2-Cache: A Novel Hierarchical Dual-Stage Cache for High-Performance Acceleration of Generative Diffusion Models","year":2025,"lang":"en","type":"article","venue":"IEEE Open Journal of the Computer Society","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Research Foundation of Korea","keywords":"Automatic summarization; Cache; Feature (linguistics); Process (computing); Key (lock); Similarity (geometry); Acceleration; Generative grammar; Scalability","score_opus":0.04194187516402282,"score_gpt":0.27620541627301504,"score_spread":0.23426354110899222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416965660","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07488962,0.00006307778,0.91922235,0.0034629337,0.001809333,0.00045963735,0.000010318778,0.0000072940034,0.00007543761],"genre_scores_gemma":[0.6217766,0.000042993706,0.37650615,0.0008900881,0.00035444603,0.000009196426,9.86405e-7,0.000007699065,0.00041187502],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832296,0.00018129231,0.0006359389,0.00028728237,0.00033010624,0.00024240058],"domain_scores_gemma":[0.9981154,0.00023612629,0.0005846969,0.0004675446,0.00053041155,0.00006582769],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010144083,0.00020142698,0.00043874898,0.000047759837,0.00042782023,0.00037875245,0.0020961391,0.00010201456,0.0000030950423],"category_scores_gemma":[0.000019342331,0.00013289881,0.0003572562,0.0003900597,0.00010169793,0.0012741884,0.00089295337,0.00031961643,3.507776e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012187732,0.00046341636,0.00010134801,0.00007175439,0.0005155502,0.0000014269987,0.0036151782,0.84992385,0.06399838,0.01467954,0.02706412,0.039443564],"study_design_scores_gemma":[0.0014590413,0.00018417048,0.00071652007,0.00013955975,0.000037672315,0.000007065291,0.00002465969,0.9359282,0.05877369,0.0020578355,0.00053315796,0.000138406],"about_ca_topic_score_codex":0.000020162197,"about_ca_topic_score_gemma":0.0000039955503,"teacher_disagreement_score":0.5468869,"about_ca_system_score_codex":0.00009549827,"about_ca_system_score_gemma":0.00032170597,"threshold_uncertainty_score":0.54194564},"labels":[],"label_agreement":null},{"id":"W4416999248","doi":"10.1016/j.jcp.2025.114550","title":"Learning enhanced ensemble filters","year":2025,"lang":"en","type":"article","venue":"Journal of Computational Physics","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Power Generation; Vector Institute","funders":"Resnick Sustainability Institute for Science, Energy and Sustainability, California Institute of Technology; California Institute of Technology; U.S. Department of Defense; National Science Foundation","keywords":"Ensemble learning; Ensemble Kalman filter; Measure (data warehouse); Kalman filter; Filter (signal processing); Metric (unit); Ensemble forecasting; Generalization; Gaussian","score_opus":0.008463391023895709,"score_gpt":0.24578884901619658,"score_spread":0.23732545799230087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416999248","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063452455,0.000057044857,0.9898583,0.000725236,0.00046905945,0.000027754466,1.9684985e-7,0.000012215578,0.0025049234],"genre_scores_gemma":[0.87055326,0.000006655082,0.12870114,0.00032989486,0.00020138957,4.780572e-7,6.9713826e-7,0.0000027578135,0.00020375731],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992367,0.00008038021,0.00025154895,0.000095556185,0.0002313892,0.00010440627],"domain_scores_gemma":[0.9989812,0.00027340086,0.00023087977,0.00007372677,0.00040508664,0.00003573914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017877163,0.00007614672,0.00015427069,0.00006650348,0.00010627491,0.00010236159,0.0003087995,0.00001942282,0.0000037266798],"category_scores_gemma":[0.000053446187,0.00006814911,0.000111186324,0.00031393798,0.00002253333,0.0004523013,0.00006327533,0.00016184966,0.0000069848606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000072863536,0.00003183247,0.00002326546,0.0000036254662,0.00004834481,0.0000028295099,0.00016342195,0.8866802,0.002049918,0.017217858,0.0017975108,0.09197393],"study_design_scores_gemma":[0.0005754453,0.00015467509,0.0013481281,0.00007775065,0.000018496827,0.000007493595,0.000046777677,0.70235205,0.020178346,0.27277243,0.002335797,0.00013258788],"about_ca_topic_score_codex":8.3766975e-7,"about_ca_topic_score_gemma":1.16461685e-7,"teacher_disagreement_score":0.864208,"about_ca_system_score_codex":0.000031690928,"about_ca_system_score_gemma":0.00015894308,"threshold_uncertainty_score":0.27790397},"labels":[],"label_agreement":null},{"id":"W4417000825","doi":"10.1145/3763326","title":"AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Intrinsics; Rendering (computer graphics); View synthesis; Gaussian; Graphics pipeline; Point cloud; Deep neural networks","score_opus":0.02030212405609238,"score_gpt":0.25677373036170764,"score_spread":0.23647160630561526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417000825","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011942228,0.00014912734,0.9897038,0.004794804,0.0008964916,0.00019838432,0.000032123226,0.00018729943,0.002843778],"genre_scores_gemma":[0.7864865,0.00013352606,0.2109412,0.0019526624,0.000077472185,0.000028668204,0.000007961127,0.000013499642,0.00035849155],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983448,0.0001358736,0.0003616076,0.0005711702,0.00023498165,0.00035157238],"domain_scores_gemma":[0.9981977,0.00044335183,0.000089405934,0.0010755197,0.00008224709,0.000111824724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026546977,0.00025937086,0.00028505822,0.00032915163,0.0005746999,0.00022100785,0.0009901075,0.00015236132,0.000081576676],"category_scores_gemma":[0.000039565864,0.00024117171,0.00023308606,0.0012680267,0.000119822544,0.0004523302,0.000026996595,0.00039792966,0.00003578512],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055117525,0.00040390604,0.00053220615,0.0000334944,0.00061744207,0.000034799454,0.00093598064,0.01353015,0.0032938428,0.021656971,0.0022976655,0.9566084],"study_design_scores_gemma":[0.00534255,0.0006576111,0.012996066,0.0011705924,0.000817138,0.000029932571,0.00075774756,0.58106184,0.06492675,0.1675374,0.16152039,0.0031819707],"about_ca_topic_score_codex":0.0001427225,"about_ca_topic_score_gemma":0.00033993978,"teacher_disagreement_score":0.9534265,"about_ca_system_score_codex":0.00003599256,"about_ca_system_score_gemma":0.00010670889,"threshold_uncertainty_score":0.98346967},"labels":[],"label_agreement":null},{"id":"W4417062149","doi":"10.1109/iccv51701.2025.01039","title":"Reangle-A-Video: 4D Video Generation as Video-to-Video Translation","year":2025,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Research Foundation of Korea","keywords":"Frame (networking); Task (project management); Motion (physics); Video tracking; Consistency (knowledge bases); Code (set theory); Set (abstract data type); Motion compensation","score_opus":0.023621137296168097,"score_gpt":0.2637395867254565,"score_spread":0.2401184494292884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417062149","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022678992,0.00032319388,0.95387805,0.016035654,0.0011469194,0.00048368136,0.0000030220915,0.00026211416,0.025599467],"genre_scores_gemma":[0.7597127,0.000051135034,0.22613636,0.007745478,0.0005857692,0.00008251101,0.000021000084,0.000021033076,0.005644054],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975728,0.00026103834,0.0005116307,0.00083551666,0.00037985833,0.00043919205],"domain_scores_gemma":[0.99836236,0.000253862,0.00009326816,0.0008874109,0.00023154609,0.0001715458],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00062477915,0.0002974597,0.00030853835,0.00028410924,0.00047034095,0.00073305157,0.0007734758,0.00014200009,0.00019927094],"category_scores_gemma":[0.0002022914,0.00027162582,0.00016371798,0.0010928276,0.000051272586,0.0011437386,0.00018618332,0.00016074898,0.00026011988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005276007,0.00016097166,0.00023667287,0.00002457363,0.00013731902,0.000016049982,0.0012222026,0.04412553,0.06991376,0.10855197,0.13067985,0.6448783],"study_design_scores_gemma":[0.00078802643,0.00018390566,0.00077183644,0.000072443305,0.000051019084,0.000006122385,0.000055393935,0.7182763,0.11859403,0.0075121354,0.1530997,0.0005890692],"about_ca_topic_score_codex":0.0004948009,"about_ca_topic_score_gemma":0.00055848993,"teacher_disagreement_score":0.7574448,"about_ca_system_score_codex":0.00009931784,"about_ca_system_score_gemma":0.00019542227,"threshold_uncertainty_score":0.9999736},"labels":[],"label_agreement":null},{"id":"W4417098422","doi":"10.48550/arxiv.2510.04290","title":"ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Image editing; Rendering (computer graphics); Leverage (statistics); Generative grammar; Generative model; Inference; Fidelity; Representation (politics); Video editing","score_opus":0.040047585258848925,"score_gpt":0.30292341283081153,"score_spread":0.2628758275719626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417098422","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014480718,0.0003662128,0.9785988,0.0011792034,0.0026399677,0.0005300676,0.000031840693,0.0001595143,0.002013679],"genre_scores_gemma":[0.82722986,0.000019795085,0.16869211,0.00026289636,0.0024824578,0.00007543687,0.000044175413,0.00001664315,0.0011766054],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817073,0.00009661856,0.00036739215,0.0008381986,0.00017612595,0.0003509386],"domain_scores_gemma":[0.9985392,0.00028951807,0.0002788192,0.0005585865,0.00024409882,0.000089772344],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005230192,0.0003108083,0.0003876915,0.00016986055,0.00028772344,0.00034901215,0.0005591366,0.00015330897,0.000015293954],"category_scores_gemma":[0.00038623737,0.00031096974,0.00015029503,0.00022716116,0.00006407174,0.00048026847,0.0012905897,0.00035097453,0.0000049410064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000099508674,0.00022968331,0.1404262,0.0015338315,0.00070402265,0.00005610759,0.0031349005,0.43002227,0.0015258145,0.0040805386,0.028617786,0.38956934],"study_design_scores_gemma":[0.000316286,0.000029803865,0.016641395,0.00038575765,0.000046446785,6.499868e-7,0.000023868819,0.9688598,0.001989369,0.000943215,0.010392871,0.0003705474],"about_ca_topic_score_codex":0.00014561461,"about_ca_topic_score_gemma":0.000059830672,"teacher_disagreement_score":0.81274915,"about_ca_system_score_codex":0.00008476501,"about_ca_system_score_gemma":0.00019106189,"threshold_uncertainty_score":0.99993426},"labels":[],"label_agreement":null},{"id":"W4417124644","doi":"10.1145/3757377.3763904","title":"In-2-4D: Inbetweening from Two Single-View Images to 4D Generation","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Interpolation (computer graphics); Motion field; Motion interpolation; Motion (physics); Motion capture; Leverage (statistics); Merge (version control); Motion estimation; Affine transformation","score_opus":0.032139291051561436,"score_gpt":0.28603726443291455,"score_spread":0.2538979733813531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417124644","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012015116,0.002916584,0.96176225,0.013232439,0.003780307,0.0005888069,0.000014668388,0.00006865208,0.0056211874],"genre_scores_gemma":[0.729615,0.000114206996,0.26010442,0.005930312,0.0016048236,0.000025910818,0.000011097003,0.00001969729,0.0025745428],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956637,0.0006133662,0.0010261042,0.0014947302,0.00040663627,0.00079544866],"domain_scores_gemma":[0.99790394,0.0003852552,0.00017154831,0.0010224185,0.00028466794,0.00023213906],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00071527757,0.00053785095,0.00072020513,0.00047942228,0.000612112,0.0026578254,0.0011378253,0.00016173514,0.00063934684],"category_scores_gemma":[0.0002630471,0.00053764164,0.00019388423,0.0021494408,0.00014788176,0.0016727446,0.001046631,0.00033335807,0.00015329584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026688283,0.00021700223,0.001168748,0.000023959472,0.00014969769,0.00004385915,0.0013563004,0.10967894,0.07961514,0.011450473,0.017444424,0.77882475],"study_design_scores_gemma":[0.00092592346,0.00014543046,0.0011888293,0.00038767097,0.00007265436,9.941053e-7,0.000074789954,0.7945935,0.17675759,0.0020889558,0.02304088,0.0007227726],"about_ca_topic_score_codex":0.0027711662,"about_ca_topic_score_gemma":0.0017470113,"teacher_disagreement_score":0.778102,"about_ca_system_score_codex":0.0002443735,"about_ca_system_score_gemma":0.00038805456,"threshold_uncertainty_score":0.9997075},"labels":[],"label_agreement":null},{"id":"W4417125414","doi":"10.1145/3757377.3763889","title":"MVP4D: Multi-View Portrait Video Diffusion for Animatable 4D Avatars","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Avatar; Rendering (computer graphics); Viewpoints; Process (computing); Virtual reality; Virtual image; Consistency (knowledge bases); Augmented reality","score_opus":0.024158862627907382,"score_gpt":0.2795018970375476,"score_spread":0.2553430344096402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417125414","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00035636683,0.0049090944,0.98023456,0.004298679,0.0030505478,0.0015793825,0.000054249616,0.00013989683,0.0053772456],"genre_scores_gemma":[0.24486671,0.001506841,0.6809721,0.005439754,0.00049247465,0.00019246066,0.00003581442,0.000053858443,0.06644001],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957042,0.00021587413,0.0010440908,0.0015530952,0.00036325757,0.001119518],"domain_scores_gemma":[0.9972187,0.0004540743,0.00027949424,0.0012947338,0.0004894448,0.00026354715],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010228062,0.000627095,0.00084842945,0.00024702933,0.0012425636,0.0012550277,0.0015300219,0.00025701078,0.00085728994],"category_scores_gemma":[0.0003199451,0.00055809936,0.00048462697,0.0011412599,0.00022339968,0.0012725438,0.0010598155,0.00026060062,0.00008963013],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013214601,0.00124668,0.0004246179,0.0005730482,0.00039061246,0.00002086454,0.00052059756,0.004853586,0.010661688,0.06869012,0.11845368,0.79403234],"study_design_scores_gemma":[0.0015965535,0.00017294075,0.00085230917,0.0003509644,0.00012613655,0.0000031041145,0.00007659059,0.77762425,0.009829826,0.0011524481,0.20766512,0.0005497878],"about_ca_topic_score_codex":0.00047806394,"about_ca_topic_score_gemma":0.00033907496,"teacher_disagreement_score":0.79348254,"about_ca_system_score_codex":0.00011857164,"about_ca_system_score_gemma":0.00062098255,"threshold_uncertainty_score":0.9997818},"labels":[],"label_agreement":null},{"id":"W4417237993","doi":"10.1109/smc58881.2025.11342641","title":"Sliced Wasserstein Discrepancy in Disentangling Representation and Adaptation Networks for Unsupervised Domain Adaptation","year":2025,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Domain adaptation; Adaptation (eye); Representation (politics); Feature (linguistics); Domain (mathematical analysis); Pattern recognition (psychology); Pipeline (software); Segmentation","score_opus":0.023580180659729586,"score_gpt":0.26312315985747153,"score_spread":0.23954297919774195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417237993","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0166267,0.00020726504,0.9800847,0.001483642,0.0002925391,0.0005502184,0.0000010280926,0.000059214366,0.0006946779],"genre_scores_gemma":[0.7434201,0.00004186928,0.25603384,0.00016281556,0.00005039976,0.00008160842,0.000017072207,0.000005381919,0.00018689656],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998803,0.00012889887,0.00032552233,0.00043090445,0.000102668746,0.00020897815],"domain_scores_gemma":[0.9992706,0.0002993969,0.000076695535,0.00023514178,0.00007765727,0.00004050805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000332798,0.00012510756,0.00016650638,0.000151274,0.0001451938,0.00018459304,0.00017462819,0.00005804801,0.0000024942888],"category_scores_gemma":[0.00008634033,0.00011686547,0.000052460593,0.00056679966,0.00002222752,0.00070752477,0.000074799806,0.00005864209,5.68555e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018934501,0.0001218439,0.0076762503,0.000048775917,0.000076595294,0.000006228792,0.0049234293,0.5043844,0.0022493326,0.20690818,0.0003065551,0.27310905],"study_design_scores_gemma":[0.00087538443,0.00003067031,0.0052125007,0.000042187705,0.000010160454,3.8223666e-7,0.0018612217,0.98100454,0.00046078372,0.010269296,0.000110003864,0.00012285619],"about_ca_topic_score_codex":0.00017283323,"about_ca_topic_score_gemma":0.00085987535,"teacher_disagreement_score":0.7267934,"about_ca_system_score_codex":0.00004649944,"about_ca_system_score_gemma":0.000035956065,"threshold_uncertainty_score":0.47656354},"labels":[],"label_agreement":null},{"id":"W4417297418","doi":"10.1016/j.compbiomed.2025.111385","title":"TagGAN: A generative model for data tagging","year":2025,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Faculty of Engineering and Information Technology, University of Technology Sydney; University of Technology Sydney","keywords":"Interpretability; Benchmark (surveying); Identification (biology); Binary classification; Domain (mathematical analysis); Translation (biology); Binary number; Generative grammar; Pattern recognition (psychology)","score_opus":0.05270634766204936,"score_gpt":0.3562049981891718,"score_spread":0.30349865052712244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417297418","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000316056,0.0014080458,0.9829745,0.013925777,0.00079095626,0.00018247482,0.0000043128884,0.000025567517,0.0003722617],"genre_scores_gemma":[0.40732124,0.0003240241,0.58250517,0.009305036,0.00026934603,0.000022937478,0.000049871647,0.0000039934835,0.00019840247],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990762,0.00006662704,0.00018205188,0.0004569268,0.000028011185,0.00019021292],"domain_scores_gemma":[0.99914896,0.00031744744,0.00004142805,0.00041886145,0.000036891448,0.000036392932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004392826,0.00010776341,0.00023957786,0.00012701737,0.00010940338,0.000014274289,0.00062149065,0.00006464391,9.749219e-7],"category_scores_gemma":[0.000110578556,0.00008103333,0.000013129082,0.00017805159,0.00017287272,0.00013536605,0.00048481542,0.000082295424,2.5692637e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045442182,0.000056793207,0.0011124193,0.000041941006,0.00010329711,0.0000067951755,0.0014884033,0.008093763,0.0033950342,0.51801336,0.066235155,0.4014076],"study_design_scores_gemma":[0.0006918636,0.000057563055,0.00012366015,0.00006487437,0.000007655826,0.0000015682948,0.000014742289,0.961116,0.000109791996,0.031768717,0.005970178,0.00007336583],"about_ca_topic_score_codex":0.000017574503,"about_ca_topic_score_gemma":0.000022034355,"teacher_disagreement_score":0.95302224,"about_ca_system_score_codex":0.000013822773,"about_ca_system_score_gemma":0.000047867976,"threshold_uncertainty_score":0.3304443},"labels":[],"label_agreement":null},{"id":"W4417314045","doi":"10.18280/isi.301016","title":"A Transformer Guided Generative Adversarial Network (TG-GAN) for Style Transfer in Artistic and Natural Scene Images","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Transformer; Adversarial system; Generative grammar; Natural (archaeology); Generative adversarial network","score_opus":0.011456206342566057,"score_gpt":0.23998591671502187,"score_spread":0.2285297103724558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417314045","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008360815,0.0022974364,0.9806964,0.00065687456,0.0029084971,0.0022825897,0.00010896409,0.00007903121,0.0026094106],"genre_scores_gemma":[0.96383154,0.0004355919,0.033737,0.00086228084,0.0004709889,0.0002742952,0.00009897805,0.000021580872,0.0002677327],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99583805,0.00035196496,0.0017516341,0.0006062884,0.00036665058,0.0010854236],"domain_scores_gemma":[0.9980864,0.0004247252,0.0002551447,0.0004225253,0.0006493094,0.00016191196],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012835235,0.0006562439,0.0008587755,0.00052138104,0.00093827164,0.0013279599,0.0005389195,0.0003328299,0.00003369889],"category_scores_gemma":[0.0004212052,0.0006527264,0.00025585128,0.0013796123,0.00047715518,0.0064635864,0.00008566486,0.00039288824,0.000011907898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014040074,0.00018559456,0.00070965313,0.001744357,0.00067016605,0.000012860758,0.032115065,0.11124139,0.0031545036,0.029042346,0.0075298543,0.8121902],"study_design_scores_gemma":[0.0047432785,0.00034242982,0.0044076894,0.0010204575,0.00019620385,0.000018387838,0.0008605355,0.96534175,0.009855208,0.007545625,0.0047766576,0.0008917893],"about_ca_topic_score_codex":0.00021347679,"about_ca_topic_score_gemma":0.00025111606,"teacher_disagreement_score":0.95547074,"about_ca_system_score_codex":0.0004593309,"about_ca_system_score_gemma":0.0005058518,"threshold_uncertainty_score":0.9997088},"labels":[],"label_agreement":null},{"id":"W4417408815","doi":"10.1109/iccv51701.2025.00995","title":"Tera: Rethinking Text-Guided Realistic 3D Avatar Generation","year":2025,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Avatar; Generative grammar; Generative model; Personalization; Generative Design; Perspective (graphical)","score_opus":0.03305778181066126,"score_gpt":0.2678968008375871,"score_spread":0.23483901902692583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417408815","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004819085,0.000097891956,0.95368814,0.0030242633,0.0008143309,0.00012174951,9.314349e-7,0.00014996003,0.04162082],"genre_scores_gemma":[0.67692065,0.000025487961,0.31301254,0.0032824918,0.00032834863,0.000013362291,0.000010450383,0.0000062786626,0.006400372],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883753,0.00011988488,0.00025523573,0.00040439997,0.0001633378,0.00021960733],"domain_scores_gemma":[0.99916697,0.00009382161,0.00005424957,0.00051855505,0.00012322732,0.000043180804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035947876,0.00013207659,0.00014852155,0.00010292963,0.00026317223,0.000325499,0.00049354444,0.00006295628,0.000065995766],"category_scores_gemma":[0.00013553833,0.000111530375,0.000051472787,0.0003996216,0.000029832077,0.00044750512,0.00020797353,0.00009837511,0.00004077984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005289418,0.000078740784,0.0003008657,0.000022057346,0.00009887907,0.000023101376,0.0008769434,0.022229059,0.031431034,0.46786785,0.2884774,0.1885888],"study_design_scores_gemma":[0.00018673876,0.000018101966,0.0004331117,0.000023912498,0.000012582886,0.0000028042507,0.000006799814,0.9630257,0.012603094,0.007906089,0.015611273,0.00016981734],"about_ca_topic_score_codex":0.00020604511,"about_ca_topic_score_gemma":0.00009965635,"teacher_disagreement_score":0.9407966,"about_ca_system_score_codex":0.000049955383,"about_ca_system_score_gemma":0.00007937128,"threshold_uncertainty_score":0.45480767},"labels":[],"label_agreement":null},{"id":"W4417442172","doi":"10.21468/scipostphyscore.8.4.095","title":"Tensorization of neural networks for improved privacy and interpretability","year":2025,"lang":"en","type":"preprint","venue":"SciPost Physics Core","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Agencia Estatal de Investigación; Government of Canada; Ministry of Colleges and Universities; Ministerio de Ciencia e Innovación; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; European Commission; Ministerio de Asuntos Económicos y Transformación Digital, Gobierno de España; NextGenerationEU; National Science Foundation; Universidad Complutense de Madrid; Comunidad de Madrid; Institut Périmètre de physique théorique; Innovation, Science and Economic Development Canada","keywords":"Interpretability; Artificial neural network; Initialization; Domain (mathematical analysis); ENCODE; Set (abstract data type); Function (biology); Interpolation (computer graphics); Feature (linguistics)","score_opus":0.02478107824929196,"score_gpt":0.27331152712670215,"score_spread":0.2485304488774102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417442172","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038284943,0.00021944456,0.99321485,0.00034715142,0.0012939716,0.0008465837,0.00009541372,0.000053572854,0.0001005496],"genre_scores_gemma":[0.9495512,0.000036712016,0.049733184,0.00012828565,0.00034314906,0.000061551546,0.00007452419,0.000011430183,0.000059919123],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985706,0.00007010734,0.00034489718,0.0006830052,0.0001018345,0.00022956243],"domain_scores_gemma":[0.9981215,0.00023691152,0.0003105573,0.0008411822,0.0004332381,0.000056626126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000221229,0.00025897037,0.00044130845,0.00004370772,0.000104746374,0.00013948388,0.0007782149,0.00015276583,9.923754e-7],"category_scores_gemma":[0.00011515485,0.00024121275,0.00017728464,0.00021235165,0.00011703134,0.0002307534,0.0018601955,0.0002582799,1.1001569e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015026575,0.00023457549,0.0014740482,0.00083257485,0.0003065831,5.559889e-7,0.0017431974,0.31311944,0.004646841,0.025539115,0.0007573946,0.6511954],"study_design_scores_gemma":[0.0001873411,0.00007064862,0.0005209204,0.000096569325,0.00004618481,1.7083845e-7,0.0000059115177,0.9681067,0.0017194023,0.02897994,0.00007182181,0.00019439848],"about_ca_topic_score_codex":0.000027914572,"about_ca_topic_score_gemma":0.0000048640068,"teacher_disagreement_score":0.94572276,"about_ca_system_score_codex":0.000032085958,"about_ca_system_score_gemma":0.000108142725,"threshold_uncertainty_score":0.98363703},"labels":[],"label_agreement":null},{"id":"W4417458336","doi":"","title":"Tuning-Free Coreset Markov Chain Monte Carlo via Hot DoG.","year":2025,"lang":"en","type":"article","venue":"PubMed","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Markov chain Monte Carlo; Markov chain; Convergence (economics); Bayesian probability; Bayesian inference; Inference; Stochastic approximation","score_opus":0.011761102405731054,"score_gpt":0.20607957318975598,"score_spread":0.19431847078402492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417458336","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032636665,0.00070793286,0.96735936,0.007020213,0.0019325562,0.00075865834,0.000012517143,0.00021906529,0.018726042],"genre_scores_gemma":[0.9820706,0.000028876619,0.009552528,0.0011841995,0.00020171468,0.00051106367,0.0000017896286,0.000009842813,0.0064393515],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844706,0.00014065788,0.00021413932,0.0004455729,0.00022333412,0.00052920857],"domain_scores_gemma":[0.9986189,0.00013688269,0.00006930702,0.00095365377,0.00008985083,0.00013141407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005244358,0.0001722497,0.00021670322,0.00014218302,0.00016819318,0.00021946519,0.0013730953,0.00006823824,0.000010521178],"category_scores_gemma":[0.00023779972,0.00015516918,0.0000971883,0.00057557056,0.00006494112,0.00032717866,0.0006847737,0.00014270277,0.00000972133],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003077632,0.000074281146,0.0016884943,0.000018280714,0.00012252518,0.000037743797,0.00021051435,0.0016684484,0.00016220512,0.0031858706,0.14293471,0.84986615],"study_design_scores_gemma":[0.0018366928,0.00004988514,0.3209578,0.000039419192,0.000054155487,0.000009146806,0.000042954587,0.5521082,0.0043854318,0.006591436,0.11312335,0.0008014982],"about_ca_topic_score_codex":0.00019959114,"about_ca_topic_score_gemma":0.00009746953,"teacher_disagreement_score":0.978807,"about_ca_system_score_codex":0.0000624105,"about_ca_system_score_gemma":0.000038829377,"threshold_uncertainty_score":0.6327616},"labels":[],"label_agreement":null},{"id":"W44815768","doi":"10.1007/978-3-642-35289-8_32","title":"A Practical Guide to Training Restricted Boltzmann Machines","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2825,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Boltzmann machine; Computer science; Set (abstract data type); Artificial intelligence; Generative grammar; Training set; Machine learning; Divergence (linguistics); Artificial neural network","score_opus":0.03733683725891546,"score_gpt":0.29671673500368906,"score_spread":0.2593798977447736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W44815768","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010678091,0.00031130074,0.9862556,0.0041503566,0.0021521396,0.0004027081,0.000004489889,0.00015677068,0.0065559642],"genre_scores_gemma":[0.04297308,0.000034470217,0.9515081,0.0029246013,0.0018289936,0.00001289951,0.0000036046763,0.000040098843,0.0006741677],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99581677,0.000086579224,0.0005966004,0.0014970878,0.0009918804,0.0010110606],"domain_scores_gemma":[0.9968694,0.0008121944,0.00025325903,0.0013263146,0.00029553974,0.00044329822],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010012455,0.0005890717,0.0006141935,0.0007608515,0.00033067312,0.00069122505,0.0023858713,0.00029319146,0.000040138355],"category_scores_gemma":[0.0005715084,0.00051205634,0.00014942387,0.0008750447,0.0003441351,0.0010072896,0.0015840898,0.0007959654,0.000120708064],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009352327,0.000033390068,0.000023827186,0.00001086646,0.000020546533,0.00011724772,0.0012984982,0.031321272,0.00042063458,0.011931827,0.0019729855,0.95283955],"study_design_scores_gemma":[0.00036551355,0.00032893257,0.00038422784,0.00039569096,0.000031584575,0.00022757624,6.357959e-7,0.89001286,0.0014096558,0.029257001,0.07602128,0.0015650566],"about_ca_topic_score_codex":0.000036777852,"about_ca_topic_score_gemma":0.00007571177,"teacher_disagreement_score":0.9512745,"about_ca_system_score_codex":0.00023156007,"about_ca_system_score_gemma":0.0006803909,"threshold_uncertainty_score":0.9997331},"labels":[],"label_agreement":null},{"id":"W590442793","doi":"10.48550/arxiv.1506.03504","title":"Data Generation as Sequential Decision Making","year":2015,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Generative grammar; Imputation (statistics); Machine learning; Artificial intelligence; Construct (python library); Generative model; Iterative and incremental development; Data mining; Missing data","score_opus":0.2344298734713957,"score_gpt":0.24241645810635287,"score_spread":0.007986584634957161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W590442793","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04693426,0.00003670181,0.9497926,0.0000758108,0.0006530364,0.000076286764,0.000005756497,0.00007741927,0.0023480996],"genre_scores_gemma":[0.9723618,0.000016480879,0.026783673,0.00016961448,0.0002782366,1.1360769e-7,0.000015458745,0.000006691971,0.00036795775],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880505,0.000119977,0.00011095704,0.00065525266,0.00010335331,0.00020539171],"domain_scores_gemma":[0.9985024,0.000056266337,0.00007601465,0.0011043297,0.00013257387,0.00012842893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037230476,0.00011829674,0.0001114924,0.00008592454,0.00015549416,0.00016645045,0.0013702734,0.000058913327,0.00003255873],"category_scores_gemma":[0.00011901573,0.00012383338,0.000039090577,0.00045906613,0.000039607676,0.0016495624,0.0009310217,0.0000821125,0.0002312952],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006252855,0.00009266222,0.0008212688,0.0000028333645,0.00006192411,0.00040506254,0.00023811514,0.83061033,0.0011003774,0.10714426,0.024357714,0.03510291],"study_design_scores_gemma":[0.0003149416,0.00004170611,0.00007997241,0.000009274988,0.000015875252,0.000007649612,0.00003399198,0.9849788,0.00031860935,0.008372423,0.005670096,0.00015664252],"about_ca_topic_score_codex":0.000049007445,"about_ca_topic_score_gemma":0.00007690063,"teacher_disagreement_score":0.9254275,"about_ca_system_score_codex":0.000078091696,"about_ca_system_score_gemma":0.00012752916,"threshold_uncertainty_score":0.5049779},"labels":[],"label_agreement":null},{"id":"W592244745","doi":"10.48550/arxiv.1506.02216","title":"A Recurrent Latent Variable Model for Sequential Data","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":705,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Autoencoder; Latent variable; Recurrent neural network; Computer science; Artificial intelligence; Latent variable model; Hidden variable theory; State variable; State (computer science); Machine learning; Artificial neural network; Speech recognition; Algorithm","score_opus":0.27536901168206473,"score_gpt":0.2356292871584844,"score_spread":0.03973972452358032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W592244745","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006048143,0.00013352839,0.9959058,0.00013528291,0.0014481497,0.00053018867,0.00035019295,0.00013947283,0.0007525707],"genre_scores_gemma":[0.8647785,0.00014652267,0.13147724,0.00010757524,0.00036027227,0.0000040576747,0.0003581023,0.000028417058,0.0027392888],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974772,0.00013503479,0.00022739654,0.0016102649,0.000113144786,0.00043696878],"domain_scores_gemma":[0.996487,0.00007176235,0.00024489878,0.0025693846,0.00039625325,0.00023069151],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00066822715,0.00033435246,0.00038578632,0.00012523607,0.00016860644,0.00023483248,0.0038122584,0.00024725622,0.00001288389],"category_scores_gemma":[0.00007917761,0.00036405123,0.00014954127,0.000294226,0.00006472262,0.0007175454,0.0063939574,0.00034483938,0.00002445781],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004054179,0.00007914835,0.000013057569,0.00003574421,0.00011087603,0.00001756632,0.000085213724,0.94674766,0.000020373313,0.037501708,0.014512601,0.0008354946],"study_design_scores_gemma":[0.0004493503,0.000038740924,0.0000025243373,0.0000492127,0.00012103743,0.0000011181556,0.000007001147,0.9217642,0.000026071659,0.074535735,0.0026242428,0.00038079754],"about_ca_topic_score_codex":0.00011097056,"about_ca_topic_score_gemma":0.000045444034,"teacher_disagreement_score":0.8644286,"about_ca_system_score_codex":0.00021717236,"about_ca_system_score_gemma":0.0007509603,"threshold_uncertainty_score":0.99988115},"labels":[],"label_agreement":null},{"id":"W6889525710","doi":"10.25549/webster-c100-12057","title":"Command Facts Handbook Chicago Police Department, 1992","year":2021,"lang":"en","type":"dataset","venue":"University of Southern California Digital Library","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Commission; Law enforcement; Newspaper; Criminal justice; Variety (cybernetics); Economic Justice","score_opus":0.007940943024841758,"score_gpt":0.16730931758598733,"score_spread":0.15936837456114558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6889525710","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000443255,0.0003116204,0.011835352,0.00025759856,0.000071369424,0.00014286007,0.9860942,0.00008152422,0.0011611445],"genre_scores_gemma":[0.00027902378,0.00020609479,0.0020512033,0.00028197543,0.00014482769,2.7201978e-7,0.99621457,0.000021052141,0.0008010045],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985206,0.00009551827,0.00022006808,0.0005270574,0.0003098627,0.0003269045],"domain_scores_gemma":[0.9985638,0.000115329494,0.0002672268,0.0007854215,0.00004034504,0.00022788014],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000040548664,0.0003350763,0.00046312314,0.00013843771,0.00020554788,0.00042014822,0.0014352759,0.00022656233,0.0007219364],"category_scores_gemma":[0.000012291496,0.0003433512,0.00028135648,0.00026267403,0.00018776722,0.00070031866,0.0013933365,0.00026155886,0.002914615],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020634267,0.00010642322,0.00008005277,0.000043182205,0.00011490035,0.000080873666,0.00005324981,0.000042758318,0.000002583088,0.0000029812775,0.99809617,0.0013562057],"study_design_scores_gemma":[0.00030470316,0.000030443169,0.0000047214257,0.00012861557,0.000043679694,0.0000075558582,0.00018193603,0.00024372482,0.00009390853,0.000094769115,0.9985206,0.00034530598],"about_ca_topic_score_codex":0.00022817876,"about_ca_topic_score_gemma":0.000043327975,"teacher_disagreement_score":0.010120341,"about_ca_system_score_codex":0.000026732569,"about_ca_system_score_gemma":0.00022322187,"threshold_uncertainty_score":0.99990183},"labels":[],"label_agreement":null},{"id":"W6892757835","doi":"10.5281/zenodo.12297589","title":"victaulic catalogue pdf","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Filter (signal processing); Fusible alloy; Nucleofection; Work (physics); Troubleshooting","score_opus":0.021520619563098392,"score_gpt":0.22549180990892928,"score_spread":0.2039711903458309,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6892757835","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.6866026e-7,0.0005757357,0.18118659,0.00061428035,0.0004480478,0.00024799985,0.00015431344,0.0014319944,0.8153406],"genre_scores_gemma":[0.002404602,0.00032066143,0.005025936,0.00032750343,0.0011893889,7.35909e-8,0.0019912198,0.008931147,0.97980946],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981668,0.00024859607,0.00018823855,0.00069975504,0.00033129455,0.00036533733],"domain_scores_gemma":[0.9987537,0.000011172282,0.0001029449,0.0008188439,0.00015530188,0.00015802278],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00033070426,0.00023103594,0.00020771696,0.00037204742,0.0005812811,0.0016660572,0.0021421122,0.00013817703,0.042306073],"category_scores_gemma":[0.00013847911,0.00022768432,0.00008704378,0.00063288835,0.00010913344,0.00017967411,0.0021720065,0.00032000596,0.21935447],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017753069,0.000027047847,1.7273576e-8,0.000053386146,0.000059298545,0.000029889508,0.00019394865,0.000015036656,0.00011576693,0.003721641,0.9519519,0.043830268],"study_design_scores_gemma":[0.00010811364,0.00006442771,0.0000024504902,0.00009171497,0.000015334756,0.00005187721,0.000019113962,0.0015830123,0.000076581935,0.00033044355,0.997414,0.00024296352],"about_ca_topic_score_codex":0.00004775369,"about_ca_topic_score_gemma":0.0000017028817,"teacher_disagreement_score":0.17704839,"about_ca_system_score_codex":0.00008244179,"about_ca_system_score_gemma":0.0000050016824,"threshold_uncertainty_score":0.99937034},"labels":[],"label_agreement":null},{"id":"W6892827924","doi":"10.5281/zenodo.12063917","title":"oil industry pdf","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Petroleum industry; Tonne; Palm oil; Midstream; Downstream (manufacturing); Fossil fuel; Crack spread; Product (mathematics); Petroleum","score_opus":0.025654304376033294,"score_gpt":0.23389556898188402,"score_spread":0.2082412646058507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6892827924","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.851012e-7,0.00048600987,0.0597938,0.0007972299,0.0004943564,0.0000765562,0.00007577896,0.0014167357,0.93685865],"genre_scores_gemma":[0.00058957294,0.0001820374,0.0025019983,0.00020646674,0.0008749704,3.2490142e-8,0.00025913233,0.005110985,0.9902748],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982025,0.00026052335,0.00018083285,0.0006553235,0.0003475868,0.00035322536],"domain_scores_gemma":[0.99881625,0.000010072942,0.00010416335,0.0007499869,0.0001533486,0.00016619441],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00034961765,0.00022049266,0.00019353945,0.00034586363,0.00054257235,0.0017656704,0.002016128,0.00028791183,0.08051757],"category_scores_gemma":[0.00015820761,0.00021836939,0.000077666526,0.00063187786,0.00010663263,0.00017441515,0.0021455765,0.0006654984,0.16353223],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015101267,0.000024035746,1.9597367e-8,0.000050757502,0.000050373248,0.000024388395,0.00010943984,0.000015708938,0.00007912553,0.0034976923,0.84822667,0.14792028],"study_design_scores_gemma":[0.00010842733,0.000049352086,0.0000016720273,0.00013500241,0.000014074812,0.000039656807,0.000024534753,0.0011887646,0.00006321067,0.00015727337,0.99798524,0.0002327727],"about_ca_topic_score_codex":0.000022445829,"about_ca_topic_score_gemma":4.366424e-7,"teacher_disagreement_score":0.14975859,"about_ca_system_score_codex":0.00007888692,"about_ca_system_score_gemma":0.0000056901345,"threshold_uncertainty_score":0.9992706},"labels":[],"label_agreement":null},{"id":"W6893166228","doi":"10.5281/zenodo.15188747","title":"Rescaled CIFAR-10 dataset","year":2025,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Vetenskapsrådet","keywords":"MNIST database; Gaussian; Scaling; Scale (ratio); Preprint; Set (abstract data type); Image (mathematics); Deep learning","score_opus":0.026310779582477874,"score_gpt":0.2521927547682363,"score_spread":0.22588197518575845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6893166228","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.7402134e-7,0.00011301176,0.04803795,0.00079982803,0.00035571356,0.00035745703,0.93924946,0.00037706492,0.010709143],"genre_scores_gemma":[0.0000275797,0.00023954124,0.0013013543,0.0004533081,0.00032038012,6.430776e-8,0.99567664,0.0002878669,0.0016932577],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968746,0.00074725953,0.00038207212,0.0009561875,0.0005251913,0.000514717],"domain_scores_gemma":[0.9968615,0.00006980571,0.00019754787,0.0021374305,0.00052663387,0.000207079],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008083398,0.00031254732,0.00032749926,0.000394693,0.0022937758,0.002363475,0.005440599,0.0001890952,0.014673221],"category_scores_gemma":[0.0009396514,0.00031971117,0.00009485884,0.00093141885,0.00015252315,0.00047285613,0.0062334007,0.0005304044,0.0066516697],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018632129,0.00008697288,7.9134574e-9,0.00006145317,0.00006134824,0.000029842295,0.000024810926,0.00005717191,0.000040190414,0.0002843497,0.9721948,0.027140457],"study_design_scores_gemma":[0.0002835244,0.000113533235,0.0000036217707,0.00006175824,0.00003121159,0.00002755282,0.000010303639,0.0010275115,0.00006176327,0.00006947411,0.9979998,0.00030998662],"about_ca_topic_score_codex":0.000050715356,"about_ca_topic_score_gemma":0.0000013269247,"teacher_disagreement_score":0.056427192,"about_ca_system_score_codex":0.00013483291,"about_ca_system_score_gemma":0.000015864885,"threshold_uncertainty_score":0.99994045},"labels":[],"label_agreement":null},{"id":"W6912775799","doi":"10.5281/zenodo.7525412","title":"3D-Aware Semantic-Guided Generative Model for Human Synthesis","year":2022,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Parks and Wilderness Society","funders":"Horizon 2020 Framework Programme","keywords":"Generative grammar; Set (abstract data type); Field (mathematics); Texture synthesis; Generative model; Code (set theory); Computer graphics; Image synthesis","score_opus":0.06255316187991244,"score_gpt":0.2628244228606647,"score_spread":0.20027126098075226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6912775799","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010307353,0.000032067044,0.98632133,0.0013164179,0.00012441665,0.0005509605,0.00023679483,0.0005348974,0.009852363],"genre_scores_gemma":[0.9745409,0.000013598605,0.021766713,0.0004552485,0.00020501547,0.0000014400156,0.0003967404,0.0007555298,0.0018648021],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977174,0.0005269371,0.0002794666,0.0006248503,0.00041950855,0.00043187133],"domain_scores_gemma":[0.99854475,0.000060990937,0.00013394562,0.0006320175,0.0004911342,0.00013718364],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00088926073,0.00017661242,0.00019907457,0.00019523872,0.006789473,0.0008685421,0.0019669982,0.000035470548,0.002584614],"category_scores_gemma":[0.00029741926,0.00019112074,0.00010016253,0.00050836353,0.00008152373,0.0004061693,0.002476249,0.00020043075,0.00030647384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051579296,0.00037306186,0.0000015827915,0.00005764748,0.00016705261,0.000020075971,0.0043826094,0.21524277,0.027326662,0.050885204,0.573226,0.12826578],"study_design_scores_gemma":[0.00027917515,0.00013161456,0.000010956378,0.000006533451,0.000015339287,0.00003085114,0.00013878633,0.74693716,0.002656749,0.0011384431,0.24843241,0.00022196874],"about_ca_topic_score_codex":0.000013682151,"about_ca_topic_score_gemma":5.43474e-7,"teacher_disagreement_score":0.9735102,"about_ca_system_score_codex":0.00018444413,"about_ca_system_score_gemma":0.000009765741,"threshold_uncertainty_score":0.99832714},"labels":[],"label_agreement":null},{"id":"W6926386288","doi":"10.25318/2710013701-eng","title":"Innovation and business strategy, strategic focus regarding goods or services","year":2019,"lang":"en","type":"dataset","venue":"Statistics Canada Dissemination","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Focus (optics); Goods and services; Strategic planning; Strategic management","score_opus":0.019046525452475576,"score_gpt":0.2665006704678247,"score_spread":0.24745414501534915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6926386288","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025318537,0.000119991215,0.14311185,0.000108653716,0.00075652625,0.00024189494,0.8555364,0.000014897875,0.00008447126],"genre_scores_gemma":[0.0063336673,0.00016569649,0.0076005775,0.00007979581,0.00016534548,0.000016616239,0.98533,0.000017113687,0.00029121552],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981835,0.00008261668,0.00043291505,0.0005225005,0.0005008079,0.00027769426],"domain_scores_gemma":[0.99808186,0.00029361632,0.00046375097,0.0004595102,0.000634743,0.0000664913],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002201834,0.0003174509,0.00033103168,0.00019404867,0.00018539159,0.0005700773,0.00050180545,0.00015189726,0.000043718017],"category_scores_gemma":[0.00010759881,0.00027982556,0.000010376578,0.00096901646,0.000030280622,0.00040289824,0.00014657326,0.00020055924,0.000002950046],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007783487,0.000012507533,0.000002923875,0.00032415448,0.000030460587,0.00004038413,0.000012900246,0.00036388374,0.000026126801,0.0049801352,0.98289627,0.011302471],"study_design_scores_gemma":[0.0013760792,0.0004930138,0.007965425,0.0020078605,0.00047164696,0.00009439597,0.0011018297,0.1536798,0.0006085444,0.016622374,0.81170547,0.003873548],"about_ca_topic_score_codex":0.07511311,"about_ca_topic_score_gemma":0.45567355,"teacher_disagreement_score":0.38056043,"about_ca_system_score_codex":0.00016392823,"about_ca_system_score_gemma":0.0008985174,"threshold_uncertainty_score":0.99996537},"labels":[],"label_agreement":null},{"id":"W6926399231","doi":"10.25316/ir-10686","title":"Nanaimo Free Press [Friday, November 13, 1896]","year":2019,"lang":"en","type":"other","venue":"VIUSpace (Vancouver Island University Library)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nice; Clothing; Navy; Population; Falling (accident)","score_opus":0.007163685337483778,"score_gpt":0.17338854334825718,"score_spread":0.1662248580107734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6926399231","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.2050315e-7,0.0004451011,0.13338457,0.0007180083,0.002434749,0.0004138499,0.00020156744,0.0005545492,0.8618468],"genre_scores_gemma":[0.00027915867,0.0005423561,0.014387518,0.00031093252,0.0005864935,0.0000011430444,0.000005312576,0.00024693555,0.98364013],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975595,0.00019374942,0.0001734617,0.0010366992,0.00044137042,0.00059520564],"domain_scores_gemma":[0.99739146,0.000106038475,0.00032381297,0.0019188446,0.00003667827,0.00022315404],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000047535657,0.00058891514,0.0006276311,0.00037251657,0.00016225362,0.00026944617,0.0028890113,0.00048413486,0.0009941544],"category_scores_gemma":[0.000013789492,0.00057056843,0.000286293,0.0004835396,0.00011326227,0.0016374001,0.0018708665,0.00040720587,0.00031908954],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020973863,0.000060893526,0.0000076074843,0.00004745177,0.00017661767,0.00011221187,0.00011162935,0.00029459188,0.0000056329136,0.002869383,0.99560267,0.00069034117],"study_design_scores_gemma":[0.0010722252,0.00006478834,0.0000114642635,0.00014730914,0.000060605493,0.0000014841623,0.000056931043,0.0028656763,0.00017780297,0.00016429833,0.99463475,0.0007426583],"about_ca_topic_score_codex":0.0013186793,"about_ca_topic_score_gemma":0.12959385,"teacher_disagreement_score":0.12827517,"about_ca_system_score_codex":0.000055644592,"about_ca_system_score_gemma":0.00021763143,"threshold_uncertainty_score":0.99991906},"labels":[],"label_agreement":null},{"id":"W6938888777","doi":"10.60692/8dbtd-79m33","title":"Modeling Personalization in Continuous Space for Response Generation via Augmented Wasserstein Autoencoders","year":2019,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Personalization; Space (punctuation); Latent variable; Distribution (mathematics); Pattern recognition (psychology); Vector space model","score_opus":0.02710254958416741,"score_gpt":0.20838768127619994,"score_spread":0.18128513169203253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6938888777","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22258878,0.0000030331278,0.77591276,0.00013882329,0.00045419042,0.00067049894,0.000008219095,0.00010002778,0.0001236616],"genre_scores_gemma":[0.98052263,8.6809884e-8,0.019014232,0.00012098309,0.00006146191,0.000082357925,0.000023165123,0.000008685384,0.00016642347],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855185,0.0001910517,0.000506945,0.00024237776,0.0002494447,0.00025834012],"domain_scores_gemma":[0.99915814,0.000018052206,0.00019255288,0.00033066564,0.00024684006,0.000053720094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090946775,0.00016775937,0.00022393304,0.00029897047,0.00011563139,0.0003296987,0.00024180474,0.0000944686,0.000006673742],"category_scores_gemma":[0.00003468087,0.00015477075,0.00007459022,0.00031562627,0.0000076801425,0.0018807355,0.000049578895,0.000055775316,0.000113273454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002260177,0.0000034270952,0.003313697,0.00011705169,0.000026023567,9.1116516e-7,0.043953065,0.9504293,0.0006391053,0.0006986031,0.000082558945,0.00051022344],"study_design_scores_gemma":[0.0010819455,0.00006555555,0.00042815795,0.00006903923,0.0000061487112,0.000004520613,0.0032501507,0.9936535,0.0011929369,0.0000021678097,0.00006673512,0.00017918652],"about_ca_topic_score_codex":0.000020234917,"about_ca_topic_score_gemma":0.0000018891263,"teacher_disagreement_score":0.7579338,"about_ca_system_score_codex":0.00021369228,"about_ca_system_score_gemma":0.000059296744,"threshold_uncertainty_score":0.6311368},"labels":[],"label_agreement":null},{"id":"W6944630391","doi":"10.20380/gi2021.09","title":"Artistic Recoloring of Image Oversegmentations","year":2021,"lang":"en","type":"article","venue":"Canada Human-Computer Communications Society","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Palette (painting); Set (abstract data type); Tree (set theory); Path (computing); Image (mathematics); Abstraction; Pruning; Local color","score_opus":0.024213742027021375,"score_gpt":0.25615083676187783,"score_spread":0.23193709473485646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6944630391","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012053662,0.00030778704,0.9928571,0.0026932075,0.00032064825,0.000103409846,0.000015579299,0.000045905315,0.0024510168],"genre_scores_gemma":[0.33694473,0.00006539406,0.6618922,0.0007048369,0.00006369408,0.000016986294,0.000039067476,0.000008582182,0.00026450717],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988225,0.00016303115,0.0003346753,0.00026293957,0.00020770937,0.00020912968],"domain_scores_gemma":[0.99730885,0.00027227862,0.00015075371,0.0018218592,0.0003654992,0.00008075948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014909207,0.00012271763,0.00019240883,0.000020229794,0.00058932806,0.00011186224,0.0012730075,0.000036465837,0.000040359428],"category_scores_gemma":[0.000022455131,0.0001414364,0.00014045161,0.00041334052,0.00012716794,0.00031495182,0.000866724,0.00016304187,0.0000028671523],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024549788,0.000831121,0.001527531,0.00016728093,0.001087768,0.000050050014,0.007273788,0.013211365,0.058767,0.2506835,0.6103333,0.056064844],"study_design_scores_gemma":[0.0011438816,0.000062915016,0.016340181,0.00013648918,0.00011068806,0.000031785316,0.0010780942,0.84103596,0.027105132,0.0034778195,0.10852623,0.0009508295],"about_ca_topic_score_codex":0.018166898,"about_ca_topic_score_gemma":0.08564555,"teacher_disagreement_score":0.8278246,"about_ca_system_score_codex":0.00021484587,"about_ca_system_score_gemma":0.00073864026,"threshold_uncertainty_score":0.9883712},"labels":[],"label_agreement":null},{"id":"W6950142740","doi":"10.5281/zenodo.6536926","title":"Microphorella vespera, sp. nov.","year":2022,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"","keywords":"Holotype; Paratype; Dorsum; Fish <Actinopterygii>; Single specimen","score_opus":0.024074817515309425,"score_gpt":0.2159005816807256,"score_spread":0.19182576416541616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6950142740","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029817123,0.0006766428,0.692635,0.008086541,0.0013840821,0.0010395023,0.00025311156,0.0015065041,0.2646015],"genre_scores_gemma":[0.99144155,0.000043791246,0.005387043,0.0006127822,0.00020436791,7.0487616e-8,0.00015329548,0.0006078575,0.0015492453],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99822277,0.00047255165,0.0001722107,0.0004431709,0.00036236143,0.0003269477],"domain_scores_gemma":[0.9990146,0.000020770527,0.00007071328,0.0005571981,0.0002175098,0.000119181816],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005945487,0.00011290388,0.00011090501,0.00015034134,0.0037772967,0.0008407854,0.0019982124,0.000021476875,0.011142396],"category_scores_gemma":[0.00011940955,0.00012344637,0.00005720259,0.00070886425,0.00007337496,0.00013927899,0.0033260228,0.00024983173,0.0031041198],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043558906,0.00026408568,0.0000029585747,0.000015707714,0.000061233935,0.00006364461,0.0024809483,0.005807634,0.111567415,0.019611591,0.5735279,0.28655338],"study_design_scores_gemma":[0.00023753096,0.00015094127,0.000090006724,0.000002809184,0.0000037347659,0.000092417686,0.00012525232,0.009803164,0.0016092613,0.00021032781,0.9875237,0.00015090061],"about_ca_topic_score_codex":0.000014133978,"about_ca_topic_score_gemma":8.1721296e-8,"teacher_disagreement_score":0.96162444,"about_ca_system_score_codex":0.00013214209,"about_ca_system_score_gemma":0.0000048136562,"threshold_uncertainty_score":0.9976721},"labels":[],"label_agreement":null},{"id":"W6957618656","doi":"10.60692/4sa0r-ktg85","title":"Modeling Personalization in Continuous Space for Response Generation via Augmented Wasserstein Autoencoders","year":2019,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Personalization; Space (punctuation); Latent variable; Distribution (mathematics); Pattern recognition (psychology); Vector space model","score_opus":0.02710254958416741,"score_gpt":0.20838768127619994,"score_spread":0.18128513169203253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6957618656","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22258878,0.0000030331278,0.77591276,0.00013882329,0.00045419042,0.00067049894,0.000008219095,0.00010002778,0.0001236616],"genre_scores_gemma":[0.98052263,8.6809884e-8,0.019014232,0.00012098309,0.00006146191,0.000082357925,0.000023165123,0.000008685384,0.00016642347],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855185,0.0001910517,0.000506945,0.00024237776,0.0002494447,0.00025834012],"domain_scores_gemma":[0.99915814,0.000018052206,0.00019255288,0.00033066564,0.00024684006,0.000053720094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00090946775,0.00016775937,0.00022393304,0.00029897047,0.00011563139,0.0003296987,0.00024180474,0.0000944686,0.000006673742],"category_scores_gemma":[0.00003468087,0.00015477075,0.00007459022,0.00031562627,0.0000076801425,0.0018807355,0.000049578895,0.000055775316,0.000113273454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002260177,0.0000034270952,0.003313697,0.00011705169,0.000026023567,9.1116516e-7,0.043953065,0.9504293,0.0006391053,0.0006986031,0.000082558945,0.00051022344],"study_design_scores_gemma":[0.0010819455,0.00006555555,0.00042815795,0.00006903923,0.0000061487112,0.000004520613,0.0032501507,0.9936535,0.0011929369,0.0000021678097,0.00006673512,0.00017918652],"about_ca_topic_score_codex":0.000020234917,"about_ca_topic_score_gemma":0.0000018891263,"teacher_disagreement_score":0.7579338,"about_ca_system_score_codex":0.00021369228,"about_ca_system_score_gemma":0.000059296744,"threshold_uncertainty_score":0.6311368},"labels":[],"label_agreement":null},{"id":"W6969313300","doi":"10.5281/zenodo.8256421","title":"A Probabilistic Framework for Mutation Testing in Deep Neural Networks - Models archive Part 4","year":2022,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Probabilistic logic; Replication (statistics); Artificial neural network; Mutation; Software; Statistical model","score_opus":0.021819605906375085,"score_gpt":0.2323912388658238,"score_spread":0.21057163295944872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6969313300","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024753981,0.0005144835,0.99327874,0.0016012854,0.00030214363,0.001355924,0.000025060297,0.00035326052,0.000093702474],"genre_scores_gemma":[0.5494869,0.000004767026,0.4473828,0.0009613588,0.00013833483,0.0019627009,0.000018735022,0.000027109476,0.000017279435],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99731225,0.00039563817,0.0005055626,0.0006748884,0.0003123964,0.00079924037],"domain_scores_gemma":[0.9976916,0.0011079615,0.00025609008,0.00067570125,0.000103009486,0.0001656486],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00094884564,0.00028566722,0.0003283393,0.00028985646,0.00059101026,0.00026657156,0.00094477,0.00010496402,0.000009568783],"category_scores_gemma":[0.0006442295,0.00031108494,0.00013999782,0.0010914622,0.000055201504,0.0005951814,0.00057027314,0.00058821234,6.6631316e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038782728,0.000110262066,0.00040667833,0.000009445205,0.000012716931,0.00003214068,0.00039456738,0.8734085,0.00006361841,0.08379374,0.00019922349,0.041530307],"study_design_scores_gemma":[0.00024724813,0.00020062385,0.00067839114,0.000018906536,0.000012404556,0.000040921746,0.0000672876,0.82240444,0.000053831052,0.17590033,0.000102509584,0.00027311835],"about_ca_topic_score_codex":0.0013769617,"about_ca_topic_score_gemma":0.00093313603,"teacher_disagreement_score":0.5470115,"about_ca_system_score_codex":0.00033334323,"about_ca_system_score_gemma":0.0001255468,"threshold_uncertainty_score":0.99993414},"labels":[],"label_agreement":null},{"id":"W6977225402","doi":"10.6084/m9.figshare.24770432.v1","title":"Additional file 1 of MedFusionGAN: multimodal medical image fusion using an unsupervised deep generative adversarial network","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Centre hospitalier universitaire de Québec","funders":"","keywords":"Adversarial system; Fusion; Generative adversarial network; Deep learning; Key (lock); Generative grammar; Pattern recognition (psychology)","score_opus":0.032847775778412865,"score_gpt":0.25700302585369933,"score_spread":0.22415525007528647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977225402","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000035759433,0.000018109944,0.012184039,0.00010234598,0.00024797293,0.0002282777,0.9863277,0.00019255465,0.00066321413],"genre_scores_gemma":[0.0015496893,0.0000024105066,0.11399314,0.00029189917,0.0020396465,0.00023887343,0.88175774,0.000030150273,0.00009647162],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975698,0.00029025663,0.00035445203,0.0005414736,0.0007855602,0.0004584704],"domain_scores_gemma":[0.99722815,0.0015218405,0.00018055779,0.00044044745,0.00035064644,0.00027835995],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001348727,0.00023431687,0.000295477,0.000111859204,0.0003739931,0.00010184583,0.0008715799,0.00019328586,0.97330695],"category_scores_gemma":[0.0023698355,0.0002156435,0.00015447247,0.0009206352,0.000036350088,0.00077507074,0.00074290624,0.00020900871,0.0012172756],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000089393325,0.000047958838,4.134667e-7,0.000011184659,0.000020870833,0.000053766795,0.00014695368,0.01164517,0.0002595123,0.000016539903,0.9785305,0.009258164],"study_design_scores_gemma":[0.00029600173,0.00006188143,0.00034377511,0.00056895247,0.000004669066,0.000007438355,0.000034943238,0.9098183,0.00047932015,0.000108391505,0.08803885,0.00023746879],"about_ca_topic_score_codex":0.000017466982,"about_ca_topic_score_gemma":0.000047192185,"teacher_disagreement_score":0.9720897,"about_ca_system_score_codex":0.00003914648,"about_ca_system_score_gemma":0.00036865048,"threshold_uncertainty_score":0.9995604},"labels":[],"label_agreement":null},{"id":"W6980263721","doi":"","title":"BioHiTech Global Reports Third Quarter 2020 Financial Results","year":2020,"lang":"en","type":"other","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Payment; Term (time); Work (physics)","score_opus":0.00786686891487259,"score_gpt":0.21727948963433533,"score_spread":0.20941262071946273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6980263721","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.315732e-7,0.0002041541,0.4067529,0.003100926,0.0014836281,0.00017281965,0.00003706062,0.00041909242,0.5878293],"genre_scores_gemma":[0.0021814564,0.00013744505,0.28198177,0.004680153,0.005832442,0.000030263698,0.000077859295,0.00018145729,0.70489717],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976593,0.00008600118,0.000450508,0.0010747347,0.0003687047,0.00036072836],"domain_scores_gemma":[0.99844563,0.000024083532,0.0003468229,0.00096595264,0.000040215284,0.00017727242],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016329225,0.00037837238,0.00044539289,0.00005089357,0.00006432388,0.00021885833,0.00074053893,0.00035038695,0.00027911176],"category_scores_gemma":[0.00014811911,0.00031325303,0.0001901041,0.00054516946,0.000048783928,0.0001262372,0.0003585128,0.00019639486,0.00042213214],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000067598526,0.000018490082,0.000008855957,0.000007439695,0.000027383196,0.0003899811,0.000026159021,0.000013900696,0.000012295778,0.0011850062,0.9925632,0.0057405494],"study_design_scores_gemma":[0.00018567401,0.000079247504,0.00007120687,0.0000504333,0.000014075492,0.0000381204,0.0000031549164,0.0024801418,0.00009164377,0.0007148278,0.9958592,0.0004122768],"about_ca_topic_score_codex":0.00033929804,"about_ca_topic_score_gemma":0.00029825213,"teacher_disagreement_score":0.124771155,"about_ca_system_score_codex":0.00003864998,"about_ca_system_score_gemma":0.00018994689,"threshold_uncertainty_score":0.99993193},"labels":[],"label_agreement":null},{"id":"W6999339067","doi":"","title":"Comparing Different Generative Adversarial Networks for Image Generation","year":2024,"lang":"en","type":"dissertation","venue":"Repository of the University of Ljubljana (University of Ljubljana)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Adversarial system; Generative grammar; Image (mathematics); Quality (philosophy); Image quality; Generative adversarial network","score_opus":0.0162737415940612,"score_gpt":0.197895924533053,"score_spread":0.1816221829389918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6999339067","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25333482,0.0012034086,0.72851545,0.00076571567,0.007091204,0.0017124687,0.00011387771,0.00013056747,0.0071324725],"genre_scores_gemma":[0.9685197,0.00019412035,0.019272625,0.000009830842,0.0003572149,3.0754623e-7,0.00017894412,0.000035945715,0.011431297],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974135,0.00033526868,0.0004264578,0.00082979526,0.0006239406,0.0003709928],"domain_scores_gemma":[0.99663454,0.00017267473,0.001287302,0.0009831201,0.00078519934,0.00013713287],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031179702,0.0004635909,0.0010615002,0.0003545283,0.00092538306,0.000064221815,0.002315125,0.0004359625,0.000024880515],"category_scores_gemma":[0.00003108437,0.0004958641,0.0011034235,0.00050904683,0.0004300214,0.0006679692,0.0005563451,0.00041699543,0.0000029096661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0039242874,0.0020341561,0.0016416416,0.0053822803,0.011881691,0.00033233155,0.06369926,0.2346183,0.46391112,0.034041848,0.15910596,0.01942712],"study_design_scores_gemma":[0.0022137072,0.00041680026,0.003919078,0.0009492026,0.0019012148,0.0000100622765,0.0080444785,0.93324167,0.043405116,0.00037036592,0.0045421747,0.0009861455],"about_ca_topic_score_codex":0.0010538682,"about_ca_topic_score_gemma":0.0019832246,"teacher_disagreement_score":0.7151849,"about_ca_system_score_codex":0.0002744494,"about_ca_system_score_gemma":0.00035831923,"threshold_uncertainty_score":0.9997493},"labels":[],"label_agreement":null},{"id":"W7011468468","doi":"","title":"Mehiläistarhojen suojaus karhuvahingoilta: karhuvahinkoja kärsineiden mehiläistarhojen suojausmenetelmät","year":2022,"lang":"fi","type":"other","venue":"Theseus (Ammattikorkeakoulujen)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Work (physics); Quarter (Canadian coin); Life style","score_opus":0.020023642404597777,"score_gpt":0.24267361330323015,"score_spread":0.22264997089863237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7011468468","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00070254685,0.0104967635,0.03218903,0.005299866,0.007911029,0.0036381567,0.0010007223,0.0016899599,0.9370719],"genre_scores_gemma":[0.033108354,0.0021752215,0.016758788,0.002500699,0.005011267,0.0005841121,0.0007395337,0.0019529072,0.93716913],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97756493,0.0041048657,0.0034614077,0.005779317,0.0040898053,0.0049996595],"domain_scores_gemma":[0.9850507,0.0017968661,0.0031833262,0.007389638,0.0007349324,0.0018445418],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"category_scores_codex":[0.0043235016,0.004231128,0.004367227,0.0018650324,0.003067961,0.0028087771,0.011706325,0.0017894831,0.067277856],"category_scores_gemma":[0.0008562958,0.004287135,0.0021385388,0.0036434198,0.0013017225,0.0021435749,0.0072212974,0.004093338,0.008642816],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00084334175,0.001857545,0.0005469505,0.0008922699,0.004554152,0.002432778,0.007737399,0.00875715,0.0018275687,0.018568074,0.04386902,0.9081138],"study_design_scores_gemma":[0.0024015165,0.0009172434,0.00072148384,0.00055120053,0.0008103413,0.00027870983,0.0006214936,0.014231177,0.0006218415,0.003293118,0.9710001,0.004551808],"about_ca_topic_score_codex":0.0048902063,"about_ca_topic_score_gemma":0.0013237001,"teacher_disagreement_score":0.92713106,"about_ca_system_score_codex":0.0023211327,"about_ca_system_score_gemma":0.0017576372,"threshold_uncertainty_score":0.9995064},"labels":[],"label_agreement":null},{"id":"W7015054489","doi":"","title":"Recurrent inference machines for accelerated MRI reconstruction.","year":2018,"lang":"en","type":"article","venue":"Data Archiving and Networked Services (DANS)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"ASTRON; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Canadian Institute for Advanced Research","keywords":"Leverage (statistics); Inference; Deep learning; Transfer of learning; Range (aeronautics); Domain (mathematical analysis)","score_opus":0.03724196802962392,"score_gpt":0.2905202634546112,"score_spread":0.25327829542498725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7015054489","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032030407,0.00031595337,0.9646501,0.00036192406,0.0012227615,0.0002646651,0.00014979184,0.00014888436,0.0008555368],"genre_scores_gemma":[0.80133414,0.0003532731,0.19577356,0.0003803341,0.0016432275,0.0000298909,0.0003674925,0.00002194876,0.00009615802],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982462,0.0001532631,0.00029033213,0.000777718,0.00013236352,0.0004001495],"domain_scores_gemma":[0.99823874,0.00034669464,0.00014699736,0.0010238881,0.000109549204,0.00013410805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004519499,0.00023296267,0.00023800465,0.0000723608,0.00061879685,0.00044274557,0.0017939447,0.0000501865,0.0000134458],"category_scores_gemma":[0.000028567474,0.00019072679,0.000036236343,0.0003083126,0.00014065871,0.0010756077,0.0010624379,0.00012868945,0.000009862901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000095094474,0.000057478017,0.0052500665,0.00010264611,0.00011555784,0.000002378222,0.002048626,0.0013661627,0.0013612359,0.0014433502,0.0027820894,0.9853753],"study_design_scores_gemma":[0.00024800847,0.00011341943,0.0045463936,0.0001482275,0.00002116174,0.0000140538305,0.000051925108,0.98432666,0.00024822922,0.0023607647,0.007672312,0.00024881528],"about_ca_topic_score_codex":0.00020298798,"about_ca_topic_score_gemma":0.0012663563,"teacher_disagreement_score":0.9851265,"about_ca_system_score_codex":0.0000106699645,"about_ca_system_score_gemma":0.000038764094,"threshold_uncertainty_score":0.7777613},"labels":[],"label_agreement":null},{"id":"W7023867778","doi":"","title":"Piffles Podcast Episode 168 - 3 and OH NO YOU DIDNT","year":2021,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Wonder; League; Zoom; Conjunction (astronomy); Representation (politics)","score_opus":0.005906373380097673,"score_gpt":0.1773298445577126,"score_spread":0.17142347117761494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7023867778","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000044108033,0.0013749409,0.00035568431,0.00030133524,0.00053062994,0.00022879714,0.00004639889,0.00011231549,0.9970455],"genre_scores_gemma":[0.00033940357,0.0007109363,0.020850288,0.00037344554,0.00031843345,0.000009469066,0.000063927226,0.0000612685,0.9772728],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984265,0.00011026063,0.0004748699,0.00033472205,0.000346636,0.0003070091],"domain_scores_gemma":[0.9986337,0.0001030486,0.00040954252,0.00052655954,0.00018941484,0.00013774543],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00018347391,0.0003478799,0.00045493746,0.000067001325,0.00009160432,0.00019846723,0.00050485256,0.00027065058,0.12204691],"category_scores_gemma":[0.00012259284,0.00032814624,0.00013534818,0.000012886304,0.00012277912,5.7656257e-7,0.0003344872,0.00020221298,0.0024733914],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008755214,0.000022071456,0.000002076913,0.00017661443,0.00005846205,0.000023273162,0.00007593956,0.00034129585,0.000001696881,0.000087815584,0.9926356,0.0065663946],"study_design_scores_gemma":[0.00026287447,0.00007458603,0.000011767483,0.0002433841,0.000023572691,0.000056667788,0.000024157143,0.0014204491,0.000028016735,0.000011925927,0.9974991,0.00034346947],"about_ca_topic_score_codex":0.002465848,"about_ca_topic_score_gemma":0.00074570277,"teacher_disagreement_score":0.11957352,"about_ca_system_score_codex":0.000024622519,"about_ca_system_score_gemma":0.000031689757,"threshold_uncertainty_score":0.99991703},"labels":[],"label_agreement":null},{"id":"W7024071819","doi":"","title":"Prévention de la violence entre membres d’une même organisation de travail : évaluation d’une intervention participative","year":2010,"lang":"fr","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Servant; Gender relations; Intervention (counseling); Poison control","score_opus":0.019591029508768364,"score_gpt":0.28127819712741897,"score_spread":0.26168716761865063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024071819","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26824874,0.00031803292,0.7240166,0.0033660303,0.0012930399,0.0003036419,0.000005171162,0.00008485055,0.0023638676],"genre_scores_gemma":[0.9514417,0.00023549193,0.043989327,0.00021824511,0.0005420032,0.000052731382,0.000017895814,0.000022940621,0.0034796465],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99632394,0.0016039051,0.0005429565,0.0005654481,0.00038757006,0.0005761982],"domain_scores_gemma":[0.99830973,0.00039644437,0.0003262276,0.0003925372,0.0003761848,0.00019885099],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0027625621,0.0002900119,0.00025039137,0.00010308446,0.0003301513,0.00053412415,0.00040135626,0.0002994721,0.0022430755],"category_scores_gemma":[0.00053806807,0.00029788862,0.00020675601,0.00057143334,0.00033656572,0.0013318964,0.00012921335,0.00043547017,0.00018941848],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048881586,0.00079162925,0.0026904773,0.00008738434,0.00011355928,0.000017944745,0.021299232,0.00795517,0.12668228,0.023828669,0.0027177203,0.8137671],"study_design_scores_gemma":[0.0008034982,0.000253018,0.067608185,0.00032715988,0.00016738154,0.00003902469,0.0017353158,0.76560384,0.124716975,0.036280844,0.002078323,0.00038644148],"about_ca_topic_score_codex":0.004842176,"about_ca_topic_score_gemma":0.0034104658,"teacher_disagreement_score":0.8133806,"about_ca_system_score_codex":0.00017952753,"about_ca_system_score_gemma":0.00032392374,"threshold_uncertainty_score":0.9999473},"labels":[],"label_agreement":null},{"id":"W7024259244","doi":"","title":"Regionalizing NAFTA: Theaters of Translation in Mexico City and Quebec","year":2019,"lang":"en","type":"other","venue":"eScholarship (California Digital Library)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Interculturalism; Politics; Regionalism (politics); Mexico city; Meaning (existential); Transculturation","score_opus":0.01758069786291472,"score_gpt":0.2079017622903003,"score_spread":0.19032106442738558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024259244","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031186903,0.006113734,0.14773032,0.0029503212,0.00076766184,0.0016631645,0.0018356172,0.0007017396,0.8351188],"genre_scores_gemma":[0.7256983,0.000419075,0.03605836,0.0010186774,0.00049104413,0.000039627113,0.00062480516,0.0007611487,0.23488897],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998397,0.00012368964,0.00036398292,0.0005564654,0.00027675516,0.0002821292],"domain_scores_gemma":[0.9990485,0.0001584388,0.00022566148,0.0004499291,0.000013656286,0.00010381939],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00013863003,0.00031876264,0.0004426218,0.000339063,0.000028478558,0.0005906882,0.0005819522,0.00025860782,0.00013327491],"category_scores_gemma":[0.000038373426,0.00028503302,0.00012300834,0.00037890312,0.000096835305,0.002292323,0.00020463295,0.00027627024,0.000096473355],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032102744,0.00084307697,0.2784878,0.0013789883,0.000697684,0.00015435374,0.00079760986,0.0005789894,0.00067807623,0.030286204,0.2960825,0.38969368],"study_design_scores_gemma":[0.0008665619,0.00006712203,0.0025628058,0.0009695775,0.000018348503,0.000006078645,0.000016831984,0.0033785165,0.0011671077,0.0038075277,0.98634017,0.00079937425],"about_ca_topic_score_codex":0.0001923141,"about_ca_topic_score_gemma":0.00014370886,"teacher_disagreement_score":0.7225796,"about_ca_system_score_codex":0.000020059748,"about_ca_system_score_gemma":0.00010383093,"threshold_uncertainty_score":0.9999602},"labels":[],"label_agreement":null},{"id":"W7024375118","doi":"","title":"Relier l’art et le français à travers les émotions, l’intericonicité et l’expérience esthétique en classe de langue : une expérience menée avec des fonctionnaires du gouvernement fédéral du Canada","year":2024,"lang":"en","type":"dissertation","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Civil servants; Discourse analysis; Civil servant; Painting; French; Pragmatics; Qualitative research","score_opus":0.005051029558466876,"score_gpt":0.20534729515362896,"score_spread":0.2002962655951621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024375118","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19293122,0.0014976509,0.74442303,0.01802875,0.0011360927,0.00057721447,0.00005365903,0.0003606176,0.040991735],"genre_scores_gemma":[0.9627771,0.0014645571,0.025484782,0.00033940558,0.00004931265,0.00014286922,0.0003488013,0.000053642285,0.009339538],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99434865,0.0030709677,0.0005667255,0.00093776314,0.00057560834,0.00050027674],"domain_scores_gemma":[0.99637085,0.0008910629,0.00035299698,0.0010936792,0.0010648466,0.0002265602],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0027430125,0.00045282987,0.0003787093,0.00016124388,0.0007149224,0.00068642286,0.0015976959,0.00022266185,0.000103529754],"category_scores_gemma":[0.00088987174,0.00046584907,0.00020477423,0.00072510226,0.00019253459,0.00062116724,0.00034682907,0.0005715644,0.000024694147],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006613171,0.001358516,0.0016791134,0.0005159507,0.00050042826,0.00036521384,0.4217557,0.005149117,0.013449693,0.31324333,0.09708917,0.14482763],"study_design_scores_gemma":[0.0023379058,0.000019581315,0.12475158,0.0071724304,0.00031455889,0.00029156313,0.023221726,0.42378536,0.13652936,0.006034268,0.2718633,0.0036783493],"about_ca_topic_score_codex":0.35944387,"about_ca_topic_score_gemma":0.82909065,"teacher_disagreement_score":0.76984584,"about_ca_system_score_codex":0.0004720076,"about_ca_system_score_gemma":0.0019831955,"threshold_uncertainty_score":0.99977934},"labels":[],"label_agreement":null},{"id":"W7024458533","doi":"","title":"Smith Digital Video History - No. 1: 1947 at the Jersey Shore","year":2021,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Shore; Digital video; George (robot); Work (physics)","score_opus":0.007158480478135901,"score_gpt":0.16674126558551638,"score_spread":0.1595827851073805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024458533","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000014182192,0.0028521726,0.000108805434,0.0004053118,0.0011939242,0.00027607984,0.00005617808,0.00012119256,0.9949849],"genre_scores_gemma":[0.00016084623,0.00030757283,0.0025269073,0.00058249605,0.00039244958,0.000013664142,0.000102912476,0.000071950984,0.9958412],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99824727,0.00010343419,0.00048781492,0.00033431457,0.0004987881,0.00032838754],"domain_scores_gemma":[0.9981703,0.00016339259,0.0004932858,0.000831277,0.00022796566,0.00011376392],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00018475125,0.0003655056,0.00039604743,0.000049305956,0.000101664,0.0001696971,0.0009012945,0.0002603134,0.30258197],"category_scores_gemma":[0.00016312326,0.000284856,0.00025492877,0.000011565421,0.00021163358,8.7315306e-7,0.0004932954,0.00024819706,0.010622658],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000133289195,0.000022645014,8.856297e-7,0.00010228493,0.00007276784,0.000022105816,0.00018072802,0.00048429042,4.7780134e-7,0.00002443169,0.99496967,0.0041063963],"study_design_scores_gemma":[0.00020056908,0.00005826212,0.0000033145309,0.00016469916,0.000023759188,0.0000433269,0.000036975733,0.0005733177,0.000008389132,0.000003451025,0.9985599,0.0003240612],"about_ca_topic_score_codex":0.0010607088,"about_ca_topic_score_gemma":0.00056975766,"teacher_disagreement_score":0.29195932,"about_ca_system_score_codex":0.00019357575,"about_ca_system_score_gemma":0.0001012797,"threshold_uncertainty_score":0.99996036},"labels":[],"label_agreement":null},{"id":"W7024502870","doi":"","title":"Scenarios for exposure of aquatic organisms to plant protection products in the Netherlands : Part 1: Field crops and downward spraying","year":2013,"lang":"nl","type":"report","venue":"Data Archiving and Networked Services (DANS)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nova scotia","score_opus":0.04895920009461476,"score_gpt":0.2513055361187886,"score_spread":0.20234633602417382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024502870","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45451656,0.006434714,0.5161722,0.00506955,0.004006566,0.011974358,0.0009837322,0.00013253908,0.00070982706],"genre_scores_gemma":[0.97532743,0.0018822042,0.01776858,0.0006784045,0.0026818947,0.0004707758,0.0007843973,0.00007407093,0.00033226237],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99576503,0.00063230074,0.000911331,0.0014405913,0.0005641684,0.00068655174],"domain_scores_gemma":[0.9964131,0.0008304434,0.0006141741,0.001824095,0.00014338299,0.00017476786],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00297813,0.00057371473,0.00081840646,0.00017258237,0.00053082977,0.00064212177,0.0020776496,0.00023632082,0.000015753218],"category_scores_gemma":[0.00024322323,0.0003983539,0.00006292233,0.0005676597,0.00009798232,0.00056741433,0.0013186296,0.0005931549,0.000004639344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00087361067,0.0006382561,0.016348973,0.011372643,0.0008308711,0.000094200026,0.15377185,0.028257038,0.0038131066,0.00006361267,0.028644627,0.7552912],"study_design_scores_gemma":[0.00072378496,0.0012118396,0.007454454,0.0044007148,0.00028655928,0.00014902376,0.004081424,0.9348456,0.0003966561,0.00018154355,0.04531308,0.00095529354],"about_ca_topic_score_codex":0.004357527,"about_ca_topic_score_gemma":0.0045483904,"teacher_disagreement_score":0.9065886,"about_ca_system_score_codex":0.000024300734,"about_ca_system_score_gemma":0.00023538375,"threshold_uncertainty_score":0.9998468},"labels":[],"label_agreement":null},{"id":"W7024503297","doi":"","title":"A Relative Impact Ranking of Political Studies in Ireland","year":2009,"lang":"en","type":"article","venue":"Arrow@dit (Dublin Institute of Technology)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity College","funders":"University of Galway; Ulster University; University of Essex","keywords":"Irish; Ranking (information retrieval); Politics; Rank (graph theory); Journal ranking; International comparisons","score_opus":0.03290792926851243,"score_gpt":0.31758927237760065,"score_spread":0.2846813431090882,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024503297","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76547164,0.0029843182,0.21672443,0.010070157,0.00096811523,0.00046015574,0.000009911099,0.00023994631,0.0030713535],"genre_scores_gemma":[0.9495388,0.00008107879,0.050229304,0.00006866465,0.000046286266,0.0000066446955,0.0000011605725,0.0000050249555,0.000022991424],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984153,0.000045948087,0.0005355584,0.00037088705,0.00020939634,0.0004229468],"domain_scores_gemma":[0.99886644,0.00009076821,0.00022818813,0.00054086227,0.000219145,0.00005461838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037264157,0.00020255057,0.00054953585,0.0007494764,0.00007119519,0.000016796379,0.00077598856,0.00020979394,0.0000041327676],"category_scores_gemma":[0.00073000666,0.00016561581,0.00013382306,0.001447908,0.0006233117,0.00091665715,0.00020911783,0.00028864373,0.000004378939],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003577337,0.00022392142,0.0031618774,0.000022927645,0.00016930286,0.0000716967,0.00048204052,0.0024955212,0.0074749477,0.9598886,0.00046351107,0.02550992],"study_design_scores_gemma":[0.0056458944,0.0027525525,0.029207198,0.0015967158,0.00013463604,0.00014244653,0.00087386207,0.05002892,0.18178533,0.722805,0.0036940814,0.0013333242],"about_ca_topic_score_codex":0.00006583175,"about_ca_topic_score_gemma":0.00003636148,"teacher_disagreement_score":0.23708351,"about_ca_system_score_codex":0.000102534505,"about_ca_system_score_gemma":0.00011790519,"threshold_uncertainty_score":0.6753617},"labels":[],"label_agreement":null},{"id":"W7024798039","doi":"","title":"A souvenir, the Thousand Islands of the St. Lawrence River from Kingston and Cape Vincent to Morristown and Brockville, with their recorded history from the earliest times, their legends, their romances, their fortifications and their contests including both the American and Canadian channels, profusely illustrated with views of natural scenery, as well as pictures of many summer villas, steamers, fishing scenes, &amp;c.","year":2014,"lang":"en","type":"article","venue":"QSpace (Queen's University Library)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cape; Subject (documents); Natural (archaeology); New guinea; Property (philosophy)","score_opus":0.012378559552876088,"score_gpt":0.1789161257900078,"score_spread":0.1665375662371317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024798039","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97563004,0.001886594,0.0029887953,0.017643945,0.00012955093,0.00087208836,0.00031895709,0.00004127452,0.0004887479],"genre_scores_gemma":[0.9966527,0.0008286744,0.001174072,0.0006842539,0.00005155853,0.0000053312956,0.000024385294,0.00002916887,0.0005498347],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99790514,0.0006266106,0.0002547421,0.000630338,0.00021167904,0.0003715148],"domain_scores_gemma":[0.9974798,0.00078264903,0.00061543105,0.0008162643,0.00012480846,0.00018103221],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022611218,0.0004384961,0.0005559456,0.00010927799,0.00075844105,0.00015514597,0.0010752345,0.00008001288,0.000014632549],"category_scores_gemma":[0.00003285419,0.00019574704,0.00007236468,0.00048955524,0.001508735,0.0005993803,0.0005588005,0.00035155696,2.3790807e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003748939,0.0005794775,0.47681645,0.00027292836,0.003943427,0.000028035298,0.29168385,0.0038460055,0.009374234,0.011554129,0.12948626,0.06866628],"study_design_scores_gemma":[0.0023992572,0.0011979343,0.4376318,0.001293411,0.00032084255,0.00001861385,0.04562685,0.010965288,0.019318879,0.0012160861,0.4783994,0.0016116523],"about_ca_topic_score_codex":0.2238725,"about_ca_topic_score_gemma":0.11700311,"teacher_disagreement_score":0.34891313,"about_ca_system_score_codex":0.00008794675,"about_ca_system_score_gemma":0.0003431282,"threshold_uncertainty_score":0.8991093},"labels":[],"label_agreement":null},{"id":"W7024989668","doi":"","title":"Tweetalig primair onderwijs : bevindingen uit de voorstudie","year":2016,"lang":"nl","type":"other","venue":"Leiden Repository (Leiden University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McGill University","keywords":"Work (physics); Field (mathematics); Subject (documents); Order (exchange)","score_opus":0.009470322088368411,"score_gpt":0.2020128342593357,"score_spread":0.1925425121709673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024989668","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011043648,0.001619264,0.25442827,0.0010006514,0.0046046707,0.0011170224,0.00003851627,0.0004926061,0.73559463],"genre_scores_gemma":[0.04916782,0.00055068644,0.0065670162,0.00021388901,0.0031735278,0.0000058028577,0.000008240537,0.00027073748,0.94004226],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99298567,0.0012472102,0.0007583854,0.0023247974,0.0010206425,0.0016632805],"domain_scores_gemma":[0.9949915,0.00041873282,0.0012348033,0.0021143237,0.00047833446,0.0007623258],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006162007,0.0012732876,0.0013843768,0.0012225216,0.0013456411,0.0006824883,0.0042935456,0.0010069747,0.002432712],"category_scores_gemma":[0.000121751684,0.0012588714,0.00088958954,0.001147715,0.0006581987,0.0012511719,0.0023365805,0.00076818315,0.0053542396],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037783658,0.00093449693,0.050735902,0.00065726734,0.007466704,0.016385369,0.0020524445,0.00096996495,0.023754358,0.011360161,0.86312926,0.022176258],"study_design_scores_gemma":[0.0015942114,0.000303021,0.006710019,0.0013970219,0.0010336685,0.0001913718,0.0002676169,0.0012089711,0.008014192,0.0002737958,0.9767091,0.0022969674],"about_ca_topic_score_codex":0.0013353348,"about_ca_topic_score_gemma":0.0002255631,"teacher_disagreement_score":0.24786125,"about_ca_system_score_codex":0.0017301325,"about_ca_system_score_gemma":0.001291816,"threshold_uncertainty_score":0.99995446},"labels":[],"label_agreement":null},{"id":"W7034336486","doi":"","title":"Taking Care Of Business","year":2005,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nice; Reputation; Business Review; Sleep (system call); Duty of care","score_opus":0.006128437420901127,"score_gpt":0.18193214666331697,"score_spread":0.17580370924241584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7034336486","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000018792107,0.00090284826,0.00051314034,0.000099076045,0.00035799897,0.00021535359,0.000039092334,0.00010064091,0.99776995],"genre_scores_gemma":[0.002855264,0.00019736533,0.025915544,0.000106214604,0.00026994012,0.0000051572542,0.000034170836,0.00005551409,0.97056085],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998686,0.000057937414,0.0004956293,0.00019698725,0.00034517868,0.00021823621],"domain_scores_gemma":[0.9981704,0.00005828089,0.00089113275,0.0004783267,0.00034240348,0.000059504335],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00010617811,0.000257061,0.00040420832,0.00008708711,0.00004423106,0.000053542335,0.00067723857,0.00023591737,0.14958002],"category_scores_gemma":[0.00008291539,0.00024513004,0.00012759716,0.000018422657,0.000084459934,4.230222e-7,0.00017766733,0.0001258782,0.0014808358],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000072228754,0.00001563716,7.5070085e-7,0.000257755,0.00003391233,0.000003905941,0.00020741897,0.0044946424,6.7567487e-7,0.00006817266,0.95891327,0.035996653],"study_design_scores_gemma":[0.00021926926,0.000038460646,0.000020082261,0.00027411783,0.000023169801,0.000011151781,0.000051428917,0.00036428685,0.000054405475,0.0000019356507,0.9987057,0.00023600894],"about_ca_topic_score_codex":0.0029426017,"about_ca_topic_score_gemma":0.00069700443,"teacher_disagreement_score":0.14809917,"about_ca_system_score_codex":0.00002878947,"about_ca_system_score_gemma":0.000044163848,"threshold_uncertainty_score":0.9996113},"labels":[],"label_agreement":null},{"id":"W7037861544","doi":"","title":"Évaluation de la variabilité interindividuelle de la toxicocinétique de composés organiques volatils chez l'humain","year":2012,"lang":"fr","type":"other","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Noise (video); Work (physics)","score_opus":0.008310472121336275,"score_gpt":0.19147673394802342,"score_spread":0.18316626182668713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7037861544","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05289438,0.008216096,0.6825301,0.00071550015,0.00092589133,0.00055980973,0.00004539366,0.00023071344,0.2538821],"genre_scores_gemma":[0.7788061,0.00061807834,0.11612202,0.00032529907,0.0010503281,0.000035696085,0.000034843924,0.00011225933,0.10289539],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9939206,0.0035151248,0.00044532228,0.0007572503,0.0004974959,0.0008641543],"domain_scores_gemma":[0.99719286,0.0009677862,0.0004443929,0.0006265034,0.00022277882,0.00054566975],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024836622,0.0006047375,0.0005482564,0.00027075986,0.003012824,0.00036536346,0.001012719,0.0009832635,0.0010908365],"category_scores_gemma":[0.00032889107,0.0007009365,0.0003388791,0.0003672892,0.0010159904,0.0006323741,0.00067659194,0.0007723138,0.00007326273],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003781978,0.0016825821,0.081283264,0.00038966184,0.0017294444,0.0024503756,0.19322036,0.053523812,0.2541772,0.32331434,0.012791984,0.07505876],"study_design_scores_gemma":[0.0021230262,0.00031957275,0.12594713,0.0010314195,0.000837849,0.0039233,0.0037956405,0.27417463,0.06346715,0.01021122,0.51204515,0.0021239175],"about_ca_topic_score_codex":0.02112398,"about_ca_topic_score_gemma":0.0011910972,"teacher_disagreement_score":0.72591174,"about_ca_system_score_codex":0.007841263,"about_ca_system_score_gemma":0.0035713979,"threshold_uncertainty_score":0.9998223},"labels":[],"label_agreement":null},{"id":"W7042938815","doi":"","title":"Simple Detection of AI-Generated Images based on Noise Correlation","year":2025,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Noise (video); Simple (philosophy); Pattern recognition (psychology); Correlation; Background noise; Image processing","score_opus":0.006874815082434797,"score_gpt":0.21250242085935594,"score_spread":0.20562760577692116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7042938815","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0074268235,0.00009324438,0.97503066,0.0037283215,0.00018061035,0.00017734751,0.0000069629737,0.000112246824,0.013243763],"genre_scores_gemma":[0.9664325,0.000017342356,0.031675886,0.00028291703,0.000009558543,0.00001638413,0.000031339656,0.000008605099,0.0015254362],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99669874,0.0021962996,0.00030611336,0.00039376193,0.00022249266,0.00018258268],"domain_scores_gemma":[0.9965349,0.0008815666,0.00018684047,0.0010093573,0.0013286852,0.000058639158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017533678,0.00014728132,0.00017538079,0.0002127528,0.00027938,0.0001808598,0.0005975393,0.00008179335,0.000028251437],"category_scores_gemma":[0.00082048494,0.00014802265,0.00009711038,0.00090589735,0.00008844193,0.00027567722,0.0001578094,0.00016470686,0.000012456072],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058984962,0.001047418,0.0041155526,0.00007279029,0.00008589423,0.000005278163,0.0013717074,0.06554895,0.38438505,0.11495365,0.0038920506,0.42446268],"study_design_scores_gemma":[0.00024376565,5.898728e-7,0.004393205,0.00009883837,0.000007580589,2.679254e-7,0.0000063373923,0.5489375,0.44406644,0.0008625676,0.0013022256,0.000080685044],"about_ca_topic_score_codex":0.00031422122,"about_ca_topic_score_gemma":0.00022493904,"teacher_disagreement_score":0.9590057,"about_ca_system_score_codex":0.000054223536,"about_ca_system_score_gemma":0.00013544568,"threshold_uncertainty_score":0.60361886},"labels":[],"label_agreement":null},{"id":"W7043663028","doi":"","title":"Study on the bilingual services offered by Air Canada : interim report of the Standing Joint Committee on Official Languages","year":2001,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Joint (building); Interim; Government (linguistics); Agency (philosophy)","score_opus":0.010058660178373705,"score_gpt":0.20028482349799462,"score_spread":0.19022616331962092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7043663028","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017440661,0.000045500074,0.000014229482,0.0006689819,0.0005009686,0.00057045225,0.00008965582,0.000044554734,0.9963216],"genre_scores_gemma":[0.15378383,0.000013786527,0.00014426289,0.0006128986,0.00014708014,0.0000074313866,0.000018973906,0.000041629617,0.8452301],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980592,0.00024243271,0.0006053508,0.00022510468,0.00065525726,0.00021266476],"domain_scores_gemma":[0.9979846,0.0002029344,0.00087975716,0.00076715543,0.000119611155,0.000045927412],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00036760492,0.00028584214,0.00037800657,0.000033054494,0.00012988177,0.000057093217,0.000921644,0.00011394511,0.013737066],"category_scores_gemma":[0.0001077655,0.00017489695,0.00011387011,0.00002171595,0.000073097515,4.0139284e-7,0.00023459477,0.00025714625,0.00009509264],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020253417,0.00008012012,0.000010526172,0.000047010642,0.00007936295,0.000041837742,0.00047363926,0.00084384,0.0000013472935,0.000022952307,0.99735695,0.0010221862],"study_design_scores_gemma":[0.0002066407,0.0001754121,0.000041341675,0.00025665603,0.000024032968,0.00003097645,0.0018133505,0.00015602108,0.00020828015,0.0000017402601,0.9969034,0.00018211638],"about_ca_topic_score_codex":0.31155658,"about_ca_topic_score_gemma":0.2935228,"teacher_disagreement_score":0.15203977,"about_ca_system_score_codex":0.0000784524,"about_ca_system_score_gemma":0.00012325312,"threshold_uncertainty_score":0.9871645},"labels":[],"label_agreement":null},{"id":"W7067221764","doi":"","title":"Le Processus méthodologique de la production étudiante : séminaire en audio-visuel à l'intention des professeurs du Cégep de Rimouski /","year":2015,"lang":"fr","type":"other","venue":"Bibliothèque et Archives nationales du Québec (Québec government)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Production (economics); Context (archaeology); Process (computing); Perspective (graphical)","score_opus":0.022341876704824612,"score_gpt":0.2590842904928408,"score_spread":0.2367424137880162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7067221764","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026125006,0.011663886,0.569114,0.039585415,0.000904282,0.0016773108,0.0001173715,0.00044492536,0.35036778],"genre_scores_gemma":[0.718552,0.0030669665,0.037106182,0.0007206971,0.001836598,0.00047753248,0.000026774174,0.00027162465,0.23794164],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9923548,0.0036366626,0.0007468043,0.0013155871,0.0010178887,0.0009282666],"domain_scores_gemma":[0.9916202,0.0060412483,0.0009265909,0.00062596216,0.0003929632,0.00039305963],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0030583434,0.00083116395,0.0007125428,0.00086624187,0.00072504353,0.00085892103,0.0015357947,0.00037305406,0.0006833016],"category_scores_gemma":[0.015560062,0.00083744386,0.00035534936,0.0013390841,0.0012774074,0.0015079386,0.0008986328,0.00084953354,0.00020025943],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0007766493,0.0036137614,0.11830467,0.0020113292,0.0016278779,0.0002958658,0.053342637,0.020063218,0.009520875,0.14469603,0.62704873,0.01869835],"study_design_scores_gemma":[0.002496533,0.0008049731,0.34406036,0.0025093567,0.0004640024,0.00093313784,0.0018567228,0.043673173,0.0036117628,0.014747842,0.5822682,0.0025739707],"about_ca_topic_score_codex":0.06028623,"about_ca_topic_score_gemma":0.81365883,"teacher_disagreement_score":0.7533726,"about_ca_system_score_codex":0.0059291646,"about_ca_system_score_gemma":0.082681865,"threshold_uncertainty_score":0.99940765},"labels":[],"label_agreement":null},{"id":"W7092462013","doi":"10.2312/pg.20251296","title":"By-Example Synthesis of Vector Textures","year":2025,"lang":"","type":"article","venue":"Eurographics","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Raster graphics; Context (archaeology); Pattern recognition (psychology); Set (abstract data type); Palette (painting); Complement (music); Field (mathematics); Texture (cosmology); Image (mathematics)","score_opus":0.011811537289556868,"score_gpt":0.23596875990360267,"score_spread":0.2241572226140458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7092462013","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003951743,0.01690095,0.9580159,0.0038228312,0.0036511978,0.00060466817,0.0001236377,0.00014263521,0.012786406],"genre_scores_gemma":[0.98698646,0.001853502,0.009523996,0.00059703866,0.00015687468,0.00002257243,0.0000040341984,0.000026615591,0.0008289025],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965466,0.00062678364,0.000776446,0.000920441,0.0004873895,0.0006423054],"domain_scores_gemma":[0.9965974,0.0012181815,0.0003573258,0.0012773107,0.0003893,0.00016049393],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007264,0.0004566537,0.00067359395,0.0004507714,0.00037639998,0.00031725777,0.0016027549,0.00023322403,0.00009918263],"category_scores_gemma":[0.00055458216,0.00045163077,0.00050038996,0.0032176136,0.0006155062,0.0003582219,0.000536626,0.0003863756,0.0000158847],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011965537,0.0015757891,0.005603925,0.0005211649,0.0016104064,0.000030031191,0.0010204543,0.001354155,0.023314409,0.1351205,0.18317683,0.6465527],"study_design_scores_gemma":[0.0012016653,0.00070582883,0.019251999,0.0012214334,0.0009314389,0.000006949112,0.0002079392,0.13672426,0.28039032,0.0058401176,0.5517339,0.0017840931],"about_ca_topic_score_codex":0.00035535448,"about_ca_topic_score_gemma":0.00003832304,"teacher_disagreement_score":0.98303473,"about_ca_system_score_codex":0.000021720181,"about_ca_system_score_gemma":0.00021426368,"threshold_uncertainty_score":0.9997935},"labels":[],"label_agreement":null},{"id":"W7098348338","doi":"","title":"Printed in the USA 0730-7268/08 $12.00 .00 MERCURY AND OTHER TRACE ELEMENTS IN FARMED AND WILD SALMON FROM","year":2007,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Biomagnification; Bioaccumulation; Mercury (programming language); Methylmercury; Bioconcentration; Aquaculture; Aquatic animal; Human health","score_opus":0.020235011759017832,"score_gpt":0.2546830236949031,"score_spread":0.23444801193588527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7098348338","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7754817,0.00041842874,0.21418737,0.0012742459,0.00014892496,0.00041289508,0.0000035627352,0.000027007196,0.008045863],"genre_scores_gemma":[0.97997737,0.000053717544,0.018456375,0.0012747328,0.00005905402,0.0000071750487,7.4978476e-7,0.0000072432717,0.000163606],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99866647,0.00015807615,0.00028864367,0.00039444744,0.00018951215,0.0003028303],"domain_scores_gemma":[0.9993254,0.0002610364,0.000060512702,0.0002788925,0.000016220656,0.000057914236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086300354,0.00015201366,0.0001736707,0.00009141457,0.00006434455,0.00013398276,0.0003577676,0.000060739232,0.00009386441],"category_scores_gemma":[0.000037705366,0.000102784994,0.00002267055,0.00025661688,0.00006226507,0.00029052203,0.00013456387,0.00014855705,0.0000071430986],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014214628,0.00050384627,0.66276777,0.000015013792,0.00008854922,0.000113804286,0.0133708315,0.00037011044,0.016763993,0.0060866927,0.0018781032,0.29789913],"study_design_scores_gemma":[0.0015181114,0.00010533414,0.89678586,0.000053811837,0.000008518667,0.0000074178506,0.00083942927,0.06646142,0.0058333785,0.0014018994,0.026595125,0.0003897197],"about_ca_topic_score_codex":0.0021821917,"about_ca_topic_score_gemma":0.00833704,"teacher_disagreement_score":0.2975094,"about_ca_system_score_codex":0.00002241318,"about_ca_system_score_gemma":0.000015336576,"threshold_uncertainty_score":0.4652264},"labels":[],"label_agreement":null},{"id":"W7098595273","doi":"","title":"The Status and Future of Canadian Subatomic Physics","year":2007,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Subatomic particle; Work (physics); Field (mathematics)","score_opus":0.008137403726632802,"score_gpt":0.2031751290383198,"score_spread":0.195037725311687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7098595273","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022728547,0.0015272174,0.935811,0.004483156,0.0008227986,0.00015191805,0.000002931565,0.000030362371,0.0344421],"genre_scores_gemma":[0.9854357,0.0004530225,0.013467902,0.00020773448,0.00024855474,4.1892994e-7,2.72932e-7,0.0000025292486,0.0001838572],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995037,0.000015048535,0.0000734679,0.000090757654,0.00006216785,0.00025486512],"domain_scores_gemma":[0.9995686,0.00006912748,0.000023625847,0.0001704852,0.00004182722,0.00012636803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017333156,0.000045194567,0.000050028248,0.000037598493,0.00013271079,0.000050062885,0.00016582671,0.000018286675,0.0000041182147],"category_scores_gemma":[0.0000055027112,0.000027717118,0.000016213466,0.00026747785,0.000039759383,0.00010821204,0.000033731383,0.000036049518,0.0000021044455],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002141766,0.000004318351,0.0013456761,0.0000012633138,0.000011988243,0.0000017268512,0.00039164457,0.000040312654,0.00042344205,0.23097362,0.0024160633,0.7643878],"study_design_scores_gemma":[0.0003532854,0.00007551011,0.07634133,0.00000537179,0.000009807582,0.00000410722,0.00082043366,0.05463068,0.037270565,0.009986778,0.82019424,0.00030785755],"about_ca_topic_score_codex":0.024805743,"about_ca_topic_score_gemma":0.120956145,"teacher_disagreement_score":0.96270716,"about_ca_system_score_codex":0.000015865797,"about_ca_system_score_gemma":0.000081197766,"threshold_uncertainty_score":0.98168814},"labels":[],"label_agreement":null},{"id":"W7098902386","doi":"","title":"–William Shakespeare, Merchant of Venice (1596–1597) As good as gold...","year":2013,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Payment; Agency (philosophy)","score_opus":0.010423408978671484,"score_gpt":0.22438284080469334,"score_spread":0.21395943182602187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7098902386","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036807727,0.00074850017,0.64118505,0.0049094446,0.0012576885,0.0008161734,0.0000051314537,0.0002778541,0.31399247],"genre_scores_gemma":[0.9388109,0.00006610346,0.04778613,0.0009116544,0.00016576578,0.000025361114,0.0000017307431,0.000014495355,0.012217884],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984557,0.0001117781,0.0003102096,0.00042187638,0.00033677695,0.00036362908],"domain_scores_gemma":[0.9986923,0.00013919428,0.000119284734,0.0006659989,0.00022585555,0.000157398],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00023364578,0.00018615216,0.00027598185,0.00007525341,0.00007137323,0.00014788387,0.00090591784,0.00007593679,0.001044468],"category_scores_gemma":[0.00009431621,0.00014720166,0.00012844239,0.00037090108,0.00006815151,0.00075964606,0.00033902528,0.00011257922,0.0019170691],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033217053,0.00080537883,0.0009690708,0.000077601035,0.00046263784,0.000053585278,0.0030911483,0.0035341003,0.12691833,0.30061823,0.13379028,0.4296464],"study_design_scores_gemma":[0.0020395357,0.0018745683,0.015996821,0.00020247603,0.00009755768,0.00009721954,0.00070843817,0.26687887,0.43856618,0.049438376,0.22202025,0.002079701],"about_ca_topic_score_codex":0.0013223552,"about_ca_topic_score_gemma":0.0000397897,"teacher_disagreement_score":0.90200317,"about_ca_system_score_codex":0.000023519695,"about_ca_system_score_gemma":0.00008169088,"threshold_uncertainty_score":0.9998687},"labels":[],"label_agreement":null},{"id":"W7099331860","doi":"","title":"The role of equity and lifestyles in education about climate change: experiences from a large-scale teacher development program, Canadian","year":2001,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Equity (law); Greenhouse gas; Sustainability; Sustainable development; Global warming; Calculator; Order (exchange); Climate change","score_opus":0.015671859107215944,"score_gpt":0.2712899030665059,"score_spread":0.25561804395928994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099331860","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9826692,0.0034540968,0.00379638,0.0013933175,0.00025793235,0.00047575907,0.0000018471212,0.00003604521,0.007915426],"genre_scores_gemma":[0.973225,0.00024451286,0.026036616,0.00015860221,0.00007072453,0.00020449795,0.000001985669,0.0000028655209,0.000055201403],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9991985,0.00005657876,0.00015285955,0.00019502014,0.00011152431,0.00028549146],"domain_scores_gemma":[0.9996272,0.00002972568,0.000045579232,0.00016063695,0.000038284088,0.00009860842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030835863,0.00007656978,0.00008593391,0.00004376394,0.00019424933,0.00015398837,0.00030869097,0.000032041306,0.000021203596],"category_scores_gemma":[0.00001490081,0.00005205992,0.0000132310715,0.00017059775,0.00004368278,0.00025933704,0.00021404015,0.000042992542,0.0000026881623],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020735565,0.00007191428,0.056231152,9.709347e-7,0.0000032102264,4.1297596e-7,0.017142761,0.000002113087,0.000035607816,0.0007642926,0.000041928284,0.9257036],"study_design_scores_gemma":[0.00023967138,0.0000582716,0.72956806,0.00007120709,0.0000046794685,0.0000023818482,0.029361054,0.07335592,0.0027895905,0.0014183258,0.16281143,0.00031937627],"about_ca_topic_score_codex":0.046107605,"about_ca_topic_score_gemma":0.38792825,"teacher_disagreement_score":0.92538416,"about_ca_system_score_codex":0.0000367414,"about_ca_system_score_gemma":0.00020232527,"threshold_uncertainty_score":0.9602444},"labels":[],"label_agreement":null},{"id":"W7103203902","doi":"","title":"Dynamic VLM-Guided Negative Prompting for Diffusion Models","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea","keywords":"Noise reduction; Benchmark (surveying); Diffusion; Noise (video); Image (mathematics); Image denoising","score_opus":0.04597462604005995,"score_gpt":0.28947350870608946,"score_spread":0.2434988826660295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7103203902","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2085501,0.00059847493,0.7820648,0.0031062283,0.0020846326,0.0014183411,0.000017324077,0.00010637662,0.0020537516],"genre_scores_gemma":[0.93946165,0.00018570185,0.051820617,0.0009817332,0.00024341086,0.00016978613,0.000009698168,0.00003938348,0.0070879986],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99586403,0.00032091342,0.0009330624,0.0015143501,0.000334312,0.0010333285],"domain_scores_gemma":[0.99701935,0.0006850876,0.00042435274,0.0010399728,0.00064131053,0.0001899431],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007409013,0.00060714927,0.00071238604,0.0002465196,0.0012553338,0.0004225129,0.0012862694,0.00026233704,0.000042115116],"category_scores_gemma":[0.0005281794,0.0005830579,0.00041570258,0.0010754049,0.00022692214,0.0013444124,0.0010110724,0.00037141654,0.0000523785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00056629826,0.0019514306,0.026825687,0.0010200215,0.001693965,0.00005644103,0.012988833,0.35687044,0.10050312,0.0281789,0.013408539,0.4559363],"study_design_scores_gemma":[0.0013606373,0.00017305913,0.008824332,0.00046387408,0.00012302583,0.0000019749289,0.00018468245,0.96842265,0.008383491,0.010666418,0.00084285304,0.00055300276],"about_ca_topic_score_codex":0.00014381447,"about_ca_topic_score_gemma":0.00006403023,"teacher_disagreement_score":0.73091155,"about_ca_system_score_codex":0.00025219313,"about_ca_system_score_gemma":0.00040656852,"threshold_uncertainty_score":0.9996621},"labels":[],"label_agreement":null},{"id":"W7104178460","doi":"10.5267/j.ijdns.2025.9.011","title":"Text-to-image fashion design generation using stable diffusion: A comprehensive framework for AI-assisted creative workflows","year":2025,"lang":"en","type":"article","venue":"International Journal of Data and Network Science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"King Khalid University","keywords":"Fashion design; Workflow; Originality; Quality (philosophy); Architecture; Automation; Fashion industry; Preprocessor","score_opus":0.08190789606640204,"score_gpt":0.3599187764696221,"score_spread":0.2780108804032201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7104178460","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00677846,0.0002582464,0.9881337,0.0024384656,0.0020641552,0.00024104773,0.000020078374,0.000010789895,0.000055007364],"genre_scores_gemma":[0.26366606,0.000086931366,0.7342146,0.0012037198,0.000779673,0.0000034387572,0.000007411829,0.000004675912,0.000033507098],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980714,0.00013208155,0.00045435998,0.00047309248,0.0005766582,0.00029241282],"domain_scores_gemma":[0.9971843,0.00047832163,0.00032612873,0.00040948266,0.0014631065,0.00013870656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012787348,0.00015444428,0.00024967955,0.0002862092,0.00047964224,0.0009927801,0.0023607244,0.000052844163,0.000009549279],"category_scores_gemma":[0.00042389455,0.00012827838,0.000051000872,0.0009324381,0.00017888675,0.0026549343,0.0009927527,0.0001685423,0.0000010831202],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005754598,0.00034750046,0.0009826899,0.000016546863,0.00046069422,0.00006203826,0.0011221084,0.27305222,0.11902111,0.047053125,0.06691575,0.49039078],"study_design_scores_gemma":[0.00041302052,0.00011709595,0.001472886,0.00023353712,0.000031068128,0.000031465275,0.000075565695,0.98492295,0.0016385166,0.0053370427,0.0055715945,0.0001552675],"about_ca_topic_score_codex":0.000008217198,"about_ca_topic_score_gemma":0.0000073061406,"teacher_disagreement_score":0.71187073,"about_ca_system_score_codex":0.00011196554,"about_ca_system_score_gemma":0.00041476876,"threshold_uncertainty_score":0.9573401},"labels":[],"label_agreement":null},{"id":"W7104448482","doi":"10.71781/10312","title":"Learning generative models from a control perspective","year":2025,"lang":"en","type":"dissertation","venue":"Open MIND","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Samsung; Institute for Catastrophic Loss Reduction; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Generative grammar; Inference; Generative model; Probabilistic logic; Perspective (graphical); Generative Design; Graph; Statistical model","score_opus":0.027911826517005685,"score_gpt":0.2906971737876121,"score_spread":0.26278534727060643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7104448482","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020220801,0.0008874015,0.75690657,0.00040172838,0.0010142743,0.000804782,0.00006753605,0.000008007485,0.23788762],"genre_scores_gemma":[0.6075621,0.000115567964,0.24046236,0.00024075221,0.00063197286,0.0001779008,0.00062010495,0.000041014267,0.1501482],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997918,0.00031978794,0.00028010062,0.0009803694,0.00023729807,0.0002644621],"domain_scores_gemma":[0.99857795,0.0002146738,0.00025755272,0.00044300227,0.00042975377,0.00007708441],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00021556123,0.00033035327,0.0005238489,0.00011064768,0.00032675912,0.0011506613,0.0015914824,0.00021870028,0.0004884831],"category_scores_gemma":[0.00010895583,0.00031339817,0.0001424457,0.00025891422,0.000017120456,0.0008900749,0.00022228269,0.00043745336,0.0001263829],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029731612,0.00019424214,0.000010395497,0.000008897674,0.001344362,0.00007472455,0.049323734,0.20867056,0.00400478,0.00876994,0.0032446904,0.72405636],"study_design_scores_gemma":[0.0010111856,0.000120647026,0.00005447705,0.00020313139,0.00015673482,5.1230603e-7,0.006009628,0.96148884,0.010413058,0.012247245,0.0076570213,0.0006375232],"about_ca_topic_score_codex":0.0012032618,"about_ca_topic_score_gemma":0.0011504311,"teacher_disagreement_score":0.7528183,"about_ca_system_score_codex":0.0001328663,"about_ca_system_score_gemma":0.0005310661,"threshold_uncertainty_score":0.9999318},"labels":[],"label_agreement":null},{"id":"W7104945513","doi":"10.5281/zenodo.17584563","title":"Conditioning Analysis of Transformer Operators: A Stability Perspective.","year":2025,"lang":"","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Jacobian matrix and determinant; Transformer; Robustness (evolution); Control theory (sociology); Stability (learning theory); Conditioning; Generalization; Inverse","score_opus":0.02895426951570058,"score_gpt":0.2640570038089288,"score_spread":0.23510273429322825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7104945513","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00711265,0.0005098647,0.8969598,0.0017947265,0.00023819461,0.0006039921,0.0004887751,0.0002325291,0.092059515],"genre_scores_gemma":[0.99760723,0.00014723805,0.001081138,0.00015196913,0.00006588626,5.4467144e-8,0.00029097736,0.00029120318,0.0003643095],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99623865,0.0011859459,0.00065047457,0.0009378006,0.0004846168,0.0005024912],"domain_scores_gemma":[0.9958532,0.000093684335,0.00020890574,0.00091737043,0.002748842,0.000177988],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001497939,0.00026605802,0.00054154685,0.0009853297,0.0030755845,0.0015392252,0.0018334781,0.000114002265,0.017151805],"category_scores_gemma":[0.00090758805,0.00028831195,0.00032998,0.006018912,0.0005497898,0.00082203106,0.00087134447,0.00034672878,0.00034137396],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000536246,0.00278997,0.00013273006,0.00045437057,0.01373136,0.000029306078,0.048925184,0.029777838,0.072392836,0.29463258,0.062681936,0.47391564],"study_design_scores_gemma":[0.002385188,0.0010231144,0.008533183,0.0003240348,0.0029184402,0.000015014663,0.010901953,0.4561782,0.056253713,0.001638478,0.45865285,0.0011758271],"about_ca_topic_score_codex":0.00012784275,"about_ca_topic_score_gemma":0.0000037562756,"teacher_disagreement_score":0.99049455,"about_ca_system_score_codex":0.00038447164,"about_ca_system_score_gemma":0.000032953845,"threshold_uncertainty_score":0.9999569},"labels":[],"label_agreement":null},{"id":"W7104988578","doi":"10.5281/zenodo.17584612","title":"Conditioning Analysis of Transformer Operators: A Stability Perspective.","year":2025,"lang":"","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Jacobian matrix and determinant; Transformer; Robustness (evolution); Control theory (sociology); Stability (learning theory); Conditioning; Generalization; Inverse","score_opus":0.02895426951570058,"score_gpt":0.2640570038089288,"score_spread":0.23510273429322825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7104988578","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00711265,0.0005098647,0.8969598,0.0017947265,0.00023819461,0.0006039921,0.0004887751,0.0002325291,0.092059515],"genre_scores_gemma":[0.99760723,0.00014723805,0.001081138,0.00015196913,0.00006588626,5.4467144e-8,0.00029097736,0.00029120318,0.0003643095],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99623865,0.0011859459,0.00065047457,0.0009378006,0.0004846168,0.0005024912],"domain_scores_gemma":[0.9958532,0.000093684335,0.00020890574,0.00091737043,0.002748842,0.000177988],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001497939,0.00026605802,0.00054154685,0.0009853297,0.0030755845,0.0015392252,0.0018334781,0.000114002265,0.017151805],"category_scores_gemma":[0.00090758805,0.00028831195,0.00032998,0.006018912,0.0005497898,0.00082203106,0.00087134447,0.00034672878,0.00034137396],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000536246,0.00278997,0.00013273006,0.00045437057,0.01373136,0.000029306078,0.048925184,0.029777838,0.072392836,0.29463258,0.062681936,0.47391564],"study_design_scores_gemma":[0.002385188,0.0010231144,0.008533183,0.0003240348,0.0029184402,0.000015014663,0.010901953,0.4561782,0.056253713,0.001638478,0.45865285,0.0011758271],"about_ca_topic_score_codex":0.00012784275,"about_ca_topic_score_gemma":0.0000037562756,"teacher_disagreement_score":0.99049455,"about_ca_system_score_codex":0.00038447164,"about_ca_system_score_gemma":0.000032953845,"threshold_uncertainty_score":0.9999569},"labels":[],"label_agreement":null},{"id":"W7105163975","doi":"10.5281/zenodo.17584562","title":"Conditioning Analysis of Transformer Operators: A Stability Perspective.","year":2025,"lang":"","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Jacobian matrix and determinant; Transformer; Robustness (evolution); Control theory (sociology); Stability (learning theory); Conditioning; Generalization; Inverse","score_opus":0.02895426951570058,"score_gpt":0.2640570038089288,"score_spread":0.23510273429322825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7105163975","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00711265,0.0005098647,0.8969598,0.0017947265,0.00023819461,0.0006039921,0.0004887751,0.0002325291,0.092059515],"genre_scores_gemma":[0.99760723,0.00014723805,0.001081138,0.00015196913,0.00006588626,5.4467144e-8,0.00029097736,0.00029120318,0.0003643095],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99623865,0.0011859459,0.00065047457,0.0009378006,0.0004846168,0.0005024912],"domain_scores_gemma":[0.9958532,0.000093684335,0.00020890574,0.00091737043,0.002748842,0.000177988],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001497939,0.00026605802,0.00054154685,0.0009853297,0.0030755845,0.0015392252,0.0018334781,0.000114002265,0.017151805],"category_scores_gemma":[0.00090758805,0.00028831195,0.00032998,0.006018912,0.0005497898,0.00082203106,0.00087134447,0.00034672878,0.00034137396],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000536246,0.00278997,0.00013273006,0.00045437057,0.01373136,0.000029306078,0.048925184,0.029777838,0.072392836,0.29463258,0.062681936,0.47391564],"study_design_scores_gemma":[0.002385188,0.0010231144,0.008533183,0.0003240348,0.0029184402,0.000015014663,0.010901953,0.4561782,0.056253713,0.001638478,0.45865285,0.0011758271],"about_ca_topic_score_codex":0.00012784275,"about_ca_topic_score_gemma":0.0000037562756,"teacher_disagreement_score":0.99049455,"about_ca_system_score_codex":0.00038447164,"about_ca_system_score_gemma":0.000032953845,"threshold_uncertainty_score":0.9999569},"labels":[],"label_agreement":null},{"id":"W7109457848","doi":"","title":"Rethinking the Use of Vision Transformers for AI-Generated Image Detection","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Robustness (evolution); Leverage (statistics); Scalability; Object detection; Feature extraction; Image processing; Feature matching; Generative grammar","score_opus":0.054291029893183136,"score_gpt":0.2800329004822134,"score_spread":0.22574187058903028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7109457848","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16194478,0.0003473779,0.8300813,0.0045017144,0.0021095974,0.0008619875,0.000014520868,0.000043770106,0.00009495884],"genre_scores_gemma":[0.9870658,0.00027618452,0.010232691,0.0014504599,0.00023113255,0.000045414014,0.0000057617067,0.000024330016,0.00066821807],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99712354,0.0004923925,0.0007832654,0.0007546207,0.00029340046,0.0005527781],"domain_scores_gemma":[0.9976175,0.00066367787,0.00029492102,0.0006239086,0.00071836327,0.00008164369],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010431096,0.0003678856,0.00044071412,0.00018949244,0.0010192689,0.00042108863,0.0006473978,0.00023872315,0.00002742083],"category_scores_gemma":[0.00037982722,0.00028088456,0.0004030278,0.0013614171,0.0003370072,0.0015743367,0.00017292102,0.00040236145,0.000010157206],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003059785,0.00016710498,0.0016505425,0.00013569933,0.00032877724,0.000003216838,0.0021130606,0.010763884,0.61742514,0.0004133142,0.0023015453,0.3643917],"study_design_scores_gemma":[0.0005983898,0.00025962788,0.0061710076,0.00018033326,0.0001493904,0.0000012091987,0.00005187378,0.57525325,0.40843567,0.00045531974,0.0082127275,0.00023116701],"about_ca_topic_score_codex":0.00023152155,"about_ca_topic_score_gemma":0.0002081484,"teacher_disagreement_score":0.82512105,"about_ca_system_score_codex":0.00009179762,"about_ca_system_score_gemma":0.00022205776,"threshold_uncertainty_score":0.99996436},"labels":[],"label_agreement":null},{"id":"W7110815279","doi":"10.5281/zenodo.17854952","title":"Implementing Single Image Denoising Diffusion Model for Image Editing and Synthesis","year":2025,"lang":"","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Image editing; Image (mathematics); Noise reduction; Range (aeronautics); Prior probability; Generative grammar; Image synthesis; Image manipulation","score_opus":0.03060336042419682,"score_gpt":0.25407042341004354,"score_spread":0.22346706298584673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7110815279","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031677878,0.00026772852,0.9735773,0.0022827962,0.0002878684,0.0008852836,0.0002305733,0.00036005274,0.01894057],"genre_scores_gemma":[0.91128033,0.00022822634,0.08468516,0.0003193188,0.0006422231,4.5178703e-7,0.0002191227,0.0012527021,0.001372466],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99598306,0.0005775482,0.0006805281,0.001179751,0.00041815988,0.0011609755],"domain_scores_gemma":[0.99718624,0.0002557474,0.00033447365,0.00070502586,0.0012810695,0.0002374533],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0022821932,0.0003828454,0.0004019812,0.0004369615,0.009324921,0.0060559907,0.0015240145,0.000120726,0.0008302515],"category_scores_gemma":[0.002929491,0.00043212337,0.00015512365,0.00085299194,0.00034326455,0.0014299129,0.005592727,0.00031215366,0.0001838628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007133202,0.0003342708,0.0000022927454,0.00037264364,0.00013396723,0.000010449081,0.0024524843,0.00082063663,0.18191557,0.004539217,0.047364112,0.76198304],"study_design_scores_gemma":[0.0007331088,0.00013876519,0.0000417469,0.00031787032,0.000101394806,0.000022062071,0.0006339088,0.8388122,0.015766354,0.00084332284,0.14221138,0.0003779355],"about_ca_topic_score_codex":0.000022041888,"about_ca_topic_score_gemma":0.0000015472647,"teacher_disagreement_score":0.9081125,"about_ca_system_score_codex":0.00024353196,"about_ca_system_score_gemma":0.000016642316,"threshold_uncertainty_score":0.9998131},"labels":[],"label_agreement":null},{"id":"W7111132206","doi":"10.5281/zenodo.17862616","title":"Implementing Single Image Denoising Diffusion Model for Image Editing and Synthesis","year":2025,"lang":"","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Image editing; Image (mathematics); Noise reduction; Range (aeronautics); Prior probability; Generative grammar; Image synthesis; Image manipulation","score_opus":0.03060336042419682,"score_gpt":0.25407042341004354,"score_spread":0.22346706298584673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7111132206","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031677878,0.00026772852,0.9735773,0.0022827962,0.0002878684,0.0008852836,0.0002305733,0.00036005274,0.01894057],"genre_scores_gemma":[0.91128033,0.00022822634,0.08468516,0.0003193188,0.0006422231,4.5178703e-7,0.0002191227,0.0012527021,0.001372466],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99598306,0.0005775482,0.0006805281,0.001179751,0.00041815988,0.0011609755],"domain_scores_gemma":[0.99718624,0.0002557474,0.00033447365,0.00070502586,0.0012810695,0.0002374533],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0022821932,0.0003828454,0.0004019812,0.0004369615,0.009324921,0.0060559907,0.0015240145,0.000120726,0.0008302515],"category_scores_gemma":[0.002929491,0.00043212337,0.00015512365,0.00085299194,0.00034326455,0.0014299129,0.005592727,0.00031215366,0.0001838628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007133202,0.0003342708,0.0000022927454,0.00037264364,0.00013396723,0.000010449081,0.0024524843,0.00082063663,0.18191557,0.004539217,0.047364112,0.76198304],"study_design_scores_gemma":[0.0007331088,0.00013876519,0.0000417469,0.00031787032,0.000101394806,0.000022062071,0.0006339088,0.8388122,0.015766354,0.00084332284,0.14221138,0.0003779355],"about_ca_topic_score_codex":0.000022041888,"about_ca_topic_score_gemma":0.0000015472647,"teacher_disagreement_score":0.9081125,"about_ca_system_score_codex":0.00024353196,"about_ca_system_score_gemma":0.000016642316,"threshold_uncertainty_score":0.9998131},"labels":[],"label_agreement":null},{"id":"W7111376625","doi":"10.5281/zenodo.17854953","title":"Implementing Single Image Denoising Diffusion Model for Image Editing and Synthesis","year":2025,"lang":"","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Image editing; Image (mathematics); Noise reduction; Range (aeronautics); Prior probability; Generative grammar; Image synthesis; Image manipulation","score_opus":0.03060336042419682,"score_gpt":0.25407042341004354,"score_spread":0.22346706298584673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7111376625","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031677878,0.00026772852,0.9735773,0.0022827962,0.0002878684,0.0008852836,0.0002305733,0.00036005274,0.01894057],"genre_scores_gemma":[0.91128033,0.00022822634,0.08468516,0.0003193188,0.0006422231,4.5178703e-7,0.0002191227,0.0012527021,0.001372466],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99598306,0.0005775482,0.0006805281,0.001179751,0.00041815988,0.0011609755],"domain_scores_gemma":[0.99718624,0.0002557474,0.00033447365,0.00070502586,0.0012810695,0.0002374533],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0022821932,0.0003828454,0.0004019812,0.0004369615,0.009324921,0.0060559907,0.0015240145,0.000120726,0.0008302515],"category_scores_gemma":[0.002929491,0.00043212337,0.00015512365,0.00085299194,0.00034326455,0.0014299129,0.005592727,0.00031215366,0.0001838628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007133202,0.0003342708,0.0000022927454,0.00037264364,0.00013396723,0.000010449081,0.0024524843,0.00082063663,0.18191557,0.004539217,0.047364112,0.76198304],"study_design_scores_gemma":[0.0007331088,0.00013876519,0.0000417469,0.00031787032,0.000101394806,0.000022062071,0.0006339088,0.8388122,0.015766354,0.00084332284,0.14221138,0.0003779355],"about_ca_topic_score_codex":0.000022041888,"about_ca_topic_score_gemma":0.0000015472647,"teacher_disagreement_score":0.9081125,"about_ca_system_score_codex":0.00024353196,"about_ca_system_score_gemma":0.000016642316,"threshold_uncertainty_score":0.9998131},"labels":[],"label_agreement":null},{"id":"W7114932866","doi":"","title":"FALCON: Few-step Accurate Likelihoods for Continuous Flows","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; Samsung; Nvidia","keywords":"Sampling (signal processing); Scalability; Importance sampling; Boltzmann constant; Flow (mathematics); Matching (statistics); Limiting; Current (fluid); Sequence (biology)","score_opus":0.03001198722604599,"score_gpt":0.27912484459675013,"score_spread":0.24911285737070415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7114932866","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042224646,0.0035960786,0.93123287,0.0071923435,0.009739288,0.001470846,0.000046117388,0.00016920868,0.00432858],"genre_scores_gemma":[0.96292067,0.0003485318,0.019545734,0.0042092055,0.0014111124,0.00018760741,0.000013986551,0.00005104303,0.011312141],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951778,0.00037618738,0.0010954291,0.001664833,0.00033139565,0.0013543731],"domain_scores_gemma":[0.99642754,0.0005663959,0.00041032836,0.0015668257,0.0007288638,0.00030002432],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000924837,0.0007596874,0.001024098,0.00024358208,0.0009842663,0.0009426743,0.0019574715,0.00038254092,0.00014358903],"category_scores_gemma":[0.0005894114,0.0007462717,0.00064953516,0.001220413,0.00022098179,0.001073128,0.0009239076,0.0004435463,0.00028286676],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048334288,0.00095792697,0.056665234,0.00043958993,0.0013353534,0.00010663616,0.0017016813,0.008013554,0.01663563,0.011372552,0.14489707,0.7573914],"study_design_scores_gemma":[0.0026513645,0.00049875694,0.019203447,0.0003812569,0.0003168863,0.0000062874315,0.00021878196,0.5957191,0.010958637,0.00084751664,0.3680908,0.0011071597],"about_ca_topic_score_codex":0.00011307014,"about_ca_topic_score_gemma":0.000093134564,"teacher_disagreement_score":0.920696,"about_ca_system_score_codex":0.00012681902,"about_ca_system_score_gemma":0.00053666387,"threshold_uncertainty_score":0.99949884},"labels":[],"label_agreement":null},{"id":"W7116175540","doi":"10.3103/s1060992x25601733","title":"Memory Stream: Enhancing Information Flow in Recurrent Memory Transformers for Efficient Long-Context Training","year":2025,"lang":"en","type":"article","venue":"Optical Memory and Neural Networks","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Transformer; High memory; Memory model; Computational complexity theory; Flat memory model; Content-addressable memory; Matching (statistics); Architecture","score_opus":0.013654559539993923,"score_gpt":0.2390468300254826,"score_spread":0.22539227048548868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116175540","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042554196,0.00070330774,0.9519312,0.0011966781,0.0014385765,0.0007002422,0.0000035736487,0.00006605145,0.0014061782],"genre_scores_gemma":[0.9921139,0.00006094353,0.0065537933,0.0009229535,0.00017083481,0.00008197949,0.000011929722,0.000008719935,0.00007497501],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980903,0.00011826176,0.0005703094,0.00043908646,0.00017905654,0.00060296134],"domain_scores_gemma":[0.99887246,0.00059368584,0.00008234293,0.00020522179,0.00008017343,0.00016610796],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006777773,0.00027952052,0.0003935971,0.00017592098,0.00027126152,0.00022401697,0.0002927695,0.00015811098,0.000009949009],"category_scores_gemma":[0.00013018251,0.0002492401,0.00013879617,0.0004434459,0.00011249381,0.00076422095,0.00010327779,0.00036002704,0.0000016655067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101268466,0.00003668879,0.0000049150362,0.000038047732,0.00001703349,0.0000044858775,0.0007780436,0.22589621,0.00005931716,0.00039007814,0.00010838882,0.77256554],"study_design_scores_gemma":[0.0011008977,0.00015055711,0.0002774567,0.00015589708,0.00002614896,0.000005548667,0.0006585749,0.9941956,0.0029130285,0.00010722072,0.00014823185,0.00026084096],"about_ca_topic_score_codex":0.000010463023,"about_ca_topic_score_gemma":0.00011171547,"teacher_disagreement_score":0.9495597,"about_ca_system_score_codex":0.00006036033,"about_ca_system_score_gemma":0.00006422509,"threshold_uncertainty_score":0.999996},"labels":[],"label_agreement":null},{"id":"W7117302013","doi":"10.1016/j.robot.2025.105320","title":"Reference-guided image inpainting via progressive feature interaction and reconstruction for mobile robots with binocular cameras","year":2025,"lang":"en","type":"article","venue":"Robotics and Autonomous Systems","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Inpainting; Feature (linguistics); Image (mathematics); Mobile robot; Robot; Mobile device; Pattern recognition (psychology); Iterative reconstruction","score_opus":0.011528503876025685,"score_gpt":0.2492561276119184,"score_spread":0.2377276237358927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117302013","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0072973436,0.001138931,0.98924243,0.0003865631,0.0006230066,0.00082967716,0.0000033201115,0.00007015157,0.00040856205],"genre_scores_gemma":[0.8513166,0.000043654378,0.14791387,0.000046888523,0.00012220713,0.00014013925,0.0000074759387,0.000011548066,0.00039765422],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989551,0.000080121434,0.00023315876,0.0004315412,0.000078812205,0.00022126701],"domain_scores_gemma":[0.99921525,0.00008748242,0.00019976171,0.00021767984,0.00022210962,0.000057707424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021445601,0.00018045961,0.000277681,0.0001062387,0.00030663825,0.00053934153,0.00012573553,0.00009135592,6.932487e-7],"category_scores_gemma":[0.000020259327,0.00014258763,0.000031742857,0.00017634762,0.000066764966,0.00041955663,0.00008442645,0.00012525867,6.4332596e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008420727,0.00014645795,0.00291858,0.0009715325,0.0006133678,0.00003642151,0.0013676494,0.46896297,0.01684339,0.027232721,0.0017154941,0.4791072],"study_design_scores_gemma":[0.00047197577,0.00018510927,0.00024433617,0.00036592223,0.0000477397,0.00014543867,0.00034086316,0.9946417,0.0015439026,0.00024175762,0.0015387909,0.00023243894],"about_ca_topic_score_codex":0.00009171074,"about_ca_topic_score_gemma":0.000013288215,"teacher_disagreement_score":0.84401923,"about_ca_system_score_codex":0.000056087185,"about_ca_system_score_gemma":0.00005789506,"threshold_uncertainty_score":0.58145547},"labels":[],"label_agreement":null},{"id":"W7117474568","doi":"10.1109/dicta68720.2025.11302481","title":"Prompt-Guided Dual Latent Steering for Inversion Problems","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Inversion (geology); Fidelity; Gaussian; Quadratic equation; Gaussian process; Inverse problem; Minification; Path (computing)","score_opus":0.036080838101935214,"score_gpt":0.2607537678971135,"score_spread":0.2246729297951783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117474568","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015224711,0.00050678087,0.9799465,0.0051644365,0.0031496116,0.0018796084,0.000006533954,0.00011747686,0.0077065933],"genre_scores_gemma":[0.8549176,0.00014298105,0.11014336,0.0011581901,0.0003746013,0.00015246157,0.0000073042715,0.000023698745,0.033079807],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972296,0.00012905638,0.00065633986,0.000971939,0.00028854213,0.000724536],"domain_scores_gemma":[0.9984633,0.00017356419,0.00016218114,0.0006372946,0.00041031794,0.00015338416],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00067729136,0.0003806925,0.00043382155,0.0002035313,0.0005674011,0.0006122949,0.0006736109,0.0001709627,0.00011131158],"category_scores_gemma":[0.00011278911,0.00033922412,0.00027048655,0.0007223108,0.00009341222,0.00073611306,0.0008028262,0.0001687108,0.000034132725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011644147,0.0007279085,0.00090708956,0.0011352599,0.00081359607,0.000016523409,0.002292869,0.22287063,0.03520281,0.09040449,0.20959957,0.43591282],"study_design_scores_gemma":[0.001060726,0.00021304403,0.00027050826,0.00030632486,0.00006881454,0.0000018818951,0.00004423454,0.9276835,0.027753992,0.0018940702,0.040329862,0.0003730537],"about_ca_topic_score_codex":0.00012205821,"about_ca_topic_score_gemma":0.000036289508,"teacher_disagreement_score":0.86980313,"about_ca_system_score_codex":0.00014063525,"about_ca_system_score_gemma":0.00030282137,"threshold_uncertainty_score":0.999906},"labels":[],"label_agreement":null},{"id":"W7117555463","doi":"10.1016/j.eswa.2025.131015","title":"Deep learning-based image outpainting of finger-vein image","year":2025,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Information Technology Research Centre; Ministry of Science and ICT, South Korea","keywords":"Image (mathematics); Image processing; Feature detection (computer vision); Pattern recognition (psychology); Image restoration; Image segmentation","score_opus":0.006220728873907623,"score_gpt":0.23824038668543232,"score_spread":0.2320196578115247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117555463","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007584173,0.00075883494,0.9923751,0.00076798187,0.000096666154,0.0005764853,0.0000014313271,0.00015255675,0.005195111],"genre_scores_gemma":[0.77281874,0.000009456996,0.225204,0.00014178701,0.000119521224,0.00086394115,0.0000075800526,0.000015173552,0.0008198221],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865526,0.00014655519,0.0003439861,0.0004207117,0.00019096704,0.00024254514],"domain_scores_gemma":[0.99850285,0.00023685324,0.00021530781,0.0006774052,0.00030684558,0.0000607583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031138767,0.00016408767,0.00026068356,0.00014011709,0.00029169547,0.00018090042,0.00059190247,0.000052229865,0.000008404745],"category_scores_gemma":[0.00006294409,0.0001373346,0.0000695489,0.0007059142,0.00009972917,0.00024978298,0.00009519351,0.00012055557,0.000024603532],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010287124,0.001609649,0.0038586454,0.001068843,0.0007349568,0.000025429596,0.0072494936,0.3179519,0.37474626,0.15922427,0.022414796,0.111012876],"study_design_scores_gemma":[0.00043730636,0.00006115231,0.00026635488,0.0001581081,0.000014379809,0.000002306954,0.00048076524,0.91789055,0.024135282,0.00009738165,0.056188505,0.00026789244],"about_ca_topic_score_codex":0.00019182525,"about_ca_topic_score_gemma":0.000011864943,"teacher_disagreement_score":0.77274287,"about_ca_system_score_codex":0.000044545905,"about_ca_system_score_gemma":0.00009626673,"threshold_uncertainty_score":0.5600343},"labels":[],"label_agreement":null},{"id":"W7119847868","doi":"10.3126/jonc.v1i1-2.89113","title":"Shades of History: Reviving Nepal’s Heritage through AI","year":2025,"lang":"","type":"article","venue":"Journal of NAST College","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Adversarial system; Limiting; Comprehension; Cultural heritage; Discriminator","score_opus":0.02035688717109358,"score_gpt":0.2581466609564489,"score_spread":0.23778977378535532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7119847868","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069025573,0.06445766,0.8828321,0.014538315,0.013842387,0.00051297306,0.00004061862,0.000020590192,0.016852777],"genre_scores_gemma":[0.9410641,0.0017057612,0.049280625,0.0016691675,0.00091381767,0.0000022828876,2.3274619e-7,0.000021799351,0.005342202],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960508,0.000582462,0.0017704016,0.00040540713,0.00070140604,0.00048952317],"domain_scores_gemma":[0.99577975,0.00040930882,0.0017199622,0.0006185073,0.0013149957,0.00015748298],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001440667,0.00038648274,0.0012317771,0.0003836638,0.00023857939,0.000126256,0.0015653338,0.00019688181,0.00034381347],"category_scores_gemma":[0.00056853704,0.0003529623,0.00071899255,0.0011746453,0.00030196417,0.0018236905,0.00045503923,0.0006869179,0.0000068965373],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008242136,0.0017452039,0.0021466936,0.0011115454,0.0022098222,0.0008991922,0.008153798,0.009943686,0.054720547,0.07352576,0.7980986,0.046620924],"study_design_scores_gemma":[0.0034838165,0.0014808656,0.0033011732,0.005833193,0.0006154728,0.00020745579,0.0013679228,0.08077041,0.013211102,0.003585477,0.88529277,0.000850359],"about_ca_topic_score_codex":0.00004375788,"about_ca_topic_score_gemma":0.000022499911,"teacher_disagreement_score":0.93416154,"about_ca_system_score_codex":0.0006487396,"about_ca_system_score_gemma":0.0017766983,"threshold_uncertainty_score":0.99989223},"labels":[],"label_agreement":null},{"id":"W7123353892","doi":"10.1109/cdc57313.2025.11312306","title":"Preventing Model Collapse when Training LLMs with Synthetic Data","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Synthetic data; Training (meteorology); Generative model; Simple (philosophy); Training set; Quality (philosophy)","score_opus":0.06272020910394469,"score_gpt":0.27216047721715636,"score_spread":0.20944026811321168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7123353892","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034258488,0.0006805003,0.92787296,0.0034762365,0.0006154887,0.00056873704,0.000028355815,0.000109100285,0.066306025],"genre_scores_gemma":[0.6252456,0.00006933564,0.35117882,0.0007130782,0.00012271226,0.000016111704,0.000008498212,0.00002224712,0.022623617],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956697,0.0003172836,0.0006908921,0.001895126,0.0004940728,0.00093291997],"domain_scores_gemma":[0.9956983,0.00033916175,0.00024915749,0.0032423325,0.00027310709,0.00019798573],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0013978948,0.00051349675,0.0006354838,0.00020114884,0.0007504193,0.0013625076,0.0036375178,0.00014591956,0.000269319],"category_scores_gemma":[0.0002596988,0.00042435076,0.00010723649,0.00091499946,0.0002491015,0.0021362859,0.0027347854,0.00032489377,0.000029231407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000091399816,0.0003417643,0.000089395326,0.00014274052,0.00069379836,0.000038894632,0.005734694,0.3568959,0.00081756775,0.019011283,0.03299034,0.58315223],"study_design_scores_gemma":[0.0006133433,0.00008534581,0.000019590949,0.00064888777,0.000217419,0.000008183308,0.00053966726,0.9899763,0.0009311127,0.003144953,0.0033146243,0.0005005781],"about_ca_topic_score_codex":0.00010244444,"about_ca_topic_score_gemma":0.00023079282,"teacher_disagreement_score":0.6330804,"about_ca_system_score_codex":0.000069025096,"about_ca_system_score_gemma":0.0012614952,"threshold_uncertainty_score":0.9998208},"labels":[],"label_agreement":null},{"id":"W7123530623","doi":"10.1109/mmsp64401.2025.11324262","title":"Multimodal Federated Learning for Personalized Clothing Recommendation","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Clothing; Recommender system; Embedding; Face (sociological concept); Construct (python library)","score_opus":0.022126693807019423,"score_gpt":0.28520828045432817,"score_spread":0.26308158664730874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7123530623","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002904814,0.00023522104,0.9713996,0.011944254,0.0023894198,0.00078123785,0.000003484066,0.00015530737,0.012801001],"genre_scores_gemma":[0.7851735,0.00011012675,0.15896301,0.0020610455,0.00035046323,0.00007797188,0.00004267987,0.000023192813,0.053198043],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99723524,0.00050888583,0.0005845568,0.0009061934,0.00016136163,0.000603748],"domain_scores_gemma":[0.99814796,0.0007891694,0.00021912287,0.00021576525,0.0005218388,0.00010612046],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010681466,0.00035580882,0.00043454376,0.00019857248,0.0017994777,0.0014636187,0.00041499283,0.00019479262,0.0006176784],"category_scores_gemma":[0.00066457083,0.00035385092,0.0002748882,0.00068972824,0.000088003995,0.00091633364,0.00027122087,0.00034009985,0.000031203985],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018051901,0.00015032194,0.0002019716,0.00007448981,0.00028818997,0.0000012295774,0.0011438407,0.02326379,0.0042800317,0.020478478,0.012082474,0.93785465],"study_design_scores_gemma":[0.0016447585,0.00012339231,0.00011929057,0.00009348613,0.000053486358,7.9655075e-7,0.00035620446,0.8572008,0.0053982963,0.0004361551,0.13425937,0.00031397195],"about_ca_topic_score_codex":0.00016701044,"about_ca_topic_score_gemma":0.000036380283,"teacher_disagreement_score":0.9375407,"about_ca_system_score_codex":0.00015241183,"about_ca_system_score_gemma":0.0002957477,"threshold_uncertainty_score":0.99989134},"labels":[],"label_agreement":null},{"id":"W7124880824","doi":"10.1109/cbmi66578.2025.11339288","title":"Binned-KMeans: Extracting Memorable, Explainable, Weighted and Sorted Colour Palettes from Videos","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Tone (literature); Coherence (philosophical gambling strategy); Metadata; Ideal (ethics); Pattern recognition (psychology); Pixel","score_opus":0.00912072193388037,"score_gpt":0.22837638538752794,"score_spread":0.21925566345364758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124880824","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025938759,0.0072957342,0.9294116,0.009331317,0.0025413295,0.00094662275,0.000032928983,0.00027931228,0.02422239],"genre_scores_gemma":[0.8614891,0.0016883867,0.11586312,0.0062743966,0.0006306371,0.00006667641,0.000018765477,0.000045438126,0.013923437],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944717,0.0007506573,0.0011497304,0.0019257958,0.0005046645,0.0011973979],"domain_scores_gemma":[0.99542606,0.0021082829,0.0004470502,0.0011768342,0.00051173463,0.0003300317],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009543597,0.000812175,0.0009966325,0.00039451284,0.001404468,0.001987447,0.0011661476,0.00039746685,0.00092804496],"category_scores_gemma":[0.00046443605,0.00075664977,0.0002202982,0.0017157394,0.00031038368,0.0021037098,0.001017287,0.000627936,0.0001212692],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048278642,0.0013488064,0.010216574,0.0003654646,0.003016505,0.00069330307,0.003574068,0.0041724546,0.05698381,0.02381271,0.10974601,0.7855875],"study_design_scores_gemma":[0.0017805988,0.00016652171,0.003940439,0.0005845708,0.00029535196,0.0000056501203,0.0012945492,0.91713846,0.03792428,0.00696991,0.028835813,0.0010638678],"about_ca_topic_score_codex":0.0017984014,"about_ca_topic_score_gemma":0.00030678767,"teacher_disagreement_score":0.912966,"about_ca_system_score_codex":0.00011622032,"about_ca_system_score_gemma":0.00038167308,"threshold_uncertainty_score":0.9999852},"labels":[],"label_agreement":null},{"id":"W7125532663","doi":"10.1109/iceei68459.2025.11330577","title":"Neural Radiance Field Reconstruction for Preserving Cultural Heritage Sites Through Immersive Virtual Experiences","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Cultural heritage; Field (mathematics); Virtual reality; Radiance; Visualization","score_opus":0.026007585497522454,"score_gpt":0.28268580125091153,"score_spread":0.25667821575338906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125532663","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0431627,0.0024803097,0.9296816,0.010234181,0.0067526675,0.00084502855,0.000009457277,0.000059198253,0.00677487],"genre_scores_gemma":[0.94116074,0.00029516453,0.047468763,0.0028179502,0.000669179,0.00017722153,0.000004554573,0.000011077417,0.0073953248],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99717295,0.00021001014,0.00059625675,0.0010693234,0.00023283518,0.0007186471],"domain_scores_gemma":[0.99794513,0.00076875894,0.00022423008,0.00058297877,0.00037110833,0.00010776584],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021923291,0.00042523083,0.000467779,0.00008049164,0.0010380627,0.0009857188,0.0011509601,0.00020566279,0.00053576427],"category_scores_gemma":[0.00047690183,0.0003736897,0.00033739454,0.0007011224,0.0003006079,0.0039806413,0.0004652256,0.00023392,0.000009479439],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005255905,0.00025275923,0.0012333235,0.0002298423,0.0006509687,0.000019039338,0.0949555,0.016659,0.027379066,0.034527652,0.15902686,0.6645404],"study_design_scores_gemma":[0.00070261006,0.0005460895,0.00009301626,0.00017266256,0.000051642135,0.0000115632765,0.049069315,0.835389,0.1064845,0.0011054362,0.0058109905,0.0005631657],"about_ca_topic_score_codex":0.00028807696,"about_ca_topic_score_gemma":0.00012450085,"teacher_disagreement_score":0.8979981,"about_ca_system_score_codex":0.00007355169,"about_ca_system_score_gemma":0.00014451676,"threshold_uncertainty_score":0.9998715},"labels":[],"label_agreement":null},{"id":"W7125820309","doi":"10.21428/594757db.f60795db","title":"GANsemble for Small and Imbalanced Data Sets : A Baseline for Synthetic Microplastics Data","year":2024,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Microplastics; Oversampling; Data quality; Synthetic data; Baseline (sea); Missing data; Filter (signal processing); Data set","score_opus":0.08262116980739041,"score_gpt":0.30343819996264937,"score_spread":0.22081703015525894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125820309","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010224378,0.0009911837,0.99410766,0.0024951342,0.0006239238,0.0004226433,0.0010610372,0.00010880023,0.000087369466],"genre_scores_gemma":[0.079372205,0.00012216084,0.91856307,0.00037333547,0.00030188082,0.000030368341,0.00047407704,0.00002238357,0.00074054993],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998565,0.00003431643,0.00018925854,0.0008687222,0.000072166076,0.0002705148],"domain_scores_gemma":[0.9971518,0.0011488983,0.000027250411,0.0015299427,0.00006630015,0.00007582342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070675864,0.00014454077,0.00017022439,0.000045138582,0.00011663826,0.0004466769,0.0014342763,0.000042440563,0.000009255445],"category_scores_gemma":[0.0003431157,0.00011358375,0.000026867045,0.00012784771,0.000032909495,0.00050680095,0.00107635,0.00004922111,0.000006872436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007127772,0.00012241727,0.0000207715,0.0005540115,0.0002463931,0.000017575216,0.00021156138,0.0009305483,0.022390997,0.010493956,0.3759047,0.5890358],"study_design_scores_gemma":[0.00019857915,0.000050531773,0.0000054016537,0.000043586875,0.00004181408,0.000009451389,0.000010798121,0.86148226,0.0022064662,0.0007689122,0.13503996,0.00014226776],"about_ca_topic_score_codex":0.000017326944,"about_ca_topic_score_gemma":0.00009658921,"teacher_disagreement_score":0.8605517,"about_ca_system_score_codex":0.0000083213445,"about_ca_system_score_gemma":0.00008995722,"threshold_uncertainty_score":0.46318108},"labels":[],"label_agreement":null},{"id":"W7125901270","doi":"10.1109/smc58881.2025.11342953","title":"Audio-Visual Cross-Attention for Improved Deepfake Video Detection and Forgery Localization","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Robustness (evolution); Focus (optics); Modalities; Detector; Complementarity (molecular biology); Pattern recognition (psychology)","score_opus":0.009150315507077044,"score_gpt":0.273934550027488,"score_spread":0.26478423452041094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125901270","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005519026,0.000550988,0.988246,0.0008127249,0.0032768126,0.0011217834,0.0000069512234,0.000101695456,0.00036397832],"genre_scores_gemma":[0.9809127,0.00020000855,0.013498743,0.00080449076,0.00039867853,0.00010049023,0.00001234753,0.000020657311,0.004051891],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974593,0.00016071451,0.0006801153,0.0010067292,0.00015637107,0.00053676893],"domain_scores_gemma":[0.99836874,0.0002701414,0.00025015438,0.0003569184,0.00063439994,0.000119657874],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00079304585,0.0003539364,0.0003741496,0.00026553604,0.0010850155,0.0013114548,0.0002473922,0.00027971267,0.000025990388],"category_scores_gemma":[0.0003387461,0.00035233435,0.00021647151,0.00077883335,0.00018429045,0.0014808716,0.00028145497,0.00012969233,0.000006138097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022523454,0.00014701272,0.001092184,0.00018274291,0.00016541693,5.901006e-7,0.00010310945,0.004933002,0.05379937,0.0022217382,0.0008215396,0.9363081],"study_design_scores_gemma":[0.001153192,0.00029056557,0.0053284313,0.000077761695,0.00010016738,0.000002276515,0.000042491083,0.94248766,0.04321569,0.002403704,0.004566327,0.00033172444],"about_ca_topic_score_codex":0.00009680168,"about_ca_topic_score_gemma":0.0002315763,"teacher_disagreement_score":0.97539365,"about_ca_system_score_codex":0.000121258156,"about_ca_system_score_gemma":0.00013867185,"threshold_uncertainty_score":0.9998929},"labels":[],"label_agreement":null},{"id":"W7125910072","doi":"10.1109/smc58881.2025.11343065","title":"A Dual-Branch Unsupervised Network with Wavelet Transform and Style Consistency for CT to MRI Image Generation <sup>*</sup>","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Natural Science Foundation of China","keywords":"Pattern recognition (psychology); Consistency (knowledge bases); Wavelet transform; Wavelet; Image (mathematics); Representation (politics); Feature extraction; Translation (biology)","score_opus":0.012888248410121027,"score_gpt":0.23209862219167202,"score_spread":0.21921037378155098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125910072","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052208663,0.0008375706,0.96781945,0.016246872,0.0005592026,0.003307323,0.00007534946,0.00009992825,0.005833436],"genre_scores_gemma":[0.6114483,0.00026684903,0.37784684,0.0042790216,0.0009917866,0.00032496869,0.00005086334,0.00004904716,0.004742361],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954551,0.00028408537,0.0009323418,0.0016856508,0.00041696924,0.001225885],"domain_scores_gemma":[0.9974615,0.0004150733,0.00012994892,0.0009207928,0.0006540818,0.00041857976],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009599846,0.000767972,0.00093033415,0.0002390417,0.0013101343,0.0013748622,0.00053127354,0.00014999336,0.00016868162],"category_scores_gemma":[0.00007590771,0.0006452273,0.00024798824,0.0015042229,0.00027920425,0.0011877868,0.00022982627,0.00024953968,0.000018206412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007659482,0.0005116447,0.0001893598,0.0004589058,0.0011040985,0.000055633805,0.0060363323,0.16671893,0.004318333,0.030612132,0.12172929,0.66749936],"study_design_scores_gemma":[0.003021264,0.00093793805,0.00016070904,0.00022654081,0.00025701668,0.000023694878,0.00033755403,0.9604719,0.007651236,0.0010264927,0.025054978,0.0008306497],"about_ca_topic_score_codex":0.00015386174,"about_ca_topic_score_gemma":0.00039412733,"teacher_disagreement_score":0.793753,"about_ca_system_score_codex":0.00009948387,"about_ca_system_score_gemma":0.000559029,"threshold_uncertainty_score":0.99999005},"labels":[],"label_agreement":null},{"id":"W7125938147","doi":"10.26634/jpr.12.2.22080","title":"Development of AI/ML based solution for detection of face-swap based deepfake videos software","year":2025,"lang":"en","type":"article","venue":"i-manager’s Journal on Pattern Recognition","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"WSP (Canada)","funders":"","keywords":"Variety (cybernetics); Construct (python library); Quality (philosophy); Deep learning; Software","score_opus":0.028083465803503623,"score_gpt":0.260017888708311,"score_spread":0.23193442290480737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125938147","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012930128,0.00003970753,0.98514843,0.00058976264,0.00079804996,0.00038591766,0.000017573591,0.0000415355,0.00004888277],"genre_scores_gemma":[0.8360018,0.0000062715603,0.16298454,0.0008363218,0.00007495708,0.00003966351,0.0000220437,0.000012408842,0.00002195681],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982144,0.00018317677,0.0006841618,0.00032058873,0.00033457807,0.00026305873],"domain_scores_gemma":[0.99838406,0.0002638085,0.00052830257,0.00023165469,0.00052312063,0.00006905221],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073248113,0.00020098916,0.00029314496,0.0005169504,0.00028237185,0.00010157319,0.00031546262,0.00010795803,0.000024348039],"category_scores_gemma":[0.00017324559,0.00019184168,0.00021695843,0.0003691369,0.000032035423,0.00042724342,0.0000460806,0.00021172527,0.000008473899],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010262236,0.00015421222,0.00013263646,0.0001285318,0.00007143629,0.00000301657,0.00008646957,0.006095585,0.018125063,0.0000068420336,0.0002187607,0.9748748],"study_design_scores_gemma":[0.0016268698,0.0003142149,0.0034151564,0.00080009113,0.00007850922,0.0000033254319,0.00003525717,0.41606647,0.5747023,0.0010993117,0.0015895993,0.00026885094],"about_ca_topic_score_codex":0.000009572885,"about_ca_topic_score_gemma":0.000054356107,"teacher_disagreement_score":0.974606,"about_ca_system_score_codex":0.00014471194,"about_ca_system_score_gemma":0.00019104875,"threshold_uncertainty_score":0.7823077},"labels":[],"label_agreement":null},{"id":"W7126156957","doi":"10.21428/594757db.e2edb565","title":"Enhancing Predictive Coding Networks for Multi-Modal Generation and Classification","year":2025,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Predictive coding; Coding (social sciences); Generative grammar; Generative model; Class (philosophy); Artificial neural network; Encoding (memory)","score_opus":0.04009890578739156,"score_gpt":0.2821540879954053,"score_spread":0.24205518220801375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126156957","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00060836604,0.00012627336,0.997308,0.0005263199,0.00047643523,0.00030630728,0.0000010243052,0.00006718674,0.0005800431],"genre_scores_gemma":[0.7324077,0.00003187241,0.266551,0.00025757565,0.00015639723,0.00005210464,0.000004999916,0.0000030970875,0.0005352658],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927366,0.00004686023,0.0001597687,0.0003155884,0.000053572916,0.00015053576],"domain_scores_gemma":[0.9995351,0.00011063297,0.000048172365,0.00016010275,0.000113387316,0.00003263575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025422947,0.00008772201,0.00010021843,0.000058248756,0.00025248047,0.0001812299,0.00013771083,0.000056136843,0.0000019584004],"category_scores_gemma":[0.00006696829,0.00007871724,0.00003059833,0.00015981162,0.000023725333,0.00038695987,0.00007291452,0.00004869893,7.749273e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042257325,0.00013292732,0.0011728094,0.000042149702,0.0001613091,8.584283e-7,0.00084982335,0.07364341,0.25747538,0.3809806,0.0091520725,0.2763464],"study_design_scores_gemma":[0.00026518,0.000027366723,0.002324008,0.000012830367,0.000009747597,3.0736916e-7,0.00003534769,0.9792251,0.01740841,0.00020528998,0.00040980466,0.00007662664],"about_ca_topic_score_codex":0.00000846677,"about_ca_topic_score_gemma":0.000053368145,"teacher_disagreement_score":0.90558165,"about_ca_system_score_codex":0.000032729058,"about_ca_system_score_gemma":0.000032864013,"threshold_uncertainty_score":0.3209996},"labels":[],"label_agreement":null},{"id":"W7126222530","doi":"10.1109/iscmi67495.2025.11358601","title":"Hybrid Merging Projection Wasserstein Distance for Semantics-Aware Optimal Transport","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bishop's University","funders":"Qatar National Research Fund","keywords":"Projection (relational algebra); Random projection; Distribution (mathematics); Projection method; Probability distribution; Transfer (computing)","score_opus":0.012601442296988832,"score_gpt":0.252613752538447,"score_spread":0.24001231024145814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126222530","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020176668,0.00048862246,0.98582524,0.0044059413,0.0032644311,0.0013836438,0.00003930351,0.00014949882,0.0024256646],"genre_scores_gemma":[0.89658016,0.00013687287,0.08805358,0.00034512114,0.00034847113,0.00011035404,0.000018366947,0.000026140648,0.014380909],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99666995,0.00012478317,0.0007590109,0.0012747471,0.00033057106,0.0008409112],"domain_scores_gemma":[0.9982862,0.0001871079,0.00020904643,0.00073160726,0.00045496112,0.00013106974],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006367683,0.0004974157,0.000586247,0.00023074378,0.00088266557,0.00042186104,0.00083178026,0.00012362131,0.00006654355],"category_scores_gemma":[0.00005318887,0.00048329376,0.00044369115,0.00077651325,0.00014141647,0.0010913952,0.00013669448,0.00023231075,0.000009998581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010273998,0.0013466747,0.0018106458,0.002072726,0.001749159,0.000109726745,0.0031323184,0.31619152,0.007483684,0.12648734,0.0358078,0.50278103],"study_design_scores_gemma":[0.00081104855,0.00016866399,0.00020413475,0.00028650305,0.00017181924,0.0000037079953,0.00028307363,0.932909,0.040181845,0.00048265743,0.023992222,0.00050528237],"about_ca_topic_score_codex":0.00012973478,"about_ca_topic_score_gemma":0.00012549381,"teacher_disagreement_score":0.89777166,"about_ca_system_score_codex":0.00016208856,"about_ca_system_score_gemma":0.00043879854,"threshold_uncertainty_score":0.9997619},"labels":[],"label_agreement":null},{"id":"W7126434387","doi":"10.21428/594757db.e068aace","title":"Progressively Growing Generative Adversarial Network BasedAuto-encoder for MRI Image Inpainting","year":2024,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University; University of Calgary; Ontario Tech University","funders":"","keywords":"Inpainting; Image (mathematics); Artifact (error); Deep learning; Image restoration; Adversarial system; Noise (video); Iterative reconstruction; Generative grammar","score_opus":0.012261638837989168,"score_gpt":0.25711282120215245,"score_spread":0.24485118236416328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126434387","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010237804,0.0006298007,0.98687255,0.004153635,0.0026523685,0.000625754,0.000005368234,0.0005363018,0.0044218283],"genre_scores_gemma":[0.10867473,0.000017736931,0.8846545,0.0012122579,0.0036978722,0.00017155908,0.0000127933135,0.00004083326,0.001517712],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975377,0.00018290331,0.00039167085,0.00088039425,0.0002884909,0.0007188473],"domain_scores_gemma":[0.99864554,0.00054687116,0.000083696745,0.00037947157,0.00020933167,0.0001350643],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00095876266,0.0003155847,0.00030243123,0.00010318755,0.0004890576,0.0012592365,0.00063262356,0.00010686182,0.00008217856],"category_scores_gemma":[0.00013297527,0.0002562743,0.0002720055,0.00060709135,0.00008365708,0.0024139632,0.00031402678,0.00020623695,0.00005158962],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000069033915,0.00012307988,0.00010310377,0.00017606768,0.00060481334,0.00020299492,0.002240191,0.10355365,0.015997956,0.41340822,0.21507452,0.24844635],"study_design_scores_gemma":[0.0003066899,0.00009924139,0.0000222447,0.00010175248,0.00003138065,0.000006186421,0.000055299017,0.93951344,0.009229925,0.0053479807,0.044925738,0.0003601264],"about_ca_topic_score_codex":0.000019494173,"about_ca_topic_score_gemma":0.000009780601,"teacher_disagreement_score":0.8359598,"about_ca_system_score_codex":0.000074088486,"about_ca_system_score_gemma":0.00018210312,"threshold_uncertainty_score":0.999989},"labels":[],"label_agreement":null},{"id":"W7127998310","doi":"10.22260/crc-csce-2025/0053","title":"Large Language Model and Synthetic Dataset Based Occupant Clothing Insulation Recognition","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Clothing; Language model; Matching (statistics); Feature (linguistics); Identification (biology)","score_opus":0.022486171800709012,"score_gpt":0.27187225661460934,"score_spread":0.24938608481390034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7127998310","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009895814,0.0006329566,0.9848567,0.0013745384,0.0004005306,0.00035665787,0.001082619,0.00006568575,0.0013344456],"genre_scores_gemma":[0.93970454,0.00007964432,0.056553826,0.0027826864,0.00006846952,0.000013170226,0.0004966542,0.000011333198,0.0002896746],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977767,0.00030486667,0.00043754667,0.00080981525,0.00023169015,0.0004393733],"domain_scores_gemma":[0.99873,0.00024147208,0.00013660998,0.0006650082,0.00011462913,0.00011225246],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00087845867,0.0002907299,0.00029629428,0.00023929449,0.00047232155,0.0005754845,0.00034704825,0.00014544408,0.00013875801],"category_scores_gemma":[0.00021707355,0.0002761919,0.000068851994,0.00048328508,0.00007433603,0.00096910354,0.0003881159,0.0002047872,0.000036166748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025862383,0.0010761743,0.00035221525,0.0004935543,0.0002799378,0.00005564911,0.005472359,0.18819164,0.023447488,0.012443326,0.019423112,0.74850595],"study_design_scores_gemma":[0.00071887235,0.00003845474,0.00037898496,0.0002239309,0.00009011893,0.0000014643182,0.0001986853,0.9919011,0.0040666573,0.0011818084,0.00089552486,0.00030438905],"about_ca_topic_score_codex":0.00014157701,"about_ca_topic_score_gemma":0.000077908204,"teacher_disagreement_score":0.92980874,"about_ca_system_score_codex":0.000057183533,"about_ca_system_score_gemma":0.00020109916,"threshold_uncertainty_score":0.999969},"labels":[],"label_agreement":null},{"id":"W7130276194","doi":"","title":"Training diffusion-based generative models with limited data","year":2025,"lang":"en","type":"article","venue":"Research Portal (Queen's University Belfast)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Queen's University; Queen's University Belfast; Department for the Economy","keywords":"Matching (statistics); Function (biology); Noise reduction; Generative model; Generative grammar; Training (meteorology); Score; Space (punctuation)","score_opus":0.06751690461589212,"score_gpt":0.29223591430995194,"score_spread":0.22471900969405983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7130276194","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042311363,0.000021480044,0.963729,0.0055800085,0.00009412221,0.00041601004,0.000063002655,0.00014222955,0.02572297],"genre_scores_gemma":[0.91912615,0.000049214283,0.072623126,0.00024494258,0.00008047527,0.0000028966244,0.00011680068,0.000015429143,0.007740942],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966123,0.0006258643,0.00018171706,0.0010141855,0.00082323246,0.00074268965],"domain_scores_gemma":[0.99714607,0.00041175084,0.000077615325,0.0015125846,0.0005908439,0.00026111992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008701518,0.00023785127,0.00030180364,0.00062610157,0.0010119887,0.00024521726,0.002509538,0.00011396643,0.000061319224],"category_scores_gemma":[0.00010763832,0.00021560206,0.00007054111,0.0020747925,0.0003458292,0.0015013673,0.0015971366,0.0005431822,0.000011915123],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009686294,0.001557498,0.0021193132,0.00014875036,0.001217606,0.004548996,0.004221894,0.20087808,0.0025505656,0.60089546,0.09942843,0.08146477],"study_design_scores_gemma":[0.0012372102,0.00023097006,0.0007368529,0.00014289789,0.000030503492,0.000002049815,0.0016004907,0.97202694,0.0011068222,0.0009626404,0.021555038,0.00036760877],"about_ca_topic_score_codex":0.00069078756,"about_ca_topic_score_gemma":0.00015050836,"teacher_disagreement_score":0.91489506,"about_ca_system_score_codex":0.00012210282,"about_ca_system_score_gemma":0.0012290089,"threshold_uncertainty_score":0.8791997},"labels":[],"label_agreement":null},{"id":"W7131079571","doi":"10.1109/iccvw69036.2025.00329","title":"Latent Representation of Microstructures Using Variational Autoencoders with Spatial Statistics-Space Loss","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Representation (politics); Microstructure; Latent variable; Pattern recognition (psychology); Binary number; Term (time); Compression (physics)","score_opus":0.014235732598160147,"score_gpt":0.2632522416575085,"score_spread":0.24901650905934836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7131079571","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026516442,0.00014636994,0.9939394,0.0011035628,0.0011563363,0.00037575114,0.00008012214,0.000021272388,0.0005255222],"genre_scores_gemma":[0.5581022,0.000036009835,0.44124228,0.000112520276,0.00008377384,0.0000024150079,0.00001027657,0.000008005355,0.00040255653],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99751145,0.00028797938,0.00061000977,0.00071234885,0.0005039565,0.0003742603],"domain_scores_gemma":[0.9979893,0.00022355706,0.00044155578,0.0005212165,0.00073879317,0.000085601336],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021609514,0.00030857508,0.00043519697,0.0002132007,0.00031589682,0.0003010149,0.0004510709,0.00011495131,0.00021070548],"category_scores_gemma":[0.000104382605,0.0002645121,0.00009132901,0.0008734247,0.00034530717,0.0004666336,0.00026594044,0.00015500632,0.0000029516782],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018820041,0.00010814056,0.0060093193,0.000067574925,0.00039545918,0.00001571378,0.0007426321,0.9200044,0.0061110714,0.051733673,0.0010075988,0.013616194],"study_design_scores_gemma":[0.0008112931,0.00011567222,0.024733838,0.00012799272,0.00014690694,0.000007331037,0.000058071386,0.9417042,0.028519439,0.0034339046,0.00008747982,0.0002538312],"about_ca_topic_score_codex":0.0039039345,"about_ca_topic_score_gemma":0.00033715818,"teacher_disagreement_score":0.55545056,"about_ca_system_score_codex":0.00011285277,"about_ca_system_score_gemma":0.0008689267,"threshold_uncertainty_score":0.9999807},"labels":[],"label_agreement":null},{"id":"W7131421266","doi":"10.1109/icdm65498.2025.00075","title":"Interpretable and Interactive Deep Survival Analysis with Time-dependent EXtreme Gradient Integration","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Interpretability; Domain knowledge; Bridging (networking); Feature (linguistics); Domain (mathematical analysis); Process (computing); Expert system; Key (lock)","score_opus":0.009593266652874525,"score_gpt":0.22341830513858968,"score_spread":0.21382503848571516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7131421266","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034410069,0.0005732543,0.9702521,0.0010302183,0.0007506356,0.00042978855,0.0000069242124,0.000066532775,0.023449564],"genre_scores_gemma":[0.954931,0.00014392752,0.02290338,0.0003003559,0.000070868526,0.000027049764,0.000010730862,0.000013752313,0.021598917],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99652547,0.00055100175,0.0006214487,0.0013218446,0.0004258243,0.0005543915],"domain_scores_gemma":[0.99781007,0.0004110625,0.00026617214,0.00079725945,0.00051902165,0.00019639109],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00069707574,0.00053745485,0.00084185455,0.0007655803,0.00038984278,0.0012612029,0.0006439344,0.00012876288,0.00069445075],"category_scores_gemma":[0.00010273117,0.00040633845,0.00024534337,0.0024969357,0.00022341547,0.0014553277,0.0006714339,0.00035333945,0.000036252077],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008334826,0.00079820567,0.005584395,0.000041145657,0.011673638,0.000054532942,0.0071088783,0.061816454,0.0037610098,0.009589256,0.001144124,0.89759487],"study_design_scores_gemma":[0.00054847304,0.0003006179,0.002265311,0.00014189897,0.0015097511,0.000003883406,0.0008814966,0.98824006,0.0048885965,0.000315213,0.0004627966,0.00044191963],"about_ca_topic_score_codex":0.0007825304,"about_ca_topic_score_gemma":0.0026849972,"teacher_disagreement_score":0.95149,"about_ca_system_score_codex":0.00021888505,"about_ca_system_score_gemma":0.00014407284,"threshold_uncertainty_score":0.9998388},"labels":[],"label_agreement":null},{"id":"W7132903106","doi":"","title":"Understanding Generative Adversarial Networks in the Context of Game Theory and Control Theory","year":2023,"lang":"","type":"dissertation","venue":"TSpace","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Adversarial system; Variety (cybernetics); Generative grammar; Context (archaeology); Game theory; Nash equilibrium","score_opus":0.04805442692928784,"score_gpt":0.30087375839912295,"score_spread":0.2528193314698351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132903106","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0062619783,0.003015969,0.9837637,0.00076216966,0.0028823465,0.0014896173,0.000018870793,0.000045044595,0.0017603203],"genre_scores_gemma":[0.9953309,0.0010734679,0.00033079955,0.0006436027,0.0007163176,0.00007857516,0.000048881397,0.000066824134,0.0017106076],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99053913,0.0059279017,0.0009315112,0.0011040199,0.0006706934,0.00082672364],"domain_scores_gemma":[0.9896886,0.008213641,0.0009083931,0.0008147452,0.00023811466,0.00013650459],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006826767,0.0007700666,0.0011697965,0.00035468576,0.000469543,0.0004216013,0.0012092362,0.00054007827,0.000073584524],"category_scores_gemma":[0.0008282447,0.0005938073,0.00032195594,0.00112461,0.00063750154,0.00040975763,0.00018008592,0.00097440166,0.000012286422],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033598384,0.0001961329,0.00014845174,0.00013328297,0.000899213,0.000097622295,0.3202338,0.06256371,0.0013253486,0.59121823,0.0010069715,0.018817388],"study_design_scores_gemma":[0.0048423433,0.00066738453,0.0017937742,0.0007801412,0.0005757408,0.00001148392,0.38466164,0.5498579,0.0011066586,0.05432153,0.00018277315,0.0011985997],"about_ca_topic_score_codex":0.00032204832,"about_ca_topic_score_gemma":0.00087000045,"teacher_disagreement_score":0.9890689,"about_ca_system_score_codex":0.00018722266,"about_ca_system_score_gemma":0.00031538654,"threshold_uncertainty_score":0.9996513},"labels":[],"label_agreement":null},{"id":"W7135727563","doi":"","title":"University of Amsterdam at TREC 2020:Deep Learning Track","year":2020,"lang":"en","type":"article","venue":"UvA-DARE (University of Amsterdam)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Canadian Institute of Steel Construction","keywords":"Track (disk drive); Window (computing); Information system; Feature (linguistics)","score_opus":0.011977540668762133,"score_gpt":0.1737110575297512,"score_spread":0.16173351686098905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7135727563","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23241305,0.0002633005,0.74828345,0.005801758,0.0003218163,0.00034179035,0.000040608516,0.00023036364,0.012303875],"genre_scores_gemma":[0.97739667,0.000120129545,0.019551983,0.00012750813,0.000069238646,3.271772e-8,0.000013813154,0.000012486365,0.0027081273],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983084,0.00025226746,0.00017298675,0.00059434545,0.00034408912,0.00032787863],"domain_scores_gemma":[0.99868506,0.00011971286,0.00032930705,0.00041954813,0.0001982463,0.0002481483],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016242625,0.00021940468,0.00047198267,0.00009382025,0.00040652516,0.000029639714,0.0012565844,0.0001229818,0.00073429086],"category_scores_gemma":[0.000032361193,0.0002827758,0.00029093013,0.0006031061,0.00024701134,0.00080256606,0.000998741,0.00023013513,0.00013278071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019986087,0.00084087363,0.021739017,0.00079492497,0.0013935253,0.0017004831,0.14428425,0.06818921,0.06248538,0.0028542946,0.053388927,0.6403305],"study_design_scores_gemma":[0.006810287,0.0021775847,0.053611107,0.00029149602,0.00039638524,0.00003594818,0.027223725,0.6659315,0.0071346723,0.00021898735,0.23425473,0.0019135759],"about_ca_topic_score_codex":0.00028289517,"about_ca_topic_score_gemma":0.00027004603,"teacher_disagreement_score":0.7449836,"about_ca_system_score_codex":0.00009067796,"about_ca_system_score_gemma":0.00006454399,"threshold_uncertainty_score":0.99996245},"labels":[],"label_agreement":null},{"id":"W7140106809","doi":"10.1109/icaiqsa67794.2025.11440594","title":"ForensicFaceGen: AI-Powered Suspect Sketch Generation Using Stable Diffusion for Criminal Investigations","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Sketch; Suspect; Diffusion; Term (time); Stability (learning theory)","score_opus":0.054465214883423846,"score_gpt":0.3019890581568952,"score_spread":0.24752384327347135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7140106809","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022818187,0.0009496271,0.96254987,0.0060131704,0.003899414,0.0014241282,0.000030268973,0.00009057583,0.0022247867],"genre_scores_gemma":[0.6792676,0.00007956781,0.3122624,0.0020680153,0.00084541406,0.000056501256,0.00004304983,0.000028256165,0.0053492417],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99629486,0.00031782064,0.00088827393,0.0012334603,0.00039444727,0.00087115826],"domain_scores_gemma":[0.9973352,0.00024748393,0.0002639719,0.000911164,0.001006534,0.00023565575],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00068261696,0.00053656986,0.00056329113,0.0003622665,0.00186434,0.0012921705,0.00067164673,0.00025942555,0.00027971732],"category_scores_gemma":[0.0003270032,0.00052842253,0.00031978023,0.0012025192,0.00025281138,0.0013932032,0.0004896561,0.00024403093,0.000016768176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012612915,0.00062357454,0.0007668389,0.0002758463,0.00046263283,0.000007875139,0.002460902,0.1399579,0.41104305,0.29437858,0.07644338,0.073453285],"study_design_scores_gemma":[0.0008396341,0.00015822196,0.0002025129,0.00011249794,0.00027346678,0.0000026517478,0.00017944751,0.8722152,0.1118743,0.007873462,0.0057974854,0.00047109832],"about_ca_topic_score_codex":0.0004977753,"about_ca_topic_score_gemma":0.0006807511,"teacher_disagreement_score":0.7322573,"about_ca_system_score_codex":0.0003132425,"about_ca_system_score_gemma":0.0011127092,"threshold_uncertainty_score":0.9997446},"labels":[],"label_agreement":null},{"id":"W7140436911","doi":"10.1109/sisimpact67725.2025.11439691","title":"Detection of Deepfake Images Using Hybrid Convolutional Neural Networks and Transformer Models","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Convolutional neural network; Pattern recognition (psychology); Transformer; Artificial neural network; Deep neural networks","score_opus":0.0173828320678217,"score_gpt":0.2325466772985343,"score_spread":0.21516384523071258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7140436911","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016340764,0.0042135166,0.9765832,0.00029670176,0.0012003506,0.00032515536,0.000012297275,0.00002952749,0.0009984851],"genre_scores_gemma":[0.9840663,0.00041748796,0.0149033265,0.00021385142,0.0001524729,0.0000050349977,0.0000018857174,0.000010811961,0.000228837],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978231,0.00021883691,0.0006175242,0.00063068984,0.00024052811,0.00046929327],"domain_scores_gemma":[0.9989462,0.00016239236,0.00016078992,0.0003005873,0.0003224195,0.00010761],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00038014795,0.00032117678,0.0004356413,0.00020213937,0.0004190172,0.00021687767,0.0003012992,0.00011822047,0.000034480076],"category_scores_gemma":[0.000019618214,0.00030972142,0.00018492411,0.000544823,0.00038214805,0.0013914575,0.00013739683,0.00023166132,4.6949188e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006701051,0.00006204876,0.00008166324,0.000040616887,0.00012439786,0.0000026786531,0.00006958385,0.786742,0.021401428,0.0031686807,0.00006865324,0.1881713],"study_design_scores_gemma":[0.00054013135,0.00008624676,0.00047534172,0.00006727405,0.00011916723,0.000018755542,0.00003220242,0.94579065,0.049838006,0.0027419187,0.000038989736,0.00025131446],"about_ca_topic_score_codex":0.00032210446,"about_ca_topic_score_gemma":0.00004457177,"teacher_disagreement_score":0.9677255,"about_ca_system_score_codex":0.00005926979,"about_ca_system_score_gemma":0.00012235073,"threshold_uncertainty_score":0.9999355},"labels":[],"label_agreement":null},{"id":"W7140905604","doi":"10.1109/sisimpact67725.2025.11439193","title":"VeriFace: Lightweight CNN Feature Extractors for Fast Deepfake Image Authentication","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Feature (linguistics); Image (mathematics); Authentication (law); Pattern recognition (psychology); Feature extraction","score_opus":0.009144426168773371,"score_gpt":0.25875667354881576,"score_spread":0.2496122473800424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7140905604","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004926681,0.0010799867,0.9598502,0.018089563,0.0053292387,0.001276908,0.000032787917,0.00013684902,0.013711786],"genre_scores_gemma":[0.58079225,0.00024673823,0.3045365,0.0012146384,0.0014340732,0.00015639346,0.000047143425,0.00004627413,0.11152602],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966404,0.00021004466,0.0006147815,0.0013194558,0.00036054995,0.00085480313],"domain_scores_gemma":[0.9972602,0.00038929423,0.0002752224,0.0012051885,0.00065446866,0.00021560509],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00055917253,0.0005745595,0.0005415199,0.00027333517,0.0008320538,0.0013155286,0.0013068932,0.00039606154,0.0004098546],"category_scores_gemma":[0.00019827796,0.0005092519,0.0004472237,0.0010923495,0.00020499375,0.0014517171,0.00040590676,0.00033493128,0.0001518074],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021897885,0.0008481312,0.00018947665,0.0003419938,0.0006592236,0.000012124368,0.0025559985,0.00064506964,0.08424169,0.08602777,0.38075343,0.44350612],"study_design_scores_gemma":[0.0010287025,0.00016941571,0.0024872506,0.00017722379,0.0002399783,0.0000024117057,0.0001730616,0.6311243,0.09913618,0.002731084,0.26204443,0.0006859407],"about_ca_topic_score_codex":0.000024783223,"about_ca_topic_score_gemma":0.000028003153,"teacher_disagreement_score":0.65531373,"about_ca_system_score_codex":0.00015419832,"about_ca_system_score_gemma":0.00035872523,"threshold_uncertainty_score":0.9997359},"labels":[],"label_agreement":null},{"id":"W7143611058","doi":"10.71465/ajainn690","title":"AI and Neural Networks in Digital Content Creation and Curation","year":2025,"lang":"","type":"article","venue":"American Journal of Artificial Intelligence and Neural Networks","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Content creation; Content (measure theory); Artificial neural network; Digital content; Automation; Field (mathematics)","score_opus":0.029828458654269464,"score_gpt":0.2794761980271698,"score_spread":0.2496477393729003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7143611058","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18262357,0.005567551,0.80571896,0.0047084754,0.0010941115,0.0002522416,0.0000022297945,0.000009730381,0.000023140674],"genre_scores_gemma":[0.9921415,0.0050417073,0.000545591,0.001583741,0.00063789164,0.0000039530482,0.0000022653542,0.000015636895,0.00002772176],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99666405,0.0003263266,0.0015092765,0.0006205063,0.00027659902,0.000603262],"domain_scores_gemma":[0.997579,0.00061671267,0.00085284276,0.00023315847,0.00042256806,0.00029571727],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000688875,0.00044753272,0.00085571647,0.00037864802,0.0003551897,0.0014883294,0.00035074042,0.0001419226,0.000007169355],"category_scores_gemma":[0.00019607226,0.0003975102,0.00014181518,0.001145243,0.0012215276,0.0026431237,0.00028539277,0.000873188,3.043749e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035566787,0.00007458436,0.0038364972,0.00000724746,0.000052108535,0.000037900205,0.00044376432,0.255072,0.000048208625,0.0014838163,0.00004236664,0.73854584],"study_design_scores_gemma":[0.00014743266,0.0013957093,0.0032741453,0.00024086934,0.00007817395,0.00010830289,0.0011536403,0.9912783,0.00014976192,0.0017951991,0.000044613687,0.00033386677],"about_ca_topic_score_codex":0.00017075264,"about_ca_topic_score_gemma":0.00013164603,"teacher_disagreement_score":0.8095179,"about_ca_system_score_codex":0.000053638047,"about_ca_system_score_gemma":0.00006681898,"threshold_uncertainty_score":0.99984765},"labels":[],"label_agreement":null},{"id":"W7154350435","doi":"10.1145/3773699.3774349","title":"Detailed Abstract Images from Automated Prompts","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Matching (statistics); Coherence (philosophical gambling strategy); Process (computing); Image (mathematics); Subject (documents); Sample (material); Visualization; Template matching","score_opus":0.011932861984739336,"score_gpt":0.2580419527982475,"score_spread":0.24610909081350815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7154350435","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010833283,0.0022427614,0.9012801,0.0054231025,0.0040025846,0.0007728648,0.000046416542,0.0013119896,0.07408689],"genre_scores_gemma":[0.92941236,0.0001395482,0.058551025,0.00097519974,0.00028403403,0.000024482026,0.000012084985,0.000018570407,0.010582706],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964798,0.0002417977,0.00081812683,0.0012935475,0.00038794804,0.000778756],"domain_scores_gemma":[0.99755317,0.00043586883,0.0002352335,0.0012256618,0.00035088364,0.00019918484],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00041238384,0.00054685626,0.0006334661,0.00021532159,0.0004934118,0.0014148358,0.0015144743,0.0002536117,0.0023776174],"category_scores_gemma":[0.00018902608,0.00048184025,0.00028185916,0.0010583416,0.00020261851,0.0011591155,0.0007574372,0.0003326894,0.000793383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001347382,0.0012527473,0.0037986601,0.00012153252,0.0017623182,0.0002198401,0.0008829415,0.016589863,0.09434121,0.0047505153,0.32994217,0.5462035],"study_design_scores_gemma":[0.00074186607,0.000050362363,0.08277538,0.00020755945,0.00009847955,8.9568016e-7,0.000046945075,0.8306153,0.078962415,0.0016959863,0.004304255,0.0005005757],"about_ca_topic_score_codex":0.0007285454,"about_ca_topic_score_gemma":0.00018008282,"teacher_disagreement_score":0.91857904,"about_ca_system_score_codex":0.00009756381,"about_ca_system_score_gemma":0.00047617964,"threshold_uncertainty_score":0.9999846},"labels":[],"label_agreement":null},{"id":"W7154993737","doi":"10.5281/zenodo.17238423","title":"A Review of 2D Diffusion Methods for 3D Medical Image Synthesis","year":2025,"lang":"en","type":"preprint","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; University of Saskatchewan","funders":"","keywords":"Image (mathematics); Image processing; Diffusion; Image synthesis; Pattern recognition (psychology); Noise (video)","score_opus":0.03952816596066888,"score_gpt":0.328394051348391,"score_spread":0.2888658853877221,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7154993737","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000043606196,0.0046499106,0.96842104,0.003048705,0.00034666606,0.00096709724,0.00023416658,0.0003464552,0.021981603],"genre_scores_gemma":[0.0006788061,0.031213924,0.9637276,0.001537753,0.00041031436,0.0000017685945,0.0008217542,0.00089732243,0.00071073626],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959341,0.0017390512,0.0006232027,0.00083093025,0.0005013329,0.0003713804],"domain_scores_gemma":[0.9963697,0.0004265548,0.00036615977,0.0012354917,0.0013963828,0.00020570778],"candidate_categories":["metaresearch","metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0038115364,0.00026990048,0.0005867355,0.00026457227,0.0009063682,0.0004960451,0.003786373,0.00019902507,0.003989555],"category_scores_gemma":[0.009727199,0.00025532005,0.0002610532,0.0005736288,0.00017958577,0.00020592962,0.008886063,0.00045470672,0.0001902359],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016406782,0.00011512722,6.666822e-8,0.004187684,0.000088475805,0.0000026977666,0.00017030757,0.000028219121,0.0006372153,0.001670568,0.1514342,0.84164906],"study_design_scores_gemma":[0.00019627663,0.00007726333,0.000008240224,0.005378946,0.00007655414,0.000013241385,0.000014308734,0.08077245,0.0015943669,0.0006603943,0.9109525,0.00025544508],"about_ca_topic_score_codex":0.000018623225,"about_ca_topic_score_gemma":1.4763185e-7,"teacher_disagreement_score":0.8413936,"about_ca_system_score_codex":0.00011305993,"about_ca_system_score_gemma":0.000041893396,"threshold_uncertainty_score":0.9999899},"labels":[],"label_agreement":null},{"id":"W7160456564","doi":"","title":"Discovering Latent Graphs with GFlowNets for Diverse Conditional Image Generation.","year":2025,"lang":"en","type":"article","venue":"PubMed","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Image (mathematics); Generative grammar; Fidelity; Generative model; Parameterized complexity; Representation (politics); Counterfactual thinking","score_opus":0.02147200335181266,"score_gpt":0.21575785225407315,"score_spread":0.1942858489022605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160456564","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006601306,0.000054873413,0.9900492,0.0012665554,0.00042640138,0.00058687216,0.000022510023,0.0000507597,0.00094154646],"genre_scores_gemma":[0.95244473,0.000008793604,0.04481476,0.00047957126,0.00013120538,0.001188484,0.000029304607,0.000005500064,0.0008976378],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999171,0.000028170454,0.00011984243,0.00029781432,0.00012507841,0.00025809417],"domain_scores_gemma":[0.9995387,0.000056271587,0.00004373579,0.00020675211,0.00009751096,0.00005701105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001465625,0.00010640908,0.000110116234,0.0000783869,0.00021654715,0.00023092536,0.00025586798,0.000025063177,0.0000056532012],"category_scores_gemma":[0.000030654195,0.00008304473,0.00006341176,0.00021773629,0.0000492961,0.0005746572,0.000095304,0.000041820233,0.000002451049],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001481251,0.00038957893,0.0053893398,0.00008124065,0.0007774345,0.000040088074,0.00041580194,0.08442858,0.0044388836,0.41268778,0.10545809,0.38574508],"study_design_scores_gemma":[0.004202096,0.00011599191,0.2792494,0.000035603076,0.00014832299,0.000009804306,0.00006874191,0.61618036,0.04493462,0.023547085,0.030495048,0.0010129199],"about_ca_topic_score_codex":0.000013969397,"about_ca_topic_score_gemma":0.000027570415,"teacher_disagreement_score":0.94584346,"about_ca_system_score_codex":0.000034189048,"about_ca_system_score_gemma":0.000033419583,"threshold_uncertainty_score":0.3386466},"labels":[],"label_agreement":null},{"id":"W7163145894","doi":"10.1109/icsm64417.2025.11541528","title":"HistDiff: Diffusion Models Empowered by Histogram Matching for Reducing Content Color Interference in Style Transfer","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Diffusion; Matching (statistics); Interference (communication); Histogram; Pattern recognition (psychology); Content (measure theory); Transfer (computing)","score_opus":0.03626797243467558,"score_gpt":0.2564377203074086,"score_spread":0.220169747872733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7163145894","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025377283,0.0016125565,0.96294785,0.0024338213,0.002262045,0.0017576531,0.0000495397,0.000087332475,0.0034718998],"genre_scores_gemma":[0.95739424,0.00030135218,0.028724724,0.0009131218,0.000057215326,0.00020921092,0.00001805131,0.000029826757,0.012352284],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99562734,0.00033040493,0.0012606392,0.0015148949,0.0002912281,0.000975517],"domain_scores_gemma":[0.9981275,0.0004864148,0.00013445178,0.0007629808,0.0002919251,0.00019672148],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00078401587,0.00061131874,0.00090294454,0.00034251765,0.00047586043,0.0005883396,0.0012741981,0.00028213926,0.00011793019],"category_scores_gemma":[0.00008124025,0.0005757233,0.00036218038,0.00068872713,0.00019190364,0.0010799395,0.00042202388,0.00041428828,0.0000054664574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015617465,0.0031519039,0.00012040955,0.0005392007,0.00036243515,0.000019312547,0.019224364,0.06486846,0.4410296,0.045471698,0.030699555,0.3929513],"study_design_scores_gemma":[0.002317144,0.00040575242,0.00006425835,0.0007535231,0.000059024176,0.0000013231457,0.000772177,0.97564673,0.013764598,0.0029772765,0.0026342971,0.00060387515],"about_ca_topic_score_codex":0.003011741,"about_ca_topic_score_gemma":0.0007000203,"teacher_disagreement_score":0.9342232,"about_ca_system_score_codex":0.00059151783,"about_ca_system_score_gemma":0.00027872427,"threshold_uncertainty_score":0.99966943},"labels":[],"label_agreement":null},{"id":"W7163176405","doi":"10.1109/icsm64417.2025.11541558","title":"ReSimX: A Local Feature-Aware Framework for Real2Sim and Sim2Real Transfer","year":2025,"lang":"","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Transfer (computing); Work (physics); Stability (learning theory); Term (time); Key (lock)","score_opus":0.01288503367512756,"score_gpt":0.26832372799533905,"score_spread":0.2554386943202115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7163176405","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000083935236,0.0019520941,0.97065276,0.020427538,0.0015020644,0.0010199571,0.000044888126,0.00009674072,0.00422005],"genre_scores_gemma":[0.83425874,0.00045379315,0.15300196,0.0038899353,0.00050183974,0.000075429925,0.0000070448214,0.000028851766,0.0077824257],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99668735,0.00027596822,0.0005004612,0.0013618956,0.00029662024,0.00087770104],"domain_scores_gemma":[0.99718595,0.0014040141,0.0000544103,0.00073879457,0.0003374267,0.00027943752],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006168109,0.0005461586,0.0006777293,0.0001907734,0.000733203,0.0007338078,0.00072071695,0.00059980556,0.00010267033],"category_scores_gemma":[0.0001955411,0.00048260792,0.00029762127,0.000887683,0.0004591516,0.0005226778,0.00030123288,0.00051679,0.000009423175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042304472,0.00019640075,0.00013005298,0.00026861473,0.00035387595,0.000017358063,0.0007134928,0.0023814572,0.00011037919,0.29332438,0.07086853,0.6312124],"study_design_scores_gemma":[0.0013720067,0.0004877306,0.00080445636,0.0005328604,0.00021861024,0.0000052152272,0.00034048737,0.88776743,0.006012542,0.05896352,0.042758178,0.0007369808],"about_ca_topic_score_codex":0.00012617826,"about_ca_topic_score_gemma":0.00017661817,"teacher_disagreement_score":0.88538593,"about_ca_system_score_codex":0.00007533413,"about_ca_system_score_gemma":0.00035109665,"threshold_uncertainty_score":0.99976254},"labels":[],"label_agreement":null},{"id":"W779272567","doi":"","title":"Understanding deep architectures and the effect of unsupervised pre-training","year":2011,"lang":"en","type":"dissertation","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Artificial intelligence; Deep learning; Computer science; Generalization; Machine learning; Artificial neural network; Class (philosophy); Unsupervised learning; Set (abstract data type); Process (computing); Variation (astronomy); Deep belief network; Deep neural networks; Restricted Boltzmann machine; Mathematics","score_opus":0.03532544690944602,"score_gpt":0.24182959386768393,"score_spread":0.2065041469582379,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W779272567","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021927498,0.00080416055,0.94605315,0.0000524277,0.00052674813,0.0005261603,9.422822e-7,0.00005308722,0.030055834],"genre_scores_gemma":[0.9936066,0.000036760863,0.005591712,0.000028840137,0.000063356936,0.000019228508,0.000007711865,0.000012955302,0.00063281995],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988336,0.00030588685,0.00021016113,0.00029600746,0.00017620936,0.00017816461],"domain_scores_gemma":[0.9987628,0.00071779365,0.00014871404,0.00030291645,0.000027614586,0.000040179682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005011628,0.00021439268,0.00038302495,0.00008906432,0.00015189644,0.000092870054,0.00048086394,0.000102541235,0.000026916046],"category_scores_gemma":[0.00009172003,0.000114963994,0.00011976848,0.00013951956,0.00010296894,0.00007279741,0.000065608336,0.00016703863,8.2990016e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029697001,0.000047154375,0.0007763002,0.0011605086,0.001711082,0.00001661869,0.16814055,0.007314583,0.0038790181,0.22881773,0.00046901562,0.5846977],"study_design_scores_gemma":[0.009549131,0.001881052,0.008383546,0.0010699977,0.0008534067,0.000028097571,0.0059408024,0.7588009,0.110727645,0.10055706,0.00020627539,0.0020020506],"about_ca_topic_score_codex":0.00011135592,"about_ca_topic_score_gemma":0.00027965347,"teacher_disagreement_score":0.9716791,"about_ca_system_score_codex":0.000011308943,"about_ca_system_score_gemma":0.000027925023,"threshold_uncertainty_score":0.46880955},"labels":[],"label_agreement":null}]}