{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":668,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":668,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"e05165058cd2","filters":{"topic":"Generative Adversarial Networks and Image Synthesis"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02716068263395695,"gpt":0.3089172964918412,"spread":0.2817566138578843,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0003331136,0.0002719425,0.0007841624,0.00009477518,0.00009075168,0.0001836859,0.00109493,0.001875155,0.00001934578],"category_scores_gemma":[0.000144473,0.0001942223,0.0002757239,0.0004769405,0.00001659082,0.0002027487,0.0003120626,0.004098183,0.0002314278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006610643,"about_ca_system_score_gemma":0.0001555423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001234231,"about_ca_topic_score_gemma":0.000001289982,"domain_scores_codex":[0.9985898,0.0002677561,0.0001941172,0.0004369398,0.0002733795,0.0002380786],"domain_scores_gemma":[0.9990619,0.00009629477,0.0001706723,0.000446208,0.0001239092,0.0001009787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[1.08829e-7,0.000004212882,5.178169e-8,0.0002780778,0.00002746967,0.00001214926,0.00001970261,0.00006594797,1.336587e-8,0.0007717669,0.007660908,0.9911596],"study_design_scores_gemma":[0.00003005479,0.00001520424,9.097077e-8,0.0007100464,0.00006011538,0.00001690781,0.000001873409,0.003742841,1.836967e-7,0.0001104533,0.9950948,0.0002174048],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.325644e-9,0.8822984,0.1116949,0.00004497925,0.0009406568,0.0001367697,7.878148e-7,0.00009262008,0.004790902],"genre_scores_gemma":[0.000001707073,0.98142,0.01628636,0.0001149303,0.0006859018,0.00001245236,0.00001712317,0.00002055418,0.001440957],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9909422,"threshold_uncertainty_score":0.9994206,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05331489208555869,"gpt":0.2591423312155596,"spread":0.205827439130001,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.000148797,0.00008480739,0.0001306796,0.00001430339,0.00028238,0.00004768344,0.0353996,0.00003687773,0.000008940502],"category_scores_gemma":[0.003149832,0.00006147038,0.0001100907,0.0004378811,0.0001723544,0.0002207331,0.02729277,0.0001642531,0.0000113338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001286333,"about_ca_system_score_gemma":0.00004931738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001655089,"about_ca_topic_score_gemma":0.00000871448,"domain_scores_codex":[0.9991148,0.0002947902,0.0001962648,0.000160802,0.0001163084,0.0001170227],"domain_scores_gemma":[0.9821339,0.0002464248,0.0001423123,0.01731137,0.0001114604,0.00005454905],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004294862,0.0002956102,0.001669282,0.00001489982,0.0003671192,0.000001022783,0.007507393,0.2461294,0.01583268,0.2335683,0.4549832,0.03958823],"study_design_scores_gemma":[0.000292579,0.0000424712,0.001002269,0.0000138961,0.00002358507,9.981933e-7,0.00006174556,0.9495769,0.006190324,0.01834853,0.02429801,0.0001487249],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002534975,0.0009048269,0.7211376,0.2738786,0.000314997,0.0002131969,0.000004091875,0.00005661614,0.003236613],"genre_scores_gemma":[0.6458602,0.000102226,0.3524299,0.001463609,0.0001053688,0.000007969606,0.000001776158,0.000004452052,0.00002446315],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7034475,"threshold_uncertainty_score":0.9805743,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03053323629475789,"gpt":0.2802265611432088,"spread":0.2496933248484509,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002740815,0.0002227108,0.0001759784,0.0002067379,0.0002447224,0.0003454382,0.001088244,0.00009961436,0.0004208186],"category_scores_gemma":[0.0009773418,0.0001942205,0.00006261079,0.0003581141,0.00005108504,0.0004365119,0.0002574299,0.001087475,0.0001512234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000236073,"about_ca_system_score_gemma":0.0001013737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003264335,"about_ca_topic_score_gemma":0.0001386816,"domain_scores_codex":[0.9984215,0.0001583835,0.0002669985,0.0005001671,0.0003954138,0.0002574635],"domain_scores_gemma":[0.9986144,0.0001871024,0.0001851649,0.0003522319,0.0005506591,0.0001104651],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001517561,0.0001794527,0.005260977,0.000008153805,0.0001690517,0.00007258736,0.0006958654,0.01241137,0.3219064,0.3174737,0.0009564979,0.3407141],"study_design_scores_gemma":[0.0003722703,0.0001338696,0.002194811,0.00001802524,0.00000494069,0.00001039932,0.00001507466,0.970197,0.005083253,0.001797459,0.01992706,0.0002458467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1044088,0.00004428881,0.7450849,0.01518962,0.009762648,0.0004232972,0.00003929313,0.0008622767,0.1241849],"genre_scores_gemma":[0.978038,0.00002627783,0.01651204,0.0003397272,0.0005923749,0.00001359958,0.00004411861,0.00001737927,0.004416505],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9577856,"threshold_uncertainty_score":0.7920082,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02008602172927967,"gpt":0.1949792179919375,"spread":0.1748931962626578,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000958231,0.0001092668,0.0001132694,0.00004438759,0.0004697117,0.0001738365,0.0001679192,0.00002749358,0.000004860242],"category_scores_gemma":[0.00001448743,0.00007960737,0.00001892843,0.0001556651,0.00007686235,0.0006689628,0.00007771909,0.0000980691,0.000002036744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001352633,"about_ca_system_score_gemma":0.0000300035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009891674,"about_ca_topic_score_gemma":0.00003772408,"domain_scores_codex":[0.9992583,0.00004115374,0.00009084059,0.0002702157,0.0001380344,0.0002014898],"domain_scores_gemma":[0.9995793,0.0001038691,0.00004731185,0.0001702334,0.00003159777,0.00006766007],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000801093,0.0002244534,0.02236671,0.00003676911,0.0002462273,0.0008087842,0.01204232,0.6771725,0.03052167,0.01147595,0.01075647,0.2342681],"study_design_scores_gemma":[0.0005996556,0.0001411634,0.02494555,0.00007521617,0.0000168665,0.00124092,0.0003833821,0.9538788,0.01653717,0.0001454807,0.001484771,0.000551063],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02338709,0.0002156438,0.970526,0.0005810917,0.00007231785,0.00005713084,8.946358e-8,0.0001023867,0.005058211],"genre_scores_gemma":[0.5865664,0.00001437107,0.4130088,0.0001666312,0.00004216246,7.4763e-7,1.92508e-7,0.000004429533,0.0001963054],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5631793,"threshold_uncertainty_score":0.361269,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Training (meteorology); Layer (electronics); Computer science; Artificial intelligence; Geography; Materials science; Composite material; Meteorology","retraction":null,"screen_n_in":null,"score":{"opus":0.08055135584822232,"gpt":0.2532535131225538,"spread":0.1727021572743315,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006693861,0.0004295942,0.0005556962,0.00008978524,0.0001830086,0.0001170375,0.001816233,0.0003132407,0.00003626679],"category_scores_gemma":[0.00001672937,0.0003145153,0.0003041899,0.00001725307,0.0002859478,0.0001000964,0.0005901618,0.0005446562,0.000009603277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002700518,"about_ca_system_score_gemma":0.00004670768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000100084,"about_ca_topic_score_gemma":0.00008846364,"domain_scores_codex":[0.9980053,0.00008389567,0.0005262198,0.000509606,0.0004172627,0.0004577224],"domain_scores_gemma":[0.9976982,0.0003499695,0.0004572661,0.001223138,0.0001579344,0.0001135341],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002874132,0.00001053973,3.294383e-7,0.00002417937,0.000337181,0.00003991565,0.002338321,0.009020125,0.00009271381,0.436746,0.001257177,0.5501048],"study_design_scores_gemma":[0.0007308588,0.0002391676,0.00001540011,0.0004693798,0.0004247024,0.00004885419,0.00003621306,0.303979,0.002970564,0.02740381,0.6622807,0.001401305],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.000001509142,0.001266034,0.4681944,0.00002054213,0.0004007906,0.0002405644,0.000003688946,0.0000526501,0.5298198],"genre_scores_gemma":[0.1223101,0.0002124709,0.02546614,0.0008789221,0.002834658,0.00004223757,0.0000112591,0.0001868422,0.8480574],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.6610236,"threshold_uncertainty_score":0.9999307,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0456119184112788,"gpt":0.1738836741732009,"spread":0.1282717557619221,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004141633,0.0005574895,0.0006014481,0.0001974742,0.0003399266,0.0003219056,0.002417743,0.0005193339,0.00007100924],"category_scores_gemma":[0.00005975835,0.0006081343,0.0004197589,0.0005136099,0.0001725606,0.0004878675,0.002828477,0.0008347105,0.0001159319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002034553,"about_ca_system_score_gemma":0.0002103774,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001343563,"about_ca_topic_score_gemma":0.00005072628,"domain_scores_codex":[0.9967249,0.0005469933,0.0002987216,0.001694569,0.0001217423,0.0006130766],"domain_scores_gemma":[0.9972146,0.0001955359,0.0003769758,0.001669118,0.0002631725,0.0002805794],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002347291,0.00004328591,0.0001098454,0.00001061665,0.0001422945,0.00009814592,0.00008637579,0.9396876,0.00001697353,0.05484639,0.003488502,0.001446512],"study_design_scores_gemma":[0.0005059288,0.00006168948,0.000130396,0.00004442269,0.00008523063,0.00000251372,0.00001613491,0.9789254,0.0001498688,0.0168035,0.002620001,0.0006549027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00278563,0.0001138434,0.9889777,0.0002353434,0.00312924,0.0003416308,0.00001014408,0.0002840158,0.004122399],"genre_scores_gemma":[0.9845417,0.0001843492,0.0119068,0.0004213016,0.001355188,0.000002164698,0.00003060217,0.00003133806,0.001526542],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9817561,"threshold_uncertainty_score":0.999637,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0418546809063375,"gpt":0.2898767614772941,"spread":0.2480220805709566,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000515379,0.000338563,0.0003379858,0.0001059234,0.0005786031,0.0006208465,0.0009622183,0.0001220077,0.0001728082],"category_scores_gemma":[0.00002249694,0.0002951276,0.00009704982,0.0007527636,0.0002504126,0.002030638,0.0001518026,0.0002144525,0.0002062895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005368607,"about_ca_system_score_gemma":0.0002569673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001496216,"about_ca_topic_score_gemma":0.00004971409,"domain_scores_codex":[0.9976036,0.0002526361,0.0003791189,0.0007917348,0.0003882872,0.0005846126],"domain_scores_gemma":[0.9985252,0.00005530435,0.0002054226,0.0004909323,0.0004873392,0.0002357714],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001203868,0.0003005027,0.00005987062,0.0000408831,0.00008500378,0.00005819276,0.001272849,0.03852045,0.03820397,0.003887539,0.02034983,0.8971005],"study_design_scores_gemma":[0.000496922,0.0004486855,0.0002121446,0.00006962534,0.00002518705,0.00001748968,0.00001150926,0.9736925,0.009490452,0.001988459,0.0131029,0.0004440604],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006140013,0.001325667,0.9929549,0.0004448648,0.001038408,0.0001816897,0.000002780667,0.0002515802,0.003186176],"genre_scores_gemma":[0.8881054,0.00006321449,0.1033505,0.001779243,0.005995813,0.00001531236,0.000008452913,0.00003597771,0.0006461281],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9351721,"threshold_uncertainty_score":0.9999501,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03733683725891546,"gpt":0.2967167350036891,"spread":0.2593798977447736,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001001245,0.0005890717,0.0006141935,0.0007608515,0.0003306731,0.0006912251,0.002385871,0.0002931915,0.00004013835],"category_scores_gemma":[0.0005715084,0.0005120563,0.0001494239,0.0008750447,0.0003441351,0.00100729,0.00158409,0.0007959654,0.0001207081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002315601,"about_ca_system_score_gemma":0.0006803909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003677785,"about_ca_topic_score_gemma":0.00007571177,"domain_scores_codex":[0.9958168,0.00008657922,0.0005966004,0.001497088,0.0009918804,0.001011061],"domain_scores_gemma":[0.9968694,0.0008121944,0.000253259,0.001326315,0.0002955397,0.0004432982],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009352327,0.00003339007,0.00002382719,0.00001086646,0.00002054653,0.0001172477,0.001298498,0.03132127,0.0004206346,0.01193183,0.001972985,0.9528396],"study_design_scores_gemma":[0.0003655136,0.0003289326,0.0003842278,0.000395691,0.00003158458,0.0002275762,6.357959e-7,0.8900129,0.001409656,0.029257,0.07602128,0.001565057],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001067809,0.0003113007,0.9862556,0.004150357,0.00215214,0.0004027081,0.000004489889,0.0001567707,0.006555964],"genre_scores_gemma":[0.04297308,0.00003447022,0.9515081,0.002924601,0.001828994,0.00001289951,0.000003604676,0.00004009884,0.0006741677],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9512745,"threshold_uncertainty_score":0.9997331,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0425718938893782,"gpt":0.2904346791370451,"spread":0.2478627852476669,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007062188,0.0004213082,0.0005036045,0.0001659393,0.0006053749,0.001681919,0.001370292,0.0002570258,0.00007575951],"category_scores_gemma":[0.0002735224,0.0003954559,0.0003376005,0.00009756168,0.00006427742,0.0007375372,0.0009174438,0.0004654486,0.0001015991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000467224,"about_ca_system_score_gemma":0.0001786578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008443422,"about_ca_topic_score_gemma":0.00004175877,"domain_scores_codex":[0.9975011,0.000172777,0.0004022649,0.001099469,0.000328744,0.0004956898],"domain_scores_gemma":[0.9977679,0.0002373097,0.0002329026,0.001181456,0.0003876515,0.000192738],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001423724,0.0002414083,0.00007154441,0.0004655189,0.0004651866,0.0000686806,0.006183532,0.1131673,0.0654531,0.00529349,0.0323738,0.7760741],"study_design_scores_gemma":[0.0006885513,0.0001437451,0.0003914174,0.0001054015,0.00005472271,0.000004114824,0.00004204135,0.9546256,0.01452332,0.00412478,0.02449664,0.0007996385],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000436294,0.000100001,0.9822923,0.005261365,0.001231385,0.001109247,0.00001508484,0.0002729568,0.009281356],"genre_scores_gemma":[0.1651932,0.00004105608,0.830521,0.0002796602,0.0008830284,0.0001997051,0.00007016026,0.00004771824,0.002764493],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8414584,"threshold_uncertainty_score":0.9998497,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.008837415005454985,"gpt":0.2244531326126371,"spread":0.2156157176071821,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007442317,0.00007244344,0.00007499436,0.00002954774,0.00007674746,0.000111594,0.0003773601,0.00001990597,0.00007608039],"category_scores_gemma":[0.00001447385,0.0000535797,0.0000411838,0.0001480978,0.000009186461,0.0003408994,0.00004471502,0.00003730603,0.0001058879],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005779497,"about_ca_system_score_gemma":0.000007538472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001029596,"about_ca_topic_score_gemma":0.000007680269,"domain_scores_codex":[0.9994676,0.00002544562,0.00008256534,0.0001808777,0.00009181116,0.0001517053],"domain_scores_gemma":[0.9996194,0.00001992272,0.00001866026,0.0002614342,0.00002968318,0.00005085618],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002114869,0.00005255027,0.0001118702,6.735004e-7,0.000008181611,0.0000108464,0.0001493245,0.00405359,0.002116857,0.1086648,0.01274448,0.8720847],"study_design_scores_gemma":[0.0001109143,0.00006585087,0.005412849,0.000001894476,0.000002101692,0.000005249643,0.000004085841,0.9661779,0.002986514,0.01452656,0.01056608,0.0001399493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002040473,0.0001124328,0.9446248,0.003489915,0.0001638625,0.00003654399,5.990948e-8,0.00011593,0.05125244],"genre_scores_gemma":[0.7978938,0.000008911165,0.1980465,0.002487388,0.0001456261,9.737957e-7,4.184863e-7,0.000001880153,0.001414424],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9621243,"threshold_uncertainty_score":0.2184917,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02158988493832117,"gpt":0.2493163160146387,"spread":0.2277264310763175,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004665436,0.0004550352,0.0004824332,0.0002261509,0.0003462131,0.0007988625,0.002786269,0.0001494178,0.001269862],"category_scores_gemma":[0.00005105172,0.0004147108,0.0002952469,0.0003751624,0.00004775709,0.0005720418,0.01180593,0.0007457973,0.0001773627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001306546,"about_ca_system_score_gemma":0.0001369781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002435122,"about_ca_topic_score_gemma":0.00001753957,"domain_scores_codex":[0.9967303,0.0002943514,0.000418728,0.001371916,0.000654804,0.0005299156],"domain_scores_gemma":[0.9974124,0.0001058461,0.0001636545,0.001912889,0.000162358,0.0002427987],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000391259,0.0005172855,0.00003599886,0.0001428413,0.000204408,0.0003021789,0.003048563,0.5054348,0.03476158,0.02579844,0.3532194,0.07649538],"study_design_scores_gemma":[0.0001722094,0.00005571801,0.0001437802,0.0000309014,0.00001814537,0.000003266482,0.00004490796,0.9616217,0.001910978,0.01945554,0.01584503,0.0006978343],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006506222,0.0000939723,0.942965,0.0061538,0.00167571,0.0005704717,0.00002608594,0.0003636598,0.04750063],"genre_scores_gemma":[0.08579796,0.0001190054,0.9021347,0.004369302,0.0005917549,0.0002543443,0.00004485746,0.00005626174,0.006631793],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4561869,"threshold_uncertainty_score":0.9998305,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2337787555715836,"gpt":0.422125356263777,"spread":0.1883466006921934,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006038809,0.0004538315,0.001912497,0.0002731394,0.0002346245,0.0001449805,0.001924297,0.000231276,0.000001377172],"category_scores_gemma":[0.0006638703,0.0003884178,0.0002536182,0.001651314,0.0001221946,0.0001538739,0.003061478,0.0003331819,0.00001527092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003414012,"about_ca_system_score_gemma":0.0001758853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009615691,"about_ca_topic_score_gemma":0.00005514855,"domain_scores_codex":[0.9890503,0.008524125,0.000925885,0.0009161353,0.0002173575,0.0003662473],"domain_scores_gemma":[0.9863213,0.01078217,0.0007429154,0.001609657,0.0004280883,0.0001158137],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[2.762829e-7,0.00002435889,0.00001234732,0.001502268,0.0001202202,9.91492e-7,0.00004536616,0.0006629907,9.445694e-7,0.0003415873,0.0001329425,0.9971557],"study_design_scores_gemma":[0.0004190091,0.000123896,0.004764354,0.008175025,0.0004272099,0.00003476091,0.00002130144,0.702764,0.00000631624,0.005118412,0.2762758,0.001869947],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.000001137732,0.469061,0.5302219,0.000004381113,0.0001710475,0.0003932768,0.00002913358,0.00008845182,0.00002969307],"genre_scores_gemma":[0.00005176151,0.8132886,0.1863408,0.00001186671,0.0001021955,0.00002957326,0.00009278674,0.00004538455,0.00003702114],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.9952857,"threshold_uncertainty_score":0.9998568,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04449516924581683,"gpt":0.3316204651828682,"spread":0.2871252959370514,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000420618,0.0001529782,0.0003588951,0.0001469414,0.0001038891,0.00005592259,0.0002224461,0.00002484976,0.00008895501],"category_scores_gemma":[0.00001485556,0.0001277755,0.0001417845,0.0008284766,0.00004272096,0.0003470081,0.000007554739,0.0001630872,0.0000019495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008654119,"about_ca_system_score_gemma":0.00001139009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001332067,"about_ca_topic_score_gemma":0.00007124227,"domain_scores_codex":[0.9986303,0.0002825353,0.0003611585,0.0004550962,0.0001483435,0.0001225856],"domain_scores_gemma":[0.999293,0.00007110955,0.0001181804,0.0002896758,0.00009178111,0.0001362888],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004016257,0.00004592269,0.00003408531,0.0002028985,0.0001490167,5.320476e-7,0.0002553187,0.01119462,0.001121404,0.00004543926,0.00001384759,0.9869329],"study_design_scores_gemma":[0.00004379713,0.000171605,0.00009473818,0.0001330346,0.0005386784,0.0000037089,0.0000274797,0.8620876,0.1355788,0.00004869547,0.001081908,0.0001899326],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001560562,0.005882774,0.9913683,0.002288009,0.0001638775,0.0000969653,0.00001006436,0.00002701196,0.000006959345],"genre_scores_gemma":[0.9341722,0.02261123,0.04226527,0.0008382693,0.00008885038,0.000009209375,0.000003847021,0.000006633366,0.000004483806],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.986743,"threshold_uncertainty_score":0.5210535,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03353096239121345,"gpt":0.2989716356777909,"spread":0.2654406732865774,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000945061,0.00008143982,0.0001143218,0.0001006301,0.00003336517,0.0000175614,0.0002045515,0.00003454102,0.00003188794],"category_scores_gemma":[0.00004116579,0.00005140446,0.00002760538,0.0002364751,0.00002979165,0.000122738,0.00001851638,0.00004511088,6.992987e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002074062,"about_ca_system_score_gemma":0.00003551699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006524801,"about_ca_topic_score_gemma":0.0001433966,"domain_scores_codex":[0.9988621,0.0001374079,0.0001892356,0.0001958866,0.0004995156,0.0001157845],"domain_scores_gemma":[0.9992151,0.0001122288,0.0001235896,0.0002675842,0.0002396394,0.00004181088],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005866744,0.0003807918,0.01319596,0.00001267354,0.00005609216,4.814183e-7,0.005501947,0.7699989,0.02103635,0.004458793,0.00002035509,0.185279],"study_design_scores_gemma":[0.0002233433,0.0005141468,0.2442944,0.000008308315,0.00001566335,4.709169e-7,0.00003946731,0.6921998,0.06127134,0.001354497,0.000007198092,0.00007130897],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3269039,0.000005430064,0.6717619,0.00004024951,0.00003476304,0.0001330495,3.147424e-7,0.00001300699,0.001107399],"genre_scores_gemma":[0.9424301,2.706842e-7,0.05749319,0.00003545961,0.0000277835,0.000002097983,0.000001769227,0.000003605438,0.00000575057],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6155262,"threshold_uncertainty_score":0.2096213,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06044979363662861,"gpt":0.2499212846951548,"spread":0.1894714910585262,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001275268,0.00009158936,0.0001012105,0.0000675512,0.0001922963,0.0001285571,0.0001188664,0.00003174547,0.000003058563],"category_scores_gemma":[0.00001453857,0.00008704609,0.00002577838,0.0001558125,0.00002654358,0.0006935199,0.000074557,0.00007822394,0.000005263392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001626941,"about_ca_system_score_gemma":0.00001028869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001155603,"about_ca_topic_score_gemma":0.000008610305,"domain_scores_codex":[0.9992864,0.00009212625,0.0001366195,0.0002424212,0.0001049893,0.0001374405],"domain_scores_gemma":[0.9996639,0.00007570913,0.00007411301,0.00008634574,0.00004819922,0.00005171075],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002562349,0.0000517959,0.02326751,0.00004204013,0.00007012031,0.00002879417,0.01347803,0.09588788,0.006404745,0.007250996,0.0002376217,0.8532549],"study_design_scores_gemma":[0.0002499283,0.0001225293,0.1546903,0.00002255626,0.00001521457,0.00001719558,0.00009327009,0.818454,0.002803896,0.02331803,0.00001776954,0.0001953062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.367521,0.00002139774,0.6318885,0.0001011634,0.000146921,0.00005920463,2.598728e-7,0.00007646799,0.0001850513],"genre_scores_gemma":[0.9343232,0.000002009131,0.06545926,0.0001150609,0.0000849249,0.000001897373,0.000002369745,0.000005681586,0.000005584167],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8530595,"threshold_uncertainty_score":0.3549637,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0162958313026846,"gpt":0.2431024191057949,"spread":0.2268065878031103,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006019807,0.0001006219,0.0001348638,0.00007649858,0.0001605759,0.0000380114,0.0001563491,0.00003832666,0.000006094457],"category_scores_gemma":[0.00004621413,0.00009190133,0.00003966279,0.0003144181,0.00006975038,0.0004028658,0.00009933245,0.00007933594,0.000001628778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000798166,"about_ca_system_score_gemma":0.00001510824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003873924,"about_ca_topic_score_gemma":0.000004021493,"domain_scores_codex":[0.9990759,0.0001137325,0.0002256536,0.0002578928,0.0001966666,0.000130139],"domain_scores_gemma":[0.9993596,0.0001773706,0.0001256254,0.0001374484,0.000149306,0.00005063664],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003837966,0.00007458568,0.009501885,0.000007108506,0.00003150289,0.00002911709,0.0009652235,0.9329822,0.002046608,0.001616705,0.001790727,0.05091596],"study_design_scores_gemma":[0.0002154338,0.00007185451,0.1710982,0.000003410594,0.000003305739,0.00002998533,0.000006189799,0.8277473,0.0001975779,0.0005234829,0.000028379,0.0000748677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2396715,0.0002633251,0.7591361,0.0003228001,0.0002339297,0.00009664597,9.231556e-7,0.00004491628,0.0002298843],"genre_scores_gemma":[0.9735461,0.00003638231,0.02614092,0.0001470191,0.0000803973,0.000003177591,0.00001239307,0.000005578016,0.00002804345],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7338746,"threshold_uncertainty_score":0.3747628,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.005286602652571105,"gpt":0.1985803319431033,"spread":0.1932937292905322,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001566238,0.0000808415,0.00007623006,0.00004025466,0.0001692913,0.0001666278,0.0005681986,0.00004930188,0.0003454823],"category_scores_gemma":[0.00009075218,0.00006648061,0.00003585799,0.0001845366,0.00002372573,0.0005490356,0.000195596,0.0001692951,0.00005409074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005322991,"about_ca_system_score_gemma":0.00001200846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002261375,"about_ca_topic_score_gemma":0.00005357153,"domain_scores_codex":[0.9993546,0.0000406663,0.0001034414,0.0002137933,0.0001201608,0.0001673534],"domain_scores_gemma":[0.9993931,0.00004493438,0.00004235039,0.0003943498,0.0000621181,0.00006316668],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001694393,0.00002661626,0.0002688803,0.000001660656,0.00001032324,0.000003672995,0.0001691079,0.815098,0.005928837,0.01307886,0.0008606356,0.1645516],"study_design_scores_gemma":[0.0001103665,0.00001816465,0.0002509984,0.000001104029,0.000001951916,0.000003922239,0.000006649467,0.9925202,0.003237118,0.0008006677,0.002950405,0.00009851385],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001285757,0.00001375209,0.9776438,0.0008075523,0.0005393652,0.00004738039,4.287946e-8,0.0001415925,0.02067793],"genre_scores_gemma":[0.4084074,0.00000425946,0.5904462,0.0001594584,0.0001404686,0.000003142782,9.86149e-7,0.000004833653,0.0008331783],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4082789,"threshold_uncertainty_score":0.3782789,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2753690116820647,"gpt":0.2356292871584844,"spread":0.03973972452358032,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006682271,0.0003343525,0.0003857863,0.0001252361,0.0001686064,0.0002348325,0.003812258,0.0002472562,0.00001288389],"category_scores_gemma":[0.00007917761,0.0003640512,0.0001495413,0.000294226,0.00006472262,0.0007175454,0.006393957,0.0003448394,0.00002445781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002171724,"about_ca_system_score_gemma":0.0007509603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001109706,"about_ca_topic_score_gemma":0.00004544403,"domain_scores_codex":[0.9974772,0.0001350348,0.0002273965,0.001610265,0.0001131448,0.0004369688],"domain_scores_gemma":[0.996487,0.00007176235,0.0002448988,0.002569385,0.0003962533,0.0002306915],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004054179,0.00007914835,0.00001305757,0.00003574421,0.000110876,0.00001756632,0.00008521372,0.9467477,0.00002037331,0.03750171,0.0145126,0.0008354946],"study_design_scores_gemma":[0.0004493503,0.00003874092,0.000002524337,0.0000492127,0.0001210374,0.000001118156,0.000007001147,0.9217642,0.00002607166,0.07453573,0.002624243,0.0003807975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006048143,0.0001335284,0.9959058,0.0001352829,0.00144815,0.0005301887,0.0003501929,0.0001394728,0.0007525707],"genre_scores_gemma":[0.8647785,0.0001465227,0.1314772,0.0001075752,0.0003602723,0.000004057675,0.0003581023,0.00002841706,0.002739289],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8644286,"threshold_uncertainty_score":0.9998811,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06793276002285821,"gpt":0.2755444880059014,"spread":0.2076117279830432,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005936886,0.0001032641,0.0001052208,0.00007619325,0.0002861418,0.00005670395,0.0003391891,0.00003325555,0.000023779],"category_scores_gemma":[0.00005425694,0.00008028447,0.00004466975,0.000387486,0.00006052178,0.0006078898,0.0001013384,0.00006285042,0.00001773468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003131854,"about_ca_system_score_gemma":0.00004432764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001290006,"about_ca_topic_score_gemma":0.000008479763,"domain_scores_codex":[0.9991605,0.00009143034,0.0001482045,0.0002744009,0.0001586592,0.0001668177],"domain_scores_gemma":[0.9994118,0.00005842659,0.00006600554,0.0003017223,0.0001069312,0.00005515132],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007009329,0.001030041,0.02307613,0.0000326296,0.0002636572,0.0002470596,0.0108688,0.03352394,0.2956937,0.3332265,0.05373031,0.2482371],"study_design_scores_gemma":[0.0001155857,0.0000234438,0.04549881,0.000003948393,0.000004630802,0.00001761835,0.0000344484,0.9493444,0.003357651,0.0007222184,0.0007447281,0.0001325282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02477782,0.00004329163,0.9664283,0.0006185251,0.0002040807,0.00008854918,8.782848e-7,0.0001040435,0.007734477],"genre_scores_gemma":[0.8435884,0.00002091577,0.1554257,0.0001263925,0.00009834085,0.000003667373,0.000002268081,0.000004941594,0.0007293953],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9158205,"threshold_uncertainty_score":0.3273906,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.008495873437115676,"gpt":0.2158275489381482,"spread":0.2073316755010325,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001611192,0.0001051788,0.0000967804,0.00003348763,0.0001531307,0.00009221609,0.0002522444,0.00002478227,0.00009616112],"category_scores_gemma":[0.00002131367,0.00006820854,0.0000305641,0.0001486733,0.00002427756,0.000790789,0.0001091066,0.00009469972,0.0001057504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009347677,"about_ca_system_score_gemma":0.000008927902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006315577,"about_ca_topic_score_gemma":0.00002069855,"domain_scores_codex":[0.9992543,0.00006633271,0.0000800871,0.0001662462,0.0001318648,0.0003011502],"domain_scores_gemma":[0.9995787,0.00005443674,0.00003408608,0.000190941,0.00003896011,0.0001028779],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003469404,0.0003168742,0.1679225,0.00001411065,0.0001445556,0.00001558337,0.004209009,0.08617451,0.004243379,0.03799313,0.00240867,0.696523],"study_design_scores_gemma":[0.0002507671,0.00007546093,0.01894351,0.000004953439,0.000007116919,0.00001444758,0.00005517341,0.9656775,0.002835835,0.00007304701,0.01182872,0.0002334649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006161517,0.0001470026,0.9784781,0.0002870641,0.000178642,0.00005487661,7.860809e-8,0.0001293707,0.01456334],"genre_scores_gemma":[0.7771049,0.000003282829,0.2214096,0.0001645949,0.0002048643,0.000004267679,6.535122e-7,0.000005806855,0.001102051],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.879503,"threshold_uncertainty_score":0.2781464,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.03475309409311431,"gpt":0.1705201107510971,"spread":0.1357670166579828,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005120975,0.0006166423,0.0006646717,0.0002920062,0.0004486892,0.0004690236,0.001789617,0.0003525017,0.00008822911],"category_scores_gemma":[0.0001312806,0.0006206739,0.0002985712,0.0006595736,0.0001944305,0.00102677,0.002476333,0.001267851,0.0002265182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002631923,"about_ca_system_score_gemma":0.0003970233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001805678,"about_ca_topic_score_gemma":0.0000652939,"domain_scores_codex":[0.9964255,0.0005778949,0.0002912893,0.001868178,0.0001632065,0.0006739002],"domain_scores_gemma":[0.9973087,0.0002934178,0.000522075,0.001224012,0.000442748,0.000209046],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006371713,0.00005812526,0.001294312,0.00004675979,0.0002491661,0.0002484549,0.0006291782,0.9826382,0.0002991389,0.01264201,0.0005907513,0.0012402],"study_design_scores_gemma":[0.000979315,0.0001803665,0.0003586284,0.0001434512,0.0001141822,0.000006534929,0.0002510404,0.9916211,0.0015322,0.002477336,0.001429219,0.0009066237],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04190781,0.00006148791,0.9467519,0.0001574659,0.001234576,0.0004909754,0.000008787009,0.0002890531,0.009097962],"genre_scores_gemma":[0.9732144,0.00007289344,0.02291158,0.0001347928,0.0006071913,0.00000231375,0.00002803786,0.00004739963,0.002981401],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9313066,"threshold_uncertainty_score":0.9996244,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03012104088694883,"gpt":0.2210626950682835,"spread":0.1909416541813346,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002970003,0.000209543,0.0002234613,0.0001581634,0.0002605347,0.0001953921,0.0005399992,0.00007339132,0.00005394957],"category_scores_gemma":[0.00003126868,0.0001445157,0.00007592708,0.0007751436,0.00004018761,0.0008865412,0.0003175994,0.00007928845,0.000279078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004855532,"about_ca_system_score_gemma":0.00003323144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004261344,"about_ca_topic_score_gemma":0.00003766291,"domain_scores_codex":[0.9982671,0.0001196711,0.0002231171,0.0005381111,0.0004077946,0.0004442631],"domain_scores_gemma":[0.9990104,0.0001261056,0.00007894898,0.0005436717,0.0001147286,0.0001261816],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006998963,0.0002069619,0.0005010609,0.00002071946,0.0001687696,0.0000969172,0.0005896414,0.8607563,0.01065077,0.05082262,0.01935463,0.05676161],"study_design_scores_gemma":[0.0002540447,0.00006849949,0.0027296,0.00004202431,0.00001976338,0.000004171159,0.00003284384,0.9864649,0.006111401,0.003606611,0.0004139994,0.0002521685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02323655,0.00003133071,0.9715504,0.002533624,0.0002938321,0.0002015357,0.000004211464,0.0005507968,0.001597706],"genre_scores_gemma":[0.9564861,0.0001124609,0.04114627,0.000243424,0.0001100896,0.00004917205,0.000006022635,0.00001942902,0.001827045],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9332495,"threshold_uncertainty_score":0.589318,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01429841267962217,"gpt":0.2316586604951138,"spread":0.2173602478154916,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002236866,0.0001396021,0.0001570194,0.00007515683,0.0001316275,0.0002430041,0.000403248,0.00006497024,0.0004459294],"category_scores_gemma":[0.00005738609,0.0001179597,0.00006505119,0.000275749,0.00002130114,0.00101282,0.0002217711,0.0001061625,0.00007081262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004476673,"about_ca_system_score_gemma":0.00003926782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004971538,"about_ca_topic_score_gemma":0.000007309357,"domain_scores_codex":[0.9988856,0.00007833436,0.000219249,0.0003911065,0.0001566389,0.0002690835],"domain_scores_gemma":[0.9992299,0.0000560186,0.00008533968,0.0004440693,0.0001234956,0.00006116894],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007301826,0.0000484166,0.008512134,0.00004279293,0.00009337209,0.000009848876,0.00087594,0.04282158,0.8764868,0.01480637,0.01322582,0.04306961],"study_design_scores_gemma":[0.00022937,0.00002693241,0.00162676,0.00001589566,0.000006273438,0.00001415572,0.00003841391,0.943472,0.05201574,0.001160084,0.001227457,0.0001669106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1373084,0.00002481062,0.8528788,0.0001789715,0.001172398,0.0001731203,0.000003158262,0.0001408198,0.008119541],"genre_scores_gemma":[0.7976685,0.00000148474,0.2013344,0.0002716891,0.0003032241,9.718386e-7,0.000002397278,0.00000913107,0.0004082796],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9006504,"threshold_uncertainty_score":0.4882614,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01628468875810614,"gpt":0.2747265167593389,"spread":0.2584418280012328,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002077644,0.0001120618,0.0001013721,0.00005211944,0.0002659867,0.00014204,0.0001975822,0.00003371453,0.000002765527],"category_scores_gemma":[0.00005087005,0.00009701189,0.00004985363,0.000161407,0.00001402686,0.0005731478,0.00004073152,0.00008058539,0.000009486265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001779127,"about_ca_system_score_gemma":0.00001041125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005076452,"about_ca_topic_score_gemma":0.000001726793,"domain_scores_codex":[0.9991345,0.0001039521,0.0001350035,0.0002237867,0.0001369169,0.0002658711],"domain_scores_gemma":[0.9995295,0.00009281559,0.0000800865,0.0001057268,0.0001009445,0.00009089013],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000746728,0.00005387026,0.000895877,0.000009485133,0.000004376627,2.573107e-7,0.0007592924,0.8982161,0.001450925,0.001098687,0.0001125743,0.09739105],"study_design_scores_gemma":[0.0001707507,0.0001268814,0.007942328,0.000003489959,0.000006104165,0.000005026759,0.00002577307,0.9902909,0.0008365939,0.0001909005,0.0002807428,0.0001205022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1248474,0.0001131483,0.8738881,0.0002332995,0.000493093,0.0002124091,4.971167e-7,0.0001309185,0.00008111919],"genre_scores_gemma":[0.929613,6.713544e-7,0.06973023,0.0001767885,0.000412719,0.00001942869,0.00001555252,0.000009661762,0.00002196608],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8047656,"threshold_uncertainty_score":0.395603,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02539865541932763,"gpt":0.2377520617173313,"spread":0.2123534062980036,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002239201,0.00009139017,0.0002002166,0.0001128642,0.0001800809,0.00002387485,0.0005073103,0.00002821745,0.000154412],"category_scores_gemma":[0.00007867698,0.00005209973,0.0001671317,0.001431681,0.00009743912,0.0001312765,0.00008991788,0.00007109076,0.00001433972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008801822,"about_ca_system_score_gemma":0.00001236995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006003478,"about_ca_topic_score_gemma":0.00006784881,"domain_scores_codex":[0.9991404,0.0001396646,0.0001712181,0.0002111836,0.0001843079,0.0001531723],"domain_scores_gemma":[0.9985656,0.0007671255,0.00008529657,0.0004461217,0.0001014014,0.00003443477],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006757614,0.000056398,0.0003430361,3.498801e-7,0.0005449996,0.00000386627,0.000621811,0.636733,0.00007452495,0.3563948,0.002242726,0.0029777],"study_design_scores_gemma":[0.00004694092,0.00007505771,0.006149437,0.000001601529,0.00005517568,4.7639e-7,0.00003805488,0.9923226,0.0005104567,0.0006210424,0.000109261,0.00006985508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007227811,0.0000918384,0.9834032,0.0006570547,0.00008866107,0.00006448,6.404496e-7,0.00002383144,0.008442496],"genre_scores_gemma":[0.9714012,0.00003895586,0.02762153,0.0007059567,0.00002091595,0.000004452216,0.000001087516,0.000002958168,0.0002029221],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9641734,"threshold_uncertainty_score":0.2124565,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1016253428139338,"gpt":0.2832050384575156,"spread":0.1815796956435818,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001837412,0.0002020286,0.0002615819,0.0001783068,0.001736919,0.0001334105,0.002422137,0.0001176444,0.0007118123],"category_scores_gemma":[0.0004762464,0.0001667026,0.000189929,0.0008760798,0.001039546,0.001361717,0.001161208,0.0005125756,0.00001592889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001257608,"about_ca_system_score_gemma":0.0001878977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003073241,"about_ca_topic_score_gemma":0.00002165044,"domain_scores_codex":[0.9971005,0.0002738968,0.0002143132,0.0005607517,0.001028446,0.0008221051],"domain_scores_gemma":[0.9969909,0.0006716175,0.0001668234,0.0008999452,0.000959914,0.0003108614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003087608,0.0003113654,0.001065556,0.000008609577,0.0002209397,0.0002616891,0.01723382,0.0003232978,0.0014133,0.01773716,0.8658361,0.09527941],"study_design_scores_gemma":[0.002207126,0.001382174,0.01034882,0.0002015909,0.00007871784,0.00003451145,0.02338242,0.692209,0.009234337,0.04570732,0.2140256,0.001188332],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02463253,0.0007947284,0.9553958,0.005842883,0.00274602,0.0007825105,0.00003376618,0.0002547352,0.009517014],"genre_scores_gemma":[0.9899911,0.0002722075,0.007552309,0.00001670005,0.0003821888,0.000005137595,0.0000115607,0.00001082769,0.001757968],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9653586,"threshold_uncertainty_score":0.9995627,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04644017211500441,"gpt":0.2691334344193685,"spread":0.2226932623043641,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002631804,0.0002287044,0.0003113949,0.0002812177,0.0005274497,0.0001716579,0.0004093137,0.0001260404,0.0001438953],"category_scores_gemma":[0.00006174578,0.0002450876,0.0002182906,0.001141838,0.0001026389,0.001786346,0.00001683546,0.0002442633,0.000009149956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004186063,"about_ca_system_score_gemma":0.0001871388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003721806,"about_ca_topic_score_gemma":0.00005535146,"domain_scores_codex":[0.9981266,0.0002668492,0.0004577616,0.0004541263,0.00040833,0.0002862906],"domain_scores_gemma":[0.9980984,0.0002605887,0.0001782502,0.000667173,0.0006962453,0.00009937616],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006525831,0.001132353,0.0002798584,0.00006084783,0.0006940992,0.0001501643,0.001015683,0.4506174,0.5227028,0.01199472,0.001378254,0.009908587],"study_design_scores_gemma":[0.0009931669,0.0001459056,0.0004345359,0.00006602168,0.0001026209,0.00004946233,0.0002577064,0.1309828,0.8592752,0.00633115,0.0009133453,0.0004480986],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02229183,0.0001277102,0.9759176,0.000736408,0.0003492578,0.0001578292,0.0002532123,0.00009675776,0.00006932997],"genre_scores_gemma":[0.8895504,0.0001428415,0.1096339,0.0003267087,0.00007087629,0.00002263334,0.0001889189,0.00001726011,0.00004645269],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8672585,"threshold_uncertainty_score":0.9994382,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02043062593792137,"gpt":0.2310940455076262,"spread":0.2106634195697049,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006492536,0.0006710961,0.0006695049,0.0005279063,0.0003140052,0.0005473844,0.003114199,0.0004131896,0.000312955],"category_scores_gemma":[0.00008306091,0.0005711089,0.0001415309,0.0006161036,0.0008800077,0.001115461,0.001201955,0.0008750449,0.0001800668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002365949,"about_ca_system_score_gemma":0.0006023414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005716191,"about_ca_topic_score_gemma":0.00005863166,"domain_scores_codex":[0.9959888,0.00006745187,0.0005047468,0.001797004,0.0008207951,0.0008211726],"domain_scores_gemma":[0.9969807,0.0004479724,0.0003410828,0.001459221,0.0005495758,0.0002214555],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001390743,0.00006488459,0.00001987636,0.00001547166,0.00005216459,0.0001647147,0.0009096684,0.02500652,0.0004319724,0.05194803,0.0003584925,0.9210143],"study_design_scores_gemma":[0.0006649357,0.0003859228,0.0004619447,0.0003612487,0.00003816434,0.00005811987,1.783428e-7,0.4998429,0.007112789,0.4497325,0.03935193,0.001989397],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000002838145,0.0004640105,0.9623535,0.0008604963,0.00373529,0.000374152,0.000004664941,0.0001567626,0.0320483],"genre_scores_gemma":[0.1633908,0.00009215403,0.8250732,0.00396862,0.001676796,0.00002226597,0.000005014555,0.00007998462,0.005691066],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9190249,"threshold_uncertainty_score":0.999674,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02078843115250906,"gpt":0.2270061392208448,"spread":0.2062177080683358,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001290782,0.00009888025,0.0000877928,0.00002702268,0.0005985461,0.00009759265,0.0006429033,0.0000246899,0.00002003497],"category_scores_gemma":[0.00005785212,0.00005555436,0.00005762176,0.0003116775,0.00006750201,0.0002255146,0.000180331,0.00009794127,0.00007043498],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001555488,"about_ca_system_score_gemma":0.00004622095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001396166,"about_ca_topic_score_gemma":0.00007259943,"domain_scores_codex":[0.9990957,0.0000985973,0.0001625378,0.0002217612,0.0001937182,0.0002277087],"domain_scores_gemma":[0.9992486,0.0001186175,0.00005003579,0.0004470686,0.0000666791,0.00006896127],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000543879,0.0002400375,0.006071665,0.000003782238,0.00009620738,0.0001294674,0.0007261033,0.0009271114,0.0007582046,0.05953896,0.5423437,0.3891104],"study_design_scores_gemma":[0.0004248708,0.0001899734,0.02206848,0.000006543092,0.000005071312,0.00005209529,0.00001906321,0.4821384,0.002354374,0.001735074,0.4906813,0.0003247633],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002648327,0.000978696,0.9758373,0.005483546,0.000892058,0.0001577942,0.000001318283,0.0001811234,0.01381979],"genre_scores_gemma":[0.9615325,0.0003491994,0.03338674,0.0003085297,0.0001818378,0.000009746563,0.00000248776,0.000005856789,0.004223085],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9588842,"threshold_uncertainty_score":0.4603593,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02491606829275419,"gpt":0.2557287928810392,"spread":0.230812724588285,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007689799,0.0001007875,0.000105604,0.00006217186,0.0001651559,0.0001288306,0.0002453434,0.00004093171,0.00002454874],"category_scores_gemma":[0.000050723,0.00008353059,0.00006871538,0.0001458484,0.000008601617,0.0005151391,0.00002586631,0.00004388397,0.000007791578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000186561,"about_ca_system_score_gemma":0.00002029857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001916847,"about_ca_topic_score_gemma":0.000004085821,"domain_scores_codex":[0.9992443,0.00003060387,0.0001557225,0.0002550721,0.0001347983,0.0001794663],"domain_scores_gemma":[0.9995391,0.0000521453,0.00004004032,0.0001819699,0.0001324138,0.0000543482],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004324908,0.0002338158,0.00006901691,0.000006975685,0.00004935702,0.000003762465,0.0002672519,0.622377,0.02569387,0.1970103,0.01457008,0.1396753],"study_design_scores_gemma":[0.0002618771,0.00006507448,0.001022613,0.000002603138,0.000003830783,0.000001184304,0.000005866197,0.9672909,0.001581805,0.02935594,0.0003012419,0.0001071107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003122867,0.00002780522,0.9937799,0.001463034,0.0001468406,0.0001731396,0.000009911768,0.0001243368,0.001152187],"genre_scores_gemma":[0.862825,0.000002890671,0.136291,0.0004040365,0.0001714759,0.000007853111,0.00004237632,0.000003381864,0.0002520094],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8597022,"threshold_uncertainty_score":0.3406278,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.01940994607784042,"gpt":0.194748224298081,"spread":0.1753382782202406,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007505514,0.0001536729,0.0001729911,0.00003636607,0.0001369724,0.0001819687,0.0004287922,0.00003329737,0.00005855847],"category_scores_gemma":[0.00006777195,0.0001121373,0.0000493195,0.0004986995,0.00005330915,0.0009101155,0.0001312491,0.00006691763,0.0001054991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001608065,"about_ca_system_score_gemma":0.00005148543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003892518,"about_ca_topic_score_gemma":0.000012954,"domain_scores_codex":[0.9989251,0.00009856558,0.0001445162,0.0003976162,0.0002115457,0.0002226034],"domain_scores_gemma":[0.9992652,0.0001057733,0.00007237941,0.000282114,0.0001361149,0.000138414],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007151504,0.0006465227,0.006328398,0.0002609709,0.001117223,0.001583228,0.01469925,0.0960102,0.02272118,0.430404,0.1714093,0.2541045],"study_design_scores_gemma":[0.0002058063,0.0001844778,0.0005124522,0.00002103345,0.00002638102,0.00001694921,0.0001500096,0.9657263,0.03093163,0.0002590721,0.001659472,0.0003064724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002528266,0.00002234811,0.9807214,0.007637218,0.00004981374,0.000142649,6.397051e-7,0.0001851747,0.01098791],"genre_scores_gemma":[0.8611133,0.00001333309,0.1370984,0.00146353,0.0001310212,0.00001217293,8.359839e-7,0.00001148542,0.0001559156],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.869716,"threshold_uncertainty_score":0.4572827,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.005926535575176141,"gpt":0.2164816060712061,"spread":0.21055507049603,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001948026,0.00006932163,0.00009788269,0.00004278366,0.00007761095,0.0000411644,0.0003425997,0.00002896498,0.0001356063],"category_scores_gemma":[0.00007377097,0.00005182728,0.0000497669,0.0001546384,0.00003597804,0.00006133176,0.0001384881,0.0001300011,0.00002920888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000219405,"about_ca_system_score_gemma":0.00001060202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003930624,"about_ca_topic_score_gemma":0.00001946062,"domain_scores_codex":[0.9994199,0.00003535442,0.0001208168,0.0001684963,0.0001220168,0.0001333863],"domain_scores_gemma":[0.9995376,0.00006763827,0.0000515973,0.000232199,0.0000673733,0.0000435793],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005674486,0.0001390321,0.00335207,0.00001026959,0.00002984469,0.000005176941,0.0008745269,0.2965115,0.2052306,0.1432849,0.0004503226,0.350106],"study_design_scores_gemma":[0.00007259395,0.00002386623,0.002088729,0.000001453725,0.00000200214,0.000002064138,0.000009843579,0.9800488,0.01603657,0.0001982008,0.001448413,0.00006748846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05082198,0.00002489938,0.9358758,0.0002299548,0.0004021573,0.00004015319,1.127099e-7,0.00005389915,0.01255102],"genre_scores_gemma":[0.8837889,9.362016e-7,0.1156919,0.00004888364,0.0000721894,0.000001459568,2.562663e-7,0.000003230489,0.0003922637],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8329669,"threshold_uncertainty_score":0.2113455,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05197575815289519,"gpt":0.3078173894272081,"spread":0.2558416312743129,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005936504,0.0001189173,0.0001958824,0.00004166448,0.0001689681,0.0001566529,0.0004354919,0.00002891906,0.000009269998],"category_scores_gemma":[0.0007153387,0.00006370814,0.00003697781,0.00008065949,0.000459485,0.00005390874,0.00005569533,0.0001179408,6.481765e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005448499,"about_ca_system_score_gemma":0.0000284661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002594124,"about_ca_topic_score_gemma":0.00005611958,"domain_scores_codex":[0.998877,0.0002149644,0.0003309037,0.0001847301,0.0002554294,0.0001369002],"domain_scores_gemma":[0.9974318,0.002075209,0.0001520812,0.0001508773,0.0001524195,0.00003765902],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001662374,0.00000712588,0.00001116603,0.000002212583,0.00001933109,8.856098e-7,0.003680728,0.001372304,0.0008520117,0.4389897,0.000004809095,0.5548935],"study_design_scores_gemma":[0.0001121132,0.0004572345,0.001142773,0.00004265944,0.00001288791,0.000004723776,0.0006535111,0.80071,0.008951396,0.1878019,0.00002558819,0.00008518693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02852775,0.0000779141,0.9686359,0.00160158,0.0001937476,0.000160776,0.0000205707,0.000009007502,0.0007727653],"genre_scores_gemma":[0.9907714,0.0001286131,0.008945464,0.00007481471,0.00005237582,0.000005289258,0.000002455883,0.000002542735,0.00001703877],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9622437,"threshold_uncertainty_score":0.2597942,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02191974366862999,"gpt":0.2456868012082372,"spread":0.2237670575396072,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009597028,0.0001366092,0.0001461563,0.00005524118,0.0001865231,0.0001405768,0.0004551686,0.00003142214,0.00004782154],"category_scores_gemma":[0.00002397175,0.0001075552,0.0001077953,0.0002542568,0.00001912964,0.0004015881,0.0001265758,0.00005562091,0.00006207648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004342757,"about_ca_system_score_gemma":0.00003288729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005186585,"about_ca_topic_score_gemma":0.000005494151,"domain_scores_codex":[0.9989361,0.00004059546,0.0001438525,0.0003977274,0.0001790345,0.0003027257],"domain_scores_gemma":[0.9993592,0.0000294139,0.00003959975,0.0002815886,0.0001224181,0.000167806],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006176467,0.000368709,0.0004024851,0.000005752197,0.0002003102,0.00006082099,0.003966183,0.05244835,0.3178361,0.07740699,0.004974374,0.5422682],"study_design_scores_gemma":[0.0002885472,0.0004629795,0.003048975,0.00002016704,0.00002610482,0.00000709545,0.0001492739,0.938066,0.0546247,0.001283121,0.00160365,0.0004194087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006093201,0.00005712529,0.9869325,0.001117941,0.0004765966,0.0001771528,0.00000193288,0.00006249454,0.005081093],"genre_scores_gemma":[0.7989488,0.000002906735,0.1992152,0.001175457,0.0001356547,0.000001796999,2.480817e-7,0.000002681537,0.000517211],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8856176,"threshold_uncertainty_score":0.4385972,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02448469902066481,"gpt":0.2509454465976662,"spread":0.2264607475770014,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007985549,0.0005285319,0.0004829955,0.0006752187,0.0005097031,0.0008507507,0.002091486,0.0002914714,0.00003633249],"category_scores_gemma":[0.0001633378,0.0004982229,0.0001528093,0.0006140558,0.0007549993,0.001094551,0.001035307,0.00046603,0.00004657723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004305324,"about_ca_system_score_gemma":0.0005729879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005664077,"about_ca_topic_score_gemma":0.0001251916,"domain_scores_codex":[0.9963677,0.0000617754,0.0005118406,0.001541504,0.0008054178,0.0007117939],"domain_scores_gemma":[0.9976575,0.0004346631,0.0003557281,0.0009996801,0.0003864494,0.0001659881],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004955774,0.00001637892,0.00006163413,0.0000165385,0.00001779631,0.00004542635,0.001134268,0.7329853,0.0009647235,0.000587188,0.00005032349,0.2641155],"study_design_scores_gemma":[0.000184999,0.00008545932,0.00004648827,0.0002410654,0.00001126795,0.00003665371,3.237382e-7,0.958207,0.00323864,0.03700952,0.0003962566,0.0005423612],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002653623,0.0002662919,0.9957481,0.0002187879,0.002453575,0.0003118203,0.000002975713,0.000135359,0.0005977192],"genre_scores_gemma":[0.1699735,0.00001321658,0.8281757,0.0006422417,0.001037728,0.000002416381,0.000003208595,0.00003597979,0.0001159802],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2635731,"threshold_uncertainty_score":0.9997469,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1333535336930498,"gpt":0.3329249490688279,"spread":0.1995714153757781,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004380683,0.0004338602,0.0007474152,0.0006200611,0.0006710791,0.0002879671,0.002904747,0.0005824525,0.0004617106],"category_scores_gemma":[0.0009660221,0.000498754,0.0004220101,0.000895558,0.0005575443,0.001324223,0.003662191,0.001130846,0.00001103972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006572461,"about_ca_system_score_gemma":0.001097156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003411181,"about_ca_topic_score_gemma":0.0000132614,"domain_scores_codex":[0.9952043,0.0003224088,0.0004194642,0.001318806,0.001732532,0.001002514],"domain_scores_gemma":[0.9939622,0.0006988406,0.0004010302,0.001415832,0.003024346,0.0004976987],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000179677,0.000209819,0.00002986143,0.00007505022,0.0001945133,0.00002221191,0.004640065,0.04922785,0.0004638176,0.00150496,0.9221715,0.02128073],"study_design_scores_gemma":[0.0009030162,0.0002806689,0.00008854891,0.0002435311,0.0000597672,0.000002350981,0.001708849,0.8723364,0.000482445,0.07046372,0.05293439,0.0004962559],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001955399,0.0003697171,0.9878169,0.004854589,0.002287838,0.001384298,0.0002517244,0.0001840075,0.0008955452],"genre_scores_gemma":[0.5778019,0.0008245604,0.4075479,0.00005878707,0.003015324,0.00009765498,0.00188982,0.00007869909,0.008685421],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8692371,"threshold_uncertainty_score":0.9997464,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Theoretical computer science; Adjacency list; Graph; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.02765445398485078,"gpt":0.2303174894395121,"spread":0.2026630354546613,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008115285,0.0007801712,0.0007652002,0.0005059065,0.0006935871,0.0007591862,0.001922715,0.0005291905,0.00002138436],"category_scores_gemma":[0.000243597,0.0007433959,0.0003565174,0.0006594531,0.0007195951,0.001007247,0.0005479179,0.0007939361,0.00002449513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002720245,"about_ca_system_score_gemma":0.0008109013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001292435,"about_ca_topic_score_gemma":0.0001131414,"domain_scores_codex":[0.9953207,0.0001081871,0.0007886562,0.002140484,0.0008844348,0.0007575705],"domain_scores_gemma":[0.9970322,0.0007405931,0.000495838,0.0009351885,0.0005081802,0.000288002],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002433553,0.00002224401,0.00001065949,0.000009260801,0.00005226486,0.00002605225,0.0004877945,0.8856007,0.0003772831,0.03271889,0.0007520529,0.07991846],"study_design_scores_gemma":[0.0007014365,0.0002784688,0.00001687938,0.00007968264,0.00003225552,0.0000174518,2.940351e-7,0.9643267,0.001258159,0.03054473,0.001953354,0.0007906227],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000009943626,0.0003698204,0.9906914,0.00222051,0.004677593,0.001053208,0.00002874509,0.000407449,0.000541341],"genre_scores_gemma":[0.1929472,0.00005470231,0.7960577,0.003297251,0.007255566,0.00005395818,0.00004869513,0.0001328371,0.0001521592],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1946337,"threshold_uncertainty_score":0.9995017,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03234249990471007,"gpt":0.2385754380548839,"spread":0.2062329381501739,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003787768,0.0001329643,0.00012822,0.000008732747,0.0003845294,0.002070459,0.0018145,0.00005156571,0.0002350246],"category_scores_gemma":[0.0001530757,0.00008106157,0.00004298477,0.0001903883,0.00006128976,0.004025831,0.0009407303,0.0001258043,0.0001830488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002248528,"about_ca_system_score_gemma":0.00004547998,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001208025,"about_ca_topic_score_gemma":0.00009219836,"domain_scores_codex":[0.9985744,0.0002317335,0.0002023827,0.0005032296,0.0002321651,0.0002560503],"domain_scores_gemma":[0.9979362,0.0002663797,0.0000792738,0.001558948,0.00009372224,0.00006544439],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003524546,0.00005125207,0.0001672137,0.00000188961,0.0001046397,0.000003231774,0.0008614784,0.00596883,0.02869758,0.005297302,0.4964636,0.4623795],"study_design_scores_gemma":[0.0001392644,0.000009452924,0.0005876051,0.00001112653,0.000007760537,9.053861e-7,0.0002475779,0.9744575,0.001404888,0.00138054,0.02162682,0.0001265496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001797187,0.0002623841,0.9798994,0.01661879,0.0008521954,0.0002012148,0.00001226381,0.0001078237,0.0002487444],"genre_scores_gemma":[0.5574859,0.0002703497,0.431583,0.004278637,0.001256771,0.00004405614,0.0007401753,0.00002062008,0.004320446],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9684887,"threshold_uncertainty_score":0.9989655,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.07168787938815764,"gpt":0.1866033410959169,"spread":0.1149154617077593,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003501855,0.0003847224,0.0004107411,0.0001787597,0.0001554086,0.0001845307,0.002190334,0.0002542522,0.00004892339],"category_scores_gemma":[0.00004115426,0.0004165193,0.0002324601,0.0006013861,0.0001266349,0.0005559375,0.001936894,0.0005202055,0.0001451436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002725224,"about_ca_system_score_gemma":0.0004394111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001554189,"about_ca_topic_score_gemma":0.00008142638,"domain_scores_codex":[0.9976849,0.0001986086,0.0002302794,0.001306744,0.0001306662,0.0004487951],"domain_scores_gemma":[0.9974789,0.00006395,0.0002996845,0.001542329,0.0003222998,0.0002928603],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002370869,0.00009557982,0.001896494,0.00002990677,0.0001802781,0.0005708057,0.0002887643,0.932151,0.00001869186,0.04486755,0.01843174,0.001445515],"study_design_scores_gemma":[0.0002895808,0.00003133921,0.0003811607,0.00003431186,0.00004539322,0.000002824316,0.00003232553,0.9360586,0.00007985066,0.05970411,0.002866377,0.0004740786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02098915,0.0001543306,0.9676859,0.0002684942,0.00115968,0.0002430944,0.0000138526,0.0003308291,0.009154609],"genre_scores_gemma":[0.9783599,0.0001344136,0.0186411,0.0001914623,0.0002007711,0.000001092376,0.00001862612,0.00002110577,0.002431506],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9573708,"threshold_uncertainty_score":0.9998286,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.07482342689117959,"gpt":0.1895635017845382,"spread":0.1147400748933586,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004682655,0.0004553241,0.000469823,0.0001705988,0.0002444841,0.0003288265,0.00184941,0.0003114607,0.00003267894],"category_scores_gemma":[0.00001613999,0.000485974,0.0002445636,0.0004761539,0.00009540619,0.0005262787,0.003088945,0.0006777195,0.00007154082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003730311,"about_ca_system_score_gemma":0.0002597397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00018389,"about_ca_topic_score_gemma":0.0000492277,"domain_scores_codex":[0.9974285,0.0003623116,0.000248317,0.001321918,0.000127373,0.0005115713],"domain_scores_gemma":[0.9977459,0.00007782541,0.0002935911,0.001268105,0.0003067502,0.0003077681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000113942,0.00004780298,0.00006943415,0.000008819067,0.0001185221,0.0001578975,0.0003061473,0.9520421,0.00001578462,0.04272357,0.003361315,0.00113719],"study_design_scores_gemma":[0.0002939515,0.00004142784,0.0000582381,0.00004914848,0.00005137483,0.000002593547,0.00006755773,0.9464874,0.00009402136,0.05112275,0.001218337,0.0005132206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007224598,0.0002679014,0.986679,0.0002609506,0.001635364,0.0003120097,0.000009930745,0.0002139443,0.003396348],"genre_scores_gemma":[0.9815139,0.000212976,0.0153861,0.0002546195,0.0005154171,0.000002236978,0.00002259381,0.00002546655,0.002066683],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9742893,"threshold_uncertainty_score":0.9997592,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.02636498055289708,"gpt":0.3402729384433184,"spread":0.3139079578904213,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002608241,0.0001276284,0.0002918371,0.0002340014,0.0001701437,0.0002707458,0.0009692506,0.00002870369,0.00003051663],"category_scores_gemma":[0.001195173,0.00009715685,0.0001618662,0.0004292087,0.00004545142,0.001156646,0.0001523119,0.0001904259,0.00001651281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003248924,"about_ca_system_score_gemma":0.0001851868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004995974,"about_ca_topic_score_gemma":0.000004762804,"domain_scores_codex":[0.9981177,0.000239307,0.0004880101,0.0002249981,0.0006155444,0.0003144229],"domain_scores_gemma":[0.9983526,0.0006088951,0.0002145789,0.0002744918,0.0003036256,0.0002458024],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001791658,0.002205069,0.04770386,0.00005603879,0.0005329603,0.003449365,0.01096751,0.002751067,0.01189718,0.0003803427,0.1560543,0.7638232],"study_design_scores_gemma":[0.001472687,0.0005327592,0.02241778,0.0001225463,0.00009854556,0.0003105608,0.003073813,0.959762,0.004121965,0.001841322,0.00586255,0.0003835117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03897286,0.00006826413,0.9498896,0.009902433,0.0007852921,0.0001495094,0.000001520145,0.00006926539,0.0001612605],"genre_scores_gemma":[0.9483442,0.00001711686,0.05015316,0.0005183935,0.000905249,0.00001053492,3.245635e-7,0.00001723792,0.00003375653],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9570109,"threshold_uncertainty_score":0.3961941,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Computer science; Deep learning; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.01505092565250138,"gpt":0.2282701358634082,"spread":0.2132192102109069,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001292177,0.0002084233,0.0002739677,0.0002983977,0.0002863401,0.0002730008,0.0003363107,0.00004639317,0.0002554929],"category_scores_gemma":[0.000002284021,0.0001505181,0.0001512997,0.0008519891,0.00007567125,0.0005422194,0.000005910034,0.0003203007,0.00004837172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001551015,"about_ca_system_score_gemma":0.00001097684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001396055,"about_ca_topic_score_gemma":0.0005575841,"domain_scores_codex":[0.9986413,0.0001246963,0.0002401865,0.0005023459,0.0002368745,0.0002546732],"domain_scores_gemma":[0.999185,0.0001343434,0.00007216656,0.0003568999,0.0001011412,0.0001504535],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002707843,0.00004029973,0.00008002925,0.000002103159,0.0002082258,0.000002188469,0.0002354678,0.4872267,0.000112875,0.00004574181,0.000002298407,0.5120413],"study_design_scores_gemma":[0.00005596484,0.0001683646,0.0002723105,0.000009562658,0.0001515152,0.000004862155,0.00005069365,0.9777511,0.02068223,0.0006277518,0.00002254262,0.0002031517],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001662545,0.00005002082,0.9971478,0.0006037092,0.00005578305,0.0001224642,0.000002526644,0.00007565452,0.0002794864],"genre_scores_gemma":[0.9872453,0.0001971707,0.01177269,0.0003537767,0.0000183492,0.00003757017,0.000001692728,0.00001031705,0.0003630947],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9855828,"threshold_uncertainty_score":0.6137951,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05773346823870358,"gpt":0.2284069599291049,"spread":0.1706734916904013,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006267994,0.00009117603,0.00007444795,0.00005601138,0.0001100453,0.00005092355,0.0002483824,0.00002167163,0.00008488201],"category_scores_gemma":[0.000003898324,0.00006499796,0.00002059904,0.0002528122,0.00001516762,0.0003448147,0.00004774947,0.00004076238,0.0002519306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001551096,"about_ca_system_score_gemma":0.00001622404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003177507,"about_ca_topic_score_gemma":0.00005952525,"domain_scores_codex":[0.9993457,0.00003424341,0.00008326011,0.0002941595,0.0001037179,0.0001388747],"domain_scores_gemma":[0.9994528,0.00002814972,0.00002611415,0.0002927348,0.0001120134,0.00008816002],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004280754,0.0002245972,0.000008460348,0.000002087213,0.0000461305,0.000004158509,0.002453763,0.0407886,0.0007463298,0.6138132,0.002067687,0.3398022],"study_design_scores_gemma":[0.0003183319,0.0006670374,0.0001555119,0.00001472759,0.0000135493,0.000005158435,0.0000978958,0.7167352,0.06264504,0.2179686,0.0009223137,0.0004565917],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002379141,0.00000516704,0.9238105,0.0002200618,0.00003133537,0.000269771,0.000001263136,0.00007192718,0.07535199],"genre_scores_gemma":[0.3724949,0.000002070885,0.6258875,0.001203374,0.0000412759,0.0001493821,0.000001712363,0.000004714013,0.0002150774],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6759467,"threshold_uncertainty_score":0.3238142,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0281739300434079,"gpt":0.240075001331752,"spread":0.2119010712883441,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003622558,0.0003849141,0.0004010315,0.0002557956,0.0007005353,0.0006805327,0.0004960381,0.00007331884,0.002079525],"category_scores_gemma":[0.000004918447,0.0003383047,0.0001181536,0.0003966214,0.0001121302,0.0007772534,0.0002252151,0.0004574976,0.0001518696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006222598,"about_ca_system_score_gemma":0.0000607735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003364615,"about_ca_topic_score_gemma":0.00003668888,"domain_scores_codex":[0.9970273,0.0005745254,0.0003978165,0.000960556,0.0006172623,0.0004225691],"domain_scores_gemma":[0.998819,0.0001736711,0.0001360002,0.0004487662,0.0002172136,0.0002053831],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001483191,0.0005684913,0.00006545786,0.00002704075,0.00006442996,0.0001115379,0.001025386,0.00028785,0.009140959,0.0002274656,0.006453375,0.9818797],"study_design_scores_gemma":[0.006053494,0.01055985,0.002340107,0.0004253964,0.00009903224,0.0003923578,0.0005102046,0.9291417,0.02053443,0.002139594,0.02561541,0.002188421],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06632833,0.00002561464,0.9288647,0.001818811,0.0008222406,0.0004518847,0.0001411471,0.0001785874,0.00136868],"genre_scores_gemma":[0.9884328,0.0000577479,0.007132184,0.003628928,0.0002507735,0.000119175,0.0001679597,0.00003152494,0.0001788543],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9796913,"threshold_uncertainty_score":0.9999069,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01138203735279639,"gpt":0.2459222741355828,"spread":0.2345402367827864,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008933407,0.0001379055,0.0001236723,0.00008810145,0.0002642628,0.0002416901,0.0002390157,0.00003921697,0.00002601382],"category_scores_gemma":[0.00003050278,0.0001087146,0.00003741426,0.0003529228,0.00002439533,0.0005996063,0.00005245601,0.0002394035,0.00002707804],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001082187,"about_ca_system_score_gemma":0.00002368624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002124823,"about_ca_topic_score_gemma":0.0002219167,"domain_scores_codex":[0.999007,0.00008708637,0.0001771351,0.000292394,0.0002411794,0.0001952226],"domain_scores_gemma":[0.9994029,0.00008067778,0.00006731716,0.0001726677,0.0001779041,0.00009855635],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002467547,0.00003493707,0.0009784206,0.000005168162,0.00001490359,0.000004971286,0.001430101,0.7408102,0.01122894,0.0004540274,0.0004136613,0.2446],"study_design_scores_gemma":[0.0002718154,0.0002034574,0.03584676,0.000004812913,0.00000645156,0.000006694607,0.00001374694,0.9595754,0.001860263,0.0002260295,0.001818265,0.000166262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.198576,0.000003347626,0.7972455,0.002713038,0.000555994,0.0001948064,0.000001257583,0.0001407018,0.0005693512],"genre_scores_gemma":[0.9431664,5.835756e-7,0.056254,0.0002188173,0.0002030268,0.00001423872,0.00001644446,0.000009695031,0.0001167689],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7445904,"threshold_uncertainty_score":0.4433253,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Generative grammar; Artificial neural network; Artificial intelligence; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.091277332981538,"gpt":0.1974521629490948,"spread":0.1061748299675568,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004372209,0.0005431044,0.0005624021,0.0002071686,0.0003214144,0.0003445167,0.00164633,0.0003682934,0.00004116672],"category_scores_gemma":[0.00003973878,0.0005834864,0.0002875343,0.0006832068,0.0001521776,0.0008764187,0.001823724,0.0006821562,0.00001382764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002568449,"about_ca_system_score_gemma":0.0002080293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001428718,"about_ca_topic_score_gemma":0.00008819134,"domain_scores_codex":[0.9969025,0.0005008654,0.0003237489,0.001513221,0.0001574469,0.0006022514],"domain_scores_gemma":[0.9975871,0.00009002515,0.0004048628,0.001177403,0.0004009288,0.0003396746],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002252244,0.00003984314,0.00005443614,0.000007538523,0.0001113739,0.0001305002,0.0007776786,0.9902427,0.000007116721,0.003643813,0.0003631804,0.004599262],"study_design_scores_gemma":[0.0003802587,0.00006576163,0.00002534804,0.00003533995,0.00008648272,0.000006326202,0.0001392139,0.9882996,0.00003527831,0.01017487,0.0001252424,0.0006262576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002364404,0.0001800945,0.9930975,0.0001608473,0.001672756,0.000381365,0.00001228428,0.0002784791,0.001852224],"genre_scores_gemma":[0.946556,0.00009958699,0.05195058,0.000181708,0.0005990079,0.000002686025,0.00007580975,0.00003759549,0.0004970356],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9441916,"threshold_uncertainty_score":0.9996617,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01451056422384049,"gpt":0.2381944619302341,"spread":0.2236838977063936,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002694791,0.00009176824,0.0001071126,0.00004218637,0.0001066119,0.00009605135,0.0004156706,0.00003698073,0.00004191758],"category_scores_gemma":[0.00003410271,0.00007530367,0.00003969674,0.0001276783,0.00001639585,0.0004004518,0.0001566127,0.00006333176,0.0003252198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001588795,"about_ca_system_score_gemma":0.00001214461,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005585681,"about_ca_topic_score_gemma":0.000006628454,"domain_scores_codex":[0.9991826,0.00006164725,0.0001439216,0.0002397159,0.0002065259,0.0001656308],"domain_scores_gemma":[0.9994287,0.00005816098,0.00005045693,0.0003389039,0.00005454281,0.00006920494],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001734777,0.0003444378,0.001795085,0.00002509477,0.00008342941,0.00000785285,0.0007494886,0.3838385,0.02548012,0.0597397,0.01490453,0.5130144],"study_design_scores_gemma":[0.0001993273,0.0000310706,0.004857361,0.000005571207,0.000002621735,0.000001776791,0.000003076078,0.9859567,0.005759709,0.0009505265,0.002131655,0.0001006371],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005103838,0.000005044292,0.9850072,0.0005607369,0.0003757477,0.00007786013,2.282388e-7,0.00007662455,0.008792728],"genre_scores_gemma":[0.7715456,0.000001574435,0.2275679,0.0003614279,0.00009241513,0.000003613441,0.000002420289,0.000003776759,0.0004212664],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7664418,"threshold_uncertainty_score":0.4180151,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01234276547243436,"gpt":0.2103868907219398,"spread":0.1980441252495055,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00007524632,0.00007066972,0.00008124138,0.00001924309,0.00004069923,0.0001737057,0.000293481,0.00002705989,0.0006441666],"category_scores_gemma":[0.000008083415,0.00005672178,0.00003751044,0.00009034493,0.000008135418,0.0005952474,0.00009827669,0.00003783365,0.001497825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001070225,"about_ca_system_score_gemma":0.00001561857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001277064,"about_ca_topic_score_gemma":0.00001713853,"domain_scores_codex":[0.9993849,0.00004030462,0.00009197945,0.000251981,0.0001107387,0.0001200543],"domain_scores_gemma":[0.9995062,0.00002872381,0.0000265882,0.0003596182,0.00004169452,0.00003718639],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004243194,0.00006877854,0.001845264,0.000001886751,0.00005193322,0.000007757082,0.0004881556,0.003716728,0.8021799,0.07175753,0.07248873,0.04738914],"study_design_scores_gemma":[0.0001519379,0.00002066103,0.001624655,0.000001664386,0.000002110845,4.209043e-7,0.000009439588,0.9525619,0.03450599,0.0008849163,0.01011864,0.0001176794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02902628,0.0000346358,0.9474909,0.0008342562,0.0006113667,0.00007766371,0.000001456121,0.00007673203,0.02184671],"genre_scores_gemma":[0.6712181,0.00000293427,0.3257136,0.000585443,0.0002569468,0.00000228889,0.000005999885,0.00000377495,0.002210894],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9488451,"threshold_uncertainty_score":0.9992796,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03970591529768274,"gpt":0.24661055085706,"spread":0.2069046355593772,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006874144,0.00009388624,0.0001014823,0.00004293599,0.0003372502,0.00006598199,0.0001292592,0.0000238798,0.000002752576],"category_scores_gemma":[0.00002853314,0.00008731653,0.00002555218,0.0001629748,0.00005099574,0.000520666,0.0001029722,0.00006542105,0.000006611187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001357364,"about_ca_system_score_gemma":0.00001333222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003395037,"about_ca_topic_score_gemma":0.000002616931,"domain_scores_codex":[0.9992505,0.00007582743,0.00012385,0.0002556416,0.0001320413,0.0001621069],"domain_scores_gemma":[0.9996394,0.00008870383,0.00005801809,0.00007743722,0.00007839514,0.00005805455],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002904485,0.00006810875,0.01412265,0.00002696197,0.00005592594,0.0001827794,0.005225856,0.5209548,0.03496009,0.00691797,0.00337063,0.4140852],"study_design_scores_gemma":[0.000170214,0.00004006536,0.03347445,0.000005165821,0.000003955754,0.0000433855,0.00001455445,0.963959,0.001689345,0.0004015424,0.00008767897,0.0001106348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2311601,0.0001701287,0.7678217,0.0002831341,0.0002892646,0.00006712271,5.521413e-7,0.0000638231,0.0001442547],"genre_scores_gemma":[0.9524497,0.00003844761,0.04708449,0.0002899935,0.0001022605,0.000003043596,0.000001909347,0.000004095551,0.00002601605],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7212897,"threshold_uncertainty_score":0.3560665,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02418145173831861,"gpt":0.237948323936502,"spread":0.2137668721981834,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001010135,0.00008626745,0.0001543664,0.0001656925,0.0007442479,0.00003393073,0.001100982,0.0002281391,0.00001982329],"category_scores_gemma":[0.0001093883,0.00009606887,0.00008546833,0.00008906456,0.0002431696,0.0008230265,0.0003297596,0.000138247,0.000008821734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002293198,"about_ca_system_score_gemma":0.00003441022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005378326,"about_ca_topic_score_gemma":0.00004065979,"domain_scores_codex":[0.9993876,0.0000144611,0.00005881396,0.0002893758,0.00009613538,0.0001536632],"domain_scores_gemma":[0.9988685,0.00004399804,0.0002163496,0.0006895596,0.0001489503,0.00003270172],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001157558,0.0002665061,0.01748111,0.00004792856,0.000387441,0.000064846,0.000735819,0.004677393,0.0206912,0.5974716,0.05810838,0.2999521],"study_design_scores_gemma":[0.002151046,0.0002268411,0.1186119,0.00008865241,0.0001100801,0.00003138696,0.0003300119,0.5910655,0.01696571,0.05253104,0.2172691,0.0006187231],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002963063,0.00007016264,0.9796945,0.01458151,0.0003057901,0.0001429265,0.00001394382,0.0001151043,0.00211294],"genre_scores_gemma":[0.5725609,0.00001947976,0.4251266,0.00002355208,0.00003659491,7.980722e-7,0.00000435031,0.000004304456,0.002223448],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5863882,"threshold_uncertainty_score":0.5724228,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}