{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":2372,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":2372,"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":"a80d432d834b","filters":{"topic":"Neural Networks and Applications"}},"results":[{"id":"W2100495367","doi":"10.1126/science.1127647","title":"Reducing the Dimensionality of Data with Neural Networks","year":2006,"lang":"en","type":"article","venue":"Science","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":20953,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; University of New Brunswick","funders":"","keywords":"Autoencoder; Curse of dimensionality; Initialization; Gradient descent; Artificial neural network; Computer science; Principal component analysis; Artificial intelligence; Pattern recognition (psychology); Layer (electronics); High dimensional; Principal (computer security); Algorithm; Materials science; Nanotechnology","retraction":null,"screen_n_in":null,"score":{"opus":0.02973157325527122,"gpt":0.276790050995563,"spread":0.2470584777402918,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005265945,0.00004894465,0.00005221579,0.00001702203,0.0003162309,0.00009459401,0.002523398,0.000007951001,0.000001641591],"category_scores_gemma":[0.000006815731,0.00002622642,0.000009154939,0.00109601,0.0005157934,0.0006429875,0.0006715378,0.00007112655,0.00000103605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006308826,"about_ca_system_score_gemma":0.00005468521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001195178,"about_ca_topic_score_gemma":0.00002163401,"domain_scores_codex":[0.9990424,0.0000167717,0.0001105284,0.0003452997,0.0003013061,0.0001837132],"domain_scores_gemma":[0.9984931,0.00007752509,0.00007295805,0.00126106,0.00006484637,0.0000304592],"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":[0.000006636444,0.0001280139,0.003475391,0.000005106132,0.000003974991,0.000005250487,0.00009407605,0.4065786,0.01347584,0.4391162,0.004385148,0.1327258],"study_design_scores_gemma":[0.0000319856,0.00001194472,0.01812793,0.000005291723,0.000001492883,0.00001059558,0.000002441876,0.9789166,0.0004298319,0.001820132,0.000595943,0.00004581763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3416273,0.0003079697,0.6491382,0.006597493,0.0002414931,0.0002501066,0.000004470845,0.00008515083,0.001747843],"genre_scores_gemma":[0.9888866,0.000001553074,0.01085627,0.0001564633,0.00005974308,0.000002720948,0.000001517926,0.000001480597,0.00003367252],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6472592,"threshold_uncertainty_score":0.4689143,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2990138404","doi":"10.7551/mitpress/7503.001.0001","title":"Advances in Neural Information Processing Systems 19","year":2007,"lang":"en","type":"book","venue":"The MIT Press eBooks","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":15653,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Presentation (obstetrics); Computer science; Artificial intelligence; Artificial neural network; Neural system; Information processing; Computation; Cognitive science; Computational neuroscience; Data science; Psychology; Neuroscience; Medicine; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.02324598906576989,"gpt":0.2595556331874428,"spread":0.2363096441216729,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002455104,0.0001914832,0.0001888813,0.00008312333,0.0001514421,0.000393053,0.001216134,0.0001168011,3.759437e-7],"category_scores_gemma":[0.000004164615,0.0001326792,0.00004678431,0.00003863569,0.00007196594,0.0006295816,0.0002362586,0.0003873874,0.0000104192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005999385,"about_ca_system_score_gemma":0.00008560498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004715829,"about_ca_topic_score_gemma":0.0000176658,"domain_scores_codex":[0.9988297,0.0000353735,0.0003871642,0.0002038983,0.0002835417,0.0002603128],"domain_scores_gemma":[0.9989512,0.00009570671,0.0003119082,0.0005286706,0.00005981806,0.00005269899],"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":[0.000006607064,0.00000623809,0.000001031452,0.0002422369,0.00000502074,0.000004840449,0.0008631006,0.005960553,0.000002214078,0.2110602,0.006056977,0.7757909],"study_design_scores_gemma":[0.000100059,0.00001152954,0.000004354726,0.0001895386,0.000007693951,0.00001678145,0.000006137894,0.1043613,0.00001124776,0.003115498,0.8919953,0.0001806397],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.000007423416,0.009250483,0.07264421,0.00007368043,0.0003560756,0.0008580135,0.000005344085,0.0001800585,0.9166247],"genre_scores_gemma":[0.03363869,0.0005767288,0.001288155,0.001538076,0.001323293,0.0006876396,0.00005706139,0.00006108698,0.9608293],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.8859383,"threshold_uncertainty_score":0.5410502,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1533861849","doi":"","title":"Understanding the difficulty of training deep feedforward neural networks","year":2010,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":12692,"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":"Initialization; Computer science; Artificial neural network; Artificial intelligence; Deep neural networks; Deep learning; Gradient descent; Jacobian matrix and determinant; Sigmoid function; Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0766112791778204,"gpt":0.2560151960910123,"spread":0.1794039169131919,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001348502,0.00007370247,0.00008520162,0.00001701556,0.0002011595,0.00008899577,0.0006619082,0.00003703808,0.00001803568],"category_scores_gemma":[0.000006632384,0.00004259344,0.00005890067,0.0002987618,0.0000771252,0.0001361097,0.0001224949,0.0002272308,0.000001723102],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006628966,"about_ca_system_score_gemma":0.000007299157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000664315,"about_ca_topic_score_gemma":0.00008055416,"domain_scores_codex":[0.9993667,0.00001527436,0.0001453698,0.0001611062,0.0001151528,0.0001963939],"domain_scores_gemma":[0.9993367,0.0001616732,0.00006337836,0.0003652685,0.00002126118,0.00005171751],"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":[0.00000130474,0.00001825658,0.0002587744,0.000001427557,0.000008563504,8.019522e-7,0.000592118,0.03048772,0.001653858,0.9373038,0.0007940409,0.02887934],"study_design_scores_gemma":[0.00007343879,0.00001167282,0.00140226,0.000001537455,0.000002991004,0.000009276871,0.0001604139,0.9926758,0.00007465102,0.005216208,0.0003064002,0.0000653758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02871195,0.000009785513,0.9652681,0.002458029,0.0002788863,0.00009974415,2.341066e-7,0.00007782802,0.003095463],"genre_scores_gemma":[0.9949362,0.000002744761,0.00453255,0.0003260238,0.0001227311,0.000007770795,7.162992e-7,0.000004203295,0.00006704874],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9662243,"threshold_uncertainty_score":0.173691,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2557283755","doi":"","title":"Deep Learning","year":2016,"lang":"de","type":"book","venue":"MIT Press eBooks","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":8960,"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":"Deep learning; Computer science; Artificial intelligence; Algorithmic learning theory; Machine learning; Computational learning theory; Active learning (machine learning)","retraction":null,"screen_n_in":null,"score":{"opus":0.02801402541004143,"gpt":0.2453007604005888,"spread":0.2172867349905473,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001943977,0.0005312682,0.0004775354,0.00008043359,0.0005230563,0.0004930309,0.002016958,0.000404775,0.00008155565],"category_scores_gemma":[0.00001495344,0.0004368855,0.0002805266,0.00002484255,0.0002270401,0.0001246458,0.001059536,0.0009057464,0.001144412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008389734,"about_ca_system_score_gemma":0.000119784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002790025,"about_ca_topic_score_gemma":0.000007504893,"domain_scores_codex":[0.9970171,0.0001559889,0.0005192061,0.001105575,0.0004607743,0.0007413125],"domain_scores_gemma":[0.9975494,0.0003148812,0.0004239122,0.001287171,0.000145045,0.0002796047],"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":[0.000009387148,0.00002781344,0.00000615084,0.0000820436,0.0001540128,0.00005856947,0.0003714069,0.0003115329,0.0002433058,0.3389819,0.02852829,0.6312256],"study_design_scores_gemma":[0.000249215,0.000065576,0.000009418106,0.0003301258,0.0000775458,0.00001302787,9.203035e-7,0.01498034,0.0003225144,0.004583298,0.9787937,0.0005743043],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00000919824,0.003701657,0.232069,0.0001939141,0.001016941,0.0006276477,0.00001069292,0.0003492585,0.7620217],"genre_scores_gemma":[0.001954238,0.0003731385,0.001641755,0.000324772,0.002326363,0.0001891525,0.00001837398,0.00007765589,0.9930946],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.9502654,"threshold_uncertainty_score":0.9998083,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1673923490","doi":"10.48550/arxiv.1312.6199","title":"Intriguing properties of neural networks","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":5745,"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 neural network; Artifact (error); Perturbation (astronomy); Artificial intelligence; Deep neural networks; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.07728990108899962,"gpt":0.1701870991943954,"spread":0.0928971981053958,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008425785,0.0002067847,0.0002616588,0.00009851163,0.0001039313,0.00009703667,0.001694724,0.0001701541,0.00001228762],"category_scores_gemma":[0.000006885123,0.0001987883,0.0001478421,0.0004299554,0.000111517,0.0002833951,0.001909495,0.0004555708,0.00001703648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004164759,"about_ca_system_score_gemma":0.00004202702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001606429,"about_ca_topic_score_gemma":0.000008803483,"domain_scores_codex":[0.9987804,0.00006581539,0.000201278,0.0006309309,0.00005422464,0.000267304],"domain_scores_gemma":[0.9984729,0.00003618543,0.0002528706,0.0009893302,0.0001477632,0.0001009561],"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":[0.000004191344,0.00003712624,0.0003507134,0.00003680055,0.00002674555,0.00001257888,0.00005222073,0.8779278,0.00009884881,0.1187561,0.0004496281,0.002247262],"study_design_scores_gemma":[0.0001016139,0.00001692272,0.0001851214,0.00006987686,0.00001926433,0.000001877811,0.00001138354,0.9909154,0.000223318,0.008101819,0.0001399488,0.000213485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4524943,0.000212587,0.5458264,0.0001791939,0.0003519256,0.0003201387,0.000001562392,0.0001549285,0.0004589239],"genre_scores_gemma":[0.9985267,0.0001349753,0.0006260335,0.00007786498,0.0001125365,0.000002651722,0.000003143167,0.00001103242,0.0005050815],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5460324,"threshold_uncertainty_score":0.8106353,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2296073425","doi":"10.1145/1553374.1553380","title":"Curriculum learning","year":2009,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":4978,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Canadian Institute for Advanced Research","keywords":"Curriculum; Computer science; Generalization; Context (archaeology); Maxima and minima; Process (computing); Convergence (economics); Artificial intelligence; Set (abstract data type); Artificial neural network; Machine learning; Quality (philosophy); Mathematics; Pedagogy; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.006241040853153789,"gpt":0.2329453405396021,"spread":0.2267042996864483,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00002327845,0.00002447263,0.00002324538,0.000008872494,0.00006079009,0.00004780029,0.0002010639,0.000007759912,0.00001307336],"category_scores_gemma":[0.000001719189,0.00001860541,0.00001363098,0.0001493156,0.000002586015,0.0001020567,0.00002159399,0.00004662851,0.00009460536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002168525,"about_ca_system_score_gemma":0.000002488684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003277692,"about_ca_topic_score_gemma":4.025039e-7,"domain_scores_codex":[0.9997522,0.000004964894,0.00003683652,0.00008906036,0.00004139499,0.00007556287],"domain_scores_gemma":[0.9998387,0.000004757772,0.000009678994,0.0001106929,0.00000973484,0.0000264634],"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":[2.345036e-8,0.00001861352,0.0005252927,1.184948e-7,3.578483e-7,9.400222e-7,0.00001318297,0.0004592882,0.000276513,0.8347209,0.005875478,0.1581093],"study_design_scores_gemma":[0.0001001627,0.00009120844,0.006112925,0.000003731366,0.000001036369,0.00001290615,0.00001505481,0.7805358,0.0007378651,0.03135203,0.180867,0.0001703594],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01876992,0.00002811245,0.9252193,0.006684596,0.00003975127,0.00003844802,9.339796e-9,0.0003188509,0.04890104],"genre_scores_gemma":[0.9822096,0.000005061161,0.01558395,0.0007091445,0.000035968,0.000001326254,1.77663e-7,5.787705e-7,0.001454243],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9634396,"threshold_uncertainty_score":0.1215992,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1815076433","doi":"10.48550/arxiv.1211.5063","title":"On the difficulty of training Recurrent Neural Networks","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":3804,"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":"Constraint (computer-aided design); Perspective (graphical); Computer science; Artificial neural network; Simple (philosophy); Norm (philosophy); Artificial intelligence; Gradient descent; Algorithm; Mathematical optimization; Mathematics; Geometry; Epistemology","retraction":null,"screen_n_in":null,"score":{"opus":0.1297134932191586,"gpt":0.2002915810523392,"spread":0.07057808783318056,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001687753,0.0002081376,0.0002156892,0.00005189482,0.0001606939,0.00005029282,0.001650132,0.0001311556,0.00001673967],"category_scores_gemma":[0.00001088182,0.000160111,0.000194102,0.0004047268,0.00009630374,0.0001071848,0.001005951,0.0006418378,0.000009700831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004233395,"about_ca_system_score_gemma":0.00002755613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001489359,"about_ca_topic_score_gemma":0.00000639882,"domain_scores_codex":[0.9988281,0.0001145951,0.0001646229,0.0005165026,0.00007038518,0.000305811],"domain_scores_gemma":[0.9982595,0.0002908367,0.0002617836,0.001020018,0.00006118655,0.0001066043],"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":[0.000005279468,0.00005951638,0.0001045659,0.000006554753,0.00002037978,0.000004975371,0.0001492858,0.5043672,0.000005788212,0.4905089,0.00065002,0.004117513],"study_design_scores_gemma":[0.00009714736,0.00002420111,0.00110259,0.00004858106,0.00002651872,0.000001393128,0.00002937135,0.9875546,0.00001267714,0.01069216,0.0002210639,0.000189765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4255062,0.00008327095,0.5712043,0.0005502145,0.0008123084,0.0003665476,0.000009165301,0.0001196904,0.001348272],"genre_scores_gemma":[0.9993502,0.00006802109,0.0001348274,0.0001382865,0.0001448371,0.000002249695,0.000007808053,0.000008889551,0.0001448698],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.573844,"threshold_uncertainty_score":0.6529137,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4236362309","doi":"10.1017/cbo9781107298019","title":"Understanding Machine Learning","year":2014,"lang":"en","type":"book","venue":"Cambridge University Press eBooks","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":2928,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Stability (learning theory); Algorithmic learning theory; Computational learning theory; Machine learning; Presentation (obstetrics); Stochastic gradient descent; Convexity; Online machine learning; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.05762217010005879,"gpt":0.2046455974230524,"spread":0.1470234273229936,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001009119,0.0002485792,0.0002622651,0.0001173096,0.000414022,0.0001294712,0.001211538,0.0001930615,8.699756e-7],"category_scores_gemma":[0.000003604813,0.0002856335,0.0001426548,0.00002674047,0.00009477842,0.0001133689,0.0007153347,0.000629918,0.00001754375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003542686,"about_ca_system_score_gemma":0.00009971356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002473984,"about_ca_topic_score_gemma":0.00000180942,"domain_scores_codex":[0.998781,0.00007308075,0.0001259354,0.0005250244,0.0002124162,0.0002825684],"domain_scores_gemma":[0.9988942,0.0001231324,0.0001908193,0.0005948472,0.00004747845,0.0001494787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002763021,0.000003108744,9.586888e-7,0.00001984543,0.00002230032,0.00003341856,0.00001152847,0.00008662833,0.000007737931,0.8615418,0.1376904,0.0005795018],"study_design_scores_gemma":[0.0002015491,0.0000282476,0.000001479958,0.00006304532,0.00003369712,0.00001096938,0.000003144427,0.02888526,0.00002501162,0.0001001394,0.9703448,0.0003026473],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00000139262,0.00003817111,0.380899,0.0000374941,0.0001041715,0.0001271857,0.000009869626,0.0002295493,0.6185532],"genre_scores_gemma":[0.001134221,0.00004181499,0.0006878793,0.00009777147,0.0001540374,7.042436e-7,0.00003628258,0.00002294792,0.9978243],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.8614417,"threshold_uncertainty_score":0.9999596,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2255466643","doi":"10.1007/978-3-642-24797-2_4","title":"Long Short-Term Memory","year":2012,"lang":"en","type":"book-chapter","venue":"Studies in computational intelligence","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":2210,"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","funders":"","keywords":"Recurrent neural network; Term (time); Context (archaeology); Computer science; Range (aeronautics); Artificial intelligence; Artificial neural network; Algorithm; History; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1345260632334938,"gpt":0.3677383313228128,"spread":0.233212268089319,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002239589,0.000347765,0.0003923778,0.0001732686,0.0001662529,0.0000589526,0.001007292,0.0001284747,0.00005536958],"category_scores_gemma":[0.00001635783,0.0003367562,0.0001270855,0.0001355665,0.0003166778,0.000241657,0.0007751985,0.0004412323,0.0002952178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001505374,"about_ca_system_score_gemma":0.00005952765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000204028,"about_ca_topic_score_gemma":0.0000213648,"domain_scores_codex":[0.9980469,0.00001993443,0.0005705442,0.0006019959,0.0004288035,0.0003318001],"domain_scores_gemma":[0.9984093,0.0006366261,0.0001532824,0.0004603595,0.0002528262,0.00008763797],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001818466,0.00002745283,0.00006472057,0.00004326789,0.00007525955,0.0000372092,0.0003975427,0.02768159,5.817568e-7,0.7921205,0.001434518,0.1781155],"study_design_scores_gemma":[0.000065564,0.00006799877,0.0007084536,0.0006937141,0.00003802464,0.0001080592,0.00005532864,0.0346926,0.0000610764,0.9504216,0.01195854,0.001129025],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00005499609,0.02660946,0.8434322,0.0009049121,0.001731956,0.0006231011,0.00001513684,0.0002055864,0.1264226],"genre_scores_gemma":[0.7290986,0.01522206,0.08873793,0.001870189,0.002794906,0.0003476375,0.0001338201,0.0001645232,0.1616304],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7546943,"threshold_uncertainty_score":0.9999084,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2792919287","doi":"10.1038/nmeth.4642","title":"Statistics versus machine learning","year":2018,"lang":"en","type":"article","venue":"Nature Methods","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1490,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"National Institute of Mental Health","keywords":"Computer science; Statistics; Computational biology; Artificial intelligence; Machine learning; Biology; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02982139966341541,"gpt":0.4125295686340756,"spread":0.3827081689706602,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003866513,0.00007241018,0.00007851949,0.00002949892,0.0001739495,0.00006464415,0.000434364,0.00009604434,0.00003503096],"category_scores_gemma":[0.0001659767,0.0000598747,0.00002200786,0.0003495865,0.00003982949,0.00007670196,0.0001414544,0.0005244471,0.00004007155],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001137918,"about_ca_system_score_gemma":0.00001463402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004844168,"about_ca_topic_score_gemma":0.000006864556,"domain_scores_codex":[0.9992747,0.0001614074,0.00008544438,0.0002156506,0.0001083402,0.0001545011],"domain_scores_gemma":[0.9990788,0.000439866,0.00004538825,0.0002986443,0.00008227558,0.00005504736],"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":[0.00000770559,0.0000103932,0.00003920195,0.000001862228,0.000007813067,0.000001967966,0.00005851593,0.00002788398,0.001118475,0.3299319,0.006085683,0.6627086],"study_design_scores_gemma":[0.0002398149,0.0001285674,0.0004184403,0.000003162122,0.000006566474,0.000004651032,0.000002247658,0.2451328,0.004626358,0.01446938,0.734838,0.0001299858],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001255978,0.0003676185,0.9930895,0.0006495796,0.0009980379,0.00004865931,0.000002856095,0.0001282558,0.004589885],"genre_scores_gemma":[0.02861033,0.0000170672,0.9699241,0.0003990953,0.0003432235,0.000004700017,0.000004128671,0.000006137806,0.0006912137],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7287523,"threshold_uncertainty_score":0.2441619,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4231081240","doi":"10.1017/cbo9781107447615","title":"Neuronal Dynamics","year":2014,"lang":"en","type":"book","venue":"Cambridge University Press eBooks","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1482,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Field (mathematics); Graduate students; Ideal (ethics); Code (set theory); Computational neuroscience; Cognitive science; Dynamics (music); Artificial intelligence; Mathematics; Psychology; Epistemology; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01261663598135967,"gpt":0.1844475031943825,"spread":0.1718308672130228,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00005330666,0.0002489738,0.000243932,0.00008452644,0.0002053551,0.0001020078,0.001796977,0.0001992753,5.145207e-7],"category_scores_gemma":[0.00000200347,0.0002924015,0.0001573347,0.00002063559,0.0001116109,0.0001011829,0.0008517631,0.0004331918,0.0000265634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001949825,"about_ca_system_score_gemma":0.0001552895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001617248,"about_ca_topic_score_gemma":0.000002281323,"domain_scores_codex":[0.9987774,0.0000465741,0.0001258283,0.0005628042,0.0002183319,0.0002690014],"domain_scores_gemma":[0.9985918,0.00008453647,0.0001608161,0.0009164862,0.00008489804,0.0001614055],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001890915,0.000004189078,2.392978e-7,0.00001249217,0.0000114848,0.00002378889,0.000002383193,0.00001637378,0.000002002441,0.7168006,0.2797502,0.003374367],"study_design_scores_gemma":[0.000148445,0.00002447044,0.00001175763,0.00002916591,0.0000288367,0.00001129851,6.155319e-7,0.03365987,0.00001737731,0.00005194551,0.9657314,0.0002847859],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00001189352,0.00001507582,0.1775621,0.00007932715,0.0002273295,0.0001852836,0.00005286479,0.0002250521,0.8216411],"genre_scores_gemma":[0.0001842721,0.0000155089,0.0008690821,0.0002476673,0.000205466,9.891901e-7,0.00005980218,0.00002070714,0.9983965],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.7167486,"threshold_uncertainty_score":0.9999528,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2157444450","doi":"","title":"Stochastic Neighbor Embedding","year":2002,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1461,"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":"Embedding; Probabilistic logic; Dimensionality reduction; Gaussian; Artificial intelligence; Computer science; Pairwise comparison; Object (grammar); Pattern recognition (psychology); Curse of dimensionality; Probability distribution; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02553129081262742,"gpt":0.2468882646029416,"spread":0.2213569737903142,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00001832721,0.00003818022,0.00003505977,0.0000152873,0.0000687068,0.00006557803,0.0002898212,0.00001093269,0.0002148798],"category_scores_gemma":[0.000002742723,0.00003045494,0.00001797273,0.0001707603,0.000007482363,0.0001363948,0.00006474266,0.00003637454,0.000386848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004405116,"about_ca_system_score_gemma":0.000001231681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001986537,"about_ca_topic_score_gemma":6.919708e-7,"domain_scores_codex":[0.9996374,0.000003935244,0.00005720406,0.0001293293,0.00006060322,0.0001115281],"domain_scores_gemma":[0.9996777,0.00003334304,0.00001318212,0.0002220645,0.00001045947,0.00004323167],"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":[1.249425e-7,0.00003968337,0.00001190909,0.000001068394,0.000003051016,0.000002296308,0.00008911602,0.006989913,0.0003586838,0.8375745,0.04009578,0.1148339],"study_design_scores_gemma":[0.00003549474,0.0000064183,0.00006001737,0.000001563682,5.842806e-7,0.000004884246,0.000001707305,0.9927369,0.00005292757,0.002696776,0.004352274,0.00005048397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009631094,0.00004005274,0.9788929,0.002227949,0.00006866893,0.00004558987,1.247579e-7,0.000156826,0.0176048],"genre_scores_gemma":[0.9746878,0.000002821266,0.0216906,0.0006152004,0.0000622803,0.000009767173,1.139814e-7,0.000002277672,0.002929141],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.985747,"threshold_uncertainty_score":0.4972277,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2524428287","doi":"10.48550/arxiv.1609.07061","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1425,"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 neural network; Computer science; Artificial intelligence; Training (meteorology); Deep neural networks; Machine learning; Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.05472264213829894,"gpt":0.1950270013615765,"spread":0.1403043592232775,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001669687,0.0004609375,0.0004463814,0.0001827354,0.0005050921,0.0003094576,0.001343899,0.0002967212,0.00001058335],"category_scores_gemma":[0.00001075579,0.0003732446,0.0001562155,0.0007366878,0.0001717587,0.0007180257,0.001251208,0.0007660251,0.000003649511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000710359,"about_ca_system_score_gemma":0.00006550121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002318733,"about_ca_topic_score_gemma":0.0000367748,"domain_scores_codex":[0.997429,0.0001681712,0.0002771558,0.001417166,0.0001249856,0.0005835665],"domain_scores_gemma":[0.9975598,0.0004471494,0.0003762728,0.001177846,0.0001460562,0.0002929091],"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":[0.00007478862,0.00005085718,0.0009694154,0.00001266324,0.00006125742,0.00007390648,0.0001023296,0.9245196,0.0000133466,0.06128363,0.0002222204,0.01261599],"study_design_scores_gemma":[0.0006791388,0.00007178754,0.001826543,0.0001645323,0.00005063385,0.00001857659,0.00002153441,0.9865987,0.00000791407,0.009901435,0.0001626409,0.0004966137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2464349,0.00009051136,0.7517152,0.0004403812,0.0003598176,0.0004525939,0.000006029177,0.0002648708,0.0002357083],"genre_scores_gemma":[0.997081,0.0002299902,0.001752892,0.0001618876,0.0003294442,0.000007595684,0.00001994748,0.00003307277,0.00038414],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7506461,"threshold_uncertainty_score":0.999872,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2218318129","doi":"","title":"Contractive Auto-Encoders: Explicit Invariance During Feature Extraction","year":2011,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1136,"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; Encoder; Jacobian matrix and determinant; Autoencoder; Algorithm; Matrix norm; Pattern recognition (psychology); Feature extraction; Range (aeronautics); Representation (politics); Term (time); Artificial intelligence; Mathematics; Mathematical optimization; Artificial neural network; Eigenvalues and eigenvectors; Applied mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03152472788549156,"gpt":0.2444016614948825,"spread":0.212876933609391,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005517667,0.00009493736,0.00008304259,0.00003122939,0.0001625048,0.00007832137,0.0003981501,0.00005699255,0.00007115947],"category_scores_gemma":[0.000006054554,0.00008099793,0.00003818553,0.0002312362,0.00001382093,0.0009499017,0.00007607753,0.0001727931,0.00009233694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002328017,"about_ca_system_score_gemma":0.00001636461,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005813528,"about_ca_topic_score_gemma":0.00001982611,"domain_scores_codex":[0.9992757,0.00001833777,0.0001010476,0.0003059926,0.0001044373,0.0001945243],"domain_scores_gemma":[0.9993972,0.00003793863,0.00007155722,0.0003757961,0.00004524528,0.00007232437],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00003151807,0.0003420798,0.0006322176,0.00001303739,0.00004239521,0.0000526859,0.002009337,0.0001209475,0.07581229,0.8837336,0.008621204,0.02858866],"study_design_scores_gemma":[0.002346499,0.0002518975,0.3347641,0.0001243814,0.00004229713,0.0004841936,0.0007388803,0.2258424,0.3248143,0.0749817,0.03371411,0.001895343],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02295735,0.0000494449,0.9358572,0.001741729,0.0002306292,0.0002391789,8.545206e-7,0.000385064,0.03853858],"genre_scores_gemma":[0.9511995,0.0000215336,0.04587879,0.0003704267,0.00009177541,0.00005346168,6.453074e-7,0.000005828649,0.002377986],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9282422,"threshold_uncertainty_score":0.3303,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2108677974","doi":"","title":"Practical Variational Inference for Neural Networks","year":2011,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1066,"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; Artificial neural network; Heuristic; Simple (philosophy); Pruning; Inference; Perspective (graphical); Artificial intelligence; Function (biology); TIMIT; Algorithm; Hidden Markov model","retraction":null,"screen_n_in":null,"score":{"opus":0.08821316975451085,"gpt":0.3227024568937303,"spread":0.2344892871392194,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008503747,0.0000580032,0.00005344275,0.00001438512,0.0000941313,0.00005903022,0.0002911093,0.00003203323,0.00006290636],"category_scores_gemma":[0.00002433334,0.00004672047,0.00003324412,0.0001372422,0.00001654803,0.000336574,0.00008988185,0.00006768121,0.00001323115],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000492274,"about_ca_system_score_gemma":0.00002186555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009031,"about_ca_topic_score_gemma":0.000004642723,"domain_scores_codex":[0.9994498,0.00001261194,0.0001116201,0.0001919825,0.00007127709,0.0001626343],"domain_scores_gemma":[0.9993744,0.0002349225,0.00003925812,0.0002236387,0.00006421154,0.00006352488],"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":[0.000002197851,0.0000349226,0.00015744,5.066193e-7,0.000002691224,4.749555e-7,0.00001949821,0.0007465028,0.000005294358,0.9883907,0.004472432,0.006167366],"study_design_scores_gemma":[0.00008008257,0.00003514762,0.002728545,6.539146e-7,0.00000223788,0.00000567405,0.000001330749,0.9695945,0.00003307685,0.02529711,0.002153042,0.00006864672],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000175407,0.000003941189,0.9932542,0.002182627,0.0001586274,0.0001525786,6.053044e-7,0.00010408,0.003967945],"genre_scores_gemma":[0.6208972,0.000001665712,0.3779199,0.0008454502,0.00009926091,0.00006380221,0.000002054453,0.000002559683,0.0001681163],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9688479,"threshold_uncertainty_score":0.1905206,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2124537004","doi":"10.1016/j.tics.2007.09.004","title":"Learning multiple layers of representation","year":2007,"lang":"en","type":"review","venue":"Trends in Cognitive Sciences","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1013,"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":"Backpropagation; Representation (politics); Artificial neural network; Computer science; Artificial intelligence; Perception; Generative model; Object (grammar); Generative grammar; Machine learning; Sensory system; Feature learning; Layer (electronics); Pattern recognition (psychology); Psychology; Neuroscience","retraction":null,"screen_n_in":null,"score":{"opus":0.4044359756793465,"gpt":0.5100302918961084,"spread":0.1055943162167619,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000693017,0.0001678388,0.0005024289,0.000694631,0.0001370651,0.00006983105,0.0007896414,0.00008217652,0.00002026165],"category_scores_gemma":[0.0001225511,0.0001325175,0.0001608377,0.004315678,0.000301316,0.0002704529,0.0001885584,0.0002768545,0.00001170928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002102658,"about_ca_system_score_gemma":0.00007056801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004343014,"about_ca_topic_score_gemma":0.00004066372,"domain_scores_codex":[0.9982464,0.000147382,0.000439646,0.0005873201,0.0003193235,0.0002598786],"domain_scores_gemma":[0.9980916,0.001258204,0.0003778831,0.0001665789,0.00006186132,0.00004386982],"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":[3.802637e-7,0.00002063341,0.0001169129,0.00006974064,0.000004668014,0.000002824172,0.00008205034,0.00003793644,2.516085e-7,0.000819259,0.0000303482,0.998815],"study_design_scores_gemma":[0.0008628422,0.0006782679,0.001283833,0.01794392,0.0002149038,0.00006325991,0.000761961,0.02581012,0.0001211359,0.001943188,0.9486737,0.001642903],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00004948347,0.967715,0.01519498,0.0000358492,0.0001814642,0.0002326556,0.000007477824,0.00006129381,0.01652181],"genre_scores_gemma":[0.006515749,0.9897853,0.003123399,0.00001731112,0.00005595374,0.00004899207,0.00001928076,0.000006843007,0.0004271531],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9971721,"threshold_uncertainty_score":0.5403907,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2120199131","doi":"10.1023/a:1024068626366","title":"Inference for the Generalization Error","year":2003,"lang":"en","type":"article","venue":"Machine Learning","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":959,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Université du Québec à Montréal; Health Canada; Center for Interuniversity Research and Analysis on Organizations","funders":"","keywords":"Estimator; Variance (accounting); Generalization; Statistical hypothesis testing; Null hypothesis; Statistics; Set (abstract data type); Generalization error; Mathematics; Computer science; Randomness; Econometrics; Artificial intelligence; Algorithm; Machine learning; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.02690503830497755,"gpt":0.2926671986209821,"spread":0.2657621603160046,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001530406,0.00004809528,0.00003927925,0.00001272394,0.0003353549,0.00008745756,0.0002428215,0.00001384908,0.00001320907],"category_scores_gemma":[0.00008193417,0.00003183263,0.00002469709,0.0001752988,0.000009492688,0.00008032174,0.0000334382,0.000076629,0.00000816784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004977682,"about_ca_system_score_gemma":0.000009825683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000129724,"about_ca_topic_score_gemma":0.0000119568,"domain_scores_codex":[0.9995982,0.00003918491,0.00007046891,0.000125849,0.00005743258,0.0001088662],"domain_scores_gemma":[0.9995756,0.0001712824,0.00003939262,0.0001681365,0.00002602071,0.00001962202],"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":[7.163455e-7,0.00001101449,0.003944558,0.000003168104,0.000004952204,2.119056e-7,0.0001500622,0.1976917,0.0005299897,0.7503098,0.0007812814,0.04657253],"study_design_scores_gemma":[0.00006444207,0.0000127712,0.0004954191,0.000001468796,0.000001955688,0.000001495161,0.00000283161,0.7737195,0.0001717651,0.00266971,0.222815,0.00004364017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001988689,0.0001858508,0.9950275,0.001831804,0.00008257948,0.0001264428,3.134595e-7,0.00007452285,0.0006822816],"genre_scores_gemma":[0.977432,0.00001893094,0.02077898,0.0004840173,0.00004645079,0.00005703879,0.000003515838,0.000005162176,0.001173967],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9754432,"threshold_uncertainty_score":0.2579313,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1517808374","doi":"","title":"No Unbiased Estimator of the Variance of K-Fold Cross-Validation","year":2003,"lang":"en","type":"article","venue":"Érudit documents and data repository (Érudit Consortium, University of Montreal)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":708,"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":"Estimator; Generalization; Mathematics; Cross-validation; Variance (accounting); Covariance matrix; Generalization error; Variance decomposition of forecast errors; Minimum-variance unbiased estimator; Eigenvalues and eigenvectors; Covariance; Bias of an estimator; Applied mathematics; Degrees of freedom (physics and chemistry); Consistent estimator; Algorithm; Statistics; Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01284528476798492,"gpt":0.2329795089063419,"spread":0.220134224138357,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001983534,0.0001287524,0.0002430722,0.0000407231,0.0003050547,0.00004019658,0.001196877,0.00006253949,0.00001642162],"category_scores_gemma":[0.00006085277,0.0001142567,0.00006202344,0.0002379116,0.0002967035,0.0006586849,0.0004668316,0.00008313271,0.000002403817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003926109,"about_ca_system_score_gemma":0.00009154305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001498952,"about_ca_topic_score_gemma":0.0001624879,"domain_scores_codex":[0.9987198,0.0001079162,0.0003207112,0.000426076,0.0002721685,0.0001533299],"domain_scores_gemma":[0.9975224,0.0001521003,0.0005934467,0.001452744,0.0002010503,0.00007833447],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005877989,0.003062746,0.3049052,0.001019655,0.001492652,0.0002686437,0.0006725887,0.005381721,0.1207103,0.4218741,0.1057732,0.03425138],"study_design_scores_gemma":[0.01068152,0.0006952924,0.2998809,0.001058451,0.0009633388,0.0003065903,0.0002931798,0.05022794,0.108514,0.007303047,0.518147,0.001928738],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9057436,0.001208074,0.06380235,0.001066414,0.001336217,0.001422592,0.0006739917,0.00009799626,0.02464879],"genre_scores_gemma":[0.9931459,0.0001999871,0.004494203,0.00001970157,0.00001975936,7.264218e-7,0.00002357435,0.000005403701,0.00209074],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4145711,"threshold_uncertainty_score":0.4659252,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2507380695","doi":"10.1038/nmeth.3968","title":"Model selection and overfitting","year":2016,"lang":"en","type":"article","venue":"Nature Methods","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":700,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Overfitting; Selection (genetic algorithm); Computational biology; Model selection; Computer science; Biology; Artificial intelligence; Machine learning; Evolutionary biology; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.02306701447789608,"gpt":0.3722396874107607,"spread":0.3491726729328647,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003189602,0.0000480989,0.00005182037,0.00002286889,0.00007715759,0.00003374386,0.0001492667,0.00008613395,0.000001601959],"category_scores_gemma":[0.00004686155,0.00002919524,0.00001597368,0.0001770282,0.000009030587,0.0001658063,0.0000746213,0.0001424604,0.000001449808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009363249,"about_ca_system_score_gemma":0.000009392493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.61991e-7,"about_ca_topic_score_gemma":8.852691e-7,"domain_scores_codex":[0.9995359,0.0000566428,0.0000591586,0.0001925057,0.00005665531,0.00009914064],"domain_scores_gemma":[0.9995788,0.0001852521,0.00002829291,0.0001429918,0.00002930691,0.00003536171],"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":[6.351469e-7,0.000003689367,0.00007017406,0.000001180232,0.000001879859,1.08612e-7,0.00001495483,0.00007521735,0.06195602,0.1986304,0.0007687099,0.7384771],"study_design_scores_gemma":[0.0001304128,0.00001319138,0.000820375,0.0000116154,0.000003097838,0.000012966,6.553666e-7,0.8457634,0.02691128,0.1071918,0.01903541,0.0001057483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003598488,0.0002073566,0.9926758,0.002516842,0.00009788419,0.00004388994,3.222205e-7,0.00008579596,0.0007736261],"genre_scores_gemma":[0.2677854,0.00001977089,0.7314329,0.000356574,0.00006128383,0.00000554644,4.965431e-8,0.000002599128,0.0003359072],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8456882,"threshold_uncertainty_score":0.1190547,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3080427797","doi":"10.1007/978-1-0716-0826-5_3","title":"Siamese Neural Networks: An Overview","year":2020,"lang":"en","type":"review","venue":"Methods in molecular biology","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":670,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Krembil Foundation","funders":"","keywords":"Artificial neural network; Computer science; Similarity (geometry); Artificial intelligence; Perceptron; Curse of dimensionality; Representation (politics); Pattern recognition (psychology); Rank (graph theory); Feedforward neural network; Cosine similarity; Euclidean distance; Machine learning; Pearson product-moment correlation coefficient; Convolutional neural network; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.1298686972305546,"gpt":0.4926620052493232,"spread":0.3627933080187686,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007999762,0.0004501398,0.001580672,0.000143116,0.00005394106,0.00008409323,0.002352735,0.0004421587,0.00001079795],"category_scores_gemma":[0.00007871651,0.0003645245,0.0004147027,0.001411641,0.00008131129,0.00007663023,0.0008029599,0.0007969111,0.00001294822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004324727,"about_ca_system_score_gemma":0.00007677578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009488236,"about_ca_topic_score_gemma":0.000002770679,"domain_scores_codex":[0.9937358,0.003929996,0.0006733172,0.001098987,0.00007373752,0.000488085],"domain_scores_gemma":[0.9978678,0.0003968935,0.0002864514,0.0012502,0.00002479014,0.0001739266],"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":[3.035263e-7,0.0000194375,3.733488e-7,0.000232742,0.00001778413,0.00005413578,0.000005600004,0.0001130959,0.00001098889,0.05832466,0.00003087383,0.94119],"study_design_scores_gemma":[0.0000536537,0.00007639799,2.811425e-7,0.0002873498,0.00004709529,0.00005840927,4.625807e-7,0.06632705,0.000002588459,0.006605817,0.926191,0.0003498974],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.755385e-8,0.5015659,0.497691,0.0001239035,0.0002073589,0.0003016229,0.000002103739,0.0000624563,0.00004556595],"genre_scores_gemma":[9.094396e-8,0.5523244,0.4467364,0.0006316359,0.000104068,0.0001481132,0.00002678513,0.00002251194,0.000005919512],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9408401,"threshold_uncertainty_score":0.9998807,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2133702739","doi":"10.1109/tnn.2002.1031938","title":"A recurrent neural network for solving Sylvester equation with time-varying coefficients","year":2002,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":660,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"iNano Medical (Canada)","funders":"","keywords":"Recurrent neural network; Artificial neural network; Computer science; Sylvester equation; Control theory (sociology); Nonlinear system; Convergence (economics); Inverted pendulum; Applied mathematics; Time delay neural network; Mathematics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.03182609708527136,"gpt":0.2418096402784719,"spread":0.2099835431932005,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001579008,0.0003657688,0.0002944507,0.0001033512,0.000894224,0.0003441382,0.0006384823,0.0001240821,0.00004868633],"category_scores_gemma":[0.000002410235,0.0003145075,0.0001942672,0.0009372933,0.00006940698,0.0005990152,0.000008051124,0.0004778517,0.0000358874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006189805,"about_ca_system_score_gemma":0.000009760769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004256507,"about_ca_topic_score_gemma":0.000009485395,"domain_scores_codex":[0.9975979,0.00007393673,0.0004270036,0.000757108,0.0003363485,0.0008076515],"domain_scores_gemma":[0.9984033,0.0004395335,0.0001815145,0.0006478915,0.0001156902,0.00021211],"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":[0.00003488516,0.0001366429,0.000007794869,0.00000633757,0.00002055009,0.000003301696,0.00005320765,0.8361887,0.00004987701,0.0001466685,0.001867861,0.1614841],"study_design_scores_gemma":[0.0006813939,0.0004265762,0.00002217044,0.0000787339,0.00004067219,0.00003325078,0.000002446503,0.9973788,0.0001281045,0.00005997413,0.0007748432,0.000373071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006568972,0.0002018674,0.9893202,0.001250599,0.00114515,0.0009998726,0.000009179844,0.0004097326,0.00009443807],"genre_scores_gemma":[0.9887136,0.00006711337,0.008687274,0.001176487,0.0004544976,0.0003783081,0.00001053204,0.00004995309,0.0004622217],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9821447,"threshold_uncertainty_score":0.9999307,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1574082713","doi":"10.1007/3-540-44634-6","title":"Algorithms and Data Structures","year":2001,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":626,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.03008785630812405,"gpt":0.2894725715367051,"spread":0.2593847152285811,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0004433717,0.0003512073,0.0003360279,0.0003000764,0.0002801741,0.0008034036,0.006551394,0.0001930387,0.000007448768],"category_scores_gemma":[0.00003254215,0.0002968016,0.00003236457,0.0009675887,0.0005725406,0.0007084371,0.004490874,0.0006298954,0.000009128433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009350035,"about_ca_system_score_gemma":0.0004728241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002168196,"about_ca_topic_score_gemma":0.00005323108,"domain_scores_codex":[0.9966862,0.00002833149,0.000307674,0.001869634,0.0005786215,0.0005295807],"domain_scores_gemma":[0.9964747,0.0003275039,0.000157008,0.00279066,0.00008270197,0.0001673575],"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":[5.14654e-7,0.00000935032,0.00002576141,0.0000104768,0.000003485473,0.00003243869,0.00007272005,0.003765514,0.00001287198,0.003995876,0.001213375,0.9908576],"study_design_scores_gemma":[0.0001049403,0.00003689048,0.0002268163,0.00006689259,0.000004451148,0.0001394463,3.027204e-8,0.768261,0.00004543137,0.2121734,0.01857368,0.0003670256],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002833822,0.000849749,0.9956442,0.001262902,0.0007981346,0.0002724261,0.00001443372,0.0001235185,0.00100629],"genre_scores_gemma":[0.006973836,0.0003400977,0.9871093,0.002798863,0.001616648,0.00001210745,0.00005485152,0.00003240747,0.00106188],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9904906,"threshold_uncertainty_score":0.9999484,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2803832867","doi":"","title":"Mutual Information Neural Estimation.","year":2018,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":598,"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":"Computer science; Mutual information; Estimation; Artificial intelligence; Artificial neural network; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02579097961051308,"gpt":0.2971756273448126,"spread":0.2713846477342995,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001176967,0.0001043602,0.00007001746,0.0001182535,0.0002103021,0.0003859146,0.0006847103,0.00003267532,0.0002986764],"category_scores_gemma":[0.00007911021,0.00009444339,0.00003404731,0.0001730396,0.00004651835,0.001028248,0.0001469127,0.0002530058,0.0009597951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000027722,"about_ca_system_score_gemma":0.00002546349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002934475,"about_ca_topic_score_gemma":0.000006884477,"domain_scores_codex":[0.9991432,0.0000375602,0.0001998024,0.0001785026,0.0002963802,0.0001444945],"domain_scores_gemma":[0.9993494,0.00005122311,0.0001256545,0.0001829647,0.0002346567,0.00005613281],"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":[0.00001179897,0.00001975319,0.0005908247,0.000001375915,0.00000948362,0.000001278277,0.0002752223,0.007351965,0.0001992953,0.7554101,0.0007401569,0.2353887],"study_design_scores_gemma":[0.0001571386,0.000105036,0.001299344,0.00001082041,0.000001190173,0.00001049954,0.00001027319,0.9711389,0.0001609706,0.004739468,0.02226378,0.0001025798],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01976282,0.000006215474,0.8918799,0.01301356,0.0007739369,0.0001362483,0.000006214522,0.0003705493,0.07405051],"genre_scores_gemma":[0.9884647,0.000005915842,0.009562886,0.001073694,0.000189444,0.00001599719,0.00004940679,0.000004182319,0.0006337367],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9687019,"threshold_uncertainty_score":0.9998181,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2161388792","doi":"10.48550/arxiv.1402.1869","title":"On the Number of Linear Regions of Deep Neural Networks","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":572,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal","funders":"","keywords":"Rectifier (neural networks); Piecewise linear function; Computer science; Computation; Artificial neural network; Feedforward neural network; Feed forward; Deep learning; Activation function; Homogeneous space; Artificial intelligence; Algorithm; Mathematics; Stochastic neural network; Recurrent neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.05273342306533113,"gpt":0.198821311659622,"spread":0.1460878885942908,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001396695,0.0001698645,0.0002423423,0.00004842724,0.00011792,0.00001901425,0.001764987,0.000144344,0.00002155014],"category_scores_gemma":[0.0000151136,0.0001390199,0.0002118215,0.0004543238,0.0001591811,0.00006302528,0.000977441,0.0004540488,0.0000139197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001940985,"about_ca_system_score_gemma":0.00002040006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004967698,"about_ca_topic_score_gemma":0.00001176568,"domain_scores_codex":[0.9989624,0.0001187398,0.0001904328,0.0004732802,0.00006716325,0.000187988],"domain_scores_gemma":[0.9976642,0.0003893278,0.000348345,0.00140895,0.0001214919,0.0000676962],"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":[0.000004156348,0.00002775317,0.0002242523,0.000006671767,0.00001421376,0.000002886441,0.00001673964,0.5188372,0.000001993063,0.480374,0.0002734051,0.0002166561],"study_design_scores_gemma":[0.00008800693,0.00001909985,0.0002777513,0.00003093658,0.00002415208,0.000001648205,0.000007026317,0.9330857,0.00002928446,0.06621289,0.0001028191,0.000120695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1757635,0.0000127768,0.8214738,0.0004185324,0.0001957598,0.0001899341,0.000003207947,0.00004911238,0.001893294],"genre_scores_gemma":[0.9989383,0.00004921901,0.0005177889,0.00018432,0.00006362818,0.000001225189,0.000004301885,0.000009311565,0.0002319593],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8231747,"threshold_uncertainty_score":0.5669068,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2151770284","doi":"10.1109/12.954505","title":"Stochastic neural computation. I. Computational elements","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Computers","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":560,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; CMC Microsystems","keywords":"Exponentiation; Computer science; Stochastic computing; Artificial neural network; Multiplication (music); Sigmoid function; Computation; Stochastic neural network; Noise (video); Binary number; Algorithm; Artificial intelligence; Time delay neural network; Arithmetic; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02110761093511192,"gpt":0.2626727902763933,"spread":0.2415651793412814,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008924396,0.0002229225,0.000174144,0.0001941521,0.0004411669,0.0002039241,0.0006139827,0.00004989659,0.00002798561],"category_scores_gemma":[8.361026e-7,0.0002294924,0.0001292506,0.0007250247,0.00005820952,0.0003914141,0.000006717341,0.0002403057,0.0002199337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000660336,"about_ca_system_score_gemma":0.00003755612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000100973,"about_ca_topic_score_gemma":0.000005384175,"domain_scores_codex":[0.9983364,0.00005922876,0.0003664922,0.0005037381,0.000382144,0.0003519591],"domain_scores_gemma":[0.9990382,0.0002497827,0.0001026235,0.0003353638,0.00009874546,0.0001752821],"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":[0.000006829933,0.0001482583,0.000005025927,0.000001651487,0.00002212613,0.000008158617,0.00004643566,0.8509004,0.00002486203,0.0008517024,0.001256338,0.1467282],"study_design_scores_gemma":[0.0005360257,0.0001089782,0.0001441987,0.00001652176,0.000009543648,0.00007677597,0.000006066009,0.9972323,0.00004220995,0.001202581,0.00039177,0.0002330291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01050669,0.00001022223,0.9856167,0.001797205,0.001195458,0.0003000839,0.00001043422,0.0004255249,0.0001377115],"genre_scores_gemma":[0.9171664,0.000004867813,0.08127531,0.00127511,0.00007648014,0.00004815956,0.000009751653,0.00001646612,0.0001274438],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9066597,"threshold_uncertainty_score":0.9358428,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1408639475","doi":"","title":"Learning Recurrent Neural Networks with Hessian-Free Optimization","year":2011,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":534,"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":"Recurrent neural network; Hessian matrix; Sequence (biology); Computer science; Artificial intelligence; Artificial neural network; Term (time); Scheme (mathematics); Optimization problem; Interpretation (philosophy); Algorithm; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02062545344930514,"gpt":0.2115079594753474,"spread":0.1908825060260423,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005864418,0.00008884609,0.00007014351,0.00002575724,0.0001500055,0.00007923073,0.0005680078,0.00002765272,0.00005611369],"category_scores_gemma":[0.000003342488,0.00006267535,0.00002218921,0.0003252963,0.00002293621,0.0003226987,0.0001578623,0.0001479821,0.000006173699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007573753,"about_ca_system_score_gemma":0.00000751753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001380917,"about_ca_topic_score_gemma":0.0000105316,"domain_scores_codex":[0.9993337,0.00002612488,0.0001092183,0.0002375068,0.0001003279,0.0001930912],"domain_scores_gemma":[0.9994125,0.00001913816,0.00005949242,0.0003968398,0.00003968741,0.00007232458],"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":[0.000005601531,0.00004176289,0.001019894,0.000001490623,0.000005208829,0.00000374297,0.0001434509,0.8985175,0.000001540171,0.03704458,0.001187047,0.06202818],"study_design_scores_gemma":[0.0001250584,0.0001113217,0.000740607,0.000005711171,0.000002763029,0.000009392345,0.000009459356,0.9982408,0.00002327041,0.0001988835,0.000428601,0.0001041819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001110348,0.00002922949,0.9865621,0.0004370848,0.0001023589,0.0001069364,8.334515e-8,0.0002530289,0.01139888],"genre_scores_gemma":[0.7826333,0.00002321843,0.2165199,0.0002382325,0.00007315108,0.00002817003,0.000003070806,0.000008649342,0.0004722875],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7815229,"threshold_uncertainty_score":0.2555827,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2951603627","doi":"","title":"On the Number of Linear Regions of Deep Neural Networks","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":488,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research; Université de Montréal","funders":"","keywords":"Rectifier (neural networks); Piecewise linear function; Computation; Artificial neural network; Computer science; Feedforward neural network; Feed forward; Deep learning; Activation function; Homogeneous space; Piecewise; Algorithm; Artificial intelligence; Mathematics; Stochastic neural network; Recurrent neural network; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.05273342306533113,"gpt":0.198821311659622,"spread":0.1460878885942908,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001396695,0.0001698645,0.0002423423,0.00004842724,0.00011792,0.00001901425,0.001764987,0.000144344,0.00002155014],"category_scores_gemma":[0.0000151136,0.0001390199,0.0002118215,0.0004543238,0.0001591811,0.00006302528,0.000977441,0.0004540488,0.0000139197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001940985,"about_ca_system_score_gemma":0.00002040006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004967698,"about_ca_topic_score_gemma":0.00001176568,"domain_scores_codex":[0.9989624,0.0001187398,0.0001904328,0.0004732802,0.00006716325,0.000187988],"domain_scores_gemma":[0.9976642,0.0003893278,0.000348345,0.00140895,0.0001214919,0.0000676962],"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":[0.000004156348,0.00002775317,0.0002242523,0.000006671767,0.00001421376,0.000002886441,0.00001673964,0.5188372,0.000001993063,0.480374,0.0002734051,0.0002166561],"study_design_scores_gemma":[0.00008800693,0.00001909985,0.0002777513,0.00003093658,0.00002415208,0.000001648205,0.000007026317,0.9330857,0.00002928446,0.06621289,0.0001028191,0.000120695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1757635,0.0000127768,0.8214738,0.0004185324,0.0001957598,0.0001899341,0.000003207947,0.00004911238,0.001893294],"genre_scores_gemma":[0.9989383,0.00004921901,0.0005177889,0.00018432,0.00006362818,0.000001225189,0.000004301885,0.000009311565,0.0002319593],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8231747,"threshold_uncertainty_score":0.5669068,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2108563286","doi":"10.1109/icassp.2013.6639349","title":"Advances in optimizing recurrent networks","year":2013,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":486,"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; Recurrent neural network; Artificial intelligence; Machine learning; Artificial neural network; Clipping (morphology); Deep learning","retraction":null,"screen_n_in":null,"score":{"opus":0.009799538304525268,"gpt":0.2427843495198029,"spread":0.2329848112152776,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00003838969,0.0000479201,0.00005174219,0.00002218455,0.00003464887,0.0000827744,0.0003206584,0.00001565169,0.00003928621],"category_scores_gemma":[0.000001505356,0.00003733261,0.0000157009,0.0002616788,0.000008897614,0.0005819063,0.00009282638,0.00007078653,0.00005838099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007932807,"about_ca_system_score_gemma":0.000003680844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001568784,"about_ca_topic_score_gemma":0.00001827449,"domain_scores_codex":[0.9995237,0.00001021042,0.0001006344,0.0001599188,0.00004973231,0.0001557858],"domain_scores_gemma":[0.9996974,0.00003486239,0.00002089431,0.0001917745,0.00001517892,0.00003987871],"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":[2.135183e-7,0.00002306385,0.0002216741,0.000001060733,3.812545e-7,5.254163e-7,0.00001869577,0.03932835,0.00001679259,0.09890921,0.003023512,0.8584565],"study_design_scores_gemma":[0.00005441449,0.00001122457,0.0007759481,0.00000854796,1.918297e-7,0.000001199769,0.000005620612,0.9826484,0.00002624508,0.005392667,0.01100473,0.00007079441],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001036483,0.0009058421,0.9795224,0.001629211,0.0001416893,0.0001491506,2.789299e-8,0.00008630038,0.01652887],"genre_scores_gemma":[0.896386,0.000948197,0.1016783,0.0005678833,0.0000756558,0.0001157481,6.576158e-7,0.000003449038,0.0002240954],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9433201,"threshold_uncertainty_score":0.152238,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2164700406","doi":"10.1146/annurev-statistics-010814-020120","title":"Learning Deep Generative Models","year":2015,"lang":"en","type":"article","venue":"Annual Review of Statistics and Its Application","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":448,"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":"Office of Naval Research; Samsung; Canadian Institute for Advanced Research","keywords":"Deep belief network; Boltzmann machine; Artificial intelligence; Computer science; Deep learning; Generative grammar; Feature (linguistics); Generative model; Object (grammar); Machine learning; Perception; Restricted Boltzmann machine; Cognitive neuroscience of visual object recognition","retraction":null,"screen_n_in":null,"score":{"opus":0.02706827500576708,"gpt":0.2962983746660544,"spread":0.2692300996602873,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002158509,0.00007180304,0.0001420932,0.00001597475,0.00005606543,0.00001741359,0.0001785844,0.00001887165,0.000001351765],"category_scores_gemma":[0.0000345663,0.00006093665,0.00001336016,0.0001779877,0.00001844319,0.0002000882,0.00007878392,0.00006399101,0.00001018101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007906233,"about_ca_system_score_gemma":0.00002518427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007499249,"about_ca_topic_score_gemma":0.00000137763,"domain_scores_codex":[0.999329,0.00003170029,0.000217703,0.0001877182,0.0001461815,0.00008770268],"domain_scores_gemma":[0.999184,0.00004730299,0.0001524779,0.0001576743,0.0003729574,0.00008564398],"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":[4.813368e-7,0.00001403504,0.000003348236,0.0001721333,0.000003047446,1.620395e-7,0.000185277,0.0003907814,0.00004755585,0.7908121,0.002378186,0.2059929],"study_design_scores_gemma":[0.0001130279,0.0001155874,0.00006498656,0.0002121954,0.00001650681,0.00000484923,0.00004424899,0.8756843,0.0001563891,0.07047569,0.05297009,0.0001421814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001229119,0.01988334,0.9780706,0.0007121666,0.00001444305,0.0002860591,0.0000286927,0.00002049236,0.0008612956],"genre_scores_gemma":[0.568473,0.1750605,0.2532554,0.002201829,0.0001381825,0.0003296364,0.0001644963,0.00002055209,0.0003564227],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8752935,"threshold_uncertainty_score":0.2484924,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1508427692","doi":"10.1007/978-3-642-35512-7","title":"Long-Memory Processes","year":2013,"lang":"en","type":"book","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":430,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01447224570866462,"gpt":0.2233181632486226,"spread":0.2088459175399579,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00002533986,0.0001490237,0.0001354181,0.00003665212,0.00006612996,0.0001915529,0.001071125,0.0001060835,0.0002613645],"category_scores_gemma":[0.000003434719,0.0001147057,0.00004174988,0.0001120312,0.00002880218,0.0002060454,0.0002446418,0.000160159,0.00199196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002091868,"about_ca_system_score_gemma":0.0002846812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004480161,"about_ca_topic_score_gemma":0.00001096057,"domain_scores_codex":[0.9991937,0.000004185161,0.0001356376,0.0003522623,0.0001529053,0.0001612745],"domain_scores_gemma":[0.9990867,0.00006135037,0.00007751376,0.0005916877,0.0001100918,0.00007264128],"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":[5.836931e-8,0.000008749511,6.698506e-7,0.00004285671,0.000004794975,0.000002572764,0.000007840808,0.00001013975,9.83712e-7,0.08107131,0.8884433,0.03040671],"study_design_scores_gemma":[0.00004464056,0.00001823201,0.00001710199,0.00005677515,0.000005591397,0.00001373374,4.993965e-7,0.00142135,0.00006755556,0.04706016,0.950993,0.0003013445],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.000001538332,0.0004475263,0.1528066,0.0008264988,0.0001244067,0.0002451663,9.953362e-7,0.0002754647,0.8452718],"genre_scores_gemma":[0.0000718529,0.0001138084,0.004998276,0.0009076927,0.0003240128,0.000072592,0.00001118228,0.00001271408,0.9934879],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.1482161,"threshold_uncertainty_score":0.9987851,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2083231156","doi":"10.1016/s0966-6362(00)00094-1","title":"A review of analytical techniques for gait data. Part 1: fuzzy, statistical and fractal methods","year":2001,"lang":"en","type":"review","venue":"Gait & Posture","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":381,"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":"Gait; Fuzzy logic; Multivariate statistics; Computer science; Gait analysis; Fractal analysis; Fractal; Data mining; Artificial intelligence; Machine learning; Mathematics; Physical medicine and rehabilitation; Fractal dimension; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.1139975489929698,"gpt":0.4550222332615494,"spread":0.3410246842685796,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008704881,0.0003487398,0.001541155,0.00006515673,0.00007713423,0.0000786097,0.001501466,0.0002488845,0.00001812728],"category_scores_gemma":[0.0002123559,0.0002485145,0.0002040504,0.0005142267,0.0001019934,0.0001559811,0.0007454893,0.0004263675,0.000005224633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000183988,"about_ca_system_score_gemma":0.0001423333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004993215,"about_ca_topic_score_gemma":0.000001744876,"domain_scores_codex":[0.9977167,0.000227594,0.000743618,0.0008212711,0.0001804107,0.0003104281],"domain_scores_gemma":[0.9969196,0.0009505287,0.0003743822,0.001473341,0.0001210706,0.0001610855],"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":[6.991104e-7,0.00002991374,1.920745e-7,0.01616684,0.00003648607,0.000003194404,0.000001547029,5.721642e-9,1.094327e-7,0.01084454,0.1465045,0.826412],"study_design_scores_gemma":[0.00003342266,0.00006240254,0.000001608712,0.02151849,0.0004969479,0.0001058882,3.986009e-7,0.000332035,2.444945e-7,0.001363204,0.9758412,0.0002441241],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[4.790486e-9,0.7201666,0.2773104,0.0004552368,0.00006690186,0.001069344,0.0005098058,0.00005835808,0.0003633288],"genre_scores_gemma":[3.583514e-8,0.7442257,0.253992,0.0006720473,0.0002727427,0.0001765928,0.000553418,0.0000189675,0.00008852965],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8293368,"threshold_uncertainty_score":0.9999967,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4399581870","doi":"10.32614/cran.package.stargazer","title":"stargazer: Well-Formatted Regression and Summary Statistics Tables","year":2012,"lang":"en","type":"dataset","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":337,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Masarykova Univerzita; Universität Stuttgart; Universität Ulm; Universiteit Antwerpen; University of Exeter; Lunds Universitet; University of Illinois at Urbana-Champaign; Toulouse School of Economics; Universiteit van Amsterdam; Universität Mannheim; McGill University; University of Wisconsin-Madison; Northwestern University; Harvard University","keywords":"Statistics; Regression; Regression analysis; Summary statistics; Geography; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01353763770055318,"gpt":0.2557678203220695,"spread":0.2422301826215163,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001157244,0.0002170825,0.00021001,0.00006611308,0.0001773843,0.0001947554,0.0006820404,0.0001357624,0.000327249],"category_scores_gemma":[0.000004692952,0.0001541506,0.00002132135,0.0001705724,0.00004679154,0.0003002841,0.0006242509,0.0002543906,0.0002694488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001412398,"about_ca_system_score_gemma":0.00003299716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001457842,"about_ca_topic_score_gemma":0.00007138891,"domain_scores_codex":[0.9989063,0.00003435806,0.0002338044,0.0003073988,0.000212012,0.0003061148],"domain_scores_gemma":[0.9987592,0.0001206506,0.0001489152,0.0007642428,0.00004198039,0.0001650753],"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":[0.000001015252,0.00002804118,0.000005577228,0.00004052135,0.000006081679,0.000003101732,0.000003070009,0.000001552486,0.00000323443,0.002451903,0.9921581,0.005297858],"study_design_scores_gemma":[0.00007517677,0.00001689155,0.0000261726,0.00004457155,0.00001464371,0.00001153428,0.000002237227,0.001670755,0.00001443109,0.0006265363,0.9972843,0.0002127731],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000001959328,0.0006813345,0.06494985,0.0003214576,0.0002510981,0.0001748403,0.933331,0.00006930538,0.0002191638],"genre_scores_gemma":[0.000005442615,0.00255093,0.02624602,0.000713467,0.0001674439,0.00002136997,0.9690328,0.000008087306,0.001254446],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.03870383,"threshold_uncertainty_score":0.628608,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2160422165","doi":"10.1016/j.neunet.2009.08.007","title":"Clustering: A neural network approach","year":2009,"lang":"en","type":"article","venue":"Neural Networks","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":325,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Cluster analysis; Fuzzy clustering; Correlation clustering; Learning vector quantization; Artificial intelligence; Pattern recognition (psychology); CURE data clustering algorithm; Computer science; Consensus clustering; Canopy clustering algorithm; Data stream clustering; Single-linkage clustering; Conceptual clustering; Neural gas; Hierarchical clustering; Data mining; Competitive learning; Vector quantization; Unsupervised learning; Artificial neural network; Time delay neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.01879314230365507,"gpt":0.2398786784885903,"spread":0.2210855361849353,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001852644,0.0003257583,0.0003038232,0.00004938049,0.0003889638,0.0003808255,0.001436879,0.0001447195,0.00001253949],"category_scores_gemma":[0.000005816997,0.0002867402,0.0001774024,0.001042112,0.00005141338,0.0005123429,0.000283374,0.0005442005,0.00001829172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002603656,"about_ca_system_score_gemma":0.00001159305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004128397,"about_ca_topic_score_gemma":0.000003392291,"domain_scores_codex":[0.9975502,0.00009319266,0.0003949906,0.0007519245,0.0002809579,0.0009286788],"domain_scores_gemma":[0.9984642,0.00008475446,0.0001442312,0.0009806862,0.00005280225,0.0002733061],"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":[0.000008265647,0.00005336101,0.00009652486,0.000001510576,0.000005056592,0.00001241157,0.00002296894,0.7908273,0.00001887239,0.007492265,0.01067127,0.1907902],"study_design_scores_gemma":[0.0002348554,0.0001253421,0.002634758,0.000007245827,0.000007562036,0.00009690862,0.000002372363,0.9905965,0.000003893868,0.00136156,0.004610788,0.0003182448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006007666,0.0007407554,0.9799489,0.004140926,0.000829189,0.0004658127,7.489745e-7,0.0006019235,0.007264077],"genre_scores_gemma":[0.9623036,0.00003945525,0.03010256,0.005491762,0.001728086,0.00003412413,0.0000129704,0.00001862015,0.000268834],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9562959,"threshold_uncertainty_score":0.9999585,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1543614656","doi":"10.1016/s0079-6123(06)65034-6","title":"To recognize shapes, first learn to generate images","year":2007,"lang":"en","type":"review","venue":"Progress in brain research","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":306,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Sensory system; Architecture; Cortex (anatomy); Machine learning; Pattern recognition (psychology); Neuroscience; Psychology; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.2749769284046011,"gpt":0.504336092142962,"spread":0.2293591637383609,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00470078,0.0003696822,0.0008327574,0.001122582,0.0003551212,0.0008173714,0.003878242,0.0002517221,0.00004226696],"category_scores_gemma":[0.0003525471,0.000311363,0.0001689066,0.005858218,0.000134627,0.0001599517,0.002487384,0.001386893,0.001297935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002401992,"about_ca_system_score_gemma":0.0002850035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003010306,"about_ca_topic_score_gemma":0.0001015498,"domain_scores_codex":[0.9948504,0.0005535986,0.0006654277,0.001414916,0.0009786943,0.001536956],"domain_scores_gemma":[0.996363,0.001565791,0.00009242496,0.001117533,0.00029498,0.000566203],"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":[0.00000232965,0.00006281591,0.00001441285,0.000962,0.000009517525,0.00007168181,0.00005003781,0.000008873577,1.684006e-7,0.001394162,0.04091011,0.9565139],"study_design_scores_gemma":[0.00006348589,0.00009089962,0.00002920775,0.00329689,0.000003540597,0.00001238175,0.000002534439,0.0002980362,0.000003854938,0.0002523974,0.9956035,0.0003432436],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000004358517,0.9814004,0.004610853,0.009657728,0.000135409,0.003010213,0.00001558384,0.0001267543,0.001038752],"genre_scores_gemma":[0.0000112224,0.9583695,0.03403278,0.000423087,0.0005491346,0.002937221,0.00001669145,0.00006673839,0.003593663],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9561706,"threshold_uncertainty_score":0.9999338,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2155894447","doi":"10.48550/arxiv.1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":292,"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":"Kronecker delta; Curvature; Stochastic gradient descent; Hessian matrix; Diagonal; Gradient descent; Artificial neural network; Mathematics; Matrix (chemical analysis); Invertible matrix; Applied mathematics; Rank (graph theory); Mathematical optimization; Algorithm; Computer science; Combinatorics; Geometry; Pure mathematics; Artificial intelligence; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.06471831599879245,"gpt":0.1881355193432239,"spread":0.1234172033444314,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001537566,0.0004371802,0.0003904653,0.0001167509,0.0002142015,0.0002931636,0.002109493,0.0003325283,0.000008768725],"category_scores_gemma":[0.000004899181,0.0004069874,0.0001465271,0.000789118,0.0001221629,0.0004645302,0.001853135,0.001103782,0.00001449261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00013553,"about_ca_system_score_gemma":0.0001201356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004565714,"about_ca_topic_score_gemma":0.0000305064,"domain_scores_codex":[0.9977612,0.00009407709,0.0001903725,0.001295348,0.0001243545,0.0005346385],"domain_scores_gemma":[0.9975487,0.00005691121,0.0003111738,0.001547085,0.0002147628,0.0003213817],"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":[0.00002358265,0.00004587022,0.0003644285,0.00001480974,0.00005134835,0.0001303051,0.0000890822,0.9774745,0.000003619603,0.02019645,0.0009479504,0.0006581317],"study_design_scores_gemma":[0.0003668276,0.00004900935,0.0001307788,0.00005564647,0.00005945777,0.00001115997,0.00002269734,0.9938928,0.00001129246,0.004106327,0.0007873484,0.0005066849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07142419,0.0002014507,0.9256894,0.000261731,0.0004104286,0.0004641962,0.00001189602,0.0003741727,0.001162509],"genre_scores_gemma":[0.9869789,0.00007948003,0.01199544,0.0001400977,0.00019401,0.000003801666,0.00005219498,0.00003158503,0.0005244248],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9155548,"threshold_uncertainty_score":0.9998382,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2168148636","doi":"","title":"Incorporating Second-Order Functional Knowledge for Better Option Pricing","year":2000,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":273,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Center for Interuniversity Research and Analysis on Organizations","funders":"","keywords":"Generalization; Computer science; A priori and a posteriori; Class (philosophy); Task (project management); Function (biology); Order (exchange); Convex function; Artificial neural network; Machine learning; Artificial intelligence; Regular polygon; Mathematical optimization; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02175691798115745,"gpt":0.2499960200512804,"spread":0.228239102070123,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002245377,0.0001383861,0.0001314884,0.00009425206,0.0006425099,0.001131259,0.0002663654,0.00006748309,0.00001953025],"category_scores_gemma":[0.000009603209,0.0001220411,0.00004267348,0.0005127758,0.00002611959,0.004415872,0.00003281737,0.000119521,0.00009886877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004455158,"about_ca_system_score_gemma":0.00007906151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004985328,"about_ca_topic_score_gemma":0.000001930434,"domain_scores_codex":[0.9988805,0.00002518997,0.0005169565,0.00018179,0.0001769234,0.0002186457],"domain_scores_gemma":[0.9991256,0.00005248611,0.0002626168,0.0001893772,0.0003092377,0.00006070391],"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":[0.00001289712,0.0000343029,0.000105498,0.0004118385,0.00000856205,2.144472e-7,0.001126758,0.05418778,0.0005253128,0.01916197,0.006474182,0.9179507],"study_design_scores_gemma":[0.0002623188,0.00002818021,0.0003121129,0.00005638396,0.000003323207,0.00002803291,0.00003757791,0.9337291,0.0001238735,0.0004310753,0.06483363,0.0001544415],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04901091,0.0001407902,0.944167,0.0008006782,0.0005188703,0.0006577048,0.000006009032,0.000376269,0.00432179],"genre_scores_gemma":[0.9889293,0.000001137114,0.008539972,0.0007566896,0.0003900887,0.0002970101,0.00006485956,0.000008680183,0.001012304],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9399183,"threshold_uncertainty_score":0.9999056,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2149614431","doi":"10.1007/s102080010030","title":"Best Choices for Regularization Parameters in Learning Theory: On the Bias—Variance Problem","year":2002,"lang":"en","type":"article","venue":"Mathematische Annalen","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":258,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Mathematics; Regularization (linguistics); Variance (accounting); Statistics; Econometrics; Applied mathematics; Mathematical optimization; Artificial intelligence; Calculus (dental); Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.08291733840487436,"gpt":0.2644609902347111,"spread":0.1815436518298367,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005183099,0.0001027296,0.0001071193,0.00004667719,0.0001898624,0.0001583662,0.0005200998,0.00003866609,0.00001704445],"category_scores_gemma":[0.00009659824,0.00006865816,0.00004530359,0.0003783253,0.00002906318,0.0002161291,0.00005796269,0.0001406681,0.00008482311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008658792,"about_ca_system_score_gemma":0.000004387736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002543,"about_ca_topic_score_gemma":0.00000283468,"domain_scores_codex":[0.9991479,0.00009754259,0.0001786162,0.0002516503,0.0001274341,0.0001968896],"domain_scores_gemma":[0.9988397,0.000624733,0.0001275872,0.0003504491,0.0000299197,0.0000275873],"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":[0.000002571307,0.00009363443,0.00008297602,0.00002440464,0.000009452024,7.193877e-7,0.0007750961,0.004652448,0.0001367247,0.9666563,0.002565519,0.02500012],"study_design_scores_gemma":[0.0002634133,0.0001434944,0.0001216345,0.0002297003,0.000009071123,0.000005974124,0.0000636433,0.6787419,0.001565029,0.2769935,0.04162464,0.000238021],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02559393,0.0002961584,0.9341866,0.01935173,0.00006426364,0.001471805,0.000003511888,0.0001780311,0.018854],"genre_scores_gemma":[0.822364,0.0002337572,0.1407415,0.0018515,0.0001634056,0.001580467,0.000008690102,0.00004914884,0.03300754],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.79677,"threshold_uncertainty_score":0.2799799,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3023430131","doi":"10.1016/b978-0-12-804291-5.00010-6","title":"Deep learning","year":2016,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":254,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Deep learning; Artificial intelligence; Computer science; Artificial neural network; Key (lock); Backpropagation; Field (mathematics); Convolutional neural network; Machine learning; Boltzmann machine; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0136882242979481,"gpt":0.2279920828319792,"spread":0.2143038585340311,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009400072,0.0002502427,0.0002403971,0.00006379241,0.0001746011,0.0001012944,0.0008480458,0.0001620914,0.00009467722],"category_scores_gemma":[0.000003482734,0.0001918053,0.0001543693,0.00001148992,0.00006022196,0.00006609244,0.0003431599,0.0003800277,0.001054526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003251854,"about_ca_system_score_gemma":0.00003102068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":3.530552e-8,"about_ca_topic_score_gemma":0.000002142298,"domain_scores_codex":[0.998799,0.00001429627,0.0002364,0.0004845602,0.0002126324,0.000253165],"domain_scores_gemma":[0.9988963,0.0000739637,0.0001749066,0.0006849408,0.00005659991,0.000113308],"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":[2.763344e-7,8.095479e-7,3.682249e-7,0.000003490962,0.000008933253,0.000006119471,0.00001708681,0.000002164776,0.00000965244,0.2822026,0.00007949365,0.717669],"study_design_scores_gemma":[0.00006100064,0.00001950899,0.000002394868,0.0001042281,0.000009098409,0.00001213629,2.00784e-7,0.0003964861,0.00001126968,0.07700455,0.9221325,0.0002466387],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[5.499808e-7,0.0005738367,0.01481349,0.0003320574,0.0002243252,0.0001994731,0.000001043264,0.0002200176,0.9836352],"genre_scores_gemma":[0.0004040778,0.0001197295,0.002236938,0.0003647765,0.0004631306,0.00003110045,0.000001932985,0.00003751381,0.9963408],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.922053,"threshold_uncertainty_score":0.9997233,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2020488014","doi":"10.5402/2012/324194","title":"Using Radial Basis Function Networks for Function Approximation and Classification","year":2012,"lang":"en","type":"article","venue":"ISRN Applied Mathematics","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":248,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Concordia University; City University of Hong Kong","keywords":"Radial basis function; Hierarchical RBF; Radial basis function network; Computer science; Function approximation; Artificial intelligence; Basis (linear algebra); Perceptron; Nonlinear system; Artificial neural network; Function (biology); Multilayer perceptron; Mathematical optimization; Machine learning; Algorithm; Mathematics; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.06864731073519341,"gpt":0.2725820986777176,"spread":0.2039347879425242,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003481946,0.0001394764,0.0001441653,0.00005955885,0.0002595411,0.0001263531,0.0001453325,0.0001010111,0.000003386788],"category_scores_gemma":[0.000007646262,0.0001315516,0.00004046125,0.0002595533,0.0000288199,0.0003755803,0.00005474812,0.00008797443,0.00001132258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003970855,"about_ca_system_score_gemma":0.00001141214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.137196e-7,"about_ca_topic_score_gemma":9.883491e-7,"domain_scores_codex":[0.9990782,0.00001026909,0.000266795,0.0002311025,0.0001352721,0.0002783458],"domain_scores_gemma":[0.9992,0.000135813,0.0001992366,0.0003282772,0.00004600617,0.00009069828],"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":[0.00001089062,0.0001074183,0.00003925581,0.00005547165,0.00001582182,1.191382e-8,0.0002164623,0.0009123567,0.00790374,0.9304502,0.0004917033,0.05979669],"study_design_scores_gemma":[0.0002603294,0.00002312128,0.000489391,0.00001014372,0.00006136631,0.000004993349,0.00008469058,0.9644827,0.0004995093,0.0325928,0.001321161,0.0001698433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006494582,0.00007982777,0.9912242,0.00009781666,0.0002747156,0.0006923401,0.000001587357,0.0001522792,0.0009826255],"genre_scores_gemma":[0.7508308,0.0000145418,0.2482367,0.0001452645,0.0004681139,0.0002352945,0.0000175887,0.00001820629,0.00003349815],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9635703,"threshold_uncertainty_score":0.5364518,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2058819127","doi":"10.1016/j.neucom.2010.06.004","title":"Chaotic time series prediction with residual analysis method using hybrid Elman–NARX neural networks","year":2010,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":248,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Residual; Chaotic; Nonlinear autoregressive exogenous model; Series (stratigraphy); Artificial neural network; Time series; Computer science; Embedding; Mathematics; Algorithm; Applied mathematics; Control theory (sociology); Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.01002891070477262,"gpt":0.2457311585198927,"spread":0.2357022478151201,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003333439,0.0002413068,0.0003045555,0.0001857586,0.0005838496,0.0003838316,0.0006755595,0.00005834131,0.00001006413],"category_scores_gemma":[0.00001342596,0.0002111634,0.0001031381,0.001563844,0.00005923308,0.0005592469,0.0003236768,0.0005810651,0.000005432831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001369782,"about_ca_system_score_gemma":0.00002617155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002479469,"about_ca_topic_score_gemma":0.00001375252,"domain_scores_codex":[0.9980224,0.0001366095,0.0003420819,0.000726894,0.0002900539,0.0004819027],"domain_scores_gemma":[0.9986395,0.0001997367,0.0002288896,0.0006892767,0.0001024687,0.0001401916],"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":[0.000009557553,0.00003578149,0.002653002,0.000005197774,0.00007811061,0.00003450259,0.00006980749,0.9727167,0.005175011,0.001248501,0.0001950334,0.01777881],"study_design_scores_gemma":[0.0001380577,0.00007336387,0.006409504,0.000007154747,0.000127003,0.000258158,0.000003529012,0.9918794,0.0005149643,0.0001115631,0.0002791834,0.0001980922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.320118,0.000009628751,0.6785664,0.0004672025,0.0002134824,0.0001845262,0.000002480109,0.0003428181,0.0000954823],"genre_scores_gemma":[0.8287567,0.000001250384,0.1701671,0.0002943089,0.0006743963,0.000008911785,0.00001095096,0.00002324182,0.0000630764],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5086387,"threshold_uncertainty_score":0.8610993,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2772747611","doi":"10.1038/nmeth.4526","title":"Machine learning: a primer","year":2017,"lang":"es","type":"article","venue":"Nature Methods","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":241,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"National Institute of Mental Health","keywords":"Primer (cosmetics); Computational biology; Computer science; Biology; Artificial intelligence; Chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.03465492183432028,"gpt":0.4239045969834016,"spread":0.3892496751490813,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00115591,0.0002282715,0.0002777311,0.000053037,0.001294372,0.001145592,0.002152096,0.0004380011,0.00005623847],"category_scores_gemma":[0.0004986198,0.000187855,0.0001554343,0.0001782226,0.0001368911,0.0003101255,0.000825551,0.002075185,0.00007399474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001867388,"about_ca_system_score_gemma":0.00004793028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004474928,"about_ca_topic_score_gemma":0.000002256776,"domain_scores_codex":[0.998166,0.0004410464,0.0002039086,0.0005967992,0.0002352218,0.0003570554],"domain_scores_gemma":[0.997326,0.0003256321,0.0003502396,0.001737481,0.000109315,0.0001513184],"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":[0.000005868996,0.0000516164,0.002992954,0.00001766165,0.00003222571,0.000009944889,0.0000616062,0.00004485507,0.002533504,0.2012369,0.002062836,0.7909501],"study_design_scores_gemma":[0.0001951477,0.00004931095,0.02079932,0.00003968658,0.00002959664,0.00001580118,0.000001195496,0.0852303,0.004404395,0.006209633,0.8827748,0.0002508369],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001484856,0.01625719,0.9129555,0.02383812,0.002802189,0.0004295029,0.000008815775,0.0002402245,0.04198364],"genre_scores_gemma":[0.3099292,0.0005159606,0.6797559,0.0008032121,0.0008103846,0.00001825631,0.000003720035,0.00002474686,0.008138582],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8807119,"threshold_uncertainty_score":0.9998913,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1983334819","doi":"10.1109/cvpr.2010.5539962","title":"Modeling pixel means and covariances using factorized third-order boltzmann machines","year":2010,"lang":"en","type":"article","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":225,"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; Artificial intelligence; Pattern recognition (psychology); Pixel; Probabilistic logic; Covariance; Covariance matrix; Image (mathematics); Boltzmann machine; Set (abstract data type); Machine learning; Generative model; Gaussian; Binary number; Mixture model; Algorithm; Generative grammar; Mathematics; Deep learning; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02851994556779858,"gpt":0.2757607040053723,"spread":0.2472407584375737,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009444598,0.00009648129,0.0000999523,0.0000272493,0.0002199956,0.0002071386,0.0003210454,0.00004261226,0.0000131786],"category_scores_gemma":[0.000009011235,0.00007198397,0.0000222585,0.0001886824,0.00002649997,0.0003484479,0.0001393757,0.0001520442,0.000005070133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002785834,"about_ca_system_score_gemma":0.00002021481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001859759,"about_ca_topic_score_gemma":0.0001291923,"domain_scores_codex":[0.999327,0.00001103725,0.0001275198,0.000266307,0.0001047158,0.0001634205],"domain_scores_gemma":[0.9995241,0.00003782153,0.00002780193,0.0002847007,0.00005684611,0.00006872907],"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":[0.000006429904,0.00008653109,0.001310355,0.00001509132,0.00002932474,0.00000270053,0.0004711091,0.05012603,0.1956386,0.7179343,0.0004028895,0.03397667],"study_design_scores_gemma":[0.0001129339,0.000004843354,0.0000643243,0.000002824706,0.000003277904,0.000009118969,0.000005641852,0.9901196,0.0001706684,0.008075959,0.001324853,0.0001059495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1974815,0.00003779545,0.800288,0.0008046774,0.0002341929,0.00007935219,8.127819e-7,0.0001161768,0.0009574511],"genre_scores_gemma":[0.7337021,0.00001761319,0.2657549,0.0002604682,0.0001156393,0.000004894577,6.365913e-7,0.000004982099,0.0001387601],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9399936,"threshold_uncertainty_score":0.2935421,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2134842679","doi":"10.48550/arxiv.1305.6663","title":"Generalized Denoising Auto-Encoders as Generative Models","year":2013,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":210,"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":"Noise (video); Infinitesimal; Computer science; Algorithm; Noise reduction; Gaussian noise; Limit (mathematics); Gaussian; Mathematics; Applied mathematics; Artificial intelligence; Mathematical optimization","retraction":null,"screen_n_in":null,"score":{"opus":0.0706505008980403,"gpt":0.1846081007012172,"spread":0.1139575998031769,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005505071,0.0001405861,0.0001251616,0.00007329575,0.0002822229,0.0001577566,0.0007533241,0.00005819216,0.00006165665],"category_scores_gemma":[0.000003170778,0.0001432524,0.00007925231,0.0005968895,0.00006160033,0.001199442,0.0002248543,0.0001156816,0.0003541633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005769745,"about_ca_system_score_gemma":0.0000482099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003143283,"about_ca_topic_score_gemma":0.00001624145,"domain_scores_codex":[0.9989733,0.00006012884,0.0001081254,0.0005131735,0.00006001647,0.0002852553],"domain_scores_gemma":[0.9991071,0.00004447816,0.00007149106,0.0005176778,0.0001015554,0.0001577124],"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":[0.000001452652,0.00002238769,0.00004857079,0.000001134132,0.00001252258,0.0000162605,0.00009544989,0.2801517,0.001275506,0.7159153,0.001578728,0.0008809262],"study_design_scores_gemma":[0.0002030901,0.00001843676,0.00006469456,0.000004166169,0.000006959701,0.000004037867,0.00002613149,0.8193079,0.0005685608,0.1790921,0.0005454309,0.0001585285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3410786,0.00002280779,0.6553304,0.0003970938,0.00006461811,0.0001591255,6.048004e-7,0.0001473933,0.00279931],"genre_scores_gemma":[0.9869101,0.00006638895,0.008654985,0.000716874,0.00004990604,0.000002682608,0.000002183181,0.000008759772,0.003588093],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6466754,"threshold_uncertainty_score":0.5841665,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W71081281","doi":"10.1007/978-3-642-35289-8_27","title":"Training Deep and Recurrent Networks with Hessian-Free Optimization","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":206,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Implementation; Hessian matrix; Heuristic; Artificial intelligence; Training (meteorology); Artificial neural network; Machine learning; Deep neural networks; Computer engineering; Software engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02176382442885493,"gpt":0.2338243518035695,"spread":0.2120605273747145,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003635343,0.0003696699,0.0003239901,0.0002416423,0.0003039303,0.0004593157,0.001757611,0.0001847949,0.00001007071],"category_scores_gemma":[0.00001241834,0.0002937987,0.00004182478,0.000479069,0.000435866,0.000589328,0.000839366,0.0005835178,0.000002431513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007890022,"about_ca_system_score_gemma":0.0001161703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003396269,"about_ca_topic_score_gemma":0.00005172738,"domain_scores_codex":[0.9977104,0.00001851376,0.0002926868,0.0009605451,0.0004546347,0.0005632065],"domain_scores_gemma":[0.9982204,0.0002174319,0.0002214886,0.001032307,0.0001005162,0.0002078703],"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":[0.000001702828,0.000006239874,0.000009047887,0.000004811924,0.000002742438,0.000004361664,0.00020407,0.4036286,7.72042e-7,0.009189485,0.000005922901,0.5869423],"study_design_scores_gemma":[0.0001603191,0.00009481824,0.00005387989,0.000206516,0.00000826779,0.00007700894,1.222942e-7,0.983337,0.000008651347,0.01484613,0.0008168868,0.0003903844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000008862313,0.00188261,0.995007,0.0007436782,0.0005374523,0.0003177579,0.000001271876,0.0001121557,0.0013892],"genre_scores_gemma":[0.06546018,0.0003130942,0.9324282,0.0009029586,0.0007587145,0.00002295564,0.000007569538,0.00003426948,0.00007199664],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5865519,"threshold_uncertainty_score":0.9999514,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4288877484","doi":"10.1007/978-1-4471-7452-3","title":"Neural Networks and Statistical Learning","year":2019,"lang":"en","type":"book","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":204,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Artificial intelligence; Artificial neural network; Deep learning; Statistical learning; Big data; Deep neural networks; Machine learning; Neural coding; Unsupervised learning; Cloud computing; Data science; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.009845208218876219,"gpt":0.2268739492605094,"spread":0.2170287410416332,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006295351,0.0001579118,0.0001880972,0.00002847524,0.00009125108,0.0001976392,0.0003676153,0.0001277787,0.00005271732],"category_scores_gemma":[0.000003966211,0.0001324957,0.00003064032,0.0000477644,0.00004311742,0.00009360966,0.000340259,0.0005137402,0.00006766941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000158137,"about_ca_system_score_gemma":0.00003602624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002792833,"about_ca_topic_score_gemma":0.000002087339,"domain_scores_codex":[0.9990895,0.0000226752,0.0001468964,0.0004078916,0.0001242961,0.0002087288],"domain_scores_gemma":[0.9992529,0.0002599528,0.00006593642,0.0003053024,0.00002407059,0.00009182446],"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":[6.759628e-7,0.000003841518,0.00002129852,0.000009286004,0.000007400477,0.000006936963,0.000005972135,0.006575486,4.385792e-7,0.7887693,0.1279978,0.07660149],"study_design_scores_gemma":[0.0000476626,0.00003399249,0.00006030298,0.000009170349,0.000005134031,0.00001319779,3.828331e-7,0.7605825,1.087806e-7,0.004804004,0.2342951,0.0001484156],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.000003158458,0.0002292339,0.762316,0.0002791811,0.0001649415,0.0001394916,0.000001362285,0.0001325864,0.236734],"genre_scores_gemma":[0.004017171,0.0001090171,0.00675112,0.0005977352,0.0002982586,0.000009276781,0.00003730761,0.00001933486,0.9881608],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7839653,"threshold_uncertainty_score":0.5403019,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2584401907","doi":"10.1007/978-3-642-24477-3_1","title":"On the Expressive Power of Deep Architectures","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":200,"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":"Computer science; Deep learning; Artificial intelligence; Expressive power; Deep neural networks; Electronic circuit; Computer architecture; Theoretical computer science; Electrical engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01627985766662682,"gpt":0.2305647609154636,"spread":0.2142849032488368,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003115527,0.0003360558,0.0003063829,0.0002767577,0.0002022299,0.0001357341,0.003943151,0.0001474786,0.00007063975],"category_scores_gemma":[0.00004708471,0.0002097451,0.0001287586,0.000369193,0.0007872193,0.00008944457,0.0009437287,0.0006632009,0.00002581268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000394645,"about_ca_system_score_gemma":0.000105337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008566211,"about_ca_topic_score_gemma":0.00001819028,"domain_scores_codex":[0.9977888,0.00003002728,0.0003337046,0.0008729057,0.0005930934,0.0003814548],"domain_scores_gemma":[0.9969178,0.0009237833,0.0002969627,0.001645033,0.0001295218,0.00008687466],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000005782447,0.00003315014,0.000004831199,0.000008006831,0.000009961058,0.00001565179,0.001282552,0.02744807,0.0001851377,0.5037134,0.00008963341,0.4672039],"study_design_scores_gemma":[0.00008203861,0.0001792148,0.00009697444,0.0001895281,0.000004138743,0.00002107178,9.372048e-8,0.08461404,0.00412427,0.9096501,0.0006948753,0.0003436528],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003222061,0.0002132379,0.9868059,0.0009783338,0.0004802971,0.0003524379,0.00000309278,0.0000548191,0.01078974],"genre_scores_gemma":[0.9300731,0.00001613639,0.06676441,0.002747423,0.0001760721,0.00002232202,8.943193e-7,0.00002433478,0.0001753088],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9297509,"threshold_uncertainty_score":0.8553159,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2959400106","doi":"10.1088/1742-6596/1237/2/022030","title":"Performance Analysis of Various Activation Functions in Artificial Neural Networks","year":2019,"lang":"en","type":"article","venue":"Journal of Physics Conference Series","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":192,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Activation function; Artificial neural network; Computer science; Artificial intelligence; Principal (computer security); Function (biology); Affect (linguistics); Machine learning; Psychology; Biology; Communication","retraction":null,"screen_n_in":null,"score":{"opus":0.01991495602824132,"gpt":0.2342995755777208,"spread":0.2143846195494795,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001232821,0.00007981175,0.0002565194,0.0001423438,0.00004374194,0.00006564753,0.0003254361,0.00003185236,0.00001479162],"category_scores_gemma":[0.000004943736,0.00006891509,0.0001036277,0.001326219,0.00003430235,0.001058561,0.00004991573,0.0001965619,0.000001750765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001831871,"about_ca_system_score_gemma":0.00006032201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001052034,"about_ca_topic_score_gemma":0.00001673444,"domain_scores_codex":[0.9991912,0.00003052022,0.0003640865,0.0001117784,0.0001788964,0.0001235431],"domain_scores_gemma":[0.999028,0.00005846982,0.0004137115,0.0002140343,0.0002534023,0.0000323927],"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":[0.00003986954,0.0001143179,0.01728799,0.000008702889,0.0001222776,8.875437e-7,0.000387115,0.7501208,0.00703425,0.06424627,0.00002966351,0.1606079],"study_design_scores_gemma":[0.000100621,0.0001675495,0.06942789,0.00002303332,0.00005628615,0.000002919893,0.00007048533,0.9217836,0.005968521,0.002262957,0.00004586186,0.00009021837],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6539517,0.000005590547,0.3454458,0.0002560089,0.0001406994,0.00004682644,8.217738e-7,0.000005674139,0.0001468989],"genre_scores_gemma":[0.9991481,0.00001791318,0.0006609791,0.00003281288,0.0000894481,0.000002124262,0.000002712454,0.000002924441,0.0000429532],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3451965,"threshold_uncertainty_score":0.2810276,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2951308445","doi":"","title":"Structure Discovery in Nonparametric Regression through Compositional Kernel Search","year":2013,"lang":"en","type":"preprint","venue":"DSpace@MIT (Massachusetts Institute of Technology)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":192,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Kernel (algebra); Extrapolation; Nonparametric statistics; Computer science; Kernel method; Kernel embedding of distributions; Nonparametric regression; Kernel regression; Range (aeronautics); Artificial intelligence; Regression; Machine learning; Data mining; Mathematics; Pattern recognition (psychology); Regression analysis; Support vector machine; Statistics; Engineering; Discrete mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02050411866690285,"gpt":0.2806218579701827,"spread":0.2601177393032799,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.00015296,0.0005960842,0.0008473821,0.001303699,0.0002006857,0.0002665538,0.003690269,0.001298008,0.00001857724],"category_scores_gemma":[0.0000621674,0.0005166332,0.0002217849,0.002771832,0.0006862852,0.001151408,0.004081747,0.002449613,0.00002742538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002527381,"about_ca_system_score_gemma":0.0003291198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002421856,"about_ca_topic_score_gemma":0.00007357793,"domain_scores_codex":[0.9964194,0.00006422235,0.0007604263,0.001373678,0.0007105141,0.0006717318],"domain_scores_gemma":[0.9967071,0.00007727826,0.0005498006,0.002339289,0.0002322616,0.00009421841],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004924438,0.001182095,0.01588959,0.0007216634,0.0003923995,0.0002254983,0.0005087626,0.0517595,0.0198265,0.8320657,0.01799069,0.05938838],"study_design_scores_gemma":[0.004183257,0.0005268987,0.03305281,0.005427025,0.0001789783,0.0003056517,0.0001368831,0.1213212,0.08475696,0.6739959,0.07133907,0.004775393],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7783323,0.002227525,0.1880272,0.02570551,0.00181254,0.001870496,0.0003869694,0.0007135911,0.0009238854],"genre_scores_gemma":[0.8618451,0.0003257387,0.1370387,0.0001562087,0.0001088249,0.0001598723,0.0001309719,0.00003028654,0.0002042867],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1580698,"threshold_uncertainty_score":0.9999985,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2102323492","doi":"10.1109/tvcg.2008.85","title":"Glimmer: Multilevel MDS on the GPU","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Visualization and Computer Graphics","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":186,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Graphics processing unit; Parallel computing; CUDA; Benchmark (surveying); General-purpose computing on graphics processing units; Computation; Graphics; Memory hierarchy; Maxima and minima; Algorithm; Computational science; Computer graphics (images); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03951219503809449,"gpt":0.2667145617690557,"spread":0.2272023667309612,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009114738,0.0001647139,0.0001143595,0.0001360323,0.0008629693,0.0001059744,0.0003539139,0.00006745137,0.00001047718],"category_scores_gemma":[8.72137e-7,0.0001222784,0.00008193153,0.0006200408,0.0001094004,0.000170185,0.000004957369,0.0001957322,0.00002364176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009660108,"about_ca_system_score_gemma":0.00002006791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009459304,"about_ca_topic_score_gemma":0.000005632442,"domain_scores_codex":[0.9989449,0.00008073104,0.0002017283,0.0003495857,0.0002429844,0.0001800285],"domain_scores_gemma":[0.9991667,0.0001921239,0.00006076288,0.0004140327,0.00007794553,0.0000884699],"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":[0.000006275017,0.0002423145,0.0000207615,0.000003992429,0.00002126279,0.000003212881,0.0005663083,0.001765041,0.00001837676,0.980315,0.001716935,0.01532056],"study_design_scores_gemma":[0.0002504036,0.0001492741,0.0007598003,0.00001790098,0.000006449541,0.00003044732,0.000005600783,0.9887034,0.001283219,0.0009837224,0.007632984,0.0001767407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01792694,0.00001756209,0.9804945,0.00068912,0.000376739,0.0002167974,0.000004976906,0.0001938339,0.00007951003],"genre_scores_gemma":[0.9934114,0.0004065263,0.0007423511,0.005173814,0.00007168965,0.00004945343,0.000002228218,0.00001308212,0.0001294972],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9869384,"threshold_uncertainty_score":0.6637349,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4252222626","doi":"10.1561/1500000061","title":"An Introduction to Neural Information Retrieval","year":2018,"lang":"en","type":"article","venue":"Foundations and Trends® in Information Retrieval","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":185,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Microsoft (Canada)","funders":"","keywords":"Information retrieval; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01178234844688753,"gpt":0.2774988290535456,"spread":0.2657164806066581,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003635361,0.00014817,0.0001273846,0.0008141898,0.000412323,0.000873381,0.0003548917,0.0000804122,0.0001040064],"category_scores_gemma":[0.00007417429,0.0001456196,0.0000317457,0.002607922,0.00007408555,0.01037661,0.0001072574,0.0001616023,0.0002156698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007416149,"about_ca_system_score_gemma":0.00003364346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000282633,"about_ca_topic_score_gemma":0.00002884022,"domain_scores_codex":[0.9986324,0.00003999993,0.0005612827,0.0002052242,0.0002989608,0.0002620822],"domain_scores_gemma":[0.9988274,0.00003163288,0.0001725186,0.0004872503,0.0003202091,0.0001609993],"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":[0.000176903,0.00008849434,0.0005336006,0.00001433734,0.00001312252,4.544148e-7,0.00438227,0.002295035,0.0002486079,0.2766958,0.0112242,0.7043272],"study_design_scores_gemma":[0.001067756,0.0007220422,0.06211844,0.00001100083,0.0000116879,0.00004870707,0.0002586972,0.4787235,0.0007692061,0.002403713,0.4533564,0.0005088761],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3614782,0.00001070401,0.6014392,0.02891662,0.001937154,0.0006743518,0.00004972687,0.0005086748,0.004985353],"genre_scores_gemma":[0.9898137,0.000006720243,0.008197025,0.001014563,0.0005123366,0.00001439541,0.0003595973,0.000004441115,0.00007721897],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7038183,"threshold_uncertainty_score":0.8422033,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}