{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":151,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":151,"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":"d2753f78f5a0","filters":{"venue":"Neural Computation"}},"results":[{"id":"W2136922672","doi":"10.1162/neco.2006.18.7.1527","title":"A Fast Learning Algorithm for Deep Belief Nets","year":2006,"lang":"en","type":"article","venue":"Neural Computation","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":16404,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Computer science; Associative property; Prior probability; Discriminative model; Generative model; Content-addressable memory; Artificial intelligence; Inference; Algorithm; Generative grammar; Pattern recognition (psychology); Deep belief network; Artificial neural network; Mathematics; Bayesian probability","retraction":null,"screen_n_in":null,"score":{"opus":0.01315184452963776,"gpt":0.2505059087497646,"spread":0.2373540642201269,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001657176,0.0001224798,0.0001165181,0.0001085005,0.000296915,0.0002568679,0.0002176187,0.00004545361,0.000005300052],"category_scores_gemma":[0.00002685602,0.0001284615,0.00006913803,0.0002822307,0.00001961505,0.0004256206,0.00005438842,0.0001461647,0.00003770347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003314869,"about_ca_system_score_gemma":0.00001887735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002611961,"about_ca_topic_score_gemma":0.000007148802,"domain_scores_codex":[0.9988977,0.00008400226,0.0002264665,0.0003137021,0.0002257683,0.0002523054],"domain_scores_gemma":[0.9994189,0.0001718623,0.0001326243,0.00009722789,0.0001273616,0.00005203583],"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":[0.000002487512,0.00002035703,0.00009015117,0.00000413982,0.00000280389,0.000003391754,0.0002453163,0.2394576,0.0002313818,0.00392845,0.0002982976,0.7557157],"study_design_scores_gemma":[0.0005225707,0.0001286744,0.004025247,0.000005006692,0.000003172771,0.00001378956,0.00003797868,0.9858533,0.00009691318,0.003128336,0.006039549,0.0001454209],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005513286,0.00006127702,0.9916763,0.0004913144,0.000348958,0.0002070341,7.766754e-7,0.0003519167,0.001349183],"genre_scores_gemma":[0.6653314,9.850065e-7,0.3335643,0.0003728108,0.0001565379,0.0000208426,0.00005763026,0.00001407839,0.0004813806],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7555702,"threshold_uncertainty_score":0.5238506,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2013035813","doi":"10.1162/neco_a_00142","title":"A Connection Between Score Matching and Denoising Autoencoders","year":2011,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":980,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Autoencoder; Restricted Boltzmann machine; Artificial intelligence; Noise reduction; Pattern recognition (psychology); Estimator; Computer science; Matching (statistics); Probabilistic logic; Unsupervised learning; Nonparametric statistics; Energy (signal processing); Rank (graph theory); Artificial neural network; Machine learning; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.06044979363662861,"gpt":0.2499212846951548,"spread":0.1894714910585262,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001275268,0.00009158936,0.0001012105,0.0000675512,0.0001922963,0.0001285571,0.0001188664,0.00003174547,0.000003058563],"category_scores_gemma":[0.00001453857,0.00008704609,0.00002577838,0.0001558125,0.00002654358,0.0006935199,0.000074557,0.00007822394,0.000005263392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001626941,"about_ca_system_score_gemma":0.00001028869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001155603,"about_ca_topic_score_gemma":0.000008610305,"domain_scores_codex":[0.9992864,0.00009212625,0.0001366195,0.0002424212,0.0001049893,0.0001374405],"domain_scores_gemma":[0.9996639,0.00007570913,0.00007411301,0.00008634574,0.00004819922,0.00005171075],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002562349,0.0000517959,0.02326751,0.00004204013,0.00007012031,0.00002879417,0.01347803,0.09588788,0.006404745,0.007250996,0.0002376217,0.8532549],"study_design_scores_gemma":[0.0002499283,0.0001225293,0.1546903,0.00002255626,0.00001521457,0.00001719558,0.00009327009,0.818454,0.002803896,0.02331803,0.00001776954,0.0001953062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.367521,0.00002139774,0.6318885,0.0001011634,0.000146921,0.00005920463,2.598728e-7,0.00007646799,0.0001850513],"genre_scores_gemma":[0.9343232,0.000002009131,0.06545926,0.0001150609,0.0000849249,0.000001897373,0.000002369745,0.000005681586,0.000005584167],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8530595,"threshold_uncertainty_score":0.3549637,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2064630666","doi":"10.1162/neco.2008.04-07-510","title":"Representational Power of Restricted Boltzmann Machines and Deep Belief Networks","year":2008,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":839,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Boltzmann machine; Deep belief network; Restricted Boltzmann machine; Artificial intelligence; Block (permutation group theory); Artificial neural network; Inference; Probabilistic logic; Computer science; Deep learning; Generative model; Boltzmann constant; Power (physics); Machine learning; Generative grammar; Theoretical computer science; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0162958313026846,"gpt":0.2431024191057949,"spread":0.2268065878031103,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006019807,0.0001006219,0.0001348638,0.00007649858,0.0001605759,0.0000380114,0.0001563491,0.00003832666,0.000006094457],"category_scores_gemma":[0.00004621413,0.00009190133,0.00003966279,0.0003144181,0.00006975038,0.0004028658,0.00009933245,0.00007933594,0.000001628778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000798166,"about_ca_system_score_gemma":0.00001510824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003873924,"about_ca_topic_score_gemma":0.000004021493,"domain_scores_codex":[0.9990759,0.0001137325,0.0002256536,0.0002578928,0.0001966666,0.000130139],"domain_scores_gemma":[0.9993596,0.0001773706,0.0001256254,0.0001374484,0.000149306,0.00005063664],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003837966,0.00007458568,0.009501885,0.000007108506,0.00003150289,0.00002911709,0.0009652235,0.9329822,0.002046608,0.001616705,0.001790727,0.05091596],"study_design_scores_gemma":[0.0002154338,0.00007185451,0.1710982,0.000003410594,0.000003305739,0.00002998533,0.000006189799,0.8277473,0.0001975779,0.0005234829,0.000028379,0.0000748677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2396715,0.0002633251,0.7591361,0.0003228001,0.0002339297,0.00009664597,9.231556e-7,0.00004491628,0.0002298843],"genre_scores_gemma":[0.9735461,0.00003638231,0.02614092,0.0001470191,0.0000803973,0.000003177591,0.00001239307,0.000005578016,0.00002804345],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7338746,"threshold_uncertainty_score":0.3747628,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2142329149","doi":"10.1162/089976603322385063","title":"A Universal Model for Spike-Frequency Adaptation","year":2003,"lang":"en","type":"article","venue":"Neural Computation","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":542,"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":"Spike (software development); Time constant; Adaptation (eye); Biological system; Biological neuron model; Computer science; Generator (circuit theory); Current (fluid); Filter (signal processing); Neuroscience; Control theory (sociology); Physics; Artificial neural network; Artificial intelligence; Power (physics); Biology; Control (management)","retraction":null,"screen_n_in":null,"score":{"opus":0.06699823300148582,"gpt":0.2725513951119858,"spread":0.2055531621105,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007602893,0.0001033339,0.00008199151,0.00007748281,0.0001763615,0.00004962163,0.00006558474,0.00004087668,0.000005630573],"category_scores_gemma":[0.0002317882,0.0001024784,0.00005853884,0.0001891282,0.00002616973,0.0003155918,0.0000076332,0.0000746536,0.00001058694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005033598,"about_ca_system_score_gemma":0.00003437526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005668519,"about_ca_topic_score_gemma":0.000007856264,"domain_scores_codex":[0.9991559,0.00007120764,0.0001507287,0.0002951892,0.0001558602,0.0001710917],"domain_scores_gemma":[0.9995741,0.0001552255,0.00008616249,0.00007477414,0.00006402864,0.0000456932],"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":[0.00004416214,0.00004145857,0.00002967255,0.00001499892,0.000001437363,0.000003269874,0.0002077462,0.7086159,0.1865948,0.09419315,0.0001847674,0.0100686],"study_design_scores_gemma":[0.0004566827,0.0001284352,0.00006892497,0.000002944451,0.000006845692,0.00001057886,0.00002323661,0.957993,0.004562514,0.0365621,0.00007514464,0.000109541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4261066,0.000003961849,0.5716935,0.0002380009,0.0003977522,0.0003286054,0.00001004035,0.00009554053,0.001126049],"genre_scores_gemma":[0.9932203,0.000002417081,0.005783186,0.000576622,0.00002929559,0.00001565358,0.000017312,0.00001573448,0.0003394418],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5671138,"threshold_uncertainty_score":0.4178947,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2143169494","doi":"10.1162/0899766054322964","title":"The Cocktail Party Problem","year":2005,"lang":"en","type":"review","venue":"Neural Computation","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":515,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Perception; Auditory scene analysis; Analogy; Computer science; Phenomenon; Process (computing); Cognitive science; Artificial intelligence; Auditory system; Auditory perception; Computational auditory scene analysis; Psychology; Cognitive psychology; Neuroscience; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.06976775862070309,"gpt":0.3699043797292316,"spread":0.3001366211085285,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004965045,0.0002782078,0.0004696785,0.0001064627,0.0003107353,0.0006738682,0.001046058,0.0001586558,0.000001924009],"category_scores_gemma":[0.00002541349,0.0001772529,0.0002365949,0.0004880637,0.00004196712,0.0004117625,0.0002278452,0.0004423709,0.0001299604],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008199638,"about_ca_system_score_gemma":0.0001677232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002635769,"about_ca_topic_score_gemma":0.000007329922,"domain_scores_codex":[0.9979185,0.0005130252,0.0005632493,0.0004155641,0.0003470267,0.0002426529],"domain_scores_gemma":[0.9984559,0.0004660238,0.0004613581,0.0004427298,0.0001158621,0.00005809349],"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":[2.6105e-7,0.000008603155,5.145307e-8,0.0001658746,0.000007978659,0.000001160535,0.00005755129,0.00008693707,2.261881e-8,0.01184273,0.003660926,0.9841679],"study_design_scores_gemma":[0.00004063886,0.00004153838,8.174082e-7,0.0003219796,0.00002368536,0.00003189034,0.000001519805,0.02497228,5.645314e-7,0.002057961,0.9723188,0.000188366],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.929875e-7,0.805357,0.1910082,0.0005839229,0.0002025728,0.0006995217,0.00000157272,0.0005854175,0.001561612],"genre_scores_gemma":[0.00002949786,0.9792781,0.01972348,0.0002631823,0.0001484854,0.0001390493,0.00003757359,0.00002378326,0.0003568018],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9839795,"threshold_uncertainty_score":0.7228165,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2071709160","doi":"10.1162/neco_a_00311","title":"An Efficient Learning Procedure for Deep Boltzmann Machines","year":2012,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":490,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Boltzmann machine; Restricted Boltzmann machine; MNIST database; Computer science; Artificial neural network; Artificial intelligence; Boltzmann constant; Deep belief network; Deep learning; Focus (optics); Inference; Algorithm; Hidden Markov model; Pattern recognition (psychology); Machine learning; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.01628468875810614,"gpt":0.2747265167593389,"spread":0.2584418280012328,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002077644,0.0001120618,0.0001013721,0.00005211944,0.0002659867,0.00014204,0.0001975822,0.00003371453,0.000002765527],"category_scores_gemma":[0.00005087005,0.00009701189,0.00004985363,0.000161407,0.00001402686,0.0005731478,0.00004073152,0.00008058539,0.000009486265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001779127,"about_ca_system_score_gemma":0.00001041125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005076452,"about_ca_topic_score_gemma":0.000001726793,"domain_scores_codex":[0.9991345,0.0001039521,0.0001350035,0.0002237867,0.0001369169,0.0002658711],"domain_scores_gemma":[0.9995295,0.00009281559,0.0000800865,0.0001057268,0.0001009445,0.00009089013],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000746728,0.00005387026,0.000895877,0.000009485133,0.000004376627,2.573107e-7,0.0007592924,0.8982161,0.001450925,0.001098687,0.0001125743,0.09739105],"study_design_scores_gemma":[0.0001707507,0.0001268814,0.007942328,0.000003489959,0.000006104165,0.000005026759,0.00002577307,0.9902909,0.0008365939,0.0001909005,0.0002807428,0.0001205022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1248474,0.0001131483,0.8738881,0.0002332995,0.000493093,0.0002124091,4.971167e-7,0.0001309185,0.00008111919],"genre_scores_gemma":[0.929613,6.713544e-7,0.06973023,0.0001767885,0.000412719,0.00001942869,0.00001555252,0.000009661762,0.00002196608],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8047656,"threshold_uncertainty_score":0.395603,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2166107799","doi":"10.1162/089976600300015187","title":"Gradient-Based Optimization of Hyperparameters","year":2000,"lang":"en","type":"article","venue":"Neural Computation","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":478,"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":"Hyperparameter; Cholesky decomposition; Gradient descent; Hyperparameter optimization; Computer science; Selection (genetic algorithm); Mathematics; Mathematical optimization; Model selection; Applied mathematics; Computation; Quadratic equation; Artificial intelligence; Algorithm; Machine learning; Artificial neural network; Support vector machine","retraction":null,"screen_n_in":null,"score":{"opus":0.01406182111473949,"gpt":0.2205749250895469,"spread":0.2065131039748074,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00001502044,0.00005651255,0.00006851542,0.00005022164,0.00001585258,0.000009284764,0.00003590442,0.00002382857,0.00002929384],"category_scores_gemma":[0.000002412878,0.00005941313,0.00002657251,0.0001023084,0.00001403498,0.00005507721,0.000001810967,0.00003584936,0.000003408782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001086307,"about_ca_system_score_gemma":0.000002205693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006641528,"about_ca_topic_score_gemma":3.877905e-7,"domain_scores_codex":[0.9996894,0.00001401631,0.0001045236,0.00006140354,0.00006666257,0.00006400901],"domain_scores_gemma":[0.9998633,0.00002212413,0.00001585858,0.00005872261,0.00002444627,0.00001549402],"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":[0.000005534419,0.000005819721,0.00004297088,0.00000439232,0.000002691198,7.198624e-7,0.00001775245,0.9583919,0.00144334,0.000005478183,0.0001606237,0.03991874],"study_design_scores_gemma":[0.0001089895,0.00003580642,0.0004803102,0.00001247525,0.000005359617,0.000001622965,0.000001893274,0.9812471,0.0179351,0.00007752127,0.00003826709,0.00005561062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8060521,0.00002516447,0.1925844,0.00001650352,0.00006863565,0.00006439186,0.000001093646,0.0003522861,0.0008354516],"genre_scores_gemma":[0.9771938,0.000004952242,0.02271366,0.00004074216,0.00001153553,0.00000186494,0.00001868594,0.00001070033,0.000004039061],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1711417,"threshold_uncertainty_score":0.2422797,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2125126592","doi":"10.1162/089976602753633402","title":"A Parallel Mixture of SVMs for Very Large Scale Problems","year":2002,"lang":"en","type":"article","venue":"Neural Computation","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":368,"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":"Support vector machine; Generalization; Benchmark (surveying); Set (abstract data type); Computer science; Artificial intelligence; Machine learning; Data set; Quadratic equation; Training set; Scale (ratio); Pattern recognition (psychology); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02876338798834915,"gpt":0.2530030794397367,"spread":0.2242396914513876,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007401753,0.00007626114,0.0001048631,0.00005940986,0.00007645616,0.00004187716,0.0001669332,0.00004952196,0.00001398176],"category_scores_gemma":[0.00001227959,0.00006727225,0.00006267729,0.0001622952,0.00001136033,0.0003571812,0.00004188325,0.0000570556,0.00002367722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007520412,"about_ca_system_score_gemma":0.000004327258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000230793,"about_ca_topic_score_gemma":0.000002926471,"domain_scores_codex":[0.9993002,0.00003266617,0.0001716314,0.0001944825,0.000149338,0.0001517096],"domain_scores_gemma":[0.9995902,0.00006555879,0.00009520093,0.0001110822,0.0001018516,0.0000361713],"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":[0.0001327345,0.001648871,0.002376913,0.0009641425,0.00006829713,0.00001151023,0.01579295,0.1645041,0.04495784,0.005655908,0.1745069,0.5893799],"study_design_scores_gemma":[0.0006526259,0.0001440249,0.0007720878,0.00003167362,0.000003855257,0.000004400862,0.00001761936,0.9917606,0.001656705,0.003675828,0.001191789,0.00008886019],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1476806,0.000108417,0.8502861,0.0008334803,0.0002929681,0.0003295944,0.000008006221,0.00009819608,0.0003626248],"genre_scores_gemma":[0.9578871,0.000007708769,0.04155884,0.0002952702,0.00004335057,0.0000319702,0.0000232552,0.000005875395,0.0001466853],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8272564,"threshold_uncertainty_score":0.2743283,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2109025268","doi":"10.1162/0899766041732396","title":"Learning Eigenfunctions Links Spectral Embedding and Kernel PCA","year":2004,"lang":"en","type":"article","venue":"Neural Computation","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":345,"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":"Isomap; Mathematics; Embedding; Nonlinear dimensionality reduction; Spectral clustering; Principal component analysis; Pattern recognition (psychology); Cluster analysis; Artificial intelligence; Laplace operator; Kernel (algebra); Multidimensional scaling; Kernel principal component analysis; Eigenfunction; Dimensionality reduction; Kernel method; Eigenvalues and eigenvectors; Computer science; Mathematical analysis; Combinatorics; Statistics; Support vector machine","retraction":null,"screen_n_in":null,"score":{"opus":0.0193230920392189,"gpt":0.2700799698759921,"spread":0.2507568778367732,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006986607,0.00008733846,0.00007525108,0.00008674085,0.0002658146,0.0001771803,0.00009123264,0.00006705244,0.00000558972],"category_scores_gemma":[0.00002265674,0.00008451809,0.0000312639,0.000183338,0.00001829158,0.0005631453,0.00006234514,0.0002777351,0.00005221555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002831683,"about_ca_system_score_gemma":0.0000183064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002444095,"about_ca_topic_score_gemma":0.000003802169,"domain_scores_codex":[0.9992935,0.00003799449,0.0001287532,0.0002434412,0.000141436,0.0001548548],"domain_scores_gemma":[0.9997198,0.00004385615,0.00005631196,0.00006923687,0.00004780915,0.00006301598],"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":[0.00001265968,0.0000534534,0.00104859,0.00002044102,0.00001116954,0.00002159721,0.002308074,0.7787964,0.009603026,0.003847316,0.0002256487,0.2040517],"study_design_scores_gemma":[0.0005685578,0.0002061666,0.01069494,0.00003525759,0.000005890371,0.00005814954,0.0001175602,0.972764,0.002249937,0.01294724,0.0001848365,0.0001674857],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5255173,0.00002658091,0.4728774,0.0006994051,0.0002371681,0.00005959092,2.388771e-7,0.0001772805,0.0004050419],"genre_scores_gemma":[0.9750391,0.0000103205,0.02455242,0.0002441941,0.00007757131,0.000004608906,0.00001010388,0.000005944938,0.00005570949],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4495218,"threshold_uncertainty_score":0.3446548,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2164921999","doi":"10.1162/089976600300015178","title":"Boosting Neural Networks","year":2000,"lang":"en","type":"article","venue":"Neural Computation","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":303,"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":"Boosting (machine learning); AdaBoost; Computer science; Artificial intelligence; Artificial neural network; Machine learning; Resampling; Weighting; Decision tree; Gradient boosting; Overfitting; Benchmark (surveying); Pattern recognition (psychology); Random forest; Classifier (UML)","retraction":null,"screen_n_in":null,"score":{"opus":0.01889837284029754,"gpt":0.2679592206379307,"spread":0.2490608477976331,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001401394,0.00009837489,0.00008235889,0.00004800043,0.0001900997,0.0002231553,0.0003218617,0.00003733609,0.00003695143],"category_scores_gemma":[0.00002566202,0.00009432388,0.00003408912,0.0002973202,0.00001592471,0.0005476798,0.00004422616,0.00018588,0.0000764053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001601032,"about_ca_system_score_gemma":0.00000724757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003038013,"about_ca_topic_score_gemma":0.000002586887,"domain_scores_codex":[0.9990367,0.0001226569,0.0001833248,0.0002980662,0.0001694215,0.0001897721],"domain_scores_gemma":[0.99951,0.0001019715,0.00006917019,0.0002228385,0.00003702592,0.000059031],"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":[0.000003190552,0.000008525633,0.0005844014,0.000001897574,0.000001145583,0.000002756427,0.00005999833,0.3333887,0.00003319878,0.0007324801,0.0003355005,0.6648482],"study_design_scores_gemma":[0.0001406048,0.00004535497,0.02874751,0.000003544451,0.000002049038,0.00002263558,0.00000249019,0.9693722,0.000009092963,0.0002697782,0.001285671,0.00009914214],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2177902,0.00007809856,0.7756361,0.002049254,0.0003216813,0.0001063083,6.463726e-7,0.0005601298,0.003457513],"genre_scores_gemma":[0.9915951,0.000004061741,0.007361867,0.0006313393,0.0001423136,0.000004115472,0.00005247734,0.000007116707,0.0002015775],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7738049,"threshold_uncertainty_score":0.3846416,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2136163184","doi":"10.1162/neco.2010.01-09-953","title":"Learning to Represent Spatial Transformations with Factored Higher-Order Boltzmann Machines","year":2010,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":231,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Transformation (genetics); Multiplicative function; Boltzmann machine; Mathematics; Artificial intelligence; Filter (signal processing); Image (mathematics); Pixel; Tensor (intrinsic definition); Computer science; Algorithm; Pattern recognition (psychology); Artificial neural network; Computer vision; Geometry; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.01138203735279639,"gpt":0.2459222741355828,"spread":0.2345402367827864,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008933407,0.0001379055,0.0001236723,0.00008810145,0.0002642628,0.0002416901,0.0002390157,0.00003921697,0.00002601382],"category_scores_gemma":[0.00003050278,0.0001087146,0.00003741426,0.0003529228,0.00002439533,0.0005996063,0.00005245601,0.0002394035,0.00002707804],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001082187,"about_ca_system_score_gemma":0.00002368624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002124823,"about_ca_topic_score_gemma":0.0002219167,"domain_scores_codex":[0.999007,0.00008708637,0.0001771351,0.000292394,0.0002411794,0.0001952226],"domain_scores_gemma":[0.9994029,0.00008067778,0.00006731716,0.0001726677,0.0001779041,0.00009855635],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002467547,0.00003493707,0.0009784206,0.000005168162,0.00001490359,0.000004971286,0.001430101,0.7408102,0.01122894,0.0004540274,0.0004136613,0.2446],"study_design_scores_gemma":[0.0002718154,0.0002034574,0.03584676,0.000004812913,0.00000645156,0.000006694607,0.00001374694,0.9595754,0.001860263,0.0002260295,0.001818265,0.000166262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.198576,0.000003347626,0.7972455,0.002713038,0.000555994,0.0001948064,0.000001257583,0.0001407018,0.0005693512],"genre_scores_gemma":[0.9431664,5.835756e-7,0.056254,0.0002188173,0.0002030268,0.00001423872,0.00001644446,0.000009695031,0.0001167689],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7445904,"threshold_uncertainty_score":0.4433253,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3108742966","doi":"10.1162/neco_a_01341","title":"Deeply Felt Affect: The Emergence of Valence in Deep Active Inference","year":2020,"lang":"en","type":"article","venue":"Neural Computation","topic":"Embodied and Extended Cognition","field":"Neuroscience","cited_by":230,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"H2020 Marie Skłodowska-Curie Actions; Social Sciences and Humanities Research Council of Canada; Canada First Research Excellence Fund; Lundbeckfonden; Aarhus Universitets Forskningsfond; Rosetrees Trust; European Commission; Aarhus Universitet; Wellcome Trust; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; William K. Warren Foundation; McGill University","keywords":"Affect (linguistics); Inference; Valence (chemistry); Psychology; Computer science; Artificial intelligence; Cognitive psychology; Physics; Communication; Quantum mechanics","retraction":null,"screen_n_in":null,"score":{"opus":0.07392864079283384,"gpt":0.3207362132718913,"spread":0.2468075724790575,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006009342,0.0000916112,0.0001025402,0.00004004416,0.00007548992,0.00001774577,0.0001871325,0.00002864692,0.00002357721],"category_scores_gemma":[0.0006377526,0.00007246957,0.00003503966,0.0005067398,0.00007758073,0.0002558004,0.0000524436,0.000182877,0.00002849926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000909305,"about_ca_system_score_gemma":0.00001782786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001988991,"about_ca_topic_score_gemma":0.0000186064,"domain_scores_codex":[0.9989982,0.0001808034,0.0001892504,0.0002599649,0.0002261922,0.0001455387],"domain_scores_gemma":[0.9993039,0.0004140719,0.0001168652,0.00007199879,0.00005183254,0.00004137942],"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":[0.000504588,0.0002127105,0.004082668,0.0002118595,0.000007001888,0.00005057906,0.01715234,0.1568959,0.391445,0.03553023,0.0002253842,0.3936817],"study_design_scores_gemma":[0.0004667808,0.0003541947,0.01982771,0.00003807139,0.00001143337,0.000006953127,0.0005662155,0.7393563,0.2018497,0.03731606,0.00001192557,0.0001946322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9812381,0.00002911617,0.009836791,0.002117342,0.0002310939,0.0003831941,0.000009618713,0.00007539966,0.006079369],"genre_scores_gemma":[0.9986148,0.00002374028,0.00009984501,0.001201903,0.00003636503,0.00001144824,0.000003727461,0.000006264291,0.000001839937],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5824604,"threshold_uncertainty_score":0.2955223,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2156740722","doi":"10.1162/neco.2008.11-07-647","title":"Justifying and Generalizing Contrastive Divergence","year":2008,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":211,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Mathematics; Estimator; Gibbs sampling; Applied mathematics; Convergence (economics); Boltzmann machine; Gradient descent; Statistics; Bayesian probability; Computer science; Artificial intelligence; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.03970591529768274,"gpt":0.24661055085706,"spread":0.2069046355593772,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006874144,0.00009388624,0.0001014823,0.00004293599,0.0003372502,0.00006598199,0.0001292592,0.0000238798,0.000002752576],"category_scores_gemma":[0.00002853314,0.00008731653,0.00002555218,0.0001629748,0.00005099574,0.000520666,0.0001029722,0.00006542105,0.000006611187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001357364,"about_ca_system_score_gemma":0.00001333222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003395037,"about_ca_topic_score_gemma":0.000002616931,"domain_scores_codex":[0.9992505,0.00007582743,0.00012385,0.0002556416,0.0001320413,0.0001621069],"domain_scores_gemma":[0.9996394,0.00008870383,0.00005801809,0.00007743722,0.00007839514,0.00005805455],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002904485,0.00006810875,0.01412265,0.00002696197,0.00005592594,0.0001827794,0.005225856,0.5209548,0.03496009,0.00691797,0.00337063,0.4140852],"study_design_scores_gemma":[0.000170214,0.00004006536,0.03347445,0.000005165821,0.000003955754,0.0000433855,0.00001455445,0.963959,0.001689345,0.0004015424,0.00008767897,0.0001106348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2311601,0.0001701287,0.7678217,0.0002831341,0.0002892646,0.00006712271,5.521413e-7,0.0000638231,0.0001442547],"genre_scores_gemma":[0.9524497,0.00003844761,0.04708449,0.0002899935,0.0001022605,0.000003043596,0.000001909347,0.000004095551,0.00002601605],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7212897,"threshold_uncertainty_score":0.3560665,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2108840817","doi":"10.1162/neco_a_00256","title":"Accelerated Multiplicative Updates and Hierarchical ALS Algorithms for Nonnegative Matrix Factorization","year":2011,"lang":"en","type":"article","venue":"Neural Computation","topic":"Tensor decomposition and applications","field":"Mathematics","cited_by":204,"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":"Non-negative matrix factorization; Multiplicative function; Image (mathematics); Convergence (economics); Matrix (chemical analysis); Simple (philosophy); Inverse; Factorization; Matrix decomposition","retraction":null,"screen_n_in":null,"score":{"opus":0.1726492887982786,"gpt":0.3975729216675088,"spread":0.2249236328692302,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007592998,0.0001356824,0.0001614546,0.00007431974,0.0001861792,0.00004519797,0.00007659361,0.00006699499,0.00002513782],"category_scores_gemma":[0.0000803528,0.0001243167,0.00004207693,0.0001629407,0.00005713776,0.0001842572,0.00002694536,0.00009219618,0.000009539226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001695878,"about_ca_system_score_gemma":0.000009878861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009152199,"about_ca_topic_score_gemma":0.00000245581,"domain_scores_codex":[0.9991607,0.00006141332,0.0002706428,0.0002656854,0.0001014718,0.0001400935],"domain_scores_gemma":[0.9990053,0.0004331473,0.0001609984,0.0000890282,0.0002387098,0.00007285023],"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":[0.0007350257,0.001737236,0.003670254,0.0003485278,0.0003331292,0.00000576795,0.02877957,0.0005578255,0.07601921,0.7557341,0.004926171,0.1271532],"study_design_scores_gemma":[0.001987238,0.0003164922,0.03009033,0.00002483074,0.00008204331,0.00001768981,0.0004367405,0.4588183,0.03351755,0.4740111,0.0002544835,0.0004432471],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3891712,0.00000893898,0.6089992,0.0003590835,0.00005750165,0.0009008448,0.00007696944,0.0001869402,0.0002393402],"genre_scores_gemma":[0.8630536,0.000002911891,0.136439,0.00007558136,0.00004867012,0.0001375295,0.0001716955,0.00001956809,0.00005145999],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4738823,"threshold_uncertainty_score":0.5069489,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2154071538","doi":"10.1162/neco_a_00312","title":"Learning Where to Attend with Deep Architectures for Image Tracking","year":2012,"lang":"en","type":"article","venue":"Neural Computation","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":200,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Artificial intelligence; Eye tracking; Computer vision; Gaze; Orientation (vector space); Reinforcement learning; Object (grammar); Fixation (population genetics); Boltzmann machine; Action selection; Machine learning; Perception; Deep learning; Mathematics; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.02223441900648307,"gpt":0.3043333604364766,"spread":0.2820989414299936,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001467459,0.00009825613,0.00008688288,0.0001017625,0.0002130503,0.0001471537,0.0001320767,0.00002452469,0.000003412707],"category_scores_gemma":[0.00002745388,0.00008177834,0.00004164267,0.0002502337,0.00001147964,0.0002904932,0.00003402052,0.0001056973,0.00002184067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002312424,"about_ca_system_score_gemma":0.000005844907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006869047,"about_ca_topic_score_gemma":0.00001724308,"domain_scores_codex":[0.9991821,0.00006545427,0.0001281284,0.0002035522,0.0001757001,0.0002450675],"domain_scores_gemma":[0.9996031,0.00006678146,0.00006533799,0.00007749148,0.00009401717,0.00009326064],"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":[0.0000728651,0.00008741631,0.005629856,0.00005630432,0.00001583057,0.000003026067,0.005663114,0.1712954,0.01614183,0.0007809813,0.000226469,0.800027],"study_design_scores_gemma":[0.0004892896,0.0008680043,0.06779978,0.00002205055,0.000009430519,0.00007194845,0.0001470661,0.9258743,0.003476464,0.0004280603,0.0005565024,0.0002571442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4228337,0.00001306153,0.5762571,0.0003593123,0.0001686473,0.0001509641,2.288323e-7,0.0001303287,0.00008666896],"genre_scores_gemma":[0.9517406,1.897107e-7,0.04782287,0.0002355194,0.0001216602,0.00001987135,0.000003550532,0.00001031149,0.00004542718],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7997698,"threshold_uncertainty_score":0.3334824,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2150439267","doi":"10.1162/0899766053630332","title":"A Unified Approach to Building and Controlling Spiking Attractor Networks","year":2005,"lang":"en","type":"article","venue":"Neural Computation","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":175,"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":"Attractor; Computer science; Context (archaeology); Artificial neural network; Chaotic; Topology (electrical circuits); Dynamical systems theory; Artificial intelligence; Theoretical computer science; Mathematics; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.03925231697323309,"gpt":0.2717821612051046,"spread":0.2325298442318715,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001152368,0.0001193967,0.0001246225,0.00008850374,0.0002001432,0.0001562621,0.00007366887,0.00004315407,0.000001461145],"category_scores_gemma":[0.00009892584,0.0001113324,0.00003096725,0.0002373463,0.00002068536,0.000257048,0.00004059044,0.0001594644,0.000003863785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003300715,"about_ca_system_score_gemma":0.00000464397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006325495,"about_ca_topic_score_gemma":0.00000202225,"domain_scores_codex":[0.9990107,0.0000709809,0.0001834989,0.0003632869,0.0001571655,0.0002144086],"domain_scores_gemma":[0.999532,0.0002116082,0.00007519918,0.00006725593,0.00002660574,0.0000873062],"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":[0.00004641505,0.00002463612,0.0001031842,0.000006054465,0.000001276744,0.000001799561,0.0000711001,0.7433251,0.1941712,0.002223477,0.00003049447,0.05999522],"study_design_scores_gemma":[0.0003496331,0.00006642734,0.00203875,0.000008075071,0.000005598172,0.00002574573,0.000008332833,0.994347,0.00259035,0.0001679653,0.0002686006,0.0001235175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.776352,0.00001491671,0.2221579,0.0005110743,0.0002262501,0.0002423506,0.00000105362,0.00009590346,0.0003985279],"genre_scores_gemma":[0.9940708,0.000003663956,0.003537167,0.002043077,0.0002827412,0.000008383897,0.000003890227,0.00001560224,0.00003470275],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2510219,"threshold_uncertainty_score":0.4540005,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2111838090","doi":"10.1162/neco.2010.08-09-1081","title":"Deep Belief Networks Are Compact Universal Approximators","year":2010,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":173,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Deep belief network; Artificial intelligence; Sigmoid function; Generative grammar; Deep neural networks; Deep learning; Computer science; Artificial neural network; Generative model; Expression (computer science); Mathematics; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01013630683391467,"gpt":0.2242362151020559,"spread":0.2140999082681412,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001399242,0.000176482,0.0001796724,0.00008668596,0.0002531545,0.0002480386,0.0004520731,0.00008460143,0.00001561399],"category_scores_gemma":[0.0000295228,0.0001641562,0.0000840563,0.0003820026,0.00006031002,0.0006942794,0.00009955374,0.0003237532,0.00002380042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002272074,"about_ca_system_score_gemma":0.00001980566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000303762,"about_ca_topic_score_gemma":0.00004984436,"domain_scores_codex":[0.9988459,0.00009268447,0.0001912103,0.0003676266,0.0002142259,0.0002882993],"domain_scores_gemma":[0.9991887,0.0001323025,0.0001603593,0.0002626014,0.0001296494,0.0001264389],"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":[0.00000974983,0.00005438594,0.001753728,0.000004320871,0.00001671019,0.00001838417,0.0001857687,0.938982,0.001408763,0.002982343,0.001619146,0.05296473],"study_design_scores_gemma":[0.0002532012,0.00004710523,0.01340782,0.000004641822,0.000006543269,0.0000134245,0.00002587636,0.9846346,0.0002973941,0.0006034981,0.0005243281,0.000181615],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04706401,0.0000302261,0.9495926,0.0007840804,0.001493699,0.0001517622,8.631208e-7,0.000205558,0.0006771339],"genre_scores_gemma":[0.9775817,0.0000024479,0.02170317,0.0003226071,0.0003340961,0.000001847165,0.0000126668,0.00001225186,0.00002918373],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9305177,"threshold_uncertainty_score":0.6694098,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2164122462","doi":"10.1162/089976600300015691","title":"Nonlinear Autoassociation Is Not Equivalent to PCA","year":2000,"lang":"en","type":"article","venue":"Neural Computation","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":170,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Tel Aviv University; Office of Naval Research; Princeton University","keywords":"Nonlinear system; Principal component analysis; Artificial neural network; Artificial intelligence; Pattern recognition (psychology); Backpropagation; Projection (relational algebra); Mathematics; Interpolation (computer graphics); Computer science; Linear interpolation; Algorithm; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.02768951998526132,"gpt":0.2925187329385902,"spread":0.2648292129533289,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008532919,0.0001116175,0.0001041597,0.00005286432,0.000174169,0.0001912137,0.0003433434,0.00004061326,0.00005718425],"category_scores_gemma":[0.000006707599,0.0001106466,0.00005748918,0.0004930067,0.000008983413,0.0003508588,0.0000640055,0.00009851787,0.0005418693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004829397,"about_ca_system_score_gemma":0.00001398485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001941623,"about_ca_topic_score_gemma":0.000003591868,"domain_scores_codex":[0.9988829,0.00004077506,0.0002198413,0.0003485513,0.0002843678,0.0002235158],"domain_scores_gemma":[0.9994682,0.00006141712,0.00006182678,0.0002208813,0.00008528026,0.0001023642],"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":[0.00001095329,0.0001012121,0.0001180735,0.000006480197,0.000008840372,0.000003596008,0.0005739563,0.08641873,0.002225564,0.003977031,0.01110607,0.8954495],"study_design_scores_gemma":[0.0001751428,0.00009855237,0.007656277,0.000006585178,0.000004022802,0.00000465937,0.00000184013,0.9762524,0.001536289,0.001707299,0.01240271,0.0001541981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7343335,0.00001073484,0.2409635,0.02255282,0.0002617782,0.00037358,0.000008728543,0.0003798124,0.001115635],"genre_scores_gemma":[0.96161,0.000005244076,0.03046309,0.007102041,0.0001954632,0.00002357082,0.00001305244,0.000009181545,0.0005783134],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8952953,"threshold_uncertainty_score":0.6964814,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4319301677","doi":"10.1162/neco_a_01563","title":"Large Language Models and the Reverse Turing Test","year":2023,"lang":"en","type":"article","venue":"Neural Computation","topic":"Topic Modeling","field":"Computer Science","cited_by":164,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institute for Advanced Research; National Science Foundation","keywords":"Psychology; Cognitive psychology; Computer science; Cognitive science","retraction":null,"screen_n_in":null,"score":{"opus":0.03063292580025428,"gpt":0.2742570784898651,"spread":0.2436241526896109,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002452734,0.00005349039,0.0000618045,0.0000442593,0.0001166273,0.00009821771,0.0001739298,0.00001722712,6.533651e-7],"category_scores_gemma":[0.00004110901,0.00003862588,0.00001989286,0.0002023008,0.00001515459,0.0003022008,0.000178131,0.00007729839,0.00001699867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007766363,"about_ca_system_score_gemma":0.000005982151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002330912,"about_ca_topic_score_gemma":0.000005385451,"domain_scores_codex":[0.999433,0.00004550986,0.00009505702,0.0001681331,0.0001289055,0.0001293629],"domain_scores_gemma":[0.9995604,0.0002208128,0.00003208293,0.0001439395,0.0000198093,0.00002302692],"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":[0.00001396753,0.00002600151,0.0004812433,0.0000547882,0.0000116471,0.00007457923,0.03096054,0.7535505,0.0009476605,0.1095319,0.00145526,0.1028919],"study_design_scores_gemma":[0.0004129182,0.000006812925,0.0006743441,0.000005226311,0.000001698364,0.000007441055,0.0001204355,0.9895766,0.00005056538,0.0090726,0.00002657035,0.00004482372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.413798,0.00005034401,0.5833945,0.00197624,0.0001471808,0.0001043383,8.631965e-7,0.0002555418,0.0002730077],"genre_scores_gemma":[0.9958519,0.000005115537,0.003546603,0.0004369744,0.00004936912,0.000004722466,0.000002669873,0.000004013912,0.00009857705],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.582054,"threshold_uncertainty_score":0.1575118,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2011868317","doi":"10.1162/neco.2008.11-07-654","title":"Stimulus Representation and the Timing of Reward-Prediction Errors in Models of the Dopamine System","year":2008,"lang":"en","type":"letter","venue":"Neural Computation","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":159,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"ENCODE; Stimulus (psychology); Mean squared prediction error; Reinforcement learning; Dopamine; Computer science; Stimulus generalization; Temporal difference learning; Artificial intelligence; Psychology; Neuroscience; Machine learning; Cognitive psychology; Perception; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.0556581134920052,"gpt":0.2627732006886095,"spread":0.2071150871966043,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001908664,0.0001713791,0.0003131527,0.0001634791,0.0001277927,0.00002168989,0.0001955573,0.0001666825,7.107841e-7],"category_scores_gemma":[0.0001774749,0.0001067861,0.0001086129,0.0004499107,0.000223867,0.0001961653,0.00009130176,0.0005764677,4.531654e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006311668,"about_ca_system_score_gemma":0.00002231249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002165483,"about_ca_topic_score_gemma":0.000007577537,"domain_scores_codex":[0.9977759,0.0006106447,0.0005723968,0.0003750081,0.0005209884,0.0001450388],"domain_scores_gemma":[0.9984511,0.0005769731,0.0006337126,0.0002421218,0.0000835972,0.00001253035],"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":[0.0004307126,0.00004058587,0.0003742969,0.0008048813,0.00001762085,0.00006916013,0.001328539,0.9521254,0.02029461,0.0006837548,0.0195112,0.004319201],"study_design_scores_gemma":[0.0008161755,0.0000573541,0.001458365,0.0001405938,0.00002942602,0.0001185243,0.00004043436,0.9949998,0.001614954,0.0005869442,0.00005391703,0.00008346207],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9316099,0.00006038143,0.003024806,0.06122177,0.001992671,0.001436721,0.00007116262,0.00006879058,0.0005137948],"genre_scores_gemma":[0.9918885,0.00002942248,0.00003487946,0.007695311,0.000182991,0.00001783236,0.00003548349,0.00002097257,0.000094602],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0602786,"threshold_uncertainty_score":0.435461,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3132401450","doi":"10.1162/neco_a_01557","title":"How to Represent Part-Whole Hierarchies in a Neural Network","year":2022,"lang":"en","type":"article","venue":"Neural Computation","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":149,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Interpretability; Parsing; Transformer; Computer science; Artificial intelligence; Artificial neural network; Hierarchy; Representation (politics); Parse tree; Natural language processing; Theoretical computer science; Machine learning; Engineering; Voltage","retraction":null,"screen_n_in":null,"score":{"opus":0.02746012427718318,"gpt":0.2652115562248038,"spread":0.2377514319476206,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001768463,0.0001304472,0.0001457003,0.0001177299,0.0003891449,0.0002805399,0.0005943299,0.00001730499,0.000005697581],"category_scores_gemma":[0.00001313653,0.0001354857,0.00005711043,0.001371925,0.00001877132,0.0003218913,0.000651821,0.0002791756,0.000008350656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005483865,"about_ca_system_score_gemma":0.00001765309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002610048,"about_ca_topic_score_gemma":0.00002773886,"domain_scores_codex":[0.9983702,0.0002154349,0.0002244626,0.0004969927,0.0003308163,0.000362042],"domain_scores_gemma":[0.9992976,0.0001429246,0.00008524137,0.0003407005,0.00003262189,0.000100942],"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":[0.000008518702,0.00003438669,0.0005682677,0.000002219221,0.000001728474,0.00001814045,0.0002231913,0.8738377,0.0001344868,0.002940248,0.01414036,0.1080907],"study_design_scores_gemma":[0.0001943477,0.0001385073,0.00847872,0.000004035924,0.000001672397,0.0000233306,0.00003540527,0.9527158,0.00002099342,0.005485818,0.03273733,0.0001640727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6751882,0.0002829992,0.2387245,0.08226894,0.001546535,0.001144933,0.00001047745,0.0004528078,0.0003805761],"genre_scores_gemma":[0.9919261,0.000001745445,0.005146534,0.002058707,0.0002629569,0.0002446381,0.00002389324,0.00001097019,0.0003245028],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3167378,"threshold_uncertainty_score":0.5524946,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2148727093","doi":"10.1162/neco.2009.05-08-785","title":"A Binary Variable Model for Affinity Propagation","year":2009,"lang":"en","type":"article","venue":"Neural Computation","topic":"Error Correcting Code Techniques","field":"Computer Science","cited_by":138,"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":"Affinity propagation; Cluster analysis; Graphical model; Computer science; Variable (mathematics); Binary number; Algorithm; Artificial intelligence; Theoretical computer science; Mathematics; Correlation clustering; Canopy clustering algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.04036854436624773,"gpt":0.3017541364138341,"spread":0.2613855920475864,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002342732,0.0001022394,0.00009905177,0.00009742085,0.0001465217,0.0001066283,0.0002928073,0.00005029379,3.912184e-7],"category_scores_gemma":[0.00007738981,0.0001036537,0.00003986628,0.0003095707,0.000008013216,0.0006321223,0.00004208508,0.00009464673,0.000003181797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005177613,"about_ca_system_score_gemma":0.00005148045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000467933,"about_ca_topic_score_gemma":0.000001221425,"domain_scores_codex":[0.9991586,0.00004293608,0.0001780304,0.0002884863,0.000158648,0.0001733144],"domain_scores_gemma":[0.9994069,0.0000878167,0.0001057515,0.0001871136,0.0001751601,0.00003730997],"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":[0.00004060688,0.0001667989,0.00005594167,0.000030908,0.000004096897,0.000002595261,0.0009329016,0.7337976,0.02544281,0.0554489,0.002830025,0.1812468],"study_design_scores_gemma":[0.0001459072,0.0002784794,0.0005530759,0.00001006554,0.000003015973,0.000006221815,0.000001932243,0.9193223,0.001949066,0.07760718,0.00001461559,0.000108143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05238274,0.000008895658,0.9447109,0.0009168138,0.0001726007,0.0004177035,9.78373e-7,0.0009886337,0.0004007346],"genre_scores_gemma":[0.6292813,3.072242e-7,0.3702531,0.0003714353,0.00002580729,0.00001755585,0.000007580001,0.000004240088,0.00003859079],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5768986,"threshold_uncertainty_score":0.4226874,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W771469340","doi":"10.1162/neco_a_00801","title":"Correlational Neural Networks","year":2015,"lang":"en","type":"article","venue":"Neural Computation","topic":"Topic Modeling","field":"Computer Science","cited_by":137,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke; Université de Montréal","funders":"H2020 European Research Council","keywords":"Artificial neural network; Computer science; Artificial intelligence; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.05615718678418956,"gpt":0.2770928872008726,"spread":0.220935700416683,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001440955,0.00008566259,0.00007911529,0.0000542876,0.00006673856,0.0001214693,0.0002700923,0.00004153066,0.000002244012],"category_scores_gemma":[0.00003037845,0.00008436458,0.00003162716,0.0002059323,0.00001382372,0.0005482222,0.0001076387,0.0001321009,0.00002474518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000398029,"about_ca_system_score_gemma":0.00002753198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001288468,"about_ca_topic_score_gemma":0.000002163784,"domain_scores_codex":[0.9990777,0.00006835872,0.0001767354,0.0002398216,0.0002750937,0.0001623116],"domain_scores_gemma":[0.9994809,0.00006754535,0.00006831032,0.0001553327,0.0001244587,0.000103442],"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":[0.000002732828,0.000007014648,0.0008870168,7.96002e-7,0.00000146275,0.00000461779,0.000133869,0.9433693,0.000004792582,0.00632907,0.0006832376,0.04857603],"study_design_scores_gemma":[0.0002597124,0.00004096481,0.002569911,0.000001928113,0.000001661844,0.00002821627,0.000006546866,0.9935102,0.000005764979,0.003357324,0.0001290856,0.00008865595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08988602,0.00007066599,0.9068421,0.001012986,0.00133105,0.00007993488,2.07665e-7,0.0002100877,0.0005669238],"genre_scores_gemma":[0.973561,2.939949e-7,0.02558402,0.0005542103,0.0002139245,0.00000343749,0.00001151514,0.00000546305,0.0000660833],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.883675,"threshold_uncertainty_score":0.3440287,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2033272835","doi":"10.1162/neco.2008.12-07-661","title":"Deep, Narrow Sigmoid Belief Networks Are Universal Approximators","year":2008,"lang":"en","type":"article","venue":"Neural Computation","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":134,"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":"Sigmoid function; Curse of dimensionality; Binary number; Computer science; Deep neural networks; Artificial intelligence; Deep belief network; Artificial neural network; Algorithm; Theoretical computer science; Mathematics; Arithmetic","retraction":null,"screen_n_in":null,"score":{"opus":0.01677067633082922,"gpt":0.2210510176949123,"spread":0.204280341364083,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005863272,0.0001646024,0.0001535759,0.00007435384,0.0004498122,0.00008314235,0.0004808825,0.00006831111,0.000005056878],"category_scores_gemma":[0.000006280376,0.0001612908,0.00007652169,0.0006359732,0.00006432161,0.0005004774,0.0001289423,0.0002062583,0.00002989703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003775849,"about_ca_system_score_gemma":0.00001946362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000112733,"about_ca_topic_score_gemma":0.000005898153,"domain_scores_codex":[0.9987741,0.00006786259,0.0002166016,0.0004134565,0.0002388796,0.0002891104],"domain_scores_gemma":[0.99925,0.00009406443,0.0001606257,0.0002766689,0.00009645937,0.0001221768],"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":[0.000006779884,0.0000702871,0.00151221,0.000006146747,0.000007325112,0.00005365229,0.0002692151,0.9631807,0.00009474131,0.009096294,0.005350335,0.02035227],"study_design_scores_gemma":[0.0002331355,0.00005082368,0.008023147,0.000005221138,0.000003674135,0.00007907592,0.00001525566,0.98985,0.000058139,0.0008129553,0.0006892677,0.0001792914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.135848,0.0001523831,0.8615233,0.00110469,0.0003437973,0.0002240325,6.167184e-7,0.0003864119,0.0004167592],"genre_scores_gemma":[0.9889008,0.00001476203,0.01014853,0.0006113776,0.0001904175,0.00001432967,0.00001673001,0.0000134874,0.00008960946],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8530528,"threshold_uncertainty_score":0.6577249,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2170780515","doi":"10.1162/089976602760805296","title":"On Different Facets of Regularization Theory","year":2002,"lang":"en","type":"article","venue":"Neural Computation","topic":"Numerical methods in inverse problems","field":"Mathematics","cited_by":130,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Regularization (linguistics); Computer science; Mathematics; Artificial intelligence; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.1152705003684308,"gpt":0.345659416090685,"spread":0.2303889157222542,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001555811,0.00009495928,0.0001559739,0.00006399213,0.00003829702,0.00001034028,0.00007400932,0.00004702438,0.0001482962],"category_scores_gemma":[0.000405017,0.00007740963,0.00004919196,0.0001262819,0.00003765154,0.0000526518,0.00002288631,0.00009715084,0.00001786582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002704366,"about_ca_system_score_gemma":0.000001214942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.16407e-7,"about_ca_topic_score_gemma":1.491624e-7,"domain_scores_codex":[0.9989937,0.0003023936,0.000241518,0.0001413732,0.0002225593,0.00009845081],"domain_scores_gemma":[0.9986233,0.0009958835,0.0001674847,0.0001305894,0.00005341386,0.00002932511],"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":[0.00005948413,0.0004233934,0.0001150135,0.0001826635,0.00003385043,0.00000200311,0.001405188,0.007320135,0.00975213,0.8063403,0.001984053,0.1723818],"study_design_scores_gemma":[0.000232926,0.0001379859,0.0001967645,0.00002585062,0.00001325818,0.000001548458,0.00001770806,0.1763952,0.006573928,0.8163249,0.00001022259,0.00006977034],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4138135,0.00001684884,0.5815949,0.0001501203,0.0002760995,0.0002402027,0.000002212902,0.00009871066,0.003807405],"genre_scores_gemma":[0.9598977,0.000002155887,0.03969057,0.00009123514,0.00002217706,0.000006213122,0.000003241543,0.00001538834,0.0002713302],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5460842,"threshold_uncertainty_score":0.3156673,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3033196763","doi":"10.1162/neco_a_01351","title":"Sophisticated Inference","year":2021,"lang":"en","type":"article","venue":"Neural Computation","topic":"Embodied and Extended Cognition","field":"Neuroscience","cited_by":120,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Google (Canada); University of Toronto","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Wellcome Trust","keywords":"Inference; Counterfactual thinking; Artificial intelligence; Free energy principle; Bayes' theorem; Computer science; Machine learning; Bayesian inference; Reinforcement learning; Bayesian probability; Psychology; Social psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.08070876741893555,"gpt":0.3307592102763773,"spread":0.2500504428574417,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00002240117,0.00005865643,0.00005729181,0.00003021836,0.00009860641,0.00005008012,0.00004633595,0.00002494179,0.00005530384],"category_scores_gemma":[0.0004787189,0.00005963631,0.00002257934,0.0002225979,0.00002779747,0.0001263979,0.00002632377,0.00008760454,0.0001983623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001300264,"about_ca_system_score_gemma":0.00002482406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001286699,"about_ca_topic_score_gemma":0.000001402085,"domain_scores_codex":[0.9993528,0.00007900845,0.0001033652,0.0002168034,0.0001355686,0.0001125169],"domain_scores_gemma":[0.9996115,0.0001759589,0.00003468553,0.00006339939,0.00007718229,0.00003725969],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003502708,0.0001473666,0.0001766779,0.0000323126,0.000002712428,0.0002727216,0.0002089504,0.005095144,0.5257851,0.3132103,0.0005706006,0.1544631],"study_design_scores_gemma":[0.0004610044,0.00007013208,0.001453272,0.00001652211,0.00001164136,0.00009582646,0.00002701859,0.2605058,0.3252524,0.41149,0.000409528,0.000206865],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7192794,0.00006094259,0.03440491,0.004358783,0.001471638,0.000239294,0.00001988975,0.0007513062,0.2394138],"genre_scores_gemma":[0.9981914,0.00000647949,0.000339348,0.001283075,0.0000520548,0.000003546237,0.00002389735,0.000005768185,0.00009448826],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2789119,"threshold_uncertainty_score":0.2549613,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2116494657","doi":"10.1162/08997660360675035","title":"Analytic Expressions for Rate and CV of a Type I Neuron Driven by White Gaussian Noise","year":2003,"lang":"en","type":"article","venue":"Neural Computation","topic":"stochastic dynamics and bifurcation","field":"Physics and Astronomy","cited_by":115,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"White noise; Biological neuron model; Gaussian noise; Mathematics; Noise (video); Gaussian; Multiplicative function; Statistical physics; Mathematical analysis; Applied mathematics; Algorithm; Physics; Statistics; Artificial neural network; Computer science; Artificial intelligence; Quantum mechanics","retraction":null,"screen_n_in":null,"score":{"opus":0.01172094551741481,"gpt":0.2620758549645966,"spread":0.2503549094471818,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00003926918,0.00006501764,0.0000864696,0.00003137529,0.00005456551,0.00001909477,0.00002655283,0.00001429814,0.000007456369],"category_scores_gemma":[0.000009938421,0.00005868821,0.00002610697,0.00008805929,0.00001543843,0.00005489578,0.000007382357,0.0000346938,8.835397e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004330939,"about_ca_system_score_gemma":0.00001317825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008553005,"about_ca_topic_score_gemma":4.954226e-7,"domain_scores_codex":[0.9996066,0.00002788988,0.0001213662,0.0001223041,0.00004596231,0.00007589364],"domain_scores_gemma":[0.9997096,0.00005570033,0.00008837527,0.00005139224,0.00006174196,0.00003317421],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000354982,0.0007690641,0.1181876,0.000227957,0.0001992976,9.734022e-7,0.001897043,0.2702551,0.4458931,0.08303412,0.007364318,0.07181647],"study_design_scores_gemma":[0.0006572853,0.0002150371,0.01861594,0.0000179352,0.00003962223,4.704247e-7,0.00008227137,0.974152,0.0006098372,0.005395391,0.0001045162,0.0001096724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7922825,0.00000996338,0.2068716,0.00007898064,0.0001075608,0.0001947741,0.00002589407,0.000007717793,0.0004210925],"genre_scores_gemma":[0.998776,3.610405e-7,0.0009612358,0.00002167638,0.00002891559,0.000008010335,0.000101276,0.000007515566,0.00009505104],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7038969,"threshold_uncertainty_score":0.2393236,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2578935686","doi":"10.1162/neco_a_00934","title":"STDP-Compatible Approximation of Backpropagation in an Energy-Based Model","year":2017,"lang":"en","type":"article","venue":"Neural Computation","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":114,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Université de Montréal; Canadian Institute for Advanced Research","funders":"Canada Research Chairs","keywords":"Backpropagation; Inference; Computer science; Artificial neural network; Latent variable; Markov chain; Algorithm; Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.0700559932964008,"gpt":0.3070109804145279,"spread":0.2369549871181271,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001173324,0.000105121,0.0001302297,0.0001467673,0.0001968879,0.0001134233,0.0001919676,0.00004815742,0.000003407853],"category_scores_gemma":[0.0001024203,0.0001029178,0.00003573254,0.0001161117,0.00005913826,0.0008128078,0.00002626242,0.00008214893,0.000002238391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000356276,"about_ca_system_score_gemma":0.00002795703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006480892,"about_ca_topic_score_gemma":0.0001200902,"domain_scores_codex":[0.9989538,0.0001010042,0.0002635466,0.0002994745,0.0002505317,0.0001316667],"domain_scores_gemma":[0.9992537,0.00006090579,0.0003391959,0.0002400469,0.00006915677,0.00003694947],"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":[0.00005789114,0.00008165311,0.001027534,0.00001942232,2.921683e-7,0.000001303395,0.00003888334,0.6163428,0.3642561,0.003842456,0.000005820074,0.0143259],"study_design_scores_gemma":[0.0004730659,0.0001377434,0.01182288,0.00001342658,0.00000255763,8.785315e-7,0.000004089005,0.8866932,0.09378974,0.006970872,0.000001629863,0.00008987875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9036737,0.000001164673,0.09516753,0.0002176473,0.00014627,0.0001568895,0.000006331499,0.00004061326,0.0005898613],"genre_scores_gemma":[0.9985671,9.466922e-7,0.001115785,0.0002018569,0.00002177052,0.00001205334,0.00004337488,0.00001271808,0.00002439883],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2704663,"threshold_uncertainty_score":0.4196867,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2134484803","doi":"10.1162/089976601300014691","title":"Subtractive and Divisive Inhibition: Effect of Voltage-Dependent Inhibitory Conductances and Noise","year":2001,"lang":"en","type":"article","venue":"Neural Computation","topic":"Fish biology, ecology, and behavior","field":"Environmental Science","cited_by":113,"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":"Inhibitory postsynaptic potential; Subthreshold conduction; Physics; Voltage; Noise (video); Topology (electrical circuits); Chemistry; Control theory (sociology); Mathematics; Biophysics; Neuroscience; Biology; Computer science; Quantum mechanics","retraction":null,"screen_n_in":null,"score":{"opus":0.01273272492194176,"gpt":0.255703992626532,"spread":0.2429712677045903,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001234076,0.00009163081,0.000131691,0.00002497765,0.00008170364,0.0000113558,0.00002617416,0.00006196653,0.00006268908],"category_scores_gemma":[0.0000237992,0.00007643005,0.00001703311,0.0000655421,0.0003022817,0.0002086697,0.00005688236,0.00008917851,0.00001096118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002256007,"about_ca_system_score_gemma":0.000002115517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006120124,"about_ca_topic_score_gemma":0.00009837913,"domain_scores_codex":[0.999365,0.00009035827,0.0001295819,0.000216061,0.00009243429,0.0001065685],"domain_scores_gemma":[0.999662,0.0001541183,0.00009272739,0.00003948677,0.000009940298,0.00004173187],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001210973,0.00004405635,0.6840902,0.00001491501,0.000004484028,0.00002480354,0.0001915123,0.0002218824,0.2982899,0.000004734048,0.0001533265,0.01683915],"study_design_scores_gemma":[0.0005446599,0.0006745064,0.980844,0.000006278245,0.00001876673,0.00005459179,0.0000656917,0.0007921113,0.01675522,0.0001340899,0.00002662053,0.00008345458],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9989959,0.00006141575,0.00006256562,0.0001110182,0.0001435807,0.000222398,0.00000502826,0.00001820181,0.0003798653],"genre_scores_gemma":[0.9997817,0.0000220697,0.00004037138,0.00007682943,0.00002928034,0.000009722407,0.000008877855,0.000004380721,0.00002679475],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2967539,"threshold_uncertainty_score":0.3116727,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2142615865","doi":"10.1162/089976606775093936","title":"Topographic Product Models Applied to Natural Scene Statistics","year":2005,"lang":"en","type":"article","venue":"Neural Computation","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research; University of Toronto","funders":"Canada Research Chairs; Gatsby Charitable Foundation; Wellcome Trust","keywords":"Computer science; Artificial intelligence; Statistical model; Relation (database); Gaussian; Mixture model; Pattern recognition (psychology); Machine learning; Contrast (vision); Scale (ratio); Product (mathematics); Mathematics; Data mining; Geography; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.02100555942873878,"gpt":0.2770095159409491,"spread":0.2560039565122103,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001836813,0.0001344077,0.0001231103,0.000211242,0.0001040093,0.0002081709,0.0003680774,0.0000301028,0.000002001693],"category_scores_gemma":[0.00001543254,0.0001336027,0.00002893274,0.0005462414,0.00001874707,0.0005921019,0.0001099243,0.0001604398,0.00003747355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003778945,"about_ca_system_score_gemma":0.0000304801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006794193,"about_ca_topic_score_gemma":0.00001511734,"domain_scores_codex":[0.9987951,0.00006116415,0.0002380358,0.0003829067,0.0003228714,0.0001999554],"domain_scores_gemma":[0.999373,0.00005100641,0.00007922863,0.0002559112,0.0001615509,0.00007935862],"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":[0.00001417096,0.00006095399,0.00001665555,0.000009323709,0.000006711079,0.000001930535,0.00143454,0.2383085,0.002458203,0.2052174,0.005615016,0.5468566],"study_design_scores_gemma":[0.0001500083,0.0000582771,0.0009074119,0.000003901097,0.000002614292,0.000006864119,0.000004971259,0.9687371,0.004763966,0.02450719,0.0006793513,0.0001782944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03857432,0.00003290212,0.956526,0.003077572,0.0001681471,0.0003936154,0.000003178819,0.0006145972,0.0006096231],"genre_scores_gemma":[0.611592,0.000001340038,0.3865764,0.001691606,0.00006397301,0.00001637235,0.00001623158,0.000007007128,0.00003504051],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7304287,"threshold_uncertainty_score":0.5448158,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2626194254","doi":"10.1162/neco_a_01174","title":"Gated Orthogonal Recurrent Units: On Learning to Forget","year":2019,"lang":"en","type":"article","venue":"Neural Computation","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":101,"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":"Army Research Office; Semiconductor Research Corporation; National Science Foundation","keywords":"Artificial intelligence; Computer science; Psychology; Pattern recognition (psychology); Machine learning; Mathematics; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.01709036190143093,"gpt":0.2741854236455876,"spread":0.2570950617441566,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001629073,0.0001150401,0.0001084624,0.0001316593,0.000109056,0.0001165484,0.0002490995,0.00003013928,0.00000916588],"category_scores_gemma":[0.00007306415,0.0001048556,0.0000290441,0.0006198479,0.000005067238,0.0001684895,0.00009507996,0.0003034959,0.0003453417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000025286,"about_ca_system_score_gemma":0.00002408616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009823089,"about_ca_topic_score_gemma":0.000001520819,"domain_scores_codex":[0.9988943,0.0001492022,0.0001505433,0.000325533,0.0002809907,0.0001993861],"domain_scores_gemma":[0.999473,0.0001195272,0.0000711481,0.0001375643,0.0001126268,0.00008613487],"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":[0.00001888318,0.00002449101,0.001950737,0.000009469662,0.00000450145,0.000005021219,0.0005970645,0.5443528,0.0002437735,0.002666009,0.0004811285,0.4496462],"study_design_scores_gemma":[0.0002523657,0.0008756903,0.008366786,0.00002652948,0.000001261291,0.000006874576,0.00001819609,0.9846373,0.0001079924,0.0002335488,0.005333672,0.0001397504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8281415,0.000008121241,0.1682651,0.001152248,0.0008474666,0.0001704903,7.652407e-7,0.0003099566,0.001104304],"genre_scores_gemma":[0.9930192,5.368529e-7,0.005779626,0.000605056,0.00007571565,0.00000285304,0.00002914579,0.000009325608,0.0004785828],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4495064,"threshold_uncertainty_score":0.4438785,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2110316244","doi":"10.1162/089976603762552915","title":"Interspike Interval Correlations, Memory, Adaptation, and Refractoriness in a Leaky Integrate-and-Fire Model with Threshold Fatigue","year":2003,"lang":"en","type":"article","venue":"Neural Computation","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":99,"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":"Waveform; Refractory period; Stimulus (psychology); White noise; Time constant; Chaotic; Physics; Interval (graph theory); Statistical physics; Mathematics; Control theory (sociology); Voltage; Statistics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.06342231573025016,"gpt":0.2755747761819044,"spread":0.2121524604516543,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001128766,0.0001676641,0.0001545247,0.0001297304,0.0001207616,0.0001084991,0.00005929046,0.00005346544,0.000003192813],"category_scores_gemma":[0.0001555921,0.0001375094,0.00001973864,0.0002962451,0.00008191691,0.0005151324,0.00002757076,0.0002519795,0.000001704803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004705457,"about_ca_system_score_gemma":0.00002622766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004373314,"about_ca_topic_score_gemma":0.0001515276,"domain_scores_codex":[0.9989055,0.000104693,0.0002484215,0.0004047813,0.0001766601,0.0001598864],"domain_scores_gemma":[0.9995265,0.0001524162,0.0001134615,0.0000882048,0.00006096155,0.00005844657],"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":[0.0003713703,0.000146473,0.009558463,0.00006604369,0.000007021769,0.00003858336,0.004006631,0.9117918,0.01392257,0.01500222,0.00009647963,0.04499232],"study_design_scores_gemma":[0.0006310166,0.0001725446,0.003806547,0.00004429608,0.000007239095,0.00005827125,0.0003032966,0.9920954,0.0005438668,0.002172477,0.00001031941,0.0001547006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9397355,0.0000235502,0.05904688,0.0004150862,0.0002100636,0.0002671832,0.000003484373,0.00005543299,0.0002428656],"genre_scores_gemma":[0.9987689,0.00001642214,0.0006407044,0.0003503523,0.0000138302,0.00001884284,0.0000119066,0.00001846358,0.0001605311],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08030361,"threshold_uncertainty_score":0.5607468,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2169090997","doi":"10.1162/neco.2008.07-06-295","title":"Solving the Problem of Negative Synaptic Weights in Cortical Models","year":2008,"lang":"en","type":"article","venue":"Neural Computation","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":95,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; University of Toronto","funders":"","keywords":"Constraint (computer-aided design); Constructive; Computer science; Feed forward; Artificial neural network; Feedforward neural network; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0496745408348768,"gpt":0.2585284198859928,"spread":0.208853879051116,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007857299,0.00008170433,0.0001082571,0.0000656241,0.0001544939,0.00001404559,0.00009925124,0.00002953004,0.000003427681],"category_scores_gemma":[0.00007475528,0.00005591205,0.0000380624,0.0003006149,0.000125744,0.0002403982,0.00003514274,0.0001842323,0.000004685648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002560653,"about_ca_system_score_gemma":0.00001859781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003516433,"about_ca_topic_score_gemma":0.00001249273,"domain_scores_codex":[0.9990235,0.0001750225,0.0002362813,0.0002059357,0.000216016,0.0001432338],"domain_scores_gemma":[0.9991732,0.0005958644,0.00009770699,0.00006953643,0.00003949612,0.00002423866],"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":[0.0001932541,0.0002146465,0.001258423,0.00004483469,0.000006948017,0.00007599377,0.003704354,0.6766993,0.2790308,0.02814901,0.00007295466,0.01054949],"study_design_scores_gemma":[0.0002356879,0.0001132643,0.00780801,0.00001203593,0.000003014099,0.00004570106,0.00001826323,0.9658253,0.006740513,0.01913403,0.000002703497,0.00006147735],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9939453,0.000006192022,0.004604265,0.000420616,0.00009959079,0.0002649268,0.000001600916,0.00003076616,0.0006267374],"genre_scores_gemma":[0.9991941,0.000008362789,0.0004789263,0.000255806,0.00002022711,0.000008559217,0.000001531848,0.000007583915,0.00002489887],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.289126,"threshold_uncertainty_score":0.2280027,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2983826605","doi":"10.1162/neco_a_01246","title":"Toward Training Recurrent Neural Networks for Lifelong Learning","year":2019,"lang":"en","type":"article","venue":"Neural Computation","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Forgetting; Computer science; Lifelong learning; Artificial intelligence; Benchmark (surveying); Machine learning; Context (archaeology); Artificial neural network; Recurrent neural network; Psychology; Cognitive psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.06471803080604753,"gpt":0.2908396529338382,"spread":0.2261216221277907,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003552244,0.0001734987,0.0002040871,0.000120894,0.0002085993,0.0003184279,0.000333026,0.00006715202,0.00001147107],"category_scores_gemma":[0.00009153755,0.0001778415,0.0001162725,0.0003312811,0.00001743315,0.0006226437,0.00008748799,0.0003425646,0.00003144279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004239102,"about_ca_system_score_gemma":0.00002929825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003448963,"about_ca_topic_score_gemma":0.000001017131,"domain_scores_codex":[0.9984297,0.0001606958,0.0003111938,0.0004510616,0.0002671077,0.0003802237],"domain_scores_gemma":[0.9990415,0.000385105,0.0002018984,0.0001401553,0.0001254673,0.0001058784],"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":[0.00001458225,0.000008477342,0.0005303649,0.00001331606,0.000005583211,0.000001944123,0.001736013,0.6319463,0.00006463878,0.002024504,0.00008498743,0.3635693],"study_design_scores_gemma":[0.0006745584,0.0002821332,0.003774875,0.00001823514,0.000004652147,0.0000153192,0.0002351503,0.9926008,0.00001123604,0.0003297615,0.001845698,0.0002075893],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1376894,0.00007569076,0.85855,0.0008229375,0.00164728,0.0003793315,3.653036e-7,0.0003524267,0.0004826596],"genre_scores_gemma":[0.9780668,0.000003241101,0.0208581,0.0006228563,0.0002099777,0.00002101178,0.00003670243,0.00002015186,0.0001611815],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8403774,"threshold_uncertainty_score":0.7252167,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2579313944","doi":"10.1162/neco_a_00929","title":"Deep Learning with Dynamic Spiking Neurons and Fixed Feedback Weights","year":2017,"lang":"en","type":"article","venue":"Neural Computation","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":82,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"York University; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"MNIST database; Computer science; Spiking neural network; Backpropagation; Artificial neural network; Deep learning; Artificial intelligence; Feed forward; Piecewise; Learning rule; Algorithm; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01107484831472345,"gpt":0.2411140993521576,"spread":0.2300392510374341,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00003051043,0.0001416713,0.0001253701,0.00003296534,0.0005188119,0.0001353806,0.00009553612,0.00003256598,0.000002436252],"category_scores_gemma":[0.00002391987,0.0001297236,0.00001979375,0.00004113023,0.00004117012,0.0003688758,0.00004414394,0.0002576408,0.000004896349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001400997,"about_ca_system_score_gemma":0.000002150756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001889238,"about_ca_topic_score_gemma":0.000009153175,"domain_scores_codex":[0.9993929,0.00002200229,0.0001149567,0.0001923734,0.00009095173,0.0001867932],"domain_scores_gemma":[0.999675,0.00006128028,0.00007270039,0.00009908361,0.0000244919,0.00006740881],"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":[0.00001872124,0.000002230185,0.00152044,0.00004686801,0.000006062849,0.00002114667,0.0002007917,0.9007451,0.005068139,0.0000175793,0.00000215373,0.09235076],"study_design_scores_gemma":[0.0003705991,0.00009619654,0.04900505,0.0000311472,0.000009617434,0.00003154475,0.00002530019,0.9493147,0.0008270346,0.00008860412,0.00004336608,0.0001568991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9307135,0.00009077974,0.06821606,0.00009189605,0.0001470118,0.0001012698,2.614056e-7,0.0002861756,0.0003530375],"genre_scores_gemma":[0.9980429,0.00001391377,0.001778312,0.00004401682,0.00006570329,0.000002007226,0.000005368275,0.00002922603,0.00001851755],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09219386,"threshold_uncertainty_score":0.5289975,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2106439909","doi":"10.1162/neco_a_00158","title":"Quickly Generating Representative Samples from an RBM-Derived Process","year":2011,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Gibbs sampling; Herding; Sampling (signal processing); Exploit; Markov chain; Computer science; Algorithm; Markov process; Mixing (physics); Process (computing); Divergence (linguistics); Mathematics; Artificial intelligence; Machine learning; Statistics; Bayesian probability","retraction":null,"screen_n_in":null,"score":{"opus":0.07464532759247174,"gpt":0.3044249065450997,"spread":0.229779578952628,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001202774,0.0001683334,0.0001710311,0.00005907003,0.0002535602,0.0002031858,0.0004247349,0.00004608326,0.00003222829],"category_scores_gemma":[0.00005472661,0.000154996,0.00004956525,0.0002456398,0.00004686804,0.001445499,0.0001003303,0.0001083004,0.00001575385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001887207,"about_ca_system_score_gemma":0.00003497525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006419101,"about_ca_topic_score_gemma":0.00006927308,"domain_scores_codex":[0.9984452,0.0002957783,0.0002603435,0.0005486397,0.000225818,0.0002242335],"domain_scores_gemma":[0.9991523,0.0001139168,0.0001736568,0.000258424,0.0002031092,0.00009858802],"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":[0.00009304521,0.0003724654,0.005753937,0.0000212787,0.0001301739,0.00006028235,0.06410374,0.4470319,0.1337053,0.001885829,0.0008826722,0.3459593],"study_design_scores_gemma":[0.0002258361,0.0001303954,0.01859046,0.000007175554,0.000008465119,0.000002767364,0.0003374083,0.9380725,0.03729144,0.005139416,0.000005359495,0.0001887368],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3969911,0.0000207765,0.6022308,0.00009167354,0.000254826,0.0001133716,0.000003497633,0.0001160354,0.0001779143],"genre_scores_gemma":[0.7861745,0.000001646188,0.2132137,0.0003341569,0.0002137687,0.00001261721,0.00003228824,0.00001035181,0.000006953385],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4910406,"threshold_uncertainty_score":0.6320554,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2021394691","doi":"10.1162/neco.2007.19.2.404","title":"Fast Population Coding","year":2007,"lang":"en","type":"letter","venue":"Neural Computation","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":69,"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":"Neural coding; Encoder; Computer science; Decoding methods; Stimulus (psychology); Computation; Population; ENCODE; Theoretical computer science; Models of neural computation; Coding (social sciences); Artificial intelligence; Artificial neural network; Algorithm; Neuroscience; Psychology; Mathematics; Cognitive psychology; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.04796961973270329,"gpt":0.2877586968825501,"spread":0.2397890771498468,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001093946,0.0002857408,0.0002333583,0.000310135,0.000238151,0.0001800961,0.0001733341,0.0003988957,0.00003182273],"category_scores_gemma":[0.0001336059,0.0002801635,0.0001230073,0.0003603988,0.00003883879,0.0002620316,0.00005239303,0.00119256,0.0001035617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001275208,"about_ca_system_score_gemma":0.00001093655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004236097,"about_ca_topic_score_gemma":0.000005231707,"domain_scores_codex":[0.9978731,0.0001673055,0.000372016,0.0006288036,0.0005896821,0.0003690747],"domain_scores_gemma":[0.9990305,0.0003993388,0.0003114154,0.0001618591,0.00005615275,0.00004078899],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005004858,0.00003193052,0.0001774499,0.0001774023,0.000007507562,0.0006524646,0.00006408046,0.01188776,0.03160921,0.0003337938,0.8621455,0.09286288],"study_design_scores_gemma":[0.0007994255,0.0003787133,0.006001696,0.0001360496,0.00005304251,0.0003899776,0.000008237005,0.8242021,0.00474597,0.004317121,0.1575536,0.001414135],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.2305589,0.00003192246,0.03743412,0.7054601,0.01544838,0.001879709,0.0001230372,0.001551948,0.00751189],"genre_scores_gemma":[0.4452999,0.000006326189,0.0001190349,0.5504991,0.002479387,0.000006656875,0.0006963745,0.00005821181,0.0008349619],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.8123143,"threshold_uncertainty_score":0.9999651,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2132613708","doi":"10.1162/neco.2006.18.12.2942","title":"A Spiking Neuron Model of Cortical Correlates of Sensorineural Hearing Loss: Spontaneous Firing, Synchrony, and Tinnitus","year":2006,"lang":"en","type":"article","venue":"Neural Computation","topic":"Hearing, Cochlea, Tinnitus, Genetics","field":"Neuroscience","cited_by":66,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Tinnitus; Auditory cortex; Neuroscience; Excitatory postsynaptic potential; Sensorineural hearing loss; Hearing loss; Sensory system; Auditory system; Inhibitory postsynaptic potential; Percept; Hair cell; Psychology; Audiology; Cochlea; Medicine; Perception","retraction":null,"screen_n_in":null,"score":{"opus":0.0375497319122443,"gpt":0.2717095112320245,"spread":0.2341597793197802,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000119277,0.0002099148,0.0003040615,0.000148833,0.0001194033,0.000044477,0.0001356494,0.00008409542,0.000004791233],"category_scores_gemma":[0.0003408311,0.0002272664,0.00006401147,0.0002398233,0.0002302985,0.0001319844,0.0001554456,0.0003061284,0.00000435247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003604502,"about_ca_system_score_gemma":0.00003745011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001045719,"about_ca_topic_score_gemma":0.00001681919,"domain_scores_codex":[0.9980538,0.0001401226,0.0006067911,0.0004437973,0.0004112693,0.0003441698],"domain_scores_gemma":[0.9989383,0.000424127,0.0002732182,0.000185121,0.00009932242,0.00007988401],"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":[0.0000821341,0.00006994866,0.01138649,0.0001106281,0.000002026508,0.0001492054,0.000165694,0.5163461,0.4685952,0.0003914838,0.00001018749,0.002690854],"study_design_scores_gemma":[0.0004214039,0.0002534396,0.04487739,0.00005629427,0.00001992909,0.0006957536,0.00001040426,0.891689,0.06120919,0.0005934369,0.000003783709,0.0001699678],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9949723,0.00005000544,0.004092936,0.00006034639,0.0001504638,0.0002558421,0.000007518308,0.00009266335,0.000317891],"genre_scores_gemma":[0.9984343,0.000009483876,0.001336444,0.00006796409,0.00005883032,0.000002305825,0.000003953282,0.00003570901,0.00005099307],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.407386,"threshold_uncertainty_score":0.9267653,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2773393927","doi":"10.1162/neco_a_01046","title":"Improving Spiking Dynamical Networks: Accurate Delays, Higher-Order Synapses, and Time Cells","year":2017,"lang":"en","type":"article","venue":"Neural Computation","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":66,"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; ENCODE; Dynamical systems theory; Spiking neural network; Synapse; Representation (politics); Artificial neural network; Artificial intelligence; Neuroscience; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.02188286788206041,"gpt":0.2617647700605966,"spread":0.2398819021785362,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001143043,0.0001832986,0.000164879,0.00005486379,0.000789245,0.0006016817,0.0002160852,0.00008602909,0.00001613844],"category_scores_gemma":[0.0001533358,0.0001679662,0.0000422125,0.0000928079,0.0001261137,0.0006450316,0.0001917933,0.0002376498,0.00002723836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003548418,"about_ca_system_score_gemma":0.00001186222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005367076,"about_ca_topic_score_gemma":0.000006590189,"domain_scores_codex":[0.9986978,0.00009612933,0.0002235545,0.0004974496,0.0001916294,0.0002934803],"domain_scores_gemma":[0.9991314,0.0002214659,0.0002842604,0.0002232479,0.00005162047,0.00008797932],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001190357,0.00005715267,0.0004376275,0.00004213714,0.000007443815,0.00008909592,0.00003438449,0.08052136,0.7810716,0.001910258,0.0003029913,0.1354069],"study_design_scores_gemma":[0.0003362061,0.0001147851,0.006237444,0.0000136114,0.00001250432,0.00002744343,0.000001641382,0.9900099,0.002344557,0.0006264597,0.0000856711,0.000189764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.978606,0.00001929386,0.01840441,0.0007690166,0.00136257,0.0002555294,0.000007043275,0.0001425279,0.0004336363],"genre_scores_gemma":[0.9984184,0.00001189382,0.0004422932,0.000603057,0.0001931203,0.000005465688,0.00001334257,0.00002529046,0.0002871743],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9094886,"threshold_uncertainty_score":0.6849464,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2121934186","doi":"10.1162/089976606775093855","title":"Identification of Multiple-Input Systems with Highly Coupled Inputs: Application to EMG Prediction from Multiple Intracortical Electrodes","year":2005,"lang":"en","type":"article","venue":"Neural Computation","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":65,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Neurological Disorders and Stroke; Natural Sciences and Engineering Research Council of Canada; Kavli Institute for Theoretical Physics, University of California, Santa Barbara; National Science Foundation","keywords":"Singular value decomposition; Computer science; Artificial neural network; Set (abstract data type); Algorithm; SIGNAL (programming language); Control theory (sociology); Identification (biology); Pattern recognition (psychology); Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01465204451813484,"gpt":0.2601378575872378,"spread":0.245485813069103,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001471842,0.0001994604,0.0002369613,0.00016729,0.0001287383,0.00013795,0.0002441915,0.00008391231,0.000002128339],"category_scores_gemma":[0.0002101754,0.0001766885,0.00004292691,0.0004239771,0.0000652822,0.0004747925,0.0000423815,0.0001654517,0.0000423895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001017763,"about_ca_system_score_gemma":0.00002544346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001175435,"about_ca_topic_score_gemma":0.0000669635,"domain_scores_codex":[0.9978294,0.0001548801,0.0006747819,0.0006169408,0.0004792086,0.0002448119],"domain_scores_gemma":[0.9985496,0.0005584193,0.0003408151,0.0002523469,0.0001962874,0.0001025398],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001742121,0.0001129662,0.002308802,0.00001952558,0.000006999683,7.794153e-7,0.0003345453,0.2568851,0.7345071,0.00007668298,0.00006063711,0.005512625],"study_design_scores_gemma":[0.0004524953,0.0002056325,0.01072553,0.00002408042,0.00001403026,0.00000791014,0.00001991441,0.6248073,0.3635477,0.00003321045,0.00005648226,0.0001057472],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6174324,0.00001343206,0.3811631,0.000411294,0.0001909293,0.0005743399,0.000036433,0.0001672023,0.00001095415],"genre_scores_gemma":[0.997716,0.000003005969,0.001476321,0.0002644674,0.000307516,0.0001005513,0.00008564817,0.00002593385,0.00002057449],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3802836,"threshold_uncertainty_score":0.7205147,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2124581141","doi":"10.1162/089976603321780281","title":"A Taxonomy for Spatiotemporal Connectionist Networks Revisited: The Unsupervised Case","year":2003,"lang":"en","type":"review","venue":"Neural Computation","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"","keywords":"Connectionism; Computer science; Artificial intelligence; Taxonomy (biology); Generative grammar; Machine learning; Unsupervised learning; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.1191324994956734,"gpt":0.337637395656113,"spread":0.2185048961604396,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003257825,0.0004236258,0.0007422474,0.0000980717,0.0009063574,0.000682549,0.0006678902,0.0001974012,0.000004567708],"category_scores_gemma":[0.00002078027,0.0002988059,0.0004798753,0.0009543702,0.00009841022,0.0002728936,0.0001148302,0.0004271423,0.00001574371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008336203,"about_ca_system_score_gemma":0.0001016445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001498284,"about_ca_topic_score_gemma":0.000008345441,"domain_scores_codex":[0.9976825,0.0003595632,0.0007183427,0.0007175076,0.0001670266,0.000355124],"domain_scores_gemma":[0.9976812,0.0008365851,0.0005733037,0.0006296108,0.0001766196,0.0001026636],"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":[0.000001025698,0.0000189456,3.294692e-7,0.0005072553,0.00002764284,0.00002721772,0.000008694352,0.004620008,1.43283e-8,0.01068986,0.006073328,0.9780257],"study_design_scores_gemma":[0.0001190543,0.0000451802,2.128227e-7,0.0002361086,0.0001078524,0.0009261845,0.000002516814,0.3461179,6.473381e-8,0.0002933497,0.6519227,0.0002288318],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[8.373759e-7,0.4465983,0.5502911,0.0001728411,0.0004118466,0.002318227,0.00001273417,0.0001166997,0.00007741594],"genre_scores_gemma":[0.00129,0.9724234,0.01961723,0.001034929,0.001150652,0.003625802,0.000545504,0.00007993243,0.0002325201],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.9777969,"threshold_uncertainty_score":0.9999464,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2110531579","doi":"10.1162/neco_a_00621","title":"The Competing Benefits of Noise and Heterogeneity in Neural Coding","year":2014,"lang":"en","type":"article","venue":"Neural Computation","topic":"stochastic dynamics and bifurcation","field":"Physics and Astronomy","cited_by":59,"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":"Neural coding; Population; ENCODE; Computer science; Noise (video); Coding (social sciences); Stimulus (psychology); Linearization; Biological system; Neuroscience; Artificial intelligence; Mathematics; Physics; Biology; Psychology; Nonlinear system; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01278733158202136,"gpt":0.2489547129570523,"spread":0.2361673813750309,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001221204,0.00005211797,0.00006930931,0.00001729023,0.00008411107,0.0000295158,0.00004063206,0.000009530059,5.155476e-7],"category_scores_gemma":[0.000008734836,0.00004078258,0.00001773761,0.00006146741,0.0000232166,0.00004381104,0.00002488522,0.0000510641,4.108669e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004678871,"about_ca_system_score_gemma":0.000002877022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006842854,"about_ca_topic_score_gemma":0.00002117194,"domain_scores_codex":[0.9995847,0.00003774792,0.0001433448,0.00008854916,0.00006481956,0.0000808062],"domain_scores_gemma":[0.9996356,0.0001827402,0.00008786285,0.00004397861,0.00003376128,0.00001601246],"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":[0.00002247749,0.00003219716,0.2230622,0.00001343151,0.000007958991,5.073077e-8,0.0003090367,0.2081226,0.002145517,0.02768034,0.000005058304,0.5385991],"study_design_scores_gemma":[0.0001725151,0.00002193417,0.2354289,0.000008438984,0.000002140128,3.156411e-7,0.00003884229,0.7633022,0.0001299419,0.0008588393,0.000003174547,0.00003274408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9800314,0.00001950131,0.01946023,0.000108346,0.00009194858,0.00007622666,0.00000226889,0.000005528083,0.0002045859],"genre_scores_gemma":[0.9997382,6.019719e-7,0.0001540471,0.00001446008,0.00007177496,0.000002833764,0.00001309226,0.000003826128,0.000001229141],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5551795,"threshold_uncertainty_score":0.1663065,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2771330107","doi":"10.1162/neco_a_01111","title":"An Empirical Evaluation of Rule Extraction from Recurrent Neural Networks","year":2018,"lang":"en","type":"article","venue":"Neural Computation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Recurrent neural network; Computer science; Artificial intelligence; Black box; Machine learning; Artificial neural network; Rule-based machine translation","retraction":null,"screen_n_in":null,"score":{"opus":0.05760352501565048,"gpt":0.4038145947743336,"spread":0.3462110697586831,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004972932,0.0001277871,0.0001347835,0.0001098494,0.0001115077,0.0001300365,0.0003999668,0.00009287206,0.00001514609],"category_scores_gemma":[0.00007342139,0.0001174202,0.00004325244,0.000387095,0.00005482517,0.001113339,0.0000722659,0.0001869937,0.000004384508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007659342,"about_ca_system_score_gemma":0.00003443721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005908854,"about_ca_topic_score_gemma":0.00001375796,"domain_scores_codex":[0.9981959,0.0003678486,0.0002958047,0.0003838306,0.0005942116,0.0001624277],"domain_scores_gemma":[0.9986442,0.00009560632,0.000248567,0.0002814967,0.0006694161,0.00006070178],"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":[0.00002634612,0.00008299962,0.0008987187,0.000004333192,0.000005316977,0.000001488805,0.0004895927,0.01008575,0.006583991,0.0001639364,0.0002855527,0.981372],"study_design_scores_gemma":[0.0002126826,0.0002688811,0.00874653,0.00001470973,0.00001772279,0.000006723925,0.000008249859,0.9693531,0.008847818,0.01239558,0.000009191734,0.0001187694],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4513662,0.0002271155,0.547312,0.0001520045,0.0005366175,0.000133768,0.000001155593,0.0002430396,0.00002816072],"genre_scores_gemma":[0.8731139,0.000001169533,0.1263552,0.0001485498,0.0003118059,0.000008678036,0.00005162516,0.000008109295,0.000001001161],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9812532,"threshold_uncertainty_score":0.4788255,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2155217764","doi":"10.1162/neco_a_00682","title":"Efficient Training of Convolutional Deep Belief Networks in the Frequency Domain for Application to High-Resolution 2D and 3D Images","year":2014,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"National Institute of Mental Health; National Institute on Aging; National Center for Research Resources; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Benchmark (surveying); Deep learning; Artificial intelligence; Convolutional neural network; Domain (mathematical analysis); Image (mathematics); Frequency domain; Deep belief network; Training (meteorology); Pattern recognition (psychology); Voxel; Machine learning; Algorithm; Computer vision; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01236193869424194,"gpt":0.2370243755422255,"spread":0.2246624368479836,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006058703,0.00009596664,0.0001301388,0.0000758681,0.0001453519,0.00005737927,0.0002005168,0.00003771528,4.409369e-7],"category_scores_gemma":[0.00005303251,0.00007796897,0.00003026255,0.0002572239,0.00004499739,0.0001031713,0.00004169375,0.00006485038,7.367104e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002503219,"about_ca_system_score_gemma":0.00001207077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005549143,"about_ca_topic_score_gemma":0.00003073336,"domain_scores_codex":[0.9989644,0.0001973532,0.0002369997,0.0002661681,0.0001620818,0.0001729781],"domain_scores_gemma":[0.9992149,0.0004125355,0.0001125246,0.000127047,0.00009991148,0.00003307468],"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":[0.000009070637,0.00002073463,0.0000684113,0.000005251755,0.000002534865,1.117035e-7,0.0007218,0.9137423,0.001465664,0.01878866,0.00003345874,0.06514198],"study_design_scores_gemma":[0.0003183762,0.0001361835,0.02277795,0.000009063281,0.000004648416,0.000002366899,0.00005341903,0.9684321,0.00006177415,0.00809984,0.0000244792,0.00007978721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08872653,0.00006233593,0.9095817,0.0009843853,0.0001340836,0.0004444774,0.00000236383,0.00001907642,0.00004510478],"genre_scores_gemma":[0.8169749,9.397734e-7,0.1825908,0.0002450471,0.0001156025,0.00005441031,0.0000136402,0.000003999767,6.225815e-7],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7282484,"threshold_uncertainty_score":0.3179482,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1745681373","doi":"10.1162/neco_a_00848","title":"An Infinite Restricted Boltzmann Machine","year":2016,"lang":"en","type":"article","venue":"Neural Computation","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Restricted Boltzmann machine; Boltzmann machine; Limit (mathematics); Computer science; Boltzmann constant; Function (biology); Artificial intelligence; Layer (electronics); Energy (signal processing); Artificial neural network; Algorithm; Mathematics; Pattern recognition (psychology); Statistics; Physics; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.01818591154454845,"gpt":0.2571290816638627,"spread":0.2389431701193143,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008361066,0.0001094121,0.000099704,0.00008616302,0.000119063,0.0001294465,0.0003268115,0.00003499454,0.00001212695],"category_scores_gemma":[0.00004053107,0.00007312746,0.00003628353,0.0002914554,0.0000252675,0.0009971514,0.00006426146,0.00005250063,0.00004894513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000206296,"about_ca_system_score_gemma":0.00001743998,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002615506,"about_ca_topic_score_gemma":0.000008714865,"domain_scores_codex":[0.9990104,0.0001704725,0.000169334,0.0002969186,0.0001731458,0.000179687],"domain_scores_gemma":[0.9993573,0.0001312798,0.00007943513,0.0002432382,0.0001052583,0.00008343363],"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":[0.00002086107,0.00006158285,0.001044643,0.000002756756,0.00001121872,0.00001630219,0.0001632953,0.03126356,0.04507947,0.002704801,0.001405277,0.9182262],"study_design_scores_gemma":[0.0003840645,0.0001991231,0.0283115,0.000007986897,0.000003532677,0.000006532239,0.000002215765,0.9647788,0.002908396,0.002376749,0.0008730153,0.000148108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05938553,0.00002893535,0.9380362,0.00159159,0.0003618778,0.00008962744,0.00000296286,0.0001952941,0.0003079524],"genre_scores_gemma":[0.97346,0.000006292763,0.02595002,0.0003592327,0.0001484608,0.000004021909,0.000007462455,0.00000732095,0.0000572197],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9335152,"threshold_uncertainty_score":0.2982051,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2136451213","doi":"10.1162/089976601300014538","title":"Spatiotemporal Connectionist Networks: A Taxonomy and Review","year":2001,"lang":"en","type":"article","venue":"Neural Computation","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"","keywords":"Connectionism; Computer science; Artificial intelligence; Machine learning; Artificial neural network; Cognitive science; Theoretical computer science; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.03482928896846001,"gpt":0.2654551433796236,"spread":0.2306258544111636,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009912012,0.000102097,0.000124287,0.00003094927,0.000217857,0.0001547555,0.0001649899,0.00002691126,0.000006005037],"category_scores_gemma":[0.000007992533,0.00009597149,0.00003367901,0.0004040226,0.00005320847,0.0003698172,0.00007289257,0.0001005515,0.00001160792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001657059,"about_ca_system_score_gemma":0.00001131739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001716137,"about_ca_topic_score_gemma":0.000007900065,"domain_scores_codex":[0.9992106,0.00005324014,0.0002019031,0.0002825139,0.000103008,0.0001487595],"domain_scores_gemma":[0.9995209,0.00007137041,0.000104851,0.0001667021,0.00006337004,0.00007279924],"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":[0.000005554458,0.00005080326,0.002153213,0.00007287966,0.00001064033,0.00001688746,0.00002189074,0.02414276,0.00002926798,0.03463404,0.01944063,0.9194214],"study_design_scores_gemma":[0.0001552581,0.00005210768,0.003129812,0.00007236036,0.000007025018,0.0001118016,0.000001772307,0.9590458,0.000005697661,0.001270209,0.03601256,0.000135605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006640046,0.002796677,0.9828417,0.006203496,0.0001917284,0.0004635508,4.275092e-7,0.0001961307,0.0006662037],"genre_scores_gemma":[0.9878587,0.001489967,0.007438784,0.002897982,0.0001436682,0.00008376168,0.00001537142,0.000005375844,0.00006644797],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9812186,"threshold_uncertainty_score":0.3913604,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2346181499","doi":"10.1162/neco_a_00837","title":"Robust Support Vector Machines for Classification with Nonconvex and Smooth Losses","year":2016,"lang":"en","type":"article","venue":"Neural Computation","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Support vector machine; Artificial intelligence; Computer science; Pattern recognition (psychology); Mathematics; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.04856399756352703,"gpt":0.2679607977473139,"spread":0.2193968001837869,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000729975,0.00009253714,0.00008574767,0.00006095516,0.0001033799,0.00009719944,0.0001086362,0.00003466913,0.000006880278],"category_scores_gemma":[0.00001985928,0.00005578722,0.00001975837,0.00009750871,0.000033087,0.0006211509,0.00002733466,0.00002989093,0.00001328792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001425074,"about_ca_system_score_gemma":0.00002284963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005331274,"about_ca_topic_score_gemma":0.000007388686,"domain_scores_codex":[0.999322,0.00002935291,0.0001263148,0.0002725874,0.0001259143,0.0001238494],"domain_scores_gemma":[0.9994765,0.0001590828,0.00008937675,0.0001044562,0.0001197979,0.00005077577],"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":[0.000113291,0.00006130127,0.004725739,0.00006328831,0.00001189041,0.000003984973,0.000288328,0.0004256499,0.03586271,0.002749597,0.003492335,0.9522019],"study_design_scores_gemma":[0.001678257,0.0008877683,0.1030113,0.00009296076,0.00001746232,0.00003952078,0.00003128743,0.8776581,0.01016847,0.004812403,0.001247449,0.0003550788],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2262742,0.000009583407,0.7702999,0.002823426,0.000145401,0.0002063817,0.000006192184,0.0001071095,0.0001278401],"genre_scores_gemma":[0.9734513,0.000004670324,0.02609749,0.0002325988,0.00005736307,0.00003496639,0.00002310363,0.000007710202,0.00009079294],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9518468,"threshold_uncertainty_score":0.2274937,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2751304263","doi":"10.1162/neco_a_01060","title":"Dynamic Neural Turing Machine with Continuous and Discrete Addressing Schemes","year":2018,"lang":"en","type":"article","venue":"Neural Computation","topic":"Ferroelectric and Negative Capacitance Devices","field":"Engineering","cited_by":53,"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":"Computer science; Turing machine; Inference; Artificial intelligence; Content-addressable memory; MNIST database; Artificial neural network; Universal Turing machine; Task (project management); Associative property; Variety (cybernetics); Machine learning; Theoretical computer science; Algorithm; Mathematics; Computation","retraction":null,"screen_n_in":null,"score":{"opus":0.01104784210939332,"gpt":0.2418781388662677,"spread":0.2308302967568744,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00002920777,0.000127848,0.0001226829,0.00005596661,0.0001013479,0.00006485092,0.00004228759,0.00002703988,0.00000476906],"category_scores_gemma":[0.000008108854,0.0001042171,0.00001404295,0.0001393475,0.00007817065,0.0002536799,0.00001070787,0.0001209818,0.000003082901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002163555,"about_ca_system_score_gemma":0.000002760399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005282632,"about_ca_topic_score_gemma":0.00002833202,"domain_scores_codex":[0.9994676,0.0000182921,0.0001062334,0.0001456889,0.0000953476,0.0001668829],"domain_scores_gemma":[0.9997884,0.00004174508,0.00003266857,0.00004991484,0.00004752571,0.00003975076],"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":[0.0005268041,0.00004385266,0.02688196,0.0007629378,0.0002684361,0.0001105837,0.005315908,0.1113173,0.1145824,0.0003868001,0.000444208,0.7393588],"study_design_scores_gemma":[0.0003149733,0.0001535685,0.01695947,0.00004302515,0.00001173235,0.0000305701,0.00004892433,0.9793559,0.002829264,0.00007082003,0.00004052426,0.0001412554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9733269,0.0006792494,0.02507374,0.00005853159,0.0001208634,0.00009776636,0.00000328704,0.00022614,0.0004134971],"genre_scores_gemma":[0.9981118,0.00000914192,0.001715285,0.00005400212,0.00005322216,0.00000400611,0.00001394253,0.00002233486,0.00001629137],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8680385,"threshold_uncertainty_score":0.4249852,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4281818052","doi":"10.1162/neco_a_01514","title":"A Predictive Processing Model of Episodic Memory and Time Perception","year":2022,"lang":"en","type":"article","venue":"Neural Computation","topic":"Neuroscience and Music Perception","field":"Neuroscience","cited_by":52,"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","funders":"","keywords":"Episodic memory; Recall; Perception; Time perception; Cognitive psychology; Psychology; Cognition; Stimulus (psychology); Coding (social sciences); Reconstructive memory; Computational model; Explicit memory; Computer science; Artificial intelligence; Neuroscience","retraction":null,"screen_n_in":null,"score":{"opus":0.04212040777207077,"gpt":0.2814382000052872,"spread":0.2393177922332165,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000122246,0.00007558824,0.0000904925,0.0001116018,0.0003448475,0.00002480892,0.00008606517,0.00001562591,0.00003014057],"category_scores_gemma":[0.0000443328,0.00007795007,0.00002453208,0.000247183,0.0001135963,0.0003697921,0.00009621497,0.0001251922,0.000003928415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004115581,"about_ca_system_score_gemma":0.00003394754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004560655,"about_ca_topic_score_gemma":1.709588e-7,"domain_scores_codex":[0.9989551,0.0001285694,0.0001515976,0.0003092433,0.0003356031,0.000119928],"domain_scores_gemma":[0.9997337,0.00003847913,0.0001083286,0.00005894423,0.00002615071,0.00003436446],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003294433,0.00003083518,0.00001249644,0.00001026192,1.429592e-7,0.000001057378,0.001252081,0.1425775,0.8251522,0.00001380601,0.000049024,0.03086758],"study_design_scores_gemma":[0.0002077378,0.0002452269,0.002004324,0.000004191998,0.000006182606,0.00003472656,0.0001766465,0.9899791,0.006428186,0.0008398424,0.000004496911,0.00006930919],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9916749,0.000003503902,0.007284221,0.0001474357,0.0000892336,0.0002109152,0.00001430718,0.00006888638,0.000506616],"genre_scores_gemma":[0.9990035,0.00000302464,0.0001742472,0.0006189718,0.00002110069,0.00002222194,0.000005390237,0.000008411938,0.0001431455],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8474016,"threshold_uncertainty_score":0.3178712,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2109302401","doi":"10.1162/neco.2008.04-07-507","title":"Sensitivity Derivatives for Flexible Sensorimotor Learning","year":2008,"lang":"en","type":"article","venue":"Neural Computation","topic":"Motor Control and Adaptation","field":"Neuroscience","cited_by":49,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University; York University; University of Toronto","funders":"","keywords":"Sensitivity (control systems); Computer science; Psychology; Artificial intelligence; Machine learning; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.07841326198561792,"gpt":0.2942664919996806,"spread":0.2158532300140627,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008461344,0.0000945806,0.0001089382,0.00005553977,0.0003917106,0.00002688626,0.00003150074,0.00002972384,0.000003892228],"category_scores_gemma":[0.0005339876,0.00009174167,0.00005546786,0.0001295961,0.0000462809,0.0002478855,0.00001247913,0.00009355461,0.00001755792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001937364,"about_ca_system_score_gemma":0.00001687271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001121558,"about_ca_topic_score_gemma":0.000001181622,"domain_scores_codex":[0.999114,0.0001782723,0.0001349998,0.000253456,0.0001561296,0.0001631494],"domain_scores_gemma":[0.9991344,0.0006182638,0.00009338241,0.00004581236,0.00006714401,0.00004102492],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001061792,0.00003199333,0.0005531108,0.00001425438,0.000002040743,0.0000177619,0.0005054532,0.0926821,0.8900979,0.0005397867,0.00006493491,0.0153845],"study_design_scores_gemma":[0.0006792595,0.0001885872,0.03516462,0.000004855397,0.00000422906,0.00005558047,0.00002754348,0.8841191,0.07840659,0.0004187448,0.0007943174,0.0001365945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7976819,0.000004703322,0.2011372,0.0002501314,0.0001831751,0.0002847479,0.000003612172,0.000210793,0.0002437094],"genre_scores_gemma":[0.9975075,0.000003119294,0.001548253,0.0003422475,0.0001463937,0.0000167579,0.00001013887,0.00001288907,0.0004127003],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8116913,"threshold_uncertainty_score":0.3741117,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}