{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":127,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":127,"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","author_layer_release":"2026-06-26"},"query_hash":"a4b9ff0d8edb","filters":{"venue":"International Conference on Machine Learning"}},"results":[{"id":"W1665214252","doi":"","title":"Rectified Linear Units Improve Restricted Boltzmann Machines","year":2010,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":13244,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Boltzmann machine; Binary number; Sigmoid function; Computer science; Object (grammar); Restricted Boltzmann machine; Artificial intelligence; Inference; Pattern recognition (psychology); Feature (linguistics); Cognitive neuroscience of visual object recognition; Algorithm; Mathematics; Computer vision; Deep learning; Arithmetic; Artificial neural network","authors":[{"name":"Vinod Nair","is_ca":true},{"name":"Geoffrey E. Hinton","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03053323629475789,"gpt":0.2802265611432088,"spread":0.2496933248484509,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001184574,0.001141091,0.001535658,0.0004816662,0.0002770543,0.0008527474,0.002686423,0.001523975,0.006606211],"category_scores_gemma":[0.004999585,0.0008760685,0.001140939,0.0005322052,0.0008452683,0.002484872,0.001955863,0.002776678,0.002912994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007434928,"about_ca_system_score_gemma":0.0006569138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002203554,"about_ca_topic_score_gemma":0.002299702,"domain_scores_codex":[0.9992726,0.0001938437,0.00004524475,0.0002033851,0.0001938301,0.00009104572],"domain_scores_gemma":[0.9986261,0.0006573098,0.0001297861,0.0003000131,0.0002298637,0.00005700101],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001484445,0.00007989147,0.000368219,0.0001387986,0.0001353515,0.00006003154,0.00005816192,0.8029372,0.005183906,0.04040131,0.003779845,0.1467089],"study_design_scores_gemma":[0.00001013054,0.0000253549,0.00004659127,0.000007128492,0.000009051601,0.00001390948,0.000002821071,0.9856435,0.001231187,0.0121743,0.0008282075,0.000007768767],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01737024,0.0009450199,0.9741785,0.0003110991,0.0001872178,0.00005561122,0.000112605,0.002443991,0.004395715],"genre_scores_gemma":[0.6282246,0.001042611,0.3439321,0.000694205,0.0002638404,0.0002915338,0.0006990057,0.0008741973,0.02397791],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006606211,"threshold_uncertainty_score":0.02210003,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964212410","doi":"","title":"On calibration of modern neural networks","year":2017,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":1185,"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":"Normalization (sociology); Computer science; Artificial neural network; Correctness; Calibration; Scaling; Deep neural networks; Artificial intelligence; Machine learning; Simple (philosophy); Deep learning; Pattern recognition (psychology); Data mining; Algorithm; Mathematics; Statistics","authors":[{"name":"Chuan Guo","is_ca":true},{"name":"Geoff Pleiss","is_ca":false},{"name":"Yu Sun","is_ca":false},{"name":"Kilian Q. Weinberger","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03526583321291214,"gpt":0.3120534779422832,"spread":0.276787644729371,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009801947,0.001546925,0.001199588,0.001528918,0.001077212,0.002423774,0.003124629,0.002455019,0.002555721],"category_scores_gemma":[0.06634749,0.0009977521,0.0008241342,0.001382558,0.003131785,0.005964175,0.003758067,0.006323694,0.000991137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002778928,"about_ca_system_score_gemma":0.001476236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004311454,"about_ca_topic_score_gemma":0.002731197,"domain_scores_codex":[0.9953661,0.001680136,0.0002116157,0.001100247,0.001346593,0.000295352],"domain_scores_gemma":[0.9818045,0.008971954,0.001533997,0.004284243,0.003115315,0.0002900253],"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":[0.0002700766,0.00007259173,0.005111555,0.0001335753,0.000153817,0.00009772449,0.0002767117,0.7474628,0.004691308,0.04942009,0.003786335,0.1885234],"study_design_scores_gemma":[0.00001227953,0.00004498034,0.0008077416,0.00005483561,0.00001593263,0.0000555208,0.0000295814,0.946363,0.003522083,0.04742347,0.001645011,0.00002551934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0658917,0.002767731,0.9193286,0.002571022,0.0003057382,0.00006882412,0.0001854233,0.003188278,0.005692649],"genre_scores_gemma":[0.8029591,0.001706725,0.1886463,0.001376895,0.0003968954,0.0001998146,0.0005353052,0.0007356327,0.003443481],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009801947,"threshold_uncertainty_score":0.05183822,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2803832867","doi":"","title":"Mutual Information Neural Estimation.","year":2018,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":598,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Mutual information; Estimation; Artificial intelligence; Artificial neural network; Engineering","authors":[{"name":"Mohamed Ishmael Belghazi","is_ca":false},{"name":"Aristide Baratin","is_ca":true},{"name":"Sai Rajeshwar","is_ca":false},{"name":"Sherjil Ozair","is_ca":false},{"name":"Yoshua Bengio","is_ca":true},{"name":"Aaron Courville","is_ca":true},{"name":"Devon Hjelm","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02579097961051308,"gpt":0.2971756273448126,"spread":0.2713846477342995,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002853093,0.001173356,0.001638982,0.001488835,0.0007057922,0.001796218,0.001943653,0.001806656,0.006903655],"category_scores_gemma":[0.01396168,0.0008708992,0.000891554,0.001578802,0.001285211,0.002989538,0.002534061,0.001994494,0.00322382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007526306,"about_ca_system_score_gemma":0.001142753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00256935,"about_ca_topic_score_gemma":0.003865763,"domain_scores_codex":[0.9981332,0.0008509242,0.0001128263,0.0003172795,0.000476372,0.0001093659],"domain_scores_gemma":[0.9959358,0.002117713,0.0003694613,0.0007873261,0.0006920518,0.00009759443],"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":[0.000375938,0.0001420312,0.001844957,0.0006091339,0.0004180733,0.0001479242,0.0001701281,0.2046195,0.004568189,0.1724112,0.04352654,0.5711664],"study_design_scores_gemma":[0.00002085194,0.00005192569,0.001007537,0.00006903261,0.0000702207,0.0001174847,0.00002640692,0.8873065,0.004953613,0.09313168,0.01320304,0.00004169054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005063836,0.004080605,0.9767104,0.0008660764,0.0003775635,0.00006725858,0.000405856,0.00104918,0.01137926],"genre_scores_gemma":[0.3953602,0.003682015,0.5551668,0.0006695456,0.001169819,0.0004445442,0.002755533,0.0009943934,0.03975717],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006903655,"threshold_uncertainty_score":0.02309501,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963371670","doi":"","title":"Learning to Reweight Examples for Robust Deep Learning","year":2018,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":418,"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":"Hyperparameter; Overfitting; Computer science; Artificial intelligence; Machine learning; Regularization (linguistics); Deep learning; Gradient descent; Artificial neural network; Set (abstract data type); Deep neural networks; Supervised learning","authors":[{"name":"Mengye Ren","is_ca":true},{"name":"Wenyuan Zeng","is_ca":true},{"name":"Bin Yang","is_ca":false},{"name":"Raquel Urtasun","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06198251208780124,"gpt":0.3196849676050122,"spread":0.257702455517211,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003014941,0.001648032,0.001435648,0.0009686974,0.0004882924,0.0009747415,0.002878403,0.001764908,0.002397225],"category_scores_gemma":[0.01215782,0.001018628,0.0007445737,0.000812158,0.001190686,0.002409206,0.002192374,0.002521112,0.001623657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007359701,"about_ca_system_score_gemma":0.0009697113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00128318,"about_ca_topic_score_gemma":0.002356709,"domain_scores_codex":[0.9986085,0.0003745376,0.0001005571,0.0004126229,0.0004045675,0.00009927544],"domain_scores_gemma":[0.9973658,0.0007671358,0.0003576148,0.0008569427,0.000574527,0.00007801061],"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":[0.000387677,0.0001780349,0.001764616,0.0002018033,0.0001400272,0.0001054679,0.0001410884,0.4014745,0.029572,0.01451483,0.007002268,0.5445177],"study_design_scores_gemma":[0.0000213669,0.00005419519,0.0001696784,0.00002024808,0.00001407779,0.00004607942,0.00001236142,0.9790543,0.009618066,0.009448349,0.001530014,0.00001121626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01268174,0.000233727,0.9844466,0.0001227315,0.00004572638,0.00005527987,0.00004582364,0.001794783,0.0005737263],"genre_scores_gemma":[0.2854782,0.0002370739,0.7093232,0.0003492083,0.0000828271,0.0002777519,0.0004043261,0.0006217023,0.003225652],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003014941,"threshold_uncertainty_score":0.01594472,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963540976","doi":"","title":"Invertible Residual Networks","year":2019,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":193,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Invertible matrix; Jacobian matrix and determinant; Normalization (sociology); Residual; Computer science; Generative grammar; Block (permutation group theory); Algorithm; Simple (philosophy); Theoretical computer science; Artificial intelligence; Mathematics; Applied mathematics","authors":[{"name":"Jens Behrmann","is_ca":false},{"name":"Will Grathwohl","is_ca":false},{"name":"Ricky T. Q. Chen","is_ca":true},{"name":"David Duvenaud","is_ca":true},{"name":"Joern-Henrik Jacobsen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02215808535166284,"gpt":0.2573328756627397,"spread":0.2351747903110769,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006954714,0.001011349,0.0005174182,0.0004631275,0.0002779318,0.0008757652,0.001268173,0.0008748615,0.008725392],"category_scores_gemma":[0.003138865,0.0003532617,0.0006737569,0.000267351,0.0009797352,0.001475714,0.001660582,0.001324299,0.00238925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005155413,"about_ca_system_score_gemma":0.0005916957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00218996,"about_ca_topic_score_gemma":0.003755499,"domain_scores_codex":[0.9995162,0.00008652104,0.00001932177,0.0001382395,0.0001665043,0.00007324725],"domain_scores_gemma":[0.9992971,0.0002957573,0.00008635526,0.0001563971,0.0001212616,0.00004310266],"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":[0.0001177679,0.00007447712,0.0007567519,0.0001345396,0.00006261921,0.0003281666,0.0001385172,0.6356168,0.01361844,0.1894634,0.007184343,0.1525041],"study_design_scores_gemma":[0.00000739364,0.00003792964,0.0001018825,0.00001280038,0.00001096794,0.00009282528,0.000009670975,0.9460414,0.003425833,0.04632395,0.003926136,0.000009188696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01779944,0.0002435723,0.9654163,0.0003232396,0.0001089469,0.00004788636,0.0002301366,0.001619129,0.01421137],"genre_scores_gemma":[0.7175115,0.0005490666,0.2522803,0.0005852358,0.0001778739,0.0002000624,0.001085174,0.0006870618,0.02692368],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008725392,"threshold_uncertainty_score":0.02918941,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W13294968","doi":"10.1016/0021-8707(56)90033-8","title":"Toward Off-Policy Learning Control with Function Approximation","year":2010,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":175,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Temporal difference learning; Function approximation; Approximation algorithm; Function (biology); Computer science; Linear approximation; Bellman equation; Optimal control; Extension (predicate logic); Mathematical optimization; Control (management); Artificial intelligence; Mathematics; Reinforcement learning; Artificial neural network; Nonlinear system","authors":[{"name":"Hamid Reza Maei","is_ca":true},{"name":"Csaba Szepesv ri","is_ca":true},{"name":"Shalabh Bhatnagar","is_ca":false},{"name":"Richard Sutton","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02266731972468504,"gpt":0.2706007747695721,"spread":0.247933455044887,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002936141,0.001629104,0.001860193,0.000838263,0.0005538244,0.00166337,0.002049875,0.001860138,0.003300941],"category_scores_gemma":[0.008435267,0.0007002832,0.0009506204,0.0006141168,0.002189066,0.001531674,0.002789471,0.003554289,0.0007983472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002037738,"about_ca_system_score_gemma":0.002279104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00585327,"about_ca_topic_score_gemma":0.002625465,"domain_scores_codex":[0.9987147,0.0003347325,0.00006135148,0.0002539192,0.0004526936,0.000182676],"domain_scores_gemma":[0.9964526,0.002346283,0.0002544181,0.0002799712,0.0005250287,0.0001417132],"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":[0.0001153535,0.0001036054,0.0004194267,0.00009093137,0.00003236252,0.00005908406,0.0001201643,0.8669133,0.001411857,0.05506869,0.001403967,0.07426123],"study_design_scores_gemma":[0.000007179633,0.00001931516,0.00001368817,0.000006413277,0.000001903528,0.000005895445,0.000002909148,0.991289,0.0002004786,0.008099364,0.0003509354,0.000002805635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003765274,0.0001377512,0.9931476,0.0001473179,0.00003939305,0.0000352694,0.00001391504,0.0003708324,0.002342661],"genre_scores_gemma":[0.6216077,0.0003366968,0.3683889,0.0007247206,0.0001374821,0.0004586868,0.0001837131,0.0004023894,0.007759728],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00585327,"threshold_uncertainty_score":0.01552796,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2186489521","doi":"","title":"Unsupervised and Transfer Learning Challenge: a Deep Learning Approach","year":2011,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":147,"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":"Transfer of learning; Artificial intelligence; Computer science; Unsupervised learning; Machine learning; Deep learning; Classifier (UML); Competitive learning; Semi-supervised learning; Task (project management)","authors":[{"name":"Grégoire Mesnil","is_ca":true},{"name":"Yann Dauphin","is_ca":true},{"name":"Xavier Glorot","is_ca":true},{"name":"Salah Rifai","is_ca":true},{"name":"Yoshua Bengio","is_ca":true},{"name":"Ian Goodfellow","is_ca":true},{"name":"Erick Lavoie","is_ca":true},{"name":"Xavier Muller","is_ca":true},{"name":"Guillaume Desjardins","is_ca":true},{"name":"David Warde-Farley","is_ca":true},{"name":"Pascal Vincent","is_ca":true},{"name":"Aaron Courville","is_ca":true},{"name":"James Bergstra","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0682199232260771,"gpt":0.275857866333464,"spread":0.2076379431073869,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007351813,0.00160286,0.00192075,0.001036175,0.001229522,0.002454197,0.004127303,0.005211365,0.001892246],"category_scores_gemma":[0.0162389,0.0006088496,0.001348186,0.001564818,0.002716885,0.005175709,0.004565401,0.007827694,0.0007030549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001883187,"about_ca_system_score_gemma":0.002376356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003113645,"about_ca_topic_score_gemma":0.003404893,"domain_scores_codex":[0.9960707,0.001607553,0.00016949,0.0009456675,0.0009667077,0.000239973],"domain_scores_gemma":[0.9908798,0.005359355,0.0003098494,0.001718011,0.001252474,0.0004805777],"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":[0.0004813469,0.000752744,0.00472146,0.0007123381,0.0003831723,0.0004372807,0.0006209317,0.1661556,0.006940723,0.1606938,0.08485372,0.5732468],"study_design_scores_gemma":[0.00005247274,0.0001347994,0.001160666,0.00005648631,0.00002474236,0.0001672135,0.000169355,0.6961474,0.004327734,0.281808,0.01590117,0.00004997128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0216308,0.002083413,0.9548503,0.01397996,0.0004703874,0.0002225573,0.001023204,0.001042022,0.004697385],"genre_scores_gemma":[0.4195784,0.002147623,0.5539837,0.004117147,0.001801099,0.0009587276,0.00383928,0.0004700864,0.0131039],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007351813,"threshold_uncertainty_score":0.03888059,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2804948070","doi":"","title":"Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":129,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Task (project management); Decomposition; Artificial intelligence; Human–computer interaction; Engineering","authors":[{"name":"Rodrigo Toro Icarte","is_ca":true},{"name":"Toryn Q. Klassen","is_ca":true},{"name":"Richard Valenzano","is_ca":true},{"name":"Sheila A. McIlraith","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09333430035172953,"gpt":0.3548435333796292,"spread":0.2615092330278997,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002548145,0.001008833,0.00138035,0.0004851958,0.0005417572,0.001418746,0.001537703,0.001567223,0.00428763],"category_scores_gemma":[0.009726472,0.0008914248,0.0008940281,0.000450998,0.001341304,0.002187766,0.002053584,0.003628187,0.0008703198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001063457,"about_ca_system_score_gemma":0.001747118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002853697,"about_ca_topic_score_gemma":0.004632657,"domain_scores_codex":[0.9986793,0.0005568902,0.00009434766,0.0002207119,0.0002696562,0.0001791415],"domain_scores_gemma":[0.995841,0.002909778,0.0002672012,0.0004107089,0.0003769085,0.0001944149],"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":[0.000208343,0.0001549061,0.0006406398,0.0001236745,0.00004840447,0.00008591618,0.0001444381,0.8396086,0.005107183,0.03582956,0.001282078,0.1167662],"study_design_scores_gemma":[0.000008479065,0.00001578575,0.00003292048,0.000005340651,0.000003193726,0.000004263457,0.000003306382,0.987394,0.00072068,0.01164228,0.0001653805,0.000004351424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004756275,0.00004125893,0.9940925,0.00006205506,0.00001619092,0.00003077303,0.00001706711,0.0005299415,0.0004539775],"genre_scores_gemma":[0.5462818,0.00009231898,0.4505089,0.0001492713,0.0000331814,0.0003952037,0.0001223788,0.0002844098,0.002132419],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00428763,"threshold_uncertainty_score":0.01434356,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2740643007","doi":"","title":"Deep Spectral Clustering Learning.","year":2017,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Cluster analysis; Artificial intelligence; Computer science; Deep learning; Pattern recognition (psychology)","authors":[{"name":"Marc T. Law","is_ca":true},{"name":"Raquel Urtasun","is_ca":true},{"name":"Richard S. Zemel","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0414787561868741,"gpt":0.3124472869121453,"spread":0.2709685307252712,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009822854,0.001139081,0.001359161,0.001390676,0.0008927734,0.00150147,0.002346037,0.001702156,0.01074804],"category_scores_gemma":[0.002631073,0.0008136243,0.001003172,0.001518909,0.0007741444,0.001733974,0.001730984,0.002022675,0.007750046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001053142,"about_ca_system_score_gemma":0.001339287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008069969,"about_ca_topic_score_gemma":0.01919611,"domain_scores_codex":[0.9993902,0.0001371993,0.00003035471,0.0001814435,0.0001780087,0.00008271039],"domain_scores_gemma":[0.999007,0.0001812335,0.00006341698,0.0003182437,0.0003471696,0.00008291628],"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":[0.0002626499,0.000284044,0.001340611,0.0002741366,0.0002711582,0.00008009445,0.000107664,0.1225209,0.008534096,0.05087933,0.1105718,0.7048736],"study_design_scores_gemma":[0.00001652234,0.00002281318,0.0004783623,0.00002892787,0.00002835543,0.00004686031,0.00003817496,0.9402713,0.005417664,0.03972927,0.01390313,0.00001856474],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01632406,0.00352967,0.9545465,0.001143522,0.0005354834,0.00009191301,0.001368885,0.007527291,0.01493268],"genre_scores_gemma":[0.3050648,0.001871653,0.6290821,0.0009107671,0.000276931,0.0002107789,0.007227057,0.001832726,0.05352336],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01074804,"threshold_uncertainty_score":0.03595585,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3081963674","doi":"","title":"Contrastive Multi-View Representation Learning on Graphs","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Graph; Artificial intelligence; Node (physics); Binary classification; Theoretical computer science; Representation (politics); Machine learning; Binary number; Feature learning; Mathematics; Support vector machine","authors":[{"name":"Kaveh Hassani","is_ca":false},{"name":"Amir Hosein Khasahmadi","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0770792012378027,"gpt":0.3372805158083014,"spread":0.2602013145704987,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001142645,0.001279969,0.001102643,0.001629958,0.000352859,0.001611134,0.002518876,0.001502643,0.003123219],"category_scores_gemma":[0.006365045,0.0004369662,0.001246252,0.001265807,0.0008276078,0.003279524,0.001965184,0.002514923,0.001486499],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001014694,"about_ca_system_score_gemma":0.0005174544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002752634,"about_ca_topic_score_gemma":0.004921378,"domain_scores_codex":[0.9988772,0.0003468313,0.00003554697,0.0003797416,0.0002548179,0.0001057735],"domain_scores_gemma":[0.9975769,0.0008449022,0.0002306232,0.0008775051,0.0003459259,0.0001242287],"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":[0.0004662553,0.0003563127,0.003097111,0.000342159,0.0002400516,0.0001915772,0.0002176593,0.287541,0.02889353,0.0281108,0.02353951,0.627004],"study_design_scores_gemma":[0.00001412125,0.00005501034,0.000298506,0.00001386461,0.0000128103,0.00005576138,0.00002238274,0.9739699,0.005123452,0.01899786,0.001426465,0.000009823676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03319697,0.0005716514,0.9557092,0.0003706531,0.00009427837,0.00008926037,0.0008015324,0.006400766,0.002765846],"genre_scores_gemma":[0.5703318,0.0004023157,0.4186577,0.0005371282,0.0001547462,0.0001834826,0.00494349,0.0007529247,0.004036416],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003123219,"threshold_uncertainty_score":0.01044822,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3034607397","doi":"","title":"An Optimistic Perspective on Offline Deep Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Google (Canada); University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Perspective (graphical); Artificial intelligence; Reinforcement; Machine learning; Psychology; Social psychology","authors":[{"name":"Rishabh Agarwal","is_ca":false},{"name":"Dale Schuurmans","is_ca":true},{"name":"Mohammad Norouzi","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04466082375581626,"gpt":0.3204855486435333,"spread":0.275824724887717,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003584604,0.001083382,0.0009143619,0.0005724762,0.0008744919,0.003424035,0.001850317,0.003165564,0.007619202],"category_scores_gemma":[0.01386805,0.0004635453,0.000390664,0.000612266,0.003994334,0.008423558,0.002499212,0.008672443,0.001131431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002237679,"about_ca_system_score_gemma":0.001213309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001509513,"about_ca_topic_score_gemma":0.001077204,"domain_scores_codex":[0.9982877,0.0007985032,0.00005257446,0.0002120706,0.0005228274,0.0001263175],"domain_scores_gemma":[0.9909609,0.00668845,0.0002884717,0.0008350075,0.0008856789,0.000341529],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001316221,0.00003939254,0.0001298706,0.0001062396,0.00002574065,0.00005015662,0.00005951267,0.02138823,0.0002662009,0.9258012,0.01111441,0.04088736],"study_design_scores_gemma":[0.00001905051,0.00002473404,0.00005234688,0.00005190446,0.000007512693,0.00003058945,0.00002137016,0.04732271,0.0003027758,0.9422253,0.00992963,0.00001217535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01170174,0.01840772,0.7229164,0.1381604,0.003970206,0.00003134859,0.0003446963,0.0003284664,0.1041391],"genre_scores_gemma":[0.8172453,0.01570472,0.09115303,0.0133509,0.01136165,0.000153054,0.0002284814,0.0003069441,0.05049587],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007619202,"threshold_uncertainty_score":0.02548879,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964271895","doi":"","title":"Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data","year":2018,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":85,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Domain (mathematical analysis); Image (mathematics); Artificial intelligence; Segmentation; Image segmentation; Pattern recognition (psychology); Mathematics","authors":[{"name":"Amjad Almahairi","is_ca":false},{"name":"Sai Rajeshwar","is_ca":false},{"name":"Alessandro Sordoni","is_ca":false},{"name":"Philip Bachman","is_ca":false},{"name":"Aaron Courville","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07715892650561458,"gpt":0.3242514679354985,"spread":0.247092541429884,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00174459,0.001501825,0.001466121,0.0007567746,0.0005350013,0.0008796118,0.001925792,0.001723501,0.002046817],"category_scores_gemma":[0.005248987,0.0006024253,0.0009674127,0.0006754413,0.001533845,0.003348914,0.002478465,0.002521755,0.0006582073],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000667518,"about_ca_system_score_gemma":0.0008235541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001972717,"about_ca_topic_score_gemma":0.003441882,"domain_scores_codex":[0.9992336,0.0002772638,0.00002409356,0.0002800068,0.00009836985,0.00008671304],"domain_scores_gemma":[0.9982791,0.0009167259,0.0001102348,0.0004486576,0.0001710872,0.00007425487],"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":[0.0006679269,0.0003556289,0.006122015,0.0003275949,0.0002821303,0.0003897611,0.0003330009,0.5978578,0.01896811,0.02968371,0.009894793,0.3351175],"study_design_scores_gemma":[0.0000184087,0.0001003219,0.0004794695,0.00002007391,0.00001696887,0.0001247073,0.00002987218,0.9711838,0.002997518,0.02377901,0.001230586,0.00001925514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1175828,0.001163278,0.874144,0.000704354,0.000151812,0.000161702,0.0004784574,0.001822728,0.003791016],"genre_scores_gemma":[0.7910136,0.0004934301,0.1987423,0.00102262,0.0001046178,0.0003056964,0.002068745,0.0002704206,0.005978695],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002046817,"threshold_uncertainty_score":0.009226322,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964304579","doi":"","title":"On orthogonality and learning recurrent networks with long term dependencies","year":2017,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":71,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Orthogonality; Backpropagation; Artificial neural network; Computer science; Convergence (economics); Term (time); Stability (learning theory); Property (philosophy); Matrix (chemical analysis); Norm (philosophy); Applied mathematics; Mathematical optimization; Gradient method; Mathematics; Algorithm; Artificial intelligence; Machine learning","authors":[{"name":"Eugene Vorontsov","is_ca":true},{"name":"Chiheb Trabelsi","is_ca":true},{"name":"Samuel Kadoury","is_ca":true},{"name":"Chris Pal","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0326125001541815,"gpt":0.2885483512715729,"spread":0.2559358511173914,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003604915,0.001306642,0.0009823715,0.0007559572,0.0004473464,0.00102968,0.001167747,0.001260445,0.001650606],"category_scores_gemma":[0.01720908,0.0008422976,0.0006240071,0.0007398401,0.002258505,0.003389735,0.002434552,0.002547208,0.0003164541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009126064,"about_ca_system_score_gemma":0.0009300134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004057998,"about_ca_topic_score_gemma":0.004765189,"domain_scores_codex":[0.9990057,0.0004778117,0.00005549358,0.0001757991,0.0001938729,0.00009131946],"domain_scores_gemma":[0.9914927,0.006552231,0.0007149344,0.0004439632,0.0006091151,0.0001870776],"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":[0.0001049183,0.00005652142,0.001027876,0.0001179247,0.00006847199,0.0001241555,0.0001419782,0.8271533,0.004826208,0.1330934,0.001079272,0.03220592],"study_design_scores_gemma":[0.000004850192,0.00002496609,0.00008593875,0.00001004292,0.000004605964,0.00001455604,0.000006070834,0.9676317,0.0004937997,0.0314903,0.0002264835,0.000006678708],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02693325,0.0008222528,0.9696591,0.0006507508,0.00004402371,0.00002432649,0.00004763449,0.0001903199,0.001628326],"genre_scores_gemma":[0.7268248,0.00327364,0.261302,0.0005583695,0.0003118211,0.0002577785,0.0004177403,0.0003175227,0.006736356],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004057998,"threshold_uncertainty_score":0.01906484,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2160142299","doi":"","title":"Unsupervised Models of Images by Spike-and-Slab RBMs","year":2011,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Spike (software development); Slab; Computer science; Feature (linguistics); Pattern recognition (psychology); Variable (mathematics); Artificial intelligence; Binary number; Boltzmann machine; Latent variable; Algorithm; Mathematics; Artificial neural network; Physics; Mathematical analysis; Arithmetic","authors":[{"name":"Yoshua Bengio","is_ca":true},{"name":"Aaron Courville","is_ca":true},{"name":"James Bergstra","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05242372225847681,"gpt":0.2522785329033527,"spread":0.1998548106448759,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001014742,0.0005880458,0.001033493,0.0005472964,0.0002530403,0.0009439713,0.002450532,0.001335668,0.00194016],"category_scores_gemma":[0.003797341,0.000785785,0.001187913,0.0006642662,0.001402304,0.002394156,0.0013809,0.002203772,0.000545385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00111424,"about_ca_system_score_gemma":0.000579462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003005008,"about_ca_topic_score_gemma":0.004391215,"domain_scores_codex":[0.9995777,0.0001801207,0.0000171671,0.0000937969,0.00007256438,0.00005869537],"domain_scores_gemma":[0.9990401,0.0005181846,0.000124356,0.0001696713,0.0001004823,0.00004720548],"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":[0.0001097205,0.0000223951,0.0004620425,0.00004788743,0.00004973933,0.00004724236,0.0000975924,0.9188038,0.003097891,0.05719355,0.00103995,0.01902813],"study_design_scores_gemma":[0.000003259456,0.000005336789,0.00004456684,0.00000253297,0.000002307008,0.000008762627,0.000002760556,0.9845124,0.0003000817,0.01500252,0.0001118338,0.00000364162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04474489,0.0002944559,0.9520854,0.0003307505,0.00003548858,0.00003111024,0.0001830302,0.0007383112,0.001556582],"genre_scores_gemma":[0.8829365,0.0003342434,0.1086543,0.0002695611,0.00007354793,0.0001486121,0.0003909495,0.0002543454,0.006937898],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003005008,"threshold_uncertainty_score":0.008084357,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3034370310","doi":"","title":"Detecting Out-of-Distribution Examples with Gram Matrices","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; Dalhousie University","funders":"","keywords":"Gram; Computer science; n-gram; Distribution (mathematics); Mathematics; Artificial intelligence; Geology","authors":[{"name":"Chandramouli Shama Sastry","is_ca":true},{"name":"Sageev Oore","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05855191741722271,"gpt":0.2959750540034805,"spread":0.2374231365862577,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001284725,0.000860373,0.0007532272,0.00230502,0.0007516422,0.001199606,0.001057635,0.00195373,0.002099153],"category_scores_gemma":[0.01062835,0.000426879,0.0004804124,0.001257592,0.0007589112,0.001894498,0.001918084,0.001630844,0.001146824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004505472,"about_ca_system_score_gemma":0.0006273417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001788691,"about_ca_topic_score_gemma":0.003761075,"domain_scores_codex":[0.9982158,0.000458587,0.0001111014,0.0003466658,0.0006524117,0.0002153862],"domain_scores_gemma":[0.99246,0.004137449,0.00075355,0.0009347312,0.001332389,0.0003819858],"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":[0.002733831,0.0008921378,0.1618057,0.0004936546,0.0003566243,0.006069094,0.001097669,0.04935011,0.1411291,0.02291286,0.02267466,0.5904846],"study_design_scores_gemma":[0.00004764574,0.0001627996,0.02149502,0.00005252535,0.00005609593,0.003112761,0.0004379215,0.91707,0.03857088,0.01368245,0.005262438,0.0000494605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6196594,0.0006041713,0.3696556,0.0006594876,0.0001686373,0.0001010211,0.0008979131,0.004763612,0.003490134],"genre_scores_gemma":[0.9121309,0.000184187,0.08373009,0.0001418514,0.00008752355,0.00004103977,0.001529484,0.0003034179,0.00185158],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00230502,"threshold_uncertainty_score":0.007022381,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963723885","doi":"","title":"Understanding the Origins of Bias in Word Embeddings","year":2019,"lang":"en","type":"article","venue":"International Conference on Machine Learning","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":"University of Toronto","funders":"","keywords":"Computer science; Word (group theory); Word embedding; Natural language processing; Embedding; Artificial intelligence; TRACE (psycholinguistics); Harm; Machine learning; Linguistics; Psychology","authors":[{"name":"Marc-Etienne Brunet","is_ca":true},{"name":"Colleen Alkalay-Houlihan","is_ca":false},{"name":"Ashton Anderson","is_ca":true},{"name":"Richard S. Zemel","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1021607067859051,"gpt":0.341356417713073,"spread":0.2391957109271678,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003172817,0.0005175489,0.000473298,0.0016221,0.000544564,0.001759768,0.0005250723,0.0008547837,0.0009082171],"category_scores_gemma":[0.04818755,0.0004770156,0.0003598117,0.001608691,0.001291101,0.005480413,0.001558029,0.001543098,0.0005293573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009233513,"about_ca_system_score_gemma":0.001099742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004065749,"about_ca_topic_score_gemma":0.005401797,"domain_scores_codex":[0.9978573,0.0009006187,0.0001574326,0.0004023217,0.0005519471,0.0001304162],"domain_scores_gemma":[0.9840721,0.009261594,0.00166935,0.002558984,0.00229505,0.0001428205],"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":[0.0003789664,0.0001376245,0.09534712,0.000577245,0.000242481,0.0004587252,0.004716972,0.2014243,0.03820248,0.1334704,0.006925682,0.5181179],"study_design_scores_gemma":[0.00003288677,0.00007948787,0.01961598,0.0001557632,0.0000571231,0.0004067018,0.0009354815,0.7184461,0.03037999,0.2163332,0.01347788,0.00007950432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3268034,0.001552564,0.6644776,0.001499221,0.0001608544,0.00006812342,0.0004973945,0.0007151815,0.004225702],"genre_scores_gemma":[0.8819226,0.001012119,0.1139049,0.000243924,0.00009984298,0.0001076224,0.000698898,0.0003318803,0.001677995],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004065749,"threshold_uncertainty_score":0.01677966,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2946506331","doi":"","title":"Unreproducible Research is Reproducible","year":2019,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":57,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science","authors":[{"name":"Xavier Bouthillier","is_ca":true},{"name":"César Laurent","is_ca":true},{"name":"Pascal Vincent","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4724560828290626,"gpt":0.5226980919648335,"spread":0.05024200913577093,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1873679,0.001144463,0.003020513,0.008997427,0.003994328,0.01888849,0.005133403,0.004358014,0.01914714],"category_scores_gemma":[0.4559733,0.001588529,0.002407214,0.008655598,0.02428084,0.01246943,0.01493045,0.007324214,0.01158876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005376088,"about_ca_system_score_gemma":0.02169833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008668511,"about_ca_topic_score_gemma":0.001028973,"domain_scores_codex":[0.8000788,0.07725739,0.01888077,0.02218268,0.07781791,0.003782336],"domain_scores_gemma":[0.2349955,0.2692032,0.04132246,0.3522913,0.09408827,0.008099325],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008288081,0.0004899283,0.0198621,0.00321695,0.000904438,0.001308334,0.006465971,0.002241794,0.005871657,0.7050799,0.05870218,0.195028],"study_design_scores_gemma":[0.0002890533,0.0002343005,0.005278736,0.001278413,0.0002827327,0.0007369818,0.001107138,0.002397511,0.006180604,0.8005225,0.1816049,0.00008712706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.064553,0.0133377,0.4318514,0.138972,0.01771596,0.003201159,0.005816865,0.007297093,0.3172547],"genre_scores_gemma":[0.703055,0.007706532,0.1771862,0.01708016,0.009862456,0.004633719,0.006663668,0.003953928,0.06985836],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8126321,"threshold_uncertainty_score":0.9909078,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2804682296","doi":"","title":"Spotlight: Optimizing Device Placement for Training Deep Neural Networks","year":2018,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial neural network; Training (meteorology); Artificial intelligence","authors":[{"name":"Yuanxiang Gao","is_ca":false},{"name":"Li Chen","is_ca":false},{"name":"Baochun Li","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06539351812044211,"gpt":0.3354566578305311,"spread":0.270063139710089,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003981188,0.001968295,0.0008108728,0.0005008164,0.0003590906,0.0007974579,0.001807313,0.001116627,0.01117024],"category_scores_gemma":[0.002127648,0.0006390288,0.0005523665,0.000442454,0.0003066115,0.001014894,0.0007662983,0.001368052,0.002072936],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001139443,"about_ca_system_score_gemma":0.001473044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006624355,"about_ca_topic_score_gemma":0.01842837,"domain_scores_codex":[0.9997843,0.00004571508,0.00001190095,0.00004912151,0.00005512908,0.0000538417],"domain_scores_gemma":[0.9995462,0.0001967334,0.00003436405,0.00006225078,0.000122545,0.00003794297],"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":[0.0004811203,0.0002409005,0.001899578,0.0002691861,0.00008336358,0.0002059071,0.00006832644,0.6344073,0.01230193,0.003056625,0.02885882,0.3181269],"study_design_scores_gemma":[0.00004529392,0.0001136576,0.0001881118,0.00001461487,0.00001661642,0.00002872604,0.00002834367,0.9901401,0.005191868,0.002312917,0.001911679,0.000007960579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1215391,0.001735872,0.828808,0.0008117047,0.0008627579,0.0002540662,0.001144484,0.02900251,0.01584155],"genre_scores_gemma":[0.6682268,0.0002112667,0.3201451,0.0003207145,0.00007339413,0.0002350363,0.001034057,0.001420779,0.008332716],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01117024,"threshold_uncertainty_score":0.03736818,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3034360859","doi":"","title":"Learning with Good Feature Representations in Bandits and in RL with a Generative Model","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Feature (linguistics); Generative model; Generative grammar; Computer science; Artificial intelligence; Feature learning; Machine learning; Linguistics","authors":[{"name":"Gellért Weisz","is_ca":false},{"name":"Tor Lattimore","is_ca":false},{"name":"Csaba Szepesvári","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03676985648599293,"gpt":0.3016793059080322,"spread":0.2649094494220393,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003308018,0.001193407,0.002376899,0.0009009144,0.0008772358,0.002618845,0.002012132,0.003482681,0.003506488],"category_scores_gemma":[0.02240344,0.001492067,0.001190802,0.001149865,0.002978219,0.004883218,0.003479902,0.003540602,0.0007141049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001139996,"about_ca_system_score_gemma":0.001117548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003311217,"about_ca_topic_score_gemma":0.003261361,"domain_scores_codex":[0.9981852,0.001095964,0.00007826278,0.0002832776,0.0001976314,0.0001596122],"domain_scores_gemma":[0.9868059,0.01110559,0.0004432595,0.000933652,0.0004167691,0.0002948312],"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":[0.000173859,0.00007284684,0.0008870505,0.0001002419,0.00008995599,0.0001128479,0.0001867194,0.8067304,0.0007544821,0.1616021,0.001556422,0.02773298],"study_design_scores_gemma":[0.00001638923,0.00001171279,0.00004116561,0.000009151094,0.000007843156,0.00001189498,0.000008356005,0.9259093,0.0001260813,0.07371467,0.0001368922,0.000006503011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02793323,0.0003372102,0.968564,0.0007430987,0.00004697276,0.00002221182,0.00007770748,0.0004218732,0.001853629],"genre_scores_gemma":[0.8364969,0.0003533042,0.1561261,0.0003908229,0.0001525675,0.0001966646,0.0002653791,0.0003236437,0.005694756],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003506488,"threshold_uncertainty_score":0.01749468,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963789586","doi":"","title":"Training deep neural networks via direct loss minimization","year":2016,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Neural Network 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 Toronto","funders":"","keywords":"Computer science; Artificial neural network; Artificial intelligence; Minification; Machine learning; Deep neural networks; Entropy (arrow of time); Context (archaeology); Cross entropy; Ranking (information retrieval); Deep learning; Pattern recognition (psychology)","authors":[{"name":"Yang Song","is_ca":false},{"name":"Alexander G. Schwing","is_ca":true},{"name":"Richard S. Zemel","is_ca":true},{"name":"Raquel Urtasun","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03707372032486093,"gpt":0.2969850488209083,"spread":0.2599113284960473,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002194125,0.001937092,0.0012824,0.0007156617,0.0004925386,0.001293435,0.001842335,0.001893045,0.002715179],"category_scores_gemma":[0.005388577,0.0008856594,0.000683122,0.0007585656,0.001108094,0.001868816,0.002229397,0.003212461,0.00141842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00165259,"about_ca_system_score_gemma":0.00179353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003008013,"about_ca_topic_score_gemma":0.006186543,"domain_scores_codex":[0.99902,0.0002655553,0.00005791491,0.0002225123,0.0003306932,0.0001033233],"domain_scores_gemma":[0.9985909,0.000687097,0.0001637481,0.0002009973,0.000289604,0.00006759174],"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":[0.00008397948,0.000144191,0.0006811268,0.0001227512,0.00007461337,0.00007472454,0.0000442383,0.7875523,0.005292933,0.01559246,0.004187136,0.1861496],"study_design_scores_gemma":[0.000007799464,0.00003660484,0.0000613658,0.000009214324,0.000004216618,0.00001667207,0.000004696505,0.9907089,0.001321925,0.007334057,0.0004900677,0.000004409291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01174898,0.0003028795,0.9839214,0.0002693075,0.0000415469,0.00008322692,0.00006748823,0.001156794,0.002408393],"genre_scores_gemma":[0.4291531,0.0005743766,0.556286,0.0006570305,0.0001295658,0.0007265375,0.0006621641,0.0005557145,0.01125558],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003008013,"threshold_uncertainty_score":0.01199037,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W18175453","doi":"10.1525/tph.2007.29.3.87","title":"Algorithm-Directed Exploration for Model-Based Reinforcement Learning in Factored MDPs","year":2002,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Oracle; Computer science; Planner; Mathematical optimization; Linear programming; Artificial intelligence; Machine learning; Algorithm; Mathematics","authors":[{"name":"Carlos Guestrin","is_ca":false},{"name":"Relu Patrascu","is_ca":true},{"name":"Dale Schuurmans","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08004596865886063,"gpt":0.3027935798906811,"spread":0.2227476112318204,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003189532,0.001335515,0.002167901,0.0007845939,0.0005857314,0.001029301,0.001592689,0.001717149,0.004118219],"category_scores_gemma":[0.009815553,0.0008343204,0.0007095321,0.0005760841,0.001607974,0.001364203,0.002034388,0.001959056,0.0003698321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001545161,"about_ca_system_score_gemma":0.001937701,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01056829,"about_ca_topic_score_gemma":0.00884378,"domain_scores_codex":[0.9992098,0.0004189174,0.00004491651,0.0001063351,0.00009843826,0.0001216881],"domain_scores_gemma":[0.9931942,0.005773584,0.0003146614,0.0001751438,0.0003289902,0.0002133541],"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":[0.0000579886,0.00002475377,0.0002975464,0.00004055703,0.0000222092,0.00002620405,0.00003688104,0.9854154,0.00008188817,0.006296261,0.0003026883,0.007397663],"study_design_scores_gemma":[0.00001792578,0.00001721551,0.00001579844,0.000004730849,0.00000277018,0.000002609192,0.00000365472,0.9958584,0.00003254777,0.0039506,0.00009172709,0.000002031326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04503132,0.0004660931,0.9492612,0.0005132784,0.00006238707,0.0001232622,0.00007966167,0.0005550835,0.003907708],"genre_scores_gemma":[0.8914745,0.0002160717,0.1043474,0.0001869756,0.00004577282,0.000489363,0.0001459462,0.0001041142,0.002989718],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01056829,"threshold_uncertainty_score":0.02101356,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3035618017","doi":"","title":"Improving Transformer Optimization Through Better Initialization","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Power Transformer Diagnostics and Insulation","field":"Engineering","cited_by":51,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Initialization; Computer science; Transformer; Electrical engineering; Engineering; Voltage; Programming language","authors":[{"name":"Xiao Shi Huang","is_ca":false},{"name":"Juan Manuel Pérez","is_ca":false},{"name":"Jimmy Ba","is_ca":true},{"name":"Maksims Volkovs","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02893562775711362,"gpt":0.2536630670916855,"spread":0.2247274393345718,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008492885,0.001249458,0.0009560338,0.0005390692,0.0003832105,0.001092156,0.0006967647,0.001250147,0.0053432],"category_scores_gemma":[0.003604975,0.0007183032,0.0006563325,0.0004572845,0.0003897307,0.001646485,0.0008777447,0.001715759,0.001545867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004966898,"about_ca_system_score_gemma":0.0008146251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00407753,"about_ca_topic_score_gemma":0.005500712,"domain_scores_codex":[0.9996178,0.0001533705,0.00002571092,0.00008416147,0.00007592732,0.00004303527],"domain_scores_gemma":[0.9993043,0.0003165984,0.00005050707,0.0001560232,0.0001433088,0.00002926285],"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":[0.0002539342,0.0001348457,0.00129538,0.00007988269,0.00007912691,0.00007845904,0.000058326,0.7722101,0.0127412,0.004918465,0.00739134,0.2007589],"study_design_scores_gemma":[0.000009605436,0.00001178683,0.0001288324,0.000004104132,0.000005671918,0.00001168367,0.000003351116,0.9961598,0.00243297,0.0006958169,0.0005329829,0.000003405954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02726988,0.0002728679,0.963923,0.0003304598,0.0001429722,0.00003621322,0.00009199604,0.003185693,0.004746927],"genre_scores_gemma":[0.5480723,0.0001948332,0.4416825,0.0003679732,0.00009463492,0.00009049853,0.0006922156,0.001220988,0.007584141],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0053432,"threshold_uncertainty_score":0.01787478,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3170865782","doi":"","title":"Environment Inference for Invariant Learning","year":2021,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":51,"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":"Inference; Invariant (physics); Computer science; Benchmark (surveying); Artificial intelligence; Machine learning; Generalization; Domain (mathematical analysis); Mathematics","authors":[{"name":"Elliot Creager","is_ca":true},{"name":"Joern-Henrik Jacobsen","is_ca":false},{"name":"Richard S. Zemel","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04867667267188184,"gpt":0.3042943594813409,"spread":0.2556176868094591,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008183206,0.001195111,0.001774831,0.001330662,0.001471026,0.002670123,0.003481713,0.001785076,0.003859153],"category_scores_gemma":[0.02924538,0.0006953806,0.001233681,0.001192651,0.003686064,0.006377815,0.005316975,0.004552646,0.0008371335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002083491,"about_ca_system_score_gemma":0.002364558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002610286,"about_ca_topic_score_gemma":0.003266306,"domain_scores_codex":[0.9944728,0.002406589,0.0002074613,0.001679997,0.0007757035,0.0004574988],"domain_scores_gemma":[0.9869252,0.006403513,0.00102639,0.004295898,0.0008364457,0.0005124689],"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":[0.0002828329,0.0001887708,0.00408869,0.0001162453,0.0001183596,0.0001182072,0.000276887,0.6437113,0.002026298,0.2412951,0.004864126,0.1029131],"study_design_scores_gemma":[0.00001332391,0.00002740137,0.000190062,0.00001244016,0.000008586947,0.00002062538,0.00001972068,0.7861734,0.0008894227,0.2116725,0.0009603851,0.00001214274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008740771,0.0001717483,0.988818,0.0003052866,0.00003596341,0.00002786741,0.0001010495,0.0005289327,0.001270361],"genre_scores_gemma":[0.6921069,0.0003304487,0.3003368,0.001059203,0.0002325529,0.0002462264,0.0009535901,0.0005196651,0.004214547],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008183206,"threshold_uncertainty_score":0.0432775,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2182286517","doi":"","title":"From PAC-Bayes Bounds to Quadratic Programs for Majority Votes","year":2011,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"","keywords":"Margin (machine learning); Upper and lower bounds; AdaBoost; Bayes' theorem; Mathematics; Quadratic equation; Divergence (linguistics); Minification; Basis (linear algebra); Combinatorics; Computer science; Algorithm; Support vector machine; Mathematical optimization; Artificial intelligence; Machine learning; Bayesian probability","authors":[{"name":"Jean-Francis Roy","is_ca":true},{"name":"Mario Marchand","is_ca":true},{"name":"Fran ois Laviolette","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06972141086261915,"gpt":0.3134253480200855,"spread":0.2437039371574663,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0101115,0.002039227,0.002124246,0.001514971,0.001262892,0.00484926,0.003210419,0.002967817,0.007245364],"category_scores_gemma":[0.03875239,0.001336894,0.001179626,0.001443334,0.003869014,0.007734678,0.00529374,0.00722722,0.001564558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002975956,"about_ca_system_score_gemma":0.002603913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002218257,"about_ca_topic_score_gemma":0.002035938,"domain_scores_codex":[0.9930986,0.003218484,0.0001865273,0.0009781136,0.002035213,0.0004831257],"domain_scores_gemma":[0.9830059,0.01307651,0.0007584596,0.0009758834,0.001777894,0.0004053683],"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":[0.0001102339,0.00007755385,0.0004490569,0.0001767372,0.00005491619,0.00005456756,0.0001988971,0.2428363,0.0005501755,0.6747662,0.006242676,0.07448282],"study_design_scores_gemma":[0.00001307852,0.00001909214,0.00005148109,0.00004261693,0.000007705136,0.00001645343,0.00001538784,0.6551448,0.0004535352,0.3420186,0.002205621,0.00001164138],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001764212,0.0004570856,0.9926246,0.0004797828,0.00005567443,0.00002794901,0.00002739165,0.000106732,0.004456534],"genre_scores_gemma":[0.284379,0.001643895,0.6925526,0.001461689,0.0009500215,0.0007593217,0.0003903412,0.001059808,0.01680327],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0101115,"threshold_uncertainty_score":0.05347532,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2143797877","doi":"","title":"Deep Supervised t-Distributed Embedding","year":2010,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Embedding; Computer science; Deep learning; Pairwise comparison; Scalability; Artificial intelligence; Parametric statistics; Visualization; Architecture; Class (philosophy); Machine learning; Pattern recognition (psychology); Mathematics","authors":[{"name":"Martin Renqiang Min","is_ca":true},{"name":"L.J.P. van der Maaten","is_ca":false},{"name":"Zineng Yuan","is_ca":true},{"name":"Anthony J. Bonner","is_ca":true},{"name":"Zhaolei Zhang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0253908761679612,"gpt":0.2998689291950903,"spread":0.2744780530271291,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001383905,0.001029906,0.001033893,0.0006860639,0.0004515583,0.0008166769,0.001479123,0.001140783,0.002681238],"category_scores_gemma":[0.005580238,0.0003454481,0.0008426295,0.0007931975,0.001093056,0.002325168,0.001627948,0.001633867,0.0008410881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009937155,"about_ca_system_score_gemma":0.0009743678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001660051,"about_ca_topic_score_gemma":0.003044163,"domain_scores_codex":[0.9989135,0.0003786843,0.00006066521,0.0003221685,0.0002426625,0.00008238407],"domain_scores_gemma":[0.9967739,0.001205679,0.0003756083,0.0008309233,0.0006771923,0.0001366947],"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":[0.0002263052,0.0002049819,0.001895171,0.0001236444,0.00009488059,0.00008854739,0.0001307775,0.6255032,0.009303288,0.02649603,0.003541794,0.3323914],"study_design_scores_gemma":[0.0000041121,0.0000319689,0.00009510534,0.000002272611,0.000002517246,0.00001510705,0.00000552189,0.992417,0.00159618,0.005587103,0.000238845,0.000004286605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02741076,0.0001327306,0.9703068,0.00012329,0.00002899812,0.0000377856,0.00007981274,0.0009421604,0.0009376822],"genre_scores_gemma":[0.7113429,0.0001467146,0.281633,0.0001786502,0.00008050905,0.0002174742,0.0006342787,0.0002307082,0.005535922],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002681238,"threshold_uncertainty_score":0.008969605,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W151435321","doi":"","title":"Gaussian Processes for Bayesian Estimation in Ordinary Differential Equations","year":2014,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"","keywords":"Ode; Ordinary differential equation; Gaussian process; Applied mathematics; Estimation theory; Consistency (knowledge bases); Computer science; Gaussian; Mathematics; Bayesian probability; Mathematical optimization; Bayes estimator; Algorithm; Differential equation; Artificial intelligence; Mathematical analysis","authors":[{"name":"David Barber","is_ca":true},{"name":"Yali Wang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0237363953957338,"gpt":0.2975774090199679,"spread":0.2738410136242341,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01122096,0.00158942,0.002338094,0.00229469,0.001007395,0.002523792,0.003454904,0.003356878,0.004273046],"category_scores_gemma":[0.04342841,0.00141035,0.001944287,0.002427837,0.003661646,0.0037243,0.003726055,0.004985871,0.001316429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0025084,"about_ca_system_score_gemma":0.002951406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009102005,"about_ca_topic_score_gemma":0.005622856,"domain_scores_codex":[0.9960122,0.002003811,0.0002085875,0.0006399407,0.0009214755,0.0002139007],"domain_scores_gemma":[0.9840087,0.01237237,0.001037942,0.000999207,0.001338598,0.0002433095],"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":[0.00004666961,0.0000417531,0.0008514436,0.000203701,0.0001094198,0.0001140001,0.0001289,0.2795593,0.0007400589,0.6840998,0.00256184,0.03154317],"study_design_scores_gemma":[0.00001194171,0.00001110283,0.0001501964,0.00003721495,0.00001510294,0.0000203303,0.00001037502,0.7275253,0.0002453929,0.2699185,0.002033222,0.00002133149],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006810239,0.0003102125,0.998083,0.0002448945,0.00003348145,0.0000178158,0.00004604363,0.00009490424,0.0004886697],"genre_scores_gemma":[0.2465036,0.005197799,0.7358,0.00111218,0.0009162826,0.001141257,0.0009992887,0.0006123844,0.007717127],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01122096,"threshold_uncertainty_score":0.0593428,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2962725091","doi":"","title":"Structured Generative Models of Natural Source Code","year":2014,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Generative grammar; Source code; Probabilistic logic; Code (set theory); Context (archaeology); Generative model; Natural language processing; Artificial intelligence; Natural language; Rule-based machine translation; Language model; Statistical model; Programming language","authors":[{"name":"Chris J. Maddison","is_ca":true},{"name":"Daniel Tarlow","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02337419429426449,"gpt":0.2985761800977195,"spread":0.275201985803455,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002028039,0.0008506885,0.0005751484,0.001979819,0.0005110956,0.001523286,0.001925492,0.0014761,0.003232596],"category_scores_gemma":[0.01619317,0.0008996109,0.001452646,0.001404859,0.001903762,0.002882224,0.001316102,0.002002678,0.0009999388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00140358,"about_ca_system_score_gemma":0.00142103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006691869,"about_ca_topic_score_gemma":0.01157548,"domain_scores_codex":[0.9984428,0.0006249373,0.00006299357,0.0003967739,0.0003598765,0.0001125557],"domain_scores_gemma":[0.9831366,0.01359344,0.0009715857,0.00117539,0.0009053894,0.0002176512],"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":[0.00006589059,0.00007663778,0.004550778,0.0001992129,0.00008364551,0.0003884978,0.0008438428,0.7320086,0.002462044,0.20917,0.004444935,0.04570605],"study_design_scores_gemma":[0.000009641111,0.000009400772,0.0003024798,0.00001999444,0.000009482818,0.0000865344,0.00002555694,0.8869956,0.0004883753,0.1102592,0.001783001,0.0000108721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02641651,0.0003465416,0.968351,0.0005041801,0.0000306639,0.00005951141,0.0008158217,0.001127393,0.002348443],"genre_scores_gemma":[0.6939777,0.0008211731,0.2910915,0.0004271396,0.0001238702,0.0004996026,0.00473984,0.001155614,0.007163697],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006691869,"threshold_uncertainty_score":0.01330584,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3035353486","doi":"","title":"From Local SGD to Local Fixed Point Methods for Federated Learning","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Bottleneck; Computer science; Fixed point; Saddle point; Mathematical optimization; Context (archaeology); Computation; Operator (biology); Saddle; Convergence (economics); Theoretical computer science; Mathematics; Algorithm","authors":[{"name":"Grigory Malinovskiy","is_ca":false},{"name":"Dmitry Kovalev","is_ca":true},{"name":"Elnur Gasanov","is_ca":true},{"name":"Laurent Condat","is_ca":true},{"name":"Peter Richtárik","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0574492059463758,"gpt":0.363646518265808,"spread":0.3061973123194321,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003803421,0.001409313,0.001990894,0.0008715646,0.0006392234,0.001581953,0.002218898,0.002048092,0.002718745],"category_scores_gemma":[0.01083648,0.0006722663,0.0009575197,0.001013332,0.001982125,0.001914265,0.003167066,0.003180468,0.001021857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001225314,"about_ca_system_score_gemma":0.001583523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00260024,"about_ca_topic_score_gemma":0.002731251,"domain_scores_codex":[0.9986058,0.0006615659,0.00006943589,0.000268091,0.0003139944,0.00008108508],"domain_scores_gemma":[0.9959548,0.002545146,0.0002640559,0.0005559997,0.0005013242,0.0001787953],"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":[0.0001123273,0.00006862826,0.0005510669,0.0001308589,0.00006696858,0.0000662447,0.0001033675,0.8888733,0.001105167,0.04755024,0.00198851,0.05938331],"study_design_scores_gemma":[0.0000111515,0.00002143659,0.00002963233,0.00001013424,0.000003780417,0.000008051502,0.000007820733,0.9747167,0.0002750527,0.0243892,0.0005228007,0.000004323923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002594231,0.0001941011,0.9961346,0.0001399346,0.00003125622,0.00002173106,0.00001750991,0.0002773881,0.0005892293],"genre_scores_gemma":[0.3300406,0.000599226,0.6635331,0.0003824903,0.0001542744,0.0004328627,0.0002507199,0.0005098011,0.00409675],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003803421,"threshold_uncertainty_score":0.02011466,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2955067198","doi":"","title":"Lorentzian Distance Learning for Hyperbolic Representations","year":2019,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Topological and Geometric Data Analysis","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence","authors":[{"name":"Marc T. Law","is_ca":true},{"name":"Renjie Liao","is_ca":true},{"name":"Jake Snell","is_ca":true},{"name":"Richard S. Zemel","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03603241555476244,"gpt":0.3178020778446282,"spread":0.2817696622898658,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002465092,0.0006777537,0.00108717,0.001464466,0.0008668446,0.002309416,0.002254495,0.001298687,0.005131683],"category_scores_gemma":[0.01108483,0.0004535364,0.0009056708,0.001546281,0.001817988,0.004508098,0.00388259,0.002803688,0.001608271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001607865,"about_ca_system_score_gemma":0.001540823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003684717,"about_ca_topic_score_gemma":0.003123835,"domain_scores_codex":[0.9986584,0.000524114,0.00009245261,0.0003073922,0.0003205205,0.00009710291],"domain_scores_gemma":[0.9967145,0.001307583,0.000259935,0.0007387139,0.0007130152,0.0002662954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002059538,0.0001135421,0.001587995,0.000178543,0.00007380165,0.0000575455,0.0002388334,0.113148,0.002430392,0.6428525,0.007152941,0.23196],"study_design_scores_gemma":[0.00001572126,0.00007070893,0.0002594662,0.00001981363,0.00001008967,0.00003661907,0.00006001802,0.6119443,0.0007762869,0.38285,0.003933269,0.00002372121],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0229817,0.0004255785,0.9724582,0.0005058526,0.0001127454,0.00003989536,0.0001783466,0.0003087613,0.002988975],"genre_scores_gemma":[0.5576211,0.001474334,0.4181128,0.0005361415,0.0003799192,0.0002119252,0.002060484,0.000466415,0.01913691],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005131683,"threshold_uncertainty_score":0.01716721,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963642948","doi":"","title":"Synthesizing Programs for Images using Reinforced Adversarial Learning.","year":2018,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Discriminator; MNIST database; Artificial intelligence; Inference; Machine learning; Graphics; Rendering (computer graphics); Adversarial system; Deep learning; Generative grammar; Generative adversarial network; Computer graphics; Reinforcement learning; Computer graphics (images)","authors":[{"name":"Yaroslav Ganin","is_ca":true},{"name":"Tejas Kulkarni","is_ca":false},{"name":"I. Babuschkin","is_ca":false},{"name":"S. M. Ali Eslami","is_ca":false},{"name":"Oriol Vinyals","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05329083591455927,"gpt":0.3083080371160244,"spread":0.2550172012014652,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006226793,0.0007333261,0.000359231,0.0002893189,0.0002371629,0.0005913495,0.0009323251,0.0008104,0.003548558],"category_scores_gemma":[0.002963859,0.0003585347,0.0005399295,0.0001882925,0.001044636,0.0007100333,0.001409073,0.00167476,0.0005759826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007400499,"about_ca_system_score_gemma":0.0006143062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002151828,"about_ca_topic_score_gemma":0.00391197,"domain_scores_codex":[0.9997699,0.00006032405,0.000008497952,0.00006565716,0.00007044892,0.00002521202],"domain_scores_gemma":[0.9992194,0.0005182623,0.00006712382,0.0001069807,0.0000483567,0.00003983408],"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":[0.00005820448,0.00003766381,0.0005595168,0.00004853377,0.00002553524,0.00007261558,0.00008903787,0.9352196,0.004865624,0.01954257,0.001620692,0.03786043],"study_design_scores_gemma":[0.000004615868,0.00001163423,0.00002929552,0.000004611353,0.000002133996,0.00001197813,0.000004321926,0.9929015,0.001145903,0.005225261,0.0006564956,0.000002109997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02125921,0.0001431387,0.9728537,0.0002837145,0.00005920976,0.00008053095,0.00009691143,0.001610636,0.003612918],"genre_scores_gemma":[0.6290453,0.000182147,0.3606386,0.0003510581,0.00004171436,0.0002827486,0.0003183054,0.000599137,0.008540953],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003548558,"threshold_uncertainty_score":0.0118711,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2954460650","doi":"","title":"Empirical Analysis of Beam Search Performance Degradation in Neural Sequence Models","year":2019,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Degradation (telecommunications); Sequence (biology); Computer science; Artificial neural network; Artificial intelligence; Pattern recognition (psychology); Chemistry; Telecommunications","authors":[{"name":"Eldan Cohen","is_ca":true},{"name":"J. Christopher Beck","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1093036857200191,"gpt":0.3857356482147963,"spread":0.2764319624947772,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008425904,0.0006433566,0.0008631665,0.001056818,0.0004637208,0.0007937511,0.0009388309,0.001689385,0.001918339],"category_scores_gemma":[0.05754972,0.0004053525,0.0004291516,0.001207955,0.0007568896,0.001852863,0.0006860707,0.001414346,0.0006207352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001274676,"about_ca_system_score_gemma":0.001147602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008301697,"about_ca_topic_score_gemma":0.004825152,"domain_scores_codex":[0.9974291,0.001277781,0.0001772606,0.0003683934,0.0005253282,0.0002220872],"domain_scores_gemma":[0.9321679,0.0577975,0.001894883,0.003477601,0.004144928,0.0005171674],"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":[0.00110023,0.0002311242,0.01302465,0.0002932325,0.0001858905,0.0001192672,0.0001474031,0.90577,0.005094876,0.005649657,0.00378041,0.06460322],"study_design_scores_gemma":[0.00001671659,0.000143978,0.003719477,0.00002395603,0.00002279822,0.0001053619,0.00003239718,0.9917935,0.002503839,0.001332222,0.0002894466,0.00001638287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7383288,0.005887026,0.2481458,0.001236709,0.0001455647,0.00008107369,0.00137411,0.001723573,0.00307726],"genre_scores_gemma":[0.9736143,0.0005160783,0.02245163,0.0001293645,0.00004109454,0.00004964319,0.001939078,0.0001605515,0.001098293],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008425904,"threshold_uncertainty_score":0.04456097,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1870822514","doi":"","title":"A Deeper Look at Planning as Learning from Replay","year":2015,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Bellman equation; Markov decision process; Function (biology); Temporal difference learning; Markov chain; Equivalence (formal languages); Artificial intelligence; Markov process; Machine learning; Mathematical optimization; Mathematics","authors":[{"name":"Harm Vanseijen","is_ca":true},{"name":"Rich Sutton","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07534542055669481,"gpt":0.3228219604417945,"spread":0.2474765398850997,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001978775,0.001159294,0.001297234,0.000534215,0.0005485629,0.002275846,0.001924143,0.001976909,0.00523061],"category_scores_gemma":[0.00690223,0.0007499401,0.001492935,0.0007511142,0.003293815,0.007639389,0.002056949,0.005846545,0.0006327833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001718156,"about_ca_system_score_gemma":0.0013174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00485964,"about_ca_topic_score_gemma":0.002755284,"domain_scores_codex":[0.9988601,0.0004950304,0.00005330454,0.0002792756,0.0002443125,0.00006786358],"domain_scores_gemma":[0.9975576,0.001639299,0.0001836914,0.0003407713,0.0001723983,0.0001061629],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009092649,0.00006133776,0.0004556718,0.0003480221,0.00009722259,0.00008865405,0.0004295391,0.2832438,0.001912434,0.6599524,0.002114778,0.05120518],"study_design_scores_gemma":[0.00002488836,0.0001231302,0.0001431194,0.0001130011,0.00002615858,0.00006488646,0.00006658515,0.5853122,0.001084103,0.4031106,0.00988791,0.00004341671],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002378328,0.001685689,0.9908658,0.001578231,0.0001182073,0.00002177421,0.00002987386,0.0002397905,0.003082335],"genre_scores_gemma":[0.3859011,0.006757573,0.5892979,0.001945967,0.0006739963,0.0003111145,0.0001793546,0.0005136695,0.01441931],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00523061,"threshold_uncertainty_score":0.01749814,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2294277889","doi":"","title":"Tensor Analyzers","year":2013,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Tensor decomposition and applications","field":"Mathematics","cited_by":41,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Multilinear map; Generalization; Tensor (intrinsic definition); Artificial intelligence; Computer science; Latent variable; Face (sociological concept); Factor (programming language); Pattern recognition (psychology); Image (mathematics); Mathematics","authors":[{"name":"Yichuan Tang","is_ca":true},{"name":"Ruslan Salakhutdinov","is_ca":true},{"name":"Geoffrey E. Hinton","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0714223381075099,"gpt":0.360528478441711,"spread":0.2891061403342011,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00363253,0.002320148,0.001278711,0.0029593,0.00129838,0.003698034,0.002011152,0.001399833,0.01696278],"category_scores_gemma":[0.01435908,0.0008971128,0.002359235,0.002376656,0.002869073,0.005894019,0.003557577,0.002809044,0.00661697],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001173533,"about_ca_system_score_gemma":0.002140647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002786736,"about_ca_topic_score_gemma":0.002793609,"domain_scores_codex":[0.9960243,0.001098775,0.0003074883,0.00113738,0.001115782,0.0003163324],"domain_scores_gemma":[0.9934028,0.00178181,0.0008655803,0.001848133,0.001607599,0.0004940882],"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":[0.0003784568,0.0001084763,0.002878369,0.0003625083,0.0001839613,0.0003661621,0.000581015,0.04081381,0.01307643,0.6459462,0.0222396,0.2730651],"study_design_scores_gemma":[0.00003572458,0.0001225726,0.001204308,0.0001071541,0.00006070747,0.0005361188,0.0001806445,0.4276956,0.007616605,0.5114813,0.05085783,0.00010136],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003835046,0.0002650209,0.9893442,0.0002292869,0.0001213526,0.0000971891,0.0005873098,0.001760998,0.003759514],"genre_scores_gemma":[0.13788,0.001161974,0.8414649,0.0004720844,0.0003635464,0.0003889439,0.003096389,0.00176777,0.01340446],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01696278,"threshold_uncertainty_score":0.05674613,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2127099514","doi":"","title":"Large-Scale Learning of Embeddings with Reconstruction Sampling","year":2011,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Topic Modeling","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Vocabulary; Estimator; Context (archaeology); Sampling (signal processing); Artificial neural network; Scale (ratio); Encoder; Computer vision; Mathematics","authors":[{"name":"Xavier Glorot","is_ca":true},{"name":"Yoshua Bengio","is_ca":true},{"name":"Yann Dauphin","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05268136800075558,"gpt":0.2867230285038735,"spread":0.234041660503118,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002770897,0.001387994,0.001437096,0.0009424351,0.0005260048,0.001172289,0.002139457,0.001609628,0.001918457],"category_scores_gemma":[0.01915213,0.000977012,0.0009217142,0.001114142,0.00120737,0.004573015,0.002694857,0.002515605,0.001243223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00076125,"about_ca_system_score_gemma":0.001124028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002501535,"about_ca_topic_score_gemma":0.003958491,"domain_scores_codex":[0.998131,0.0007459968,0.0001075631,0.0004518796,0.0004410966,0.0001224952],"domain_scores_gemma":[0.9932629,0.004112736,0.0003693937,0.001421269,0.0007003625,0.0001333052],"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":[0.0004480583,0.0002483708,0.003448387,0.0003172345,0.0001594991,0.0002767766,0.0003242351,0.5476606,0.01549974,0.04928024,0.008650067,0.3736868],"study_design_scores_gemma":[0.00002297004,0.00003345259,0.0001478036,0.000005981639,0.000007249652,0.0000373682,0.00001808448,0.9812322,0.00265136,0.01501794,0.0008175885,0.000007891834],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007837283,0.0001031574,0.990684,0.0001084012,0.00002095529,0.0000298659,0.00004924332,0.0008926305,0.000274448],"genre_scores_gemma":[0.2696874,0.0002905718,0.7245209,0.0002902478,0.0001625747,0.0003723666,0.001453281,0.000359377,0.002863297],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002770897,"threshold_uncertainty_score":0.0146541,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3034672496","doi":"","title":"Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Adversarial system; Computer science; Invariant (physics); Sensitivity (control systems); Artificial intelligence; Robustness (evolution); Class (philosophy); Machine learning; Theoretical computer science; Mathematics","authors":[{"name":"Florian Tramèr","is_ca":false},{"name":"Jens Behrmann","is_ca":false},{"name":"Nicholas Carlini","is_ca":false},{"name":"Nicolas Papernot","is_ca":true},{"name":"Joern-Henrik Jacobsen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06015761417466957,"gpt":0.297905287486453,"spread":0.2377476733117834,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01358345,0.001697897,0.001143346,0.0008600819,0.0008563632,0.002664463,0.00264255,0.002756579,0.002193448],"category_scores_gemma":[0.08327256,0.0009040793,0.001075007,0.000496593,0.006087805,0.006152884,0.006072308,0.006503093,0.0005203863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001669867,"about_ca_system_score_gemma":0.0008832967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004090682,"about_ca_topic_score_gemma":0.0003489185,"domain_scores_codex":[0.9875832,0.005193582,0.0006093323,0.002026681,0.003720535,0.000866589],"domain_scores_gemma":[0.9171763,0.05771631,0.004501977,0.01741936,0.002132424,0.001053643],"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":[0.0004284055,0.0001923804,0.004060602,0.0002482032,0.0001839095,0.0004433261,0.0004579003,0.5643301,0.02372356,0.3429634,0.00257529,0.06039296],"study_design_scores_gemma":[0.00003825214,0.0003091987,0.001133386,0.00008278932,0.00004478308,0.0004508888,0.00008764007,0.6697973,0.0129172,0.3131266,0.001955549,0.00005641285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06984034,0.0005690632,0.9146304,0.003045439,0.0001140689,0.0001570876,0.0001475433,0.0007990791,0.01069714],"genre_scores_gemma":[0.9324486,0.000419843,0.06419825,0.0005673394,0.000156584,0.0002059161,0.0001481513,0.0001796522,0.001675616],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01358345,"threshold_uncertainty_score":0.07183701,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3034917202","doi":"","title":"On Variational Learning of Controllable Representations for Text without Supervision","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Autoencoder; Computer science; Unsupervised learning; Artificial intelligence; Decoding methods; Space (punctuation); Encoding (memory); Simplex; Sequence (biology); Latent variable; Machine learning; Deep learning; Algorithm; Mathematics","authors":[{"name":"Peng Xu","is_ca":false},{"name":"Jackie Chi Kit Cheung","is_ca":true},{"name":"Yanshuai Cao","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04101088640936427,"gpt":0.3026475110613343,"spread":0.26163662465197,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001294628,0.001033039,0.0008319074,0.000525652,0.0004226251,0.0008271868,0.001350951,0.001345798,0.00293584],"category_scores_gemma":[0.006149759,0.0006922206,0.0008547649,0.0005309148,0.001850767,0.001881495,0.001614147,0.002330346,0.000625035],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001049071,"about_ca_system_score_gemma":0.0009089898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003880935,"about_ca_topic_score_gemma":0.005297554,"domain_scores_codex":[0.9994417,0.0002218932,0.00002324182,0.0001645668,0.00009239154,0.00005630384],"domain_scores_gemma":[0.9973797,0.001941322,0.000166953,0.0002706003,0.0001501531,0.00009140465],"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":[0.0000778118,0.00005203352,0.0005090853,0.00007923382,0.00004195422,0.00007936451,0.0001404063,0.8959621,0.00352985,0.04881119,0.002009115,0.04870781],"study_design_scores_gemma":[0.000004543129,0.00001088382,0.00003229776,0.000004388796,0.000001762859,0.000007258224,0.000004233414,0.9857428,0.0003904701,0.01356022,0.0002376332,0.00000352163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01270205,0.0001649233,0.9848968,0.0002453169,0.00002784096,0.00003566375,0.0001022035,0.0003924257,0.001432888],"genre_scores_gemma":[0.7362354,0.0004712056,0.2475663,0.0005146468,0.00016652,0.0003912109,0.0009389121,0.0006334956,0.0130823],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003880935,"threshold_uncertainty_score":0.009821296,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3167967639","doi":"","title":"LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs","year":2021,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Topic Modeling","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Google (Canada); University of Alberta","funders":"","keywords":"Computer science; Question answering; Knowledge graph; Hop (telecommunications); Natural language processing; Artificial intelligence; Computer network","authors":[{"name":"Hongyu Ren","is_ca":false},{"name":"Hanjun Dai","is_ca":false},{"name":"Bo Dai","is_ca":false},{"name":"Xinyun Chen","is_ca":false},{"name":"Michihiro Yasunaga","is_ca":false},{"name":"Haitian Sun","is_ca":false},{"name":"Dale Schuurmans","is_ca":true},{"name":"Jure Leskovec","is_ca":false},{"name":"Denny Zhou","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08323708750218646,"gpt":0.3583986716908126,"spread":0.2751615841886262,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001781271,0.001967999,0.001332373,0.00255164,0.001124381,0.003298455,0.003312114,0.002236361,0.01465998],"category_scores_gemma":[0.009394085,0.001013056,0.002844297,0.001510385,0.001096754,0.005954714,0.005066518,0.003060741,0.004039806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001402124,"about_ca_system_score_gemma":0.002015936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01056524,"about_ca_topic_score_gemma":0.02312426,"domain_scores_codex":[0.9982174,0.0005863425,0.0001101601,0.0004786583,0.0004403316,0.0001670416],"domain_scores_gemma":[0.9959777,0.00263644,0.0001557459,0.0008173229,0.0002673301,0.0001454211],"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":[0.001612589,0.0009372862,0.004189725,0.001749239,0.0006011173,0.0008021699,0.001474806,0.1243337,0.01571962,0.09183411,0.1057148,0.6510309],"study_design_scores_gemma":[0.0001459494,0.00007671155,0.0003496112,0.00008384437,0.0001020554,0.00007383711,0.0001869171,0.8627472,0.004283352,0.1198888,0.01202237,0.00003941049],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009475557,0.0004785687,0.918133,0.0006091434,0.0001310165,0.00031829,0.004808764,0.06302729,0.003018327],"genre_scores_gemma":[0.2033065,0.000361783,0.7703645,0.0005279301,0.0001033794,0.0004032013,0.01658212,0.003286519,0.00506415],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01465998,"threshold_uncertainty_score":0.04904246,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W55051199","doi":"","title":"True Online TD(lambda)","year":2014,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Lambda; Computer science; Physics; Optics","authors":[{"name":"Harm van Seijen","is_ca":true},{"name":"Rich Sutton","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03161988976831424,"gpt":0.3009143998948404,"spread":0.2692945101265262,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00293843,0.001132889,0.001160873,0.0009524667,0.001435607,0.004514271,0.003705073,0.002241945,0.06546439],"category_scores_gemma":[0.01425935,0.0007760614,0.001158743,0.0009846404,0.001421909,0.007520533,0.005510283,0.003696846,0.02142533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001476622,"about_ca_system_score_gemma":0.003981268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003407289,"about_ca_topic_score_gemma":0.005920179,"domain_scores_codex":[0.9961008,0.0007351692,0.000232448,0.001039933,0.00119328,0.000698378],"domain_scores_gemma":[0.9895324,0.003276883,0.000261799,0.00420328,0.00223355,0.0004921164],"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":[0.003096503,0.0007079602,0.004318062,0.000904103,0.0001730059,0.0006922617,0.0004776136,0.01085608,0.01659901,0.1692294,0.1795007,0.6134454],"study_design_scores_gemma":[0.0004066948,0.0003696866,0.001596426,0.0001247846,0.00020577,0.001245169,0.0004663308,0.2278276,0.03627081,0.6288717,0.1024752,0.0001398986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02251971,0.0004086347,0.8910832,0.002748791,0.001764435,0.0001611052,0.003831724,0.03509402,0.04238834],"genre_scores_gemma":[0.4690089,0.0002958584,0.4229889,0.002712505,0.000688547,0.0003201791,0.005585814,0.007177689,0.09122171],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.06546439,"threshold_uncertainty_score":0.2190002,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963827215","doi":"","title":"Differentiable Compositional Kernel Learning for Gaussian Processes","year":2018,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":29,"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":"Kernel (algebra); Extrapolation; Differentiable function; Generalization; Computer science; Artificial intelligence; Artificial neural network; Gaussian process; Mathematics; Gaussian; Algorithm; Pattern recognition (psychology); Discrete mathematics; Statistics; Pure mathematics; Mathematical analysis","authors":[{"name":"Shengyang Sun","is_ca":true},{"name":"Guodong Zhang","is_ca":false},{"name":"Chaoqi Wang","is_ca":false},{"name":"Wenyuan Zeng","is_ca":true},{"name":"Jiaman Li","is_ca":true},{"name":"Roger Grosse","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02641541766885436,"gpt":0.2961644482254642,"spread":0.2697490305566098,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001676011,0.0006272974,0.000700415,0.0006312861,0.000393779,0.001044624,0.0009328995,0.0009794029,0.001747789],"category_scores_gemma":[0.009560085,0.0003389803,0.0007101342,0.0006232265,0.001222655,0.002199874,0.001680842,0.00199192,0.0005057763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001158986,"about_ca_system_score_gemma":0.0009292579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003221412,"about_ca_topic_score_gemma":0.003172393,"domain_scores_codex":[0.9994549,0.0001881244,0.00002578129,0.000134056,0.0001460682,0.00005109098],"domain_scores_gemma":[0.9982411,0.0009364575,0.0001544555,0.0003083205,0.0002682347,0.00009147837],"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":[0.0001107067,0.00005293097,0.001561013,0.0001301948,0.00004760261,0.00009577424,0.0001687353,0.5966153,0.005162572,0.2826063,0.001518363,0.1119305],"study_design_scores_gemma":[0.000002164832,0.00000613923,0.00009612268,0.000003938478,0.000002135233,0.000009266203,0.000003858244,0.9520828,0.0003202507,0.04722154,0.0002483735,0.000003382195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01158667,0.0001810232,0.9870733,0.0001522767,0.00001223543,0.00001187632,0.00003145682,0.0001784444,0.0007726814],"genre_scores_gemma":[0.6905538,0.0008001732,0.3036909,0.0001562563,0.00007149906,0.0001015554,0.0003362206,0.0001854889,0.004104045],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003221412,"threshold_uncertainty_score":0.008863688,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3094623068","doi":"","title":"How to Train Your Neural ODE: the World of Jacobian and Kinetic Regularization","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":29,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; McGill University","funders":"","keywords":"Ode; Solver; Regularization (linguistics); Jacobian matrix and determinant; Artificial neural network; Computer science; Convergence (economics); Applied mathematics; Stability (learning theory); Mathematical optimization; Mathematics; Artificial intelligence; Machine learning","authors":[{"name":"Chris Finlay","is_ca":true},{"name":"Jörn-Henrik Jacobsen","is_ca":true},{"name":"Levon Nurbekyan","is_ca":false},{"name":"Adam M. Oberman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04947007862184124,"gpt":0.2891593166532649,"spread":0.2396892380314237,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001391036,0.0005624608,0.0006689089,0.0003531237,0.0005418871,0.001262745,0.0009970081,0.001591629,0.004064054],"category_scores_gemma":[0.008885714,0.0006031236,0.0006086041,0.0003532142,0.001572322,0.003298905,0.001439036,0.003233715,0.001268277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000771934,"about_ca_system_score_gemma":0.001173149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005649511,"about_ca_topic_score_gemma":0.005821839,"domain_scores_codex":[0.9997104,0.0001024709,0.00001815314,0.00007164659,0.00007199364,0.00002541385],"domain_scores_gemma":[0.9987457,0.0007534302,0.00009914345,0.0001908173,0.0001313063,0.0000795832],"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":[0.00004897892,0.0000360489,0.001305795,0.0001810012,0.00006225325,0.0001059013,0.0001179814,0.7791281,0.003305877,0.1443604,0.009837835,0.06150979],"study_design_scores_gemma":[0.000008693652,0.000009077505,0.00009839486,0.00002237794,0.000005325068,0.00002463752,0.00001312505,0.9380975,0.0008438751,0.05820223,0.002663625,0.00001110102],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01459091,0.0005436443,0.9752427,0.003769994,0.0002055296,0.00002953166,0.0002052188,0.0008858704,0.004526575],"genre_scores_gemma":[0.3541695,0.001504062,0.6281974,0.001296554,0.0002395985,0.0002298253,0.0004608608,0.001372374,0.01252974],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005649511,"threshold_uncertainty_score":0.01359564,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2953418083","doi":"","title":"Compositional Fairness Constraints for Graph Embeddings","year":2019,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":28,"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":"Computer science; Adversarial system; Social graph; Recommender system; Theoretical computer science; Inference; Graph; Embedding; Knowledge graph; Machine learning; Artificial intelligence; World Wide Web; Social media","authors":[{"name":"Avishek Joey Bose","is_ca":true},{"name":"William L. Hamilton","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05734558416610852,"gpt":0.3996761543348702,"spread":0.3423305701687617,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008132136,0.001345047,0.0011852,0.001248389,0.001449287,0.002725916,0.002656283,0.002168966,0.004951586],"category_scores_gemma":[0.06218099,0.0007821085,0.001103163,0.001263395,0.002622416,0.009043214,0.004680683,0.004661809,0.0009968845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002310874,"about_ca_system_score_gemma":0.002408301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003042661,"about_ca_topic_score_gemma":0.004381413,"domain_scores_codex":[0.9924296,0.003008212,0.0004853064,0.001929378,0.00168176,0.0004658048],"domain_scores_gemma":[0.9713057,0.01671162,0.002285278,0.006034803,0.002689464,0.0009731418],"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":[0.0002159269,0.0001429251,0.002501623,0.0002176261,0.00006552466,0.0001978649,0.0004002325,0.4320611,0.002542292,0.4883206,0.004247339,0.06908685],"study_design_scores_gemma":[0.00001835109,0.00003511138,0.000224788,0.00003146809,0.00001056141,0.00005263735,0.00003953247,0.5725344,0.001221637,0.4239754,0.001841407,0.00001476457],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01275584,0.0001821335,0.9835734,0.0007154217,0.00006124099,0.00008262462,0.0003562733,0.0003051727,0.001967893],"genre_scores_gemma":[0.6925181,0.0005413974,0.2963709,0.0008585175,0.0002597944,0.0005372076,0.001423707,0.0004460285,0.007044413],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008132136,"threshold_uncertainty_score":0.04300731,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W75509695","doi":"","title":"A new Q(lambda) with interim forward view and Monte Carlo equivalence","year":2014,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Monte Carlo method; Markov decision process; Algorithm; Equivalence (formal languages); Q-learning; Markov process; Mathematical optimization; Artificial intelligence; Mathematics; Discrete mathematics; Statistics","authors":[{"name":"Rich Sutton","is_ca":true},{"name":"Ashique Rupam Mahmood","is_ca":true},{"name":"Doina Precup","is_ca":true},{"name":"Hado van Hasselt","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03106032801753098,"gpt":0.2875444306336761,"spread":0.2564841026161451,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004033861,0.0009085628,0.001027834,0.001235736,0.0009097232,0.002349419,0.00318773,0.002255155,0.008540301],"category_scores_gemma":[0.01565116,0.0007992766,0.001659164,0.00117818,0.00358259,0.005100776,0.00490481,0.006115992,0.001622458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002242083,"about_ca_system_score_gemma":0.004008454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002863303,"about_ca_topic_score_gemma":0.002443943,"domain_scores_codex":[0.997184,0.0006243773,0.000197989,0.0006789151,0.001065073,0.0002495894],"domain_scores_gemma":[0.9951552,0.002065701,0.0003150362,0.0007068469,0.00134324,0.0004139411],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002883132,0.00006585904,0.0005647421,0.0001008833,0.00002934092,0.0001068355,0.0001546259,0.05419681,0.001751577,0.8992248,0.003379408,0.0403963],"study_design_scores_gemma":[0.00002720652,0.00007208112,0.0001914375,0.00004479381,0.00001647602,0.0001402528,0.00001992135,0.5310973,0.001167625,0.4563861,0.01080196,0.0000349205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001721766,0.0001050673,0.9925323,0.0003077997,0.0001019426,0.00003712395,0.00005566178,0.0001096484,0.005028783],"genre_scores_gemma":[0.1502254,0.0004808038,0.8360615,0.0009286797,0.000411275,0.0003364732,0.0002015881,0.0004968784,0.01085741],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008540301,"threshold_uncertainty_score":0.02857018,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963558557","doi":"","title":"A Spectral Approach to Gradient Estimation for Implicit Distributions.","year":2018,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Groundwater flow and contamination studies","field":"Environmental Science","cited_by":26,"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":"Estimator; Applied mathematics; Mathematics; Inference; Kernel (algebra); Computer science; Algorithm; Mathematical optimization; Artificial intelligence; Statistics","authors":[{"name":"Jiaxin Shi","is_ca":false},{"name":"Shengyang Sun","is_ca":true},{"name":"Jun Zhu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02879580352621477,"gpt":0.2923980745180018,"spread":0.2636022709917871,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004080893,0.001086249,0.000893463,0.001572014,0.0006421201,0.001399831,0.001742032,0.001692253,0.002666067],"category_scores_gemma":[0.02148052,0.000847441,0.001067028,0.001028175,0.002539761,0.003316439,0.002894406,0.003244831,0.0007990489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001041376,"about_ca_system_score_gemma":0.001654213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00245634,"about_ca_topic_score_gemma":0.002901198,"domain_scores_codex":[0.9983749,0.0008595975,0.00006593482,0.0002304912,0.0003883343,0.00008061725],"domain_scores_gemma":[0.9940355,0.004188409,0.0004206745,0.0005523956,0.0006022836,0.0002006532],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000547693,0.00009677673,0.00127813,0.0002432004,0.0001092626,0.0001209706,0.0002159514,0.3102138,0.003589323,0.6000942,0.003534395,0.08044923],"study_design_scores_gemma":[0.000008081009,0.00001893909,0.000148265,0.00002277618,0.000008330398,0.00005051671,0.00001425334,0.8584362,0.0006208141,0.1386103,0.002046108,0.00001538196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005758054,0.00007419389,0.9989196,0.00007771858,0.00001706314,0.00001216253,0.00001225167,0.00004438025,0.000266813],"genre_scores_gemma":[0.1501921,0.0008265426,0.8430253,0.0003853767,0.000267284,0.0003022603,0.0002298299,0.0002376868,0.004533615],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004080893,"threshold_uncertainty_score":0.02158207,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964278219","doi":"","title":"Thompson Sampling for Combinatorial Semi-Bandits.","year":2018,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Thompson sampling; Matroid; Oracle; Sampling (signal processing); Mathematics; Mathematical optimization; Independence (probability theory); Computer science; Combinatorics; Statistics","authors":[{"name":"Siwei Wang","is_ca":false},{"name":"Wei Chen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2722630354409833,"gpt":0.5115727209194741,"spread":0.2393096854784908,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004932829,0.001329104,0.001772542,0.001130018,0.000840617,0.001929459,0.001966929,0.001775364,0.005039861],"category_scores_gemma":[0.02216731,0.0007568907,0.001262768,0.001627303,0.002033267,0.002528863,0.001469856,0.002433606,0.0007680389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00219685,"about_ca_system_score_gemma":0.001504463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003290706,"about_ca_topic_score_gemma":0.003993835,"domain_scores_codex":[0.9973229,0.00171204,0.00009048361,0.0003019925,0.0003860582,0.0001865938],"domain_scores_gemma":[0.9865588,0.01099243,0.0008407296,0.0008237517,0.0004154668,0.0003687042],"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":[0.0002277232,0.000116461,0.001390554,0.0001910553,0.0001119666,0.0001210758,0.00008628379,0.6585526,0.0008958898,0.3043033,0.002969212,0.03103388],"study_design_scores_gemma":[0.0000189951,0.0000287394,0.00008692448,0.00001424134,0.000009335402,0.00001923344,0.000008611239,0.9270403,0.0001964904,0.07195295,0.0006186052,0.000005671583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01752963,0.0007974888,0.9756141,0.0004623926,0.00009966984,0.0001342912,0.00009075631,0.0003003188,0.004971364],"genre_scores_gemma":[0.6492397,0.001086427,0.340095,0.0006281554,0.0002901192,0.00072301,0.0004263252,0.0002383651,0.007272953],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005039861,"threshold_uncertainty_score":0.02608764,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963408680","doi":"","title":"DVAE++: Discrete Variational Autoencoders with Overlapping Transformations","year":2018,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"D-Wave Systems (Canada)","funders":"","keywords":"Latent variable; Prior probability; Transformation (genetics); Softmax function; Smoothing; Computer science; Artificial intelligence; Algorithm; Mathematics; Applied mathematics; Convolutional neural network; Statistics; Bayesian probability","authors":[{"name":"Arash Vahdat","is_ca":true},{"name":"William G. Macready","is_ca":true},{"name":"Zhengbing Bian","is_ca":true},{"name":"Amir H. Khoshaman","is_ca":true},{"name":"Evgeny Andriyash","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02068640998251981,"gpt":0.2663003432703145,"spread":0.2456139332877947,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001355131,0.001009103,0.0009119992,0.0004194915,0.0003399254,0.001036863,0.002191516,0.001306448,0.003941245],"category_scores_gemma":[0.00453036,0.0007768964,0.0008807061,0.0005202605,0.001191476,0.002204893,0.002851178,0.003408583,0.001131072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008540086,"about_ca_system_score_gemma":0.0009380816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002958534,"about_ca_topic_score_gemma":0.005609837,"domain_scores_codex":[0.9992884,0.0002457167,0.00003343547,0.0001913569,0.0001703603,0.00007060462],"domain_scores_gemma":[0.9988,0.000696722,0.00007965451,0.0002347282,0.0001157095,0.00007315576],"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":[0.00008354191,0.00006658446,0.0007040015,0.00006847001,0.00006237131,0.00006567569,0.00009752771,0.8006102,0.004667386,0.08688087,0.002833804,0.1038596],"study_design_scores_gemma":[0.000005198982,0.000009903773,0.00003517151,0.000004601424,0.000002785002,0.00001308685,0.000003158163,0.9857138,0.0006072481,0.01287924,0.0007223031,0.000003531434],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004544963,0.0001108746,0.9936519,0.0001075872,0.00001899875,0.00001843439,0.00005043488,0.0004026988,0.001093985],"genre_scores_gemma":[0.4706727,0.0003747644,0.5154199,0.0005463081,0.0000791883,0.000332263,0.0006608667,0.000754151,0.01115995],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003941245,"threshold_uncertainty_score":0.01318473,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3169514089","doi":"","title":"EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL","year":2021,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":22,"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 Alberta; University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Backup; Heuristic; Operator (biology); Online and offline; Offline learning; Simple (philosophy); Artificial intelligence; Generative grammar; Machine learning; Mathematical optimization; Theoretical computer science; Online learning; Mathematics","authors":[{"name":"Seyed Kamyar Seyed Ghasemipour","is_ca":true},{"name":"Dale Schuurmans","is_ca":true},{"name":"Shixiang Gu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02841059612818234,"gpt":0.3196032698915692,"spread":0.2911926737633869,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00519968,0.001784533,0.001647938,0.0006282674,0.0006117325,0.001588781,0.004013773,0.00255204,0.01185209],"category_scores_gemma":[0.01789861,0.0006401663,0.0008578414,0.0007644854,0.00212092,0.002434457,0.004369552,0.004751676,0.002920569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001341384,"about_ca_system_score_gemma":0.002941414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002713011,"about_ca_topic_score_gemma":0.002770605,"domain_scores_codex":[0.9972796,0.001078184,0.0001622859,0.0005566647,0.0006657904,0.000257505],"domain_scores_gemma":[0.9943389,0.00382862,0.0002916221,0.0006943003,0.0005669346,0.0002796095],"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":[0.0004390183,0.0002848199,0.0009984175,0.0003378948,0.00005927193,0.0001536268,0.0002366032,0.5414227,0.002920643,0.1123015,0.01171898,0.3291266],"study_design_scores_gemma":[0.00003057528,0.00005913452,0.00004363084,0.00001592364,0.000003887955,0.00002810892,0.00001226916,0.9673505,0.00069554,0.0302862,0.001466506,0.000007798892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00203276,0.0001100713,0.9949514,0.0002073676,0.00004496626,0.00007740357,0.00004327358,0.0009606149,0.001572205],"genre_scores_gemma":[0.267275,0.0002583769,0.7238627,0.0007274397,0.0001481128,0.0006653057,0.0003626652,0.0007105201,0.005989853],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01185209,"threshold_uncertainty_score":0.03964919,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3034890132","doi":"","title":"Few-shot Relation Extraction via Bayesian Meta-learning on Task Graphs","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Topic Modeling","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"HEC Montréal; Université de Montréal","funders":"","keywords":"Relationship extraction; Computer science; Leverage (statistics); Parameterized complexity; Relation (database); Artificial intelligence; Bayesian probability; Graph; Machine learning; Theoretical computer science; Algorithm; Data mining","authors":[{"name":"Meng Qu","is_ca":false},{"name":"Tianyu Gao","is_ca":false},{"name":"Louis-Pascal Xhonneux","is_ca":true},{"name":"Jian Tang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08655251143981235,"gpt":0.3171795000600261,"spread":0.2306269886202137,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001875825,0.002266884,0.002221677,0.002818285,0.001046458,0.00191146,0.004636619,0.002525367,0.002634889],"category_scores_gemma":[0.007531204,0.001447567,0.002068867,0.002801023,0.001163887,0.00682424,0.002708721,0.003092628,0.001810086],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001366177,"about_ca_system_score_gemma":0.001407174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004759566,"about_ca_topic_score_gemma":0.01070057,"domain_scores_codex":[0.9979053,0.0005898841,0.0001030587,0.00089626,0.0003636877,0.0001419067],"domain_scores_gemma":[0.9969082,0.001813338,0.000244077,0.0006255217,0.0002813599,0.0001273931],"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":[0.0004982962,0.000484973,0.003084904,0.0007033962,0.0003748707,0.0007230517,0.0006832241,0.3839924,0.01322567,0.0289941,0.01603499,0.5512002],"study_design_scores_gemma":[0.00001495351,0.00003763705,0.0003320503,0.00002469238,0.00003641905,0.0000921485,0.00004294312,0.9459655,0.002383542,0.04928659,0.00176314,0.0000203657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01458752,0.0009291585,0.9793158,0.0003615677,0.00005335945,0.00009749582,0.0005715886,0.002909576,0.001173942],"genre_scores_gemma":[0.4941717,0.000913871,0.4899543,0.0008344452,0.000203947,0.0004346452,0.006250672,0.0007967323,0.006439794],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004759566,"threshold_uncertainty_score":0.009920418,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2962807943","doi":"","title":"Adaptive Consensus ADMM for Distributed Optimization","year":2017,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Node (physics); Computer science; Convergence (economics); Reliability (semiconductor); Rate of convergence; Mathematical optimization; Mathematics; Key (lock); Engineering","authors":[{"name":"Zheng Xu","is_ca":false},{"name":"Gavin Taylor","is_ca":false},{"name":"Hao Li","is_ca":false},{"name":"Mário A. T. Figueiredo","is_ca":false},{"name":"Xiaoming Yuan","is_ca":true},{"name":"Tom Goldstein","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05713070033778866,"gpt":0.328165303351882,"spread":0.2710346030140934,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001587569,0.001288135,0.001291705,0.0005540174,0.0005427664,0.0008753234,0.001933164,0.001652492,0.003268487],"category_scores_gemma":[0.004996796,0.0005369459,0.0008749398,0.001049085,0.001118021,0.001293514,0.001649866,0.002968599,0.001169768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007798883,"about_ca_system_score_gemma":0.001550218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002164317,"about_ca_topic_score_gemma":0.001892484,"domain_scores_codex":[0.9988795,0.0003527434,0.00006112885,0.0003057165,0.0003425829,0.00005837779],"domain_scores_gemma":[0.998282,0.0007975092,0.0001764417,0.0002955476,0.0003891564,0.00005942911],"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":[0.00005933169,0.00003448044,0.000207749,0.0001918839,0.00006593098,0.00007870305,0.00005728172,0.864855,0.003291459,0.05284027,0.006667232,0.07165077],"study_design_scores_gemma":[0.00001486389,0.0000148243,0.00003100508,0.000006911456,0.000004604541,0.00001944876,0.000004156398,0.9785672,0.000555102,0.01867148,0.002104347,0.000006044236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005127941,0.0001106213,0.9983855,0.00008342124,0.00003818188,0.00001144896,0.00001999053,0.0001754304,0.0006625235],"genre_scores_gemma":[0.1548609,0.0006632758,0.8363083,0.0002961957,0.0002481538,0.0004231193,0.0003894947,0.0002780644,0.006532514],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003268487,"threshold_uncertainty_score":0.01093417,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W65834064","doi":"","title":"Clustering in the Presence of Background Noise","year":2014,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":21,"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":"Cluster analysis; Robustness (evolution); Computer science; Centroid; CURE data clustering algorithm; Data mining; Cluster (spacecraft); Correlation clustering; Noise (video); Algorithm; Constrained clustering; Canopy clustering algorithm; Artificial intelligence","authors":[{"name":"Shai Ben-David","is_ca":true},{"name":"Nika Haghtalab","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05514190194778961,"gpt":0.3496198438620368,"spread":0.2944779419142471,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004129744,0.001031538,0.001637158,0.002003177,0.001272175,0.002405033,0.002741913,0.003290189,0.0008545992],"category_scores_gemma":[0.01879292,0.0006234635,0.001051129,0.00223934,0.002542645,0.002818809,0.002557754,0.002114758,0.0008906404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001448125,"about_ca_system_score_gemma":0.000981695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002632922,"about_ca_topic_score_gemma":0.001687512,"domain_scores_codex":[0.996107,0.001108161,0.0001436045,0.001080422,0.001238547,0.0003223372],"domain_scores_gemma":[0.9908144,0.004877975,0.000959158,0.001603419,0.001452754,0.0002922715],"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":[0.0003224218,0.00006073327,0.001726049,0.0002743067,0.0001581599,0.0004404297,0.0004015601,0.8401367,0.02206445,0.08893355,0.00223116,0.04325052],"study_design_scores_gemma":[0.00001009902,0.00003542747,0.0004809757,0.00001343983,0.00001777712,0.00008351672,0.00003962398,0.9554898,0.006364023,0.03571974,0.001724733,0.0000208704],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0187929,0.0002743641,0.9791661,0.0002937726,0.00005068846,0.00002780159,0.00007411163,0.0002605887,0.001059655],"genre_scores_gemma":[0.5211476,0.0008205532,0.470755,0.0004326499,0.0003009391,0.0001440664,0.0005987766,0.0003528456,0.005447545],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004129744,"threshold_uncertainty_score":0.02184039,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3094191864","doi":"","title":"Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial neural network; Sampling (signal processing); Function (biology); Artificial intelligence; Training set; Goodness of fit; Energy (signal processing); Feature (linguistics); Data modeling; Machine learning; Algorithm; Mathematics; Statistics","authors":[{"name":"Will Grathwohl","is_ca":true},{"name":"Kuan-Chieh Wang","is_ca":true},{"name":"Jörn-Henrik Jacobsen","is_ca":true},{"name":"David Duvenaud","is_ca":true},{"name":"Richard S. Zemel","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1657884621947862,"gpt":0.3439734482612751,"spread":0.1781849860664889,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01018314,0.002149267,0.001954277,0.001854222,0.0007561784,0.001811189,0.003236569,0.002893368,0.00255969],"category_scores_gemma":[0.03633792,0.001317468,0.001247348,0.0008957807,0.002965598,0.003571798,0.004496584,0.003422198,0.0009525887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002356217,"about_ca_system_score_gemma":0.002243287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004896789,"about_ca_topic_score_gemma":0.004991476,"domain_scores_codex":[0.9969527,0.001518282,0.0001746152,0.0004275175,0.0007732717,0.0001536246],"domain_scores_gemma":[0.9876769,0.008433718,0.0007726018,0.001578209,0.001142304,0.0003963492],"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":[0.0001361935,0.00006555072,0.001556586,0.00008314681,0.00007731324,0.00005415726,0.00006503888,0.9307723,0.001877578,0.02195151,0.001013471,0.04234715],"study_design_scores_gemma":[0.000004128379,0.0000204498,0.00004759235,0.000006426474,0.000002406226,0.00001104706,0.000003585078,0.9934729,0.0005301055,0.005767859,0.0001284784,0.000005113654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009616638,0.000130803,0.9888243,0.0001429365,0.00002362578,0.00003202457,0.00003853363,0.0005712544,0.0006198384],"genre_scores_gemma":[0.4605633,0.0002973338,0.5340109,0.000430449,0.00009854039,0.0003924169,0.0006745735,0.000806965,0.002725533],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01018314,"threshold_uncertainty_score":0.05385423,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}