{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":80,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":80,"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":"0738d2126206","filters":{"venue":"International Conference on Learning Representations"}},"results":[{"id":"W2753160622","doi":"","title":"Optimization as a Model for Few-Shot Learning","year":2017,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":2447,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Initialization; Artificial intelligence; Meta learning (computer science); Convergence (economics); Deep learning; Metric (unit); Artificial neural network; Machine learning; Set (abstract data type); Parametrization (atmospheric modeling); Competitive learning; Class (philosophy); Domain (mathematical analysis); Learning to learn; Mathematics; Task (project management)","authors":[{"name":"Sachin Ravi","is_ca":false},{"name":"Hugo Larochelle","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1464190826716082,"gpt":0.4031299499396052,"spread":0.256710867267997,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001901442,0.0008942978,0.001318608,0.0006107751,0.0003196266,0.001171945,0.002555717,0.002153632,0.002913608],"category_scores_gemma":[0.007025933,0.0007728736,0.0008584511,0.0007377417,0.001266599,0.003090303,0.001624269,0.002981436,0.0008467239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001191148,"about_ca_system_score_gemma":0.0007870852,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002538208,"about_ca_topic_score_gemma":0.002673791,"domain_scores_codex":[0.9992717,0.0002874014,0.00003836458,0.000212576,0.000136865,0.00005313938],"domain_scores_gemma":[0.9984187,0.0009721682,0.000149404,0.0002068142,0.0001768679,0.00007607006],"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":[0.0000462469,0.00004916178,0.0003427481,0.00008383829,0.00004078158,0.00005652731,0.00007226926,0.9091194,0.001284984,0.05894824,0.001693227,0.02826261],"study_design_scores_gemma":[0.00000257691,0.00001084746,0.00002769922,0.00000397814,0.000002392973,0.00001011354,0.000002427483,0.9815996,0.0001928304,0.01788431,0.0002596143,0.000003674584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007179576,0.0003005234,0.9908673,0.0003162681,0.00002872986,0.00002963173,0.00006999094,0.0002942729,0.0009137065],"genre_scores_gemma":[0.6653458,0.0008450198,0.3190186,0.000605992,0.0001861584,0.0005774629,0.0006336666,0.0003914734,0.01239582],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002913608,"threshold_uncertainty_score":0.01005596,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964335273","doi":"","title":"How to Construct Deep Recurrent Neural Networks","year":2014,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Music and Audio Processing","field":"Computer Science","cited_by":582,"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":"Recurrent neural network; Computer science; Deep learning; Artificial intelligence; Construct (python library); Feedforward neural network; Feed forward; Function (biology); Artificial neural network; Engineering","authors":[{"name":"Razvan Pascanu","is_ca":true},{"name":"Çağlar Gülçehre","is_ca":true},{"name":"Kyunghyun Cho","is_ca":false},{"name":"Yoshua Bengio","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03925941227028947,"gpt":0.3147329136198822,"spread":0.2754735013495928,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009555257,0.0007502528,0.0005308024,0.0004996305,0.0002797953,0.0008316292,0.0009771748,0.000855897,0.003522978],"category_scores_gemma":[0.003507933,0.0004668619,0.0006068601,0.0003782953,0.0004477171,0.002041165,0.001095475,0.001319597,0.001234269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006235508,"about_ca_system_score_gemma":0.0006437092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002513854,"about_ca_topic_score_gemma":0.003824462,"domain_scores_codex":[0.9996511,0.00009173994,0.00002959805,0.00008572071,0.00009134743,0.00005053],"domain_scores_gemma":[0.999294,0.0002845119,0.00007163855,0.0001069882,0.0002038544,0.000039038],"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":[0.0001526227,0.00008483396,0.001986124,0.0002485861,0.0001356953,0.0002578394,0.0001821272,0.5345149,0.01976183,0.0723472,0.007049818,0.3632784],"study_design_scores_gemma":[0.000006741291,0.00002388981,0.0001026934,0.00002262358,0.00001340801,0.0000251038,0.00001319272,0.9756703,0.003336464,0.01892612,0.001852758,0.000006822947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01153755,0.0002303031,0.9848915,0.0002966361,0.0000651156,0.00002951292,0.00007707856,0.0009579756,0.001914173],"genre_scores_gemma":[0.3857969,0.0004550605,0.6073133,0.0003603858,0.00007968955,0.0001317726,0.0004112747,0.0003028155,0.005148723],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003522978,"threshold_uncertainty_score":0.01178557,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963386218","doi":"","title":"A Structured Self-Attentive Sentence Embedding.","year":2017,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Topic Modeling","field":"Computer Science","cited_by":365,"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":"Embedding; Sentence; Computer science; Natural language processing; Artificial intelligence; Logical consequence; Regularization (linguistics)","authors":[{"name":"Zhouhan Lin","is_ca":true},{"name":"Minwei Feng","is_ca":false},{"name":"Cícero Nogueira dos Santos","is_ca":false},{"name":"Mo Yu","is_ca":false},{"name":"Bing Xiang","is_ca":false},{"name":"Bowen Zhou","is_ca":false},{"name":"Yoshua Bengio","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05458417324847135,"gpt":0.3661503131841141,"spread":0.3115661399356427,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003845097,0.0006732736,0.0002888856,0.0006852043,0.0001572627,0.0005433972,0.0007281756,0.0006773546,0.003148202],"category_scores_gemma":[0.002068233,0.0002517008,0.0006085125,0.0004781448,0.0002613376,0.001856121,0.0006495633,0.0009040961,0.001371495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003150561,"about_ca_system_score_gemma":0.0003484404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001136549,"about_ca_topic_score_gemma":0.002111012,"domain_scores_codex":[0.9997467,0.00008131277,0.00001530225,0.00009648712,0.00004354144,0.00001665401],"domain_scores_gemma":[0.9995179,0.0001960093,0.00006180477,0.00008805542,0.0001064485,0.00002973703],"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":[0.0003573731,0.0003777756,0.003369444,0.0006048552,0.0002235885,0.0003437334,0.0007884331,0.06386077,0.07697031,0.03943884,0.02919059,0.7844743],"study_design_scores_gemma":[0.00001504928,0.0001746299,0.001582196,0.00005433674,0.00006841644,0.0002339192,0.00007608756,0.9481597,0.01209261,0.02355309,0.01396075,0.00002914075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0269405,0.0008884918,0.9651569,0.0005855957,0.0003866068,0.0001306158,0.0009334377,0.001771541,0.003206329],"genre_scores_gemma":[0.5320228,0.001098548,0.4454457,0.0006175471,0.0004020461,0.0002968044,0.003976705,0.0003463911,0.01579355],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003148202,"threshold_uncertainty_score":0.01053178,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2901997113","doi":"","title":"Char2Wav: End-to-End Speech Synthesis","year":2017,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":335,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique; Université de Montréal","funders":"","keywords":"End-to-end principle; Computer science; Speech synthesis; Speech recognition; Artificial intelligence","authors":[{"name":"Jose Sotelo","is_ca":true},{"name":"Soroush Mehri","is_ca":false},{"name":"Kundan Kumar","is_ca":false},{"name":"João Felipe Santos","is_ca":true},{"name":"Kyle Kastner","is_ca":true},{"name":"Aaron Courville","is_ca":true},{"name":"Yoshua Bengio","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09295328918588806,"gpt":0.3624233461629727,"spread":0.2694700569770846,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007696985,0.002380631,0.001344818,0.0009871474,0.0005950771,0.001838972,0.002063848,0.001678493,0.05297149],"category_scores_gemma":[0.001656132,0.0007843404,0.001027733,0.0005160046,0.00041587,0.001226423,0.003241386,0.001686798,0.03085852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004670813,"about_ca_system_score_gemma":0.0007758544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001785834,"about_ca_topic_score_gemma":0.003682166,"domain_scores_codex":[0.9991267,0.0001022481,0.00004285313,0.0002398504,0.0003574851,0.0001309111],"domain_scores_gemma":[0.999571,0.0001198154,0.00001534092,0.0001375682,0.0001191975,0.00003703954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002556513,0.0003631441,0.0007032029,0.0005292566,0.0003034805,0.0007676902,0.0002095968,0.01737269,0.1290953,0.007819952,0.1241372,0.716142],"study_design_scores_gemma":[0.0005033736,0.0005182599,0.001299264,0.00008177346,0.00009213998,0.0008094392,0.0001558805,0.5206481,0.3414293,0.01542711,0.1188533,0.0001819944],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006284946,0.0002746154,0.7827226,0.00009152506,0.0005288473,0.0002219966,0.003220903,0.198645,0.008009537],"genre_scores_gemma":[0.1706071,0.0003033589,0.7261784,0.0005675092,0.0002184688,0.001055154,0.02347433,0.02619944,0.05139634],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05297149,"threshold_uncertainty_score":0.1772073,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2914442349","doi":"","title":"Multiple-Attribute Text Rewriting.","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":192,"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":"Rewriting; Computer science; Programming language; Natural language processing; Information retrieval","authors":[{"name":"Guillaume Lample","is_ca":false},{"name":"Sandeep Subramanian","is_ca":true},{"name":"Eric M. Smith","is_ca":false},{"name":"Ludovic Denoyer","is_ca":false},{"name":"Marc’Aurelio Ranzato","is_ca":false},{"name":"Y-Lan Boureau","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04690502205995051,"gpt":0.360655210535885,"spread":0.3137501884759345,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001967766,0.0007864202,0.0009265008,0.001216965,0.0008655207,0.002121876,0.001843467,0.0009564161,0.01395584],"category_scores_gemma":[0.0107684,0.0004197581,0.001349301,0.001403922,0.0008746064,0.00374673,0.002845957,0.002375012,0.007675766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008221274,"about_ca_system_score_gemma":0.00116045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001334336,"about_ca_topic_score_gemma":0.002827482,"domain_scores_codex":[0.9966171,0.001108684,0.0003906191,0.000799555,0.0008811556,0.0002028791],"domain_scores_gemma":[0.9933149,0.002466273,0.000261778,0.002632218,0.001141872,0.0001828933],"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":[0.0002463854,0.0003925762,0.001268596,0.001179531,0.000270682,0.0006714499,0.0009250637,0.01280617,0.02762377,0.2476604,0.1201694,0.586786],"study_design_scores_gemma":[0.00008240078,0.0001402808,0.0007814071,0.0001820516,0.0003016694,0.001079671,0.000463992,0.1561293,0.07024255,0.4956906,0.2748119,0.00009410986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01230159,0.001455055,0.9404904,0.001862641,0.001047913,0.0003174736,0.003634537,0.0144165,0.0244739],"genre_scores_gemma":[0.2707309,0.0009528874,0.6695504,0.001020769,0.0004827106,0.0002162384,0.01111062,0.003684599,0.04225086],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01395584,"threshold_uncertainty_score":0.04668689,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2751842161","doi":"","title":"Improving Generative Adversarial Networks with Denoising Feature Matching","year":2017,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":160,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Discriminator; Generator (circuit theory); Computer science; Artificial intelligence; Generative grammar; Set (abstract data type); Adversarial system; Pattern recognition (psychology); Feature (linguistics); Matching (statistics); Task (project management); Noise reduction; Encoder; Image (mathematics); Feature extraction; Machine learning; Mathematics; Power (physics); Engineering","authors":[{"name":"David Warde-Farley","is_ca":true},{"name":"Yoshua Bengio","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02734760063555377,"gpt":0.2982712933071036,"spread":0.2709236926715499,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002407143,0.001349981,0.001166653,0.0007421623,0.0003266076,0.0008914358,0.00178469,0.001626185,0.001896475],"category_scores_gemma":[0.006018437,0.0006192367,0.00078478,0.0005463114,0.001208151,0.001588823,0.002344155,0.001946297,0.0008145723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009225924,"about_ca_system_score_gemma":0.0006687686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002144806,"about_ca_topic_score_gemma":0.00234923,"domain_scores_codex":[0.9992203,0.0002666287,0.00002863736,0.0001637842,0.0002357858,0.00008496801],"domain_scores_gemma":[0.99797,0.001287586,0.0001686965,0.0003029977,0.000196394,0.00007420717],"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":[0.00008296089,0.00003993458,0.0005319241,0.00003506951,0.00004226203,0.00004526104,0.00004324844,0.9384275,0.004893792,0.01226597,0.0008935799,0.04269858],"study_design_scores_gemma":[0.000003209049,0.00001311681,0.0000327288,0.000002541449,0.000003010669,0.00001054217,0.000001921435,0.9953344,0.0008608238,0.003568968,0.0001660712,0.000002641593],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01361877,0.0001707255,0.9840059,0.0001410698,0.00002465651,0.00002162592,0.00003708476,0.0005225442,0.00145769],"genre_scores_gemma":[0.6921742,0.000263919,0.2987906,0.0005036416,0.00008825551,0.0001586949,0.0004942107,0.0004417403,0.007084726],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002407143,"threshold_uncertainty_score":0.01273036,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2785948534","doi":"","title":"NerveNet: Learning Structured Policy with Graph Neural Networks","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":155,"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":"Reinforcement learning; Concatenation (mathematics); Computer science; Transfer of learning; Artificial intelligence; Graph; Benchmarking; Machine learning; Artificial neural network; Control (management); Theoretical computer science; Mathematics","authors":[{"name":"Tingwu Wang","is_ca":true},{"name":"Renjie Liao","is_ca":true},{"name":"Jimmy Ba","is_ca":true},{"name":"Sanja Fidler","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03155445305249521,"gpt":0.3241901345896976,"spread":0.2926356815372024,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008886644,0.0007510662,0.0007149902,0.0005093642,0.0002766699,0.0005849849,0.001191748,0.001106656,0.002560674],"category_scores_gemma":[0.003573085,0.0003750398,0.0004034023,0.0004310197,0.0008421114,0.001250592,0.0008722362,0.001443749,0.000490779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008313048,"about_ca_system_score_gemma":0.001309435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005436162,"about_ca_topic_score_gemma":0.00684453,"domain_scores_codex":[0.9997265,0.00008783876,0.00001291296,0.00006914877,0.00006718761,0.00003647517],"domain_scores_gemma":[0.9990047,0.0005756516,0.0001035785,0.0001210264,0.0001269472,0.00006810696],"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":[0.00004468929,0.00004654371,0.0003578648,0.0000351798,0.00002190349,0.0000345557,0.00001687485,0.9576289,0.0005887345,0.007076573,0.001427115,0.03272104],"study_design_scores_gemma":[0.000004507508,0.00001430572,0.00002174723,0.000002453028,0.000001588965,0.000004024357,0.000001229614,0.9956046,0.0002177937,0.003896583,0.0002294372,0.000001686151],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03274063,0.0003472783,0.9600867,0.0004818095,0.0001686792,0.00007158482,0.0001935592,0.002493299,0.003416448],"genre_scores_gemma":[0.7861734,0.0003007497,0.2080812,0.0004578753,0.00007610657,0.0002276962,0.0004892196,0.0002507826,0.003942954],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005436162,"threshold_uncertainty_score":0.010809,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2907502844","doi":"","title":"Deep reinforcement learning with relational inductive biases","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"EEG and Brain-Computer Interfaces","field":"Neuroscience","cited_by":136,"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":"Inductive bias; Statistical relational learning; Reinforcement learning; Computer science; Artificial intelligence; Inductive logic programming; Machine learning; Relational database; Multi-task learning; Data mining; Engineering","authors":[{"name":"Vinícius Zambaldi","is_ca":false},{"name":"David Raposo","is_ca":false},{"name":"Adam Santoro","is_ca":true},{"name":"Victor Bapst","is_ca":false},{"name":"Yujia Li","is_ca":false},{"name":"I. Babuschkin","is_ca":false},{"name":"Karl Tuyls","is_ca":false},{"name":"David Reichert","is_ca":false},{"name":"Timothy Lillicrap","is_ca":false},{"name":"Edward Lockhart","is_ca":false},{"name":"Murray Shanahan","is_ca":false},{"name":"Victoria Langston","is_ca":false},{"name":"Razvan Pascanu","is_ca":false},{"name":"Matthew Botvinick","is_ca":false},{"name":"Oriol Vinyals","is_ca":false},{"name":"Peter Battaglia","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1159802418290208,"gpt":0.3604810611844719,"spread":0.244500819355451,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001721811,0.0006083814,0.0007862602,0.0003431814,0.0003535918,0.0009697622,0.001477694,0.001238002,0.004598733],"category_scores_gemma":[0.008113764,0.0004696109,0.0004494165,0.0004163083,0.0009528093,0.002145711,0.00220247,0.002379697,0.0005121077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008325787,"about_ca_system_score_gemma":0.0009268863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00171607,"about_ca_topic_score_gemma":0.002743534,"domain_scores_codex":[0.9994079,0.0002456826,0.00003326364,0.0001350837,0.0001065739,0.00007151012],"domain_scores_gemma":[0.9969313,0.002001027,0.0001800405,0.0003796541,0.000363558,0.0001444119],"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":[0.0003237913,0.0003078596,0.002323459,0.0001689553,0.0001377581,0.0001446955,0.0001940974,0.6110065,0.006846521,0.08573563,0.003585159,0.2892256],"study_design_scores_gemma":[0.0000135628,0.00003575595,0.00007934893,0.0000102685,0.00001085841,0.00001434966,0.000006942278,0.9709333,0.001059902,0.02740816,0.0004226304,0.000004977949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06718229,0.0004852491,0.9260755,0.001097812,0.0001655655,0.00006243877,0.0001120149,0.0006840636,0.004134982],"genre_scores_gemma":[0.8996946,0.0001930309,0.09483505,0.0002798404,0.00007945579,0.00009275026,0.0001285353,0.00008494221,0.004611741],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004598733,"threshold_uncertainty_score":0.01538432,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2996068536","doi":"","title":"Language GANs Falling Short","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Topic Modeling","field":"Computer Science","cited_by":89,"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; McGill University","funders":"","keywords":"Softmax function; Computer science; Sample (material); Inference; Metric (unit); Natural language generation; Quality (philosophy); Artificial intelligence; Diversity (politics); Machine learning; Ground truth; Fallacy; Sampling bias; Sample size determination; Statistics; Mathematics; Artificial neural network; Natural language","authors":[{"name":"M. Caccia","is_ca":false},{"name":"Lucas Caccia","is_ca":true},{"name":"William Fedus","is_ca":true},{"name":"Hugo Larochelle","is_ca":false},{"name":"Joëlle Pineau","is_ca":true},{"name":"Laurent Charlin","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09059197135597538,"gpt":0.3557337931421951,"spread":0.2651418217862197,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001392607,0.0009105079,0.0008131837,0.00039708,0.0002986031,0.001317119,0.001172228,0.0009872721,0.007294648],"category_scores_gemma":[0.006190041,0.000492821,0.0007478904,0.0003666062,0.0009094697,0.002724502,0.001749013,0.002802371,0.002629303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008162557,"about_ca_system_score_gemma":0.0008264162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001656685,"about_ca_topic_score_gemma":0.003143783,"domain_scores_codex":[0.9991036,0.0003158841,0.00003687823,0.0002403736,0.0002020494,0.0001012304],"domain_scores_gemma":[0.9978853,0.001295704,0.00010342,0.0004374586,0.0001976421,0.00008061722],"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":[0.0002772564,0.0000849756,0.001672171,0.0002535098,0.0001472941,0.0002337904,0.0002241758,0.5283517,0.009202289,0.2009665,0.0265985,0.2319879],"study_design_scores_gemma":[0.00001901838,0.00005118941,0.0003338277,0.00003230915,0.00001584536,0.0001171047,0.00002176469,0.8955649,0.002078778,0.09015306,0.01159714,0.00001520729],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02317527,0.00183973,0.9518867,0.001507418,0.0004146914,0.00007170703,0.000703031,0.003804979,0.01659637],"genre_scores_gemma":[0.7756114,0.002034256,0.1863676,0.002585619,0.0004952698,0.0003153138,0.002872219,0.001669723,0.02804864],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007294648,"threshold_uncertainty_score":0.02440304,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2966574105","doi":"","title":"Understanding Posterior Collapse in Generative Latent Variable Models","year":2019,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Topic Modeling","field":"Computer Science","cited_by":78,"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":"Latent variable; Generative grammar; Computer science; Latent variable model; Variable (mathematics); Artificial intelligence; Mathematics","authors":[{"name":"James Lucas","is_ca":true},{"name":"George Tucker","is_ca":false},{"name":"Roger Grosse","is_ca":true},{"name":"Mohammad Norouzi","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1761058557898787,"gpt":0.3340231839156236,"spread":0.1579173281257449,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005669981,0.0009215288,0.001481005,0.001752146,0.0009220875,0.003908772,0.002156711,0.002466727,0.005256454],"category_scores_gemma":[0.04113634,0.001576187,0.001767789,0.001528087,0.00187116,0.005464033,0.003965156,0.004829227,0.0008923541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001613903,"about_ca_system_score_gemma":0.001150558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007598369,"about_ca_topic_score_gemma":0.007424506,"domain_scores_codex":[0.9980612,0.00109703,0.00008850497,0.0003269181,0.0002690515,0.0001572847],"domain_scores_gemma":[0.9714516,0.02552633,0.0007290779,0.001179222,0.0007436739,0.0003699633],"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":[0.0002008228,0.0001097808,0.003949687,0.0002600152,0.0001664699,0.0003209436,0.001566466,0.2964935,0.00169983,0.6288739,0.006453747,0.05990483],"study_design_scores_gemma":[0.00001357397,0.000008339178,0.0003346339,0.00002756243,0.0000171387,0.00003420374,0.00005306989,0.7263889,0.0002292531,0.2720553,0.0008256799,0.00001235614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02629382,0.0004261274,0.9696721,0.0009639701,0.00005246225,0.00002852198,0.0002965298,0.0006284046,0.001638052],"genre_scores_gemma":[0.7955009,0.001147755,0.1931342,0.0004848927,0.0003263286,0.0002178543,0.002699986,0.0009345081,0.005553597],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007598369,"threshold_uncertainty_score":0.02998608,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2750933313","doi":"","title":"Distributed Second-Order Optimization using Kronecker-Factored Approximations","year":2017,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":72,"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":"Stochastic gradient descent; Computer science; Computation; Overhead (engineering); Artificial neural network; Curvature; Algorithm; Machine learning; Scaling; Artificial intelligence; Mathematical optimization; Mathematics","authors":[{"name":"Jimmy Ba","is_ca":true},{"name":"Roger Grosse","is_ca":true},{"name":"James Martens","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08007162583441403,"gpt":0.3591140077257221,"spread":0.279042381891308,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001259782,0.001491032,0.001401315,0.0006953948,0.0005292895,0.001368831,0.001834884,0.00155109,0.005548259],"category_scores_gemma":[0.005070476,0.0006754549,0.001215432,0.0007404721,0.001243215,0.001595276,0.001402653,0.002310744,0.002409898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001570702,"about_ca_system_score_gemma":0.00264406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01526298,"about_ca_topic_score_gemma":0.02361878,"domain_scores_codex":[0.9993919,0.0001374782,0.00003593198,0.0001387838,0.0002225652,0.00007327985],"domain_scores_gemma":[0.9983338,0.0007625262,0.0001133301,0.0003137825,0.0003663312,0.0001103515],"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":[0.00005330813,0.00003626476,0.000501837,0.00006600987,0.00003314402,0.0000606196,0.00005154507,0.939988,0.001199962,0.02535835,0.003794902,0.028856],"study_design_scores_gemma":[0.000003713293,0.000003125243,0.00001637926,0.000002217198,9.474384e-7,0.000003656665,0.000001810042,0.9960103,0.0001104759,0.003513877,0.000331305,0.000002132304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004528487,0.000157352,0.9917511,0.0001775053,0.00007034942,0.00002767845,0.00008620641,0.0009390658,0.002262292],"genre_scores_gemma":[0.2591709,0.0003385366,0.7262094,0.0003129062,0.000142697,0.0002435339,0.0006843308,0.00121307,0.01168463],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01526298,"threshold_uncertainty_score":0.0303483,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2996680032","doi":"","title":"Efficient and Information-Preserving Future Frame Prediction and Beyond","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":72,"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; MNIST database; Autoencoder; Bottleneck; Artificial intelligence; Frame (networking); Machine learning; Feature extraction; Information bottleneck method; Margin (machine learning); Feature (linguistics); High memory; Key (lock); Deep learning; State (computer science); Algorithm; Mutual information","authors":[{"name":"Wei Yu","is_ca":true},{"name":"Yichao Lu","is_ca":false},{"name":"Steve Easterbrook","is_ca":true},{"name":"Sanja Fidler","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01964610070994115,"gpt":0.2979189959929102,"spread":0.2782728952829691,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004364609,0.0006155384,0.0004701113,0.0003559703,0.0002926301,0.0005597883,0.0014387,0.0006192001,0.002792217],"category_scores_gemma":[0.001694115,0.000328672,0.0004620827,0.0003641137,0.0005211448,0.001414769,0.0008543179,0.001104884,0.0009530531],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003927263,"about_ca_system_score_gemma":0.0007492669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004173055,"about_ca_topic_score_gemma":0.006247553,"domain_scores_codex":[0.999831,0.00002391641,0.000007893635,0.0000634475,0.00004498732,0.00002880864],"domain_scores_gemma":[0.9996386,0.0001192657,0.00004646286,0.0001168147,0.00005817242,0.00002071294],"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":[0.0002452284,0.0001180721,0.001444844,0.0001204301,0.00005680004,0.0002469602,0.0001413501,0.3487969,0.0465334,0.03127112,0.004929008,0.5660959],"study_design_scores_gemma":[0.000004610367,0.0000382484,0.0002551408,0.00001325915,0.00001084259,0.00007512786,0.000009671484,0.9720666,0.0169565,0.008574023,0.001986512,0.000009549167],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0333202,0.0003160225,0.9609013,0.0001738954,0.00004928459,0.00003611196,0.00018065,0.00168788,0.003334651],"genre_scores_gemma":[0.7616254,0.0004358691,0.2297244,0.000152756,0.00005905692,0.00007671223,0.0007210146,0.0002816113,0.00692316],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004173055,"threshold_uncertainty_score":0.009340882,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2911248322","doi":"","title":"Learning to Learn with Conditional Class Dependencies","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Université de Sherbrooke; Dalhousie University","funders":"","keywords":"Computer science; Class (philosophy); Artificial intelligence; Machine learning; Theoretical computer science","authors":[{"name":"Xiang Jiang","is_ca":true},{"name":"Mohammad Havaei","is_ca":true},{"name":"Farshid Varno","is_ca":true},{"name":"Gabriel Chartrand","is_ca":true},{"name":"Nicolas Chapados","is_ca":true},{"name":"Stan Matwin","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03035484499736908,"gpt":0.3326982328008643,"spread":0.3023433878034952,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002131495,0.001127693,0.001360114,0.001126715,0.0006107151,0.001425078,0.002212648,0.002378585,0.004691888],"category_scores_gemma":[0.0122385,0.0008557086,0.00137995,0.001652828,0.001298311,0.00621838,0.002921241,0.00501928,0.001219246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001080342,"about_ca_system_score_gemma":0.001847632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00332077,"about_ca_topic_score_gemma":0.004520895,"domain_scores_codex":[0.9987283,0.0003883714,0.00007931783,0.0004406915,0.0002271072,0.0001361782],"domain_scores_gemma":[0.9938582,0.004026298,0.0002873745,0.00120998,0.000456203,0.0001618769],"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":[0.0006252598,0.0005433543,0.005990464,0.0003388124,0.0003574176,0.0002262721,0.0002305695,0.2481797,0.003812747,0.09968732,0.02940452,0.6106036],"study_design_scores_gemma":[0.00004450895,0.00005962634,0.0003152109,0.00002451657,0.00003817727,0.00005558496,0.00002203313,0.9125011,0.0009964675,0.084748,0.00118365,0.00001113698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04842542,0.0006465808,0.9442568,0.001760358,0.0001868108,0.00008439645,0.0006620078,0.001658129,0.002319618],"genre_scores_gemma":[0.7622771,0.0009484813,0.2203787,0.001380819,0.0004735006,0.0004297335,0.004233546,0.0003191879,0.009558821],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004691888,"threshold_uncertainty_score":0.01569599,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963285940","doi":"","title":"Graph HyperNetworks for Neural Architecture Search.","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":53,"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; Inference; Architecture; Artificial neural network; Network topology; Graph; Network architecture; Artificial intelligence; Machine learning; Theoretical computer science","authors":[{"name":"Wenjun Zhang","is_ca":true},{"name":"Mengye Ren","is_ca":true},{"name":"Raquel Urtasun","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05905441561582941,"gpt":0.3606030764095502,"spread":0.3015486607937208,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001193042,0.001604084,0.0008319978,0.002000713,0.0007029896,0.001310878,0.002299222,0.00192828,0.01099063],"category_scores_gemma":[0.008123529,0.0008549719,0.001269933,0.001588136,0.0009339654,0.003177151,0.001406851,0.002622742,0.002472293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001615816,"about_ca_system_score_gemma":0.001347242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004810816,"about_ca_topic_score_gemma":0.01302388,"domain_scores_codex":[0.9994009,0.0002097169,0.0000379976,0.0001660178,0.0001369737,0.00004840369],"domain_scores_gemma":[0.9982804,0.001016603,0.0001648786,0.0002997605,0.0001691924,0.00006918526],"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":[0.0001466715,0.0001132044,0.001897615,0.0004811026,0.0002049662,0.0001463595,0.00009531725,0.6307181,0.002035747,0.1011471,0.02144661,0.2415672],"study_design_scores_gemma":[0.0000254821,0.00002994273,0.0001312608,0.00003653943,0.00002013264,0.00004046324,0.00001664194,0.9071022,0.0006451942,0.08696476,0.004977074,0.00001027055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01594756,0.003196673,0.9635879,0.001050803,0.0002374662,0.0001929245,0.001205225,0.004726764,0.009854648],"genre_scores_gemma":[0.3493847,0.002419579,0.6286605,0.001003373,0.0002700809,0.0009684924,0.004542643,0.00120032,0.01155029],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01099063,"threshold_uncertainty_score":0.0367673,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2786263712","doi":"","title":"Kronecker-factored Curvature Approximations for Recurrent Neural Networks","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Advanced Neural Network Applications","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":"Kronecker delta; Recurrent neural network; Parameterized complexity; Computer science; Algorithm; Covariance; Gaussian; Inverse; Artificial neural network; Applied mathematics; Artificial intelligence; Mathematical optimization; Mathematics","authors":[{"name":"James Martens","is_ca":true},{"name":"Jimmy Ba","is_ca":true},{"name":"Matt R. Johnson","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06065494251667179,"gpt":0.3641504852356096,"spread":0.3034955427189378,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00122656,0.001193668,0.0008959702,0.0006890151,0.0003224058,0.001058303,0.001282917,0.001295828,0.002438084],"category_scores_gemma":[0.005392608,0.0006255998,0.0008748865,0.0006084624,0.0007647215,0.001727752,0.0009610013,0.001801331,0.001265152],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001367498,"about_ca_system_score_gemma":0.001171126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006359992,"about_ca_topic_score_gemma":0.008861822,"domain_scores_codex":[0.9995891,0.0001436394,0.00002974976,0.00007386296,0.0001255198,0.00003803997],"domain_scores_gemma":[0.9988877,0.0004907494,0.0001201551,0.0001867232,0.0002490584,0.00006555676],"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":[0.00005007397,0.00002058637,0.000427359,0.00005155039,0.00003028226,0.0000423582,0.0000454503,0.9364405,0.001834366,0.0236565,0.001736441,0.03566454],"study_design_scores_gemma":[9.980854e-7,0.000003514722,0.00002570074,0.000002732469,0.000001097045,0.000005233031,0.000001403757,0.9959967,0.0001597376,0.003583909,0.0002168153,0.00000217326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007426968,0.0003004003,0.9904132,0.0001003954,0.00003061989,0.00001721188,0.00008077035,0.0006711352,0.0009592402],"genre_scores_gemma":[0.466459,0.0006895682,0.5233035,0.0001759344,0.00009776734,0.0001733137,0.0008874765,0.0009629682,0.007250522],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006359992,"threshold_uncertainty_score":0.01264596,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2995122033","doi":"","title":"Learning Disentangled Representations for CounterFactual Regression","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":40,"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":"Counterfactual thinking; Leverage (statistics); Computer science; Observational study; Selection bias; Covariate; Machine learning; Selection (genetic algorithm); Econometrics; Population; Model selection; Regression; Artificial intelligence; Statistics; Mathematics; Psychology","authors":[{"name":"Negar Hassanpour","is_ca":true},{"name":"Russell Greiner","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.279971621243436,"gpt":0.4848305298920393,"spread":0.2048589086486033,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01921616,0.001696005,0.002600135,0.002247242,0.0006242189,0.003091718,0.003542276,0.0027404,0.003517062],"category_scores_gemma":[0.06536238,0.0008512179,0.002036056,0.00300602,0.001798126,0.004726478,0.003652858,0.005752333,0.0009987858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001649087,"about_ca_system_score_gemma":0.001963866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002224409,"about_ca_topic_score_gemma":0.002287706,"domain_scores_codex":[0.9908924,0.006774746,0.0003545612,0.001036592,0.0006968404,0.0002447865],"domain_scores_gemma":[0.9500248,0.04100853,0.002395305,0.005133995,0.001018795,0.0004186168],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005602501,0.0004587326,0.006669006,0.0005568768,0.0006243375,0.0001942646,0.0004480169,0.3890463,0.0008707336,0.2092816,0.006179619,0.3851102],"study_design_scores_gemma":[0.000046769,0.00005605616,0.0003760964,0.00006870915,0.00004428579,0.00004604515,0.00002434317,0.8266334,0.0003883441,0.1708489,0.001447382,0.00001965609],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008115768,0.0006762504,0.9893189,0.0005656714,0.00004458834,0.00007674594,0.0002730464,0.0003946022,0.0005344184],"genre_scores_gemma":[0.4508722,0.001397645,0.5392421,0.0009603118,0.000411022,0.000873602,0.003428379,0.000202245,0.002612483],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01921616,"threshold_uncertainty_score":0.101626,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2995291884","doi":"","title":"On Solving Minimax Optimization Locally: A Follow-the-Ridge Approach","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":38,"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":"Minimax; Mathematical optimization; Convergence (economics); Gradient descent; Optimization problem; Computer science; Mathematics; Artificial intelligence; Artificial neural network","authors":[{"name":"Yuanhao Wang","is_ca":false},{"name":"Guodong Zhang","is_ca":true},{"name":"Jimmy Ba","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06320326867818603,"gpt":0.3032700120988561,"spread":0.2400667434206701,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002471987,0.001301906,0.00205332,0.0006418698,0.0007054039,0.0009383641,0.001637926,0.002090576,0.003770327],"category_scores_gemma":[0.006949699,0.0007704822,0.0009347555,0.0006045498,0.002047616,0.002243735,0.002577999,0.003072939,0.001152431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006792238,"about_ca_system_score_gemma":0.001342067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001472986,"about_ca_topic_score_gemma":0.002066458,"domain_scores_codex":[0.9991731,0.0004143677,0.00003344487,0.0001385388,0.0001648393,0.00007567622],"domain_scores_gemma":[0.9976175,0.001664064,0.0001616842,0.000248399,0.0002091573,0.00009902862],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001209412,0.0001127804,0.0008519823,0.0002147292,0.0000898106,0.0001607431,0.0001902709,0.7750995,0.003129507,0.140775,0.004915725,0.07433911],"study_design_scores_gemma":[0.00001554415,0.00005513547,0.00004497288,0.00001912921,0.000006002134,0.00003074246,0.00001160196,0.9674944,0.0003765194,0.03111525,0.0008230974,0.00000749947],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006154044,0.0003913133,0.9897442,0.0003806731,0.00004364647,0.00003978227,0.00001580906,0.0003245413,0.002905884],"genre_scores_gemma":[0.4170362,0.0009272269,0.5683541,0.001116469,0.0002124348,0.000572884,0.0001543535,0.0007812312,0.01084518],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003770327,"threshold_uncertainty_score":0.01307327,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2996151541","doi":"","title":"A Constructive Prediction of the Generalization Error Across Scales","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Generalization; Dependency (UML); Computer science; Constructive; Construct (python library); Artificial neural network; Artificial intelligence; Functional dependency; Scale (ratio); Range (aeronautics); Scaling; Generalization error; Machine learning; Algorithm; Theoretical computer science; Data mining; Mathematics; Process (computing)","authors":[{"name":"Jonathan S. Rosenfeld","is_ca":false},{"name":"Amir Rosenfeld","is_ca":true},{"name":"Yonatan Belinkov","is_ca":false},{"name":"Nir Shavit","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0703062179486579,"gpt":0.3414039447837197,"spread":0.2710977268350617,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01608292,0.001884585,0.001522367,0.002139091,0.0009044464,0.002031936,0.002413784,0.00271033,0.003255691],"category_scores_gemma":[0.1127677,0.001123623,0.001299122,0.001220539,0.00499077,0.007708398,0.004628152,0.005085347,0.0006532668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001755996,"about_ca_system_score_gemma":0.001520581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002474946,"about_ca_topic_score_gemma":0.001906746,"domain_scores_codex":[0.9953755,0.002021991,0.0002208025,0.001198487,0.0009179999,0.0002651061],"domain_scores_gemma":[0.9258045,0.05629306,0.00411908,0.007910687,0.004784857,0.001087826],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001611218,0.0001243325,0.007259717,0.0005068026,0.0001827642,0.0004169531,0.0007434863,0.5305266,0.008375833,0.3721045,0.006638741,0.07295918],"study_design_scores_gemma":[0.00001202042,0.0000547091,0.001423178,0.00007822618,0.00001852401,0.0001155454,0.00005197304,0.859309,0.001186911,0.1368801,0.0008424525,0.00002736393],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02819211,0.0005747124,0.9646341,0.002039091,0.0001022508,0.00005607204,0.0001435188,0.0005713632,0.003686842],"genre_scores_gemma":[0.7364789,0.001378487,0.2535,0.001536661,0.0004750101,0.0004991515,0.0004701856,0.00091946,0.004742248],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01608292,"threshold_uncertainty_score":0.08505565,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3138602767","doi":"","title":"Isolating Sources of Disentanglement in Variational Autoencoders.","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Autoencoder; Hyperparameter; Mutual information; Correlation; Classifier (UML); Latent variable; Artificial intelligence; Total correlation; Computer science; Pattern recognition (psychology); Machine learning; Mathematics; Deep learning","authors":[{"name":"Tian Qi Chen","is_ca":false},{"name":"Xuechen Li","is_ca":true},{"name":"Roger Grosse","is_ca":true},{"name":"David Duvenaud","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03819528323690188,"gpt":0.3194879893338113,"spread":0.2812927060969095,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006134504,0.001604595,0.001322857,0.00125222,0.0007029746,0.002395472,0.002164652,0.002014945,0.002552145],"category_scores_gemma":[0.03645195,0.0013893,0.001184094,0.001061267,0.003009545,0.004691474,0.00671372,0.005595473,0.0004540295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001124304,"about_ca_system_score_gemma":0.001415664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001646862,"about_ca_topic_score_gemma":0.002236697,"domain_scores_codex":[0.9971418,0.001266947,0.000146482,0.0004848757,0.0007507825,0.0002091242],"domain_scores_gemma":[0.9796262,0.01583482,0.00164078,0.001738051,0.0007470182,0.0004131233],"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":[0.0003731561,0.0001206345,0.003838773,0.0003678882,0.0002566584,0.0004363446,0.0006982423,0.5339596,0.01047334,0.3686555,0.001851811,0.07896816],"study_design_scores_gemma":[0.00001489089,0.00005042541,0.0005410507,0.000061292,0.00002576852,0.0001169433,0.0000443684,0.8574758,0.002874161,0.137719,0.001054724,0.0000215058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01553124,0.0003244378,0.9820034,0.0002447146,0.00001787696,0.00002422418,0.0000611615,0.0001494166,0.001643635],"genre_scores_gemma":[0.7830971,0.0006699126,0.210719,0.0003530039,0.0001085556,0.0002421184,0.0004526924,0.000429401,0.003928315],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006134504,"threshold_uncertainty_score":0.03244275,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2996067004","doi":"","title":"Generalization of Two-layer Neural Networks: An Asymptotic Viewpoint","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Stochastic Gradient Optimization Techniques","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":"University of Toronto","funders":"","keywords":"Initialization; Generalization; Gradient descent; Layer (electronics); Artificial neural network; Population; Mathematics; Computer science; Flow (mathematics); Applied mathematics; Mathematical analysis; Artificial intelligence; Geometry; Chemistry","authors":[{"name":"Jimmy Ba","is_ca":true},{"name":"Murat A. Erdogdu","is_ca":true},{"name":"Taiji Suzuki","is_ca":false},{"name":"Denny Wu","is_ca":true},{"name":"Tianzong Zhang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08250555733982355,"gpt":0.3510375405511749,"spread":0.2685319832113514,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007599839,0.001390821,0.001066081,0.0008918666,0.0005839618,0.001331208,0.002272203,0.001883862,0.002711768],"category_scores_gemma":[0.03536998,0.0007264858,0.001336404,0.0004957762,0.002867395,0.005564086,0.004509371,0.004391959,0.0004302385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001901266,"about_ca_system_score_gemma":0.000819693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002248694,"about_ca_topic_score_gemma":0.001353939,"domain_scores_codex":[0.9982773,0.0007747918,0.00007919753,0.0003395945,0.0003699853,0.0001590315],"domain_scores_gemma":[0.9898021,0.006178983,0.0009585062,0.001670659,0.0009851652,0.0004046933],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001375122,0.00006594446,0.002442301,0.0002354233,0.000122262,0.0003075738,0.0002643402,0.5235912,0.003283354,0.4460758,0.002185014,0.02128946],"study_design_scores_gemma":[0.000008639508,0.00004176541,0.0003318472,0.00002841466,0.00001144625,0.00006755155,0.00001832771,0.8780164,0.0004768461,0.1204459,0.000541192,0.00001167852],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04869292,0.0009228216,0.9398533,0.00168622,0.00009381588,0.00005253217,0.0001046587,0.0003927675,0.008201012],"genre_scores_gemma":[0.8704663,0.001534478,0.1150717,0.001296952,0.0004034548,0.0003646893,0.0003707161,0.0003823226,0.01010942],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007599839,"threshold_uncertainty_score":0.04019231,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3127129507","doi":"","title":"Incremental few-shot learning via vector quantization in deep embedded space","year":2021,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Domain Adaptation and Few-Shot 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":"University of Toronto","funders":"","keywords":"Forgetting; Overfitting; Learning vector quantization; Computer science; Artificial intelligence; Regularization (linguistics); Machine learning; Quantization (signal processing); Incremental learning; Support vector machine; Deep learning; Reproducing kernel Hilbert space; Vector quantization; Kernel (algebra); Pattern recognition (psychology); Artificial neural network; Algorithm; Mathematics; Hilbert space","authors":[{"name":"Kuilin Chen","is_ca":true},{"name":"Chi-Guhn Lee","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05821540092947535,"gpt":0.3431383331195025,"spread":0.2849229321900272,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001072807,0.0008815868,0.001440251,0.0005369193,0.0003608342,0.0008113087,0.002234479,0.0009061279,0.00125835],"category_scores_gemma":[0.003851192,0.0004898931,0.0006238614,0.0007715303,0.0007881862,0.003015114,0.001505671,0.002285868,0.000444524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008207439,"about_ca_system_score_gemma":0.001013237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005951458,"about_ca_topic_score_gemma":0.006709753,"domain_scores_codex":[0.9992711,0.0001570234,0.00004949713,0.0002525946,0.0001986632,0.00007104113],"domain_scores_gemma":[0.9988961,0.0004465177,0.0001051631,0.0002612373,0.0002165005,0.00007449376],"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":[0.0002619131,0.0002556368,0.001912587,0.0002315489,0.0001039738,0.0001240938,0.000273943,0.3360319,0.01128077,0.01153349,0.004496409,0.6334937],"study_design_scores_gemma":[0.000008873083,0.00004655477,0.0001761609,0.000006826229,0.000008240751,0.00002467963,0.00001470113,0.99152,0.001998555,0.0057703,0.0004151073,0.00001003023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02441413,0.000729829,0.972958,0.0001401852,0.00007408906,0.00005554373,0.00009673068,0.001063061,0.0004684974],"genre_scores_gemma":[0.7403956,0.0006944091,0.2540973,0.0003156634,0.0001032527,0.000193772,0.0008867008,0.0001598001,0.003153478],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005951458,"threshold_uncertainty_score":0.01183367,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2962876041","doi":"","title":"An Exploration of Softmax Alternatives Belonging to the Spherical Loss Family","year":2016,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Topic Modeling","field":"Computer Science","cited_by":30,"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":"Softmax function; Probabilistic logic; Function (biology); Categorical variable; MNIST database; Computer science; Range (aeronautics); Mathematics; Algorithm; Artificial neural network; Artificial intelligence; Pattern recognition (psychology); Discrete mathematics; Machine learning; Engineering","authors":[{"name":"Alexandre de Brébisson","is_ca":true},{"name":"Pascal Vincent","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1042967105268677,"gpt":0.3749509464872322,"spread":0.2706542359603645,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007464447,0.001635246,0.001122599,0.001230596,0.0005317508,0.002403271,0.002021552,0.001775768,0.003188923],"category_scores_gemma":[0.01708967,0.0005103992,0.001290838,0.001241158,0.001624844,0.004285737,0.003324156,0.003243951,0.001385185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001590264,"about_ca_system_score_gemma":0.001124616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001568446,"about_ca_topic_score_gemma":0.001646278,"domain_scores_codex":[0.9969199,0.001881931,0.0001663182,0.0003123545,0.0005415376,0.0001779819],"domain_scores_gemma":[0.9945006,0.003863962,0.0003084762,0.0005327034,0.0005707045,0.0002235286],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007471766,0.0003301126,0.00191822,0.0003853273,0.0001810821,0.0002505175,0.000296265,0.5057165,0.005749571,0.2238459,0.008905797,0.2516737],"study_design_scores_gemma":[0.00002862549,0.000126225,0.0002762853,0.00006327845,0.0000211716,0.0001072738,0.00005554268,0.9342073,0.001733879,0.0612752,0.002083712,0.00002156076],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02620632,0.00139914,0.9643712,0.001485655,0.00006074282,0.00005839797,0.00009479252,0.0005905168,0.005733155],"genre_scores_gemma":[0.7324584,0.002283612,0.2556267,0.001394872,0.0002200721,0.0003368707,0.0005112169,0.0006850637,0.006483323],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007464447,"threshold_uncertainty_score":0.03947628,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2923289556","doi":"","title":"A new dog learns old tricks: RL finds classic optimization algorithms","year":2019,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Optimization and Search Problems","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Optimization algorithm; Algorithm; Mathematical optimization; Mathematics","authors":[{"name":"Weiwei Kong","is_ca":false},{"name":"Christopher Liaw","is_ca":true},{"name":"Aranyak Mehta","is_ca":false},{"name":"D. Sivakumar","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04493808541385731,"gpt":0.3381104561314346,"spread":0.2931723707175773,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002395501,0.001207264,0.001623363,0.0008858475,0.0005813155,0.001734181,0.002074725,0.003611879,0.006717972],"category_scores_gemma":[0.01000278,0.0008027235,0.0007612329,0.0006584379,0.002434701,0.004829925,0.002450304,0.002687282,0.001383331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007839406,"about_ca_system_score_gemma":0.001002943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001518338,"about_ca_topic_score_gemma":0.001672309,"domain_scores_codex":[0.9993144,0.0002302388,0.00004186707,0.0002089211,0.0001412006,0.00006338714],"domain_scores_gemma":[0.9974505,0.00144611,0.0001522477,0.0005708977,0.0002581336,0.0001220975],"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":[0.0004587637,0.0002823312,0.002578764,0.0003982921,0.000281656,0.0001850816,0.0002736909,0.4709583,0.004040535,0.1102596,0.01428963,0.3959934],"study_design_scores_gemma":[0.00006663352,0.00009826341,0.0001572629,0.00003513219,0.00003245394,0.00008162545,0.00002810819,0.9397292,0.0008650038,0.0564019,0.002489236,0.00001526575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04851241,0.001424623,0.9331961,0.002159616,0.0004863029,0.00008325806,0.00008266522,0.001675654,0.01237946],"genre_scores_gemma":[0.662826,0.0006090869,0.3154438,0.00109212,0.000483449,0.0001880552,0.0001641205,0.0005803679,0.01861309],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006717972,"threshold_uncertainty_score":0.02247387,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2907257898","doi":"","title":"Transferring Knowledge to Smaller Network with Class-Distance Loss","year":2017,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":22,"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; Class (philosophy); Computer network; Artificial intelligence","authors":[{"name":"Seung Wook Kim","is_ca":true},{"name":"Hyoeun Kim","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04954684195011518,"gpt":0.3549417961186118,"spread":0.3053949541684967,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001509944,0.001177158,0.001252846,0.001027608,0.0006634637,0.001215884,0.002271035,0.002424253,0.006992212],"category_scores_gemma":[0.005875573,0.0004570314,0.0008503619,0.001098911,0.0009510543,0.00398823,0.003001251,0.003145702,0.001533345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00136784,"about_ca_system_score_gemma":0.001220383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006614265,"about_ca_topic_score_gemma":0.006662834,"domain_scores_codex":[0.9993363,0.0001566113,0.00004041057,0.0002506166,0.000135634,0.00008039339],"domain_scores_gemma":[0.9977715,0.0009057116,0.0001030698,0.0008189823,0.0002987523,0.0001019821],"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":[0.0004313497,0.0005079728,0.001036267,0.0001354675,0.000137326,0.000189946,0.0001343976,0.4365964,0.01505215,0.01997516,0.01013789,0.5156657],"study_design_scores_gemma":[0.00001254734,0.00004982651,0.0001276485,0.000006635006,0.00001668056,0.00002477417,0.00001574958,0.9821597,0.002627556,0.01423851,0.0007162439,0.000004174872],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06490374,0.0002621466,0.927277,0.0009562871,0.0001943716,0.0001287853,0.0002548508,0.0018726,0.004150113],"genre_scores_gemma":[0.7581601,0.0002629315,0.2225136,0.0005953877,0.0002190267,0.0002995818,0.001191685,0.0003999883,0.01635773],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006992212,"threshold_uncertainty_score":0.02339131,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2996091952","doi":"","title":"Augmenting Genetic Algorithms with Deep Neural Networks for Exploring the Chemical Space","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Machine Learning in Materials Science","field":"Materials 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":"Chemical space; Interpretability; Computer science; Genetic algorithm; Discriminator; Artificial neural network; Artificial intelligence; Space (punctuation); Quality control and genetic algorithms; Machine learning; Algorithm; Meta-optimization; Bioinformatics; Drug discovery","authors":[{"name":"AkshatKumar Nigam","is_ca":true},{"name":"Pascal Friederich","is_ca":false},{"name":"Mario Krenn","is_ca":false},{"name":"Alán Aspuru‐Guzik","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07105698301146753,"gpt":0.3216329128371807,"spread":0.2505759298257131,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008097076,0.000817948,0.0005360117,0.0006679323,0.0003379222,0.0006753615,0.0009747829,0.001256257,0.00166547],"category_scores_gemma":[0.002629797,0.0004113351,0.0004635617,0.0006796521,0.0008039683,0.001011885,0.0008220518,0.001401196,0.0003418016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008734076,"about_ca_system_score_gemma":0.0007504437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002814213,"about_ca_topic_score_gemma":0.005101171,"domain_scores_codex":[0.9997628,0.00008068084,0.00001264288,0.00004444284,0.00007795223,0.0000215173],"domain_scores_gemma":[0.9991592,0.000559905,0.00007283074,0.00007482114,0.0001109891,0.00002229614],"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":[0.00001795721,0.00003824939,0.0003775684,0.00003288018,0.00002241147,0.00003161173,0.00002790087,0.9315053,0.002149995,0.01548834,0.0004203679,0.04988746],"study_design_scores_gemma":[0.000005360749,0.000009974202,0.00002064347,0.000003708504,0.000003794328,0.000006021392,0.000002689201,0.9930103,0.0004633089,0.006030662,0.0004410643,0.000002416311],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02752141,0.0003161245,0.9665412,0.0003073366,0.00006224089,0.00004620439,0.00002714983,0.0005277676,0.004650464],"genre_scores_gemma":[0.4257377,0.000482293,0.5697337,0.000335755,0.00006386094,0.0002195119,0.0001078302,0.0001690338,0.003150283],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002814213,"threshold_uncertainty_score":0.006336987,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963682248","doi":"","title":"Reinterpreting Importance-Weighted Autoencoders","year":2017,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":19,"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":"Upper and lower bounds; Interpretation (philosophy); Computer science; Marginal distribution; Artificial intelligence; Distribution (mathematics); Algorithm; Mathematics; Pattern recognition (psychology); Statistics; Random variable","authors":[{"name":"Chris Cremer","is_ca":false},{"name":"Quaid Morris","is_ca":true},{"name":"David Duvenaud","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04670941002473038,"gpt":0.3662012404771157,"spread":0.3194918304523853,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003127314,0.001195547,0.0007647404,0.001020329,0.0003816647,0.001810974,0.00169594,0.001599384,0.003204729],"category_scores_gemma":[0.01190853,0.0006887045,0.0006202763,0.0007149316,0.001978142,0.003371305,0.003020326,0.003104771,0.0006458681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009877862,"about_ca_system_score_gemma":0.0008854298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001520593,"about_ca_topic_score_gemma":0.002708763,"domain_scores_codex":[0.9986423,0.000448411,0.00007432475,0.0002562198,0.0004487104,0.0001301474],"domain_scores_gemma":[0.9968433,0.001748309,0.0002735024,0.0005307128,0.0004816942,0.0001223617],"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":[0.00005210493,0.00004572043,0.0005308836,0.0001112377,0.00005407984,0.0002007932,0.0001276551,0.3583098,0.005368236,0.5853602,0.001726983,0.04811227],"study_design_scores_gemma":[0.000008286458,0.00002114888,0.000134449,0.00002749934,0.00001261504,0.00005081491,0.00001122234,0.7692196,0.001559371,0.2274117,0.001532499,0.00001095422],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006738915,0.0001844719,0.9893509,0.0002626181,0.0000686601,0.00001578788,0.00003469246,0.00010415,0.003239859],"genre_scores_gemma":[0.6088315,0.0008523511,0.3768363,0.0005100702,0.000336029,0.0001445299,0.0002404177,0.0004483433,0.01180052],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003204729,"threshold_uncertainty_score":0.01653898,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2904014149","doi":"","title":"Finding Flatter Minima with SGD","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":18,"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":"Maxima and minima; Computer science; Artificial intelligence; Mathematics; Mathematical analysis","authors":[{"name":"Stanisław Jastrzȩbski","is_ca":false},{"name":"Zachary Kenton","is_ca":false},{"name":"Devansh Arpit","is_ca":true},{"name":"Nicolas Ballas","is_ca":true},{"name":"Asja Fischer","is_ca":false},{"name":"Yoshua Bengio","is_ca":true},{"name":"Amos Storkey","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0514478710076336,"gpt":0.3483785570925074,"spread":0.2969306860848738,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002336433,0.002298079,0.002956741,0.002389768,0.00103821,0.002068,0.001809753,0.002995811,0.0146362],"category_scores_gemma":[0.0102901,0.001667268,0.001606715,0.001542679,0.001441751,0.002770636,0.002986094,0.003308178,0.003071231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001025726,"about_ca_system_score_gemma":0.001604368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002783182,"about_ca_topic_score_gemma":0.004545108,"domain_scores_codex":[0.9990085,0.0003420722,0.0000777255,0.0002526786,0.0002150973,0.000103944],"domain_scores_gemma":[0.9975498,0.001561311,0.0001345495,0.0003648995,0.0002665409,0.0001230048],"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":[0.0006436342,0.0002504713,0.001373687,0.0003514887,0.0001953979,0.0002375761,0.0002272107,0.5764237,0.005313766,0.04689321,0.01882637,0.3492635],"study_design_scores_gemma":[0.00007117677,0.00006738495,0.0001206312,0.00002530177,0.00001650502,0.0000326065,0.00003064722,0.9612436,0.0009239032,0.0363182,0.001138879,0.0000111812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02137474,0.0004456179,0.9703159,0.0004148908,0.0001502976,0.00008610493,0.0001345731,0.00245077,0.004627147],"genre_scores_gemma":[0.2197748,0.000185264,0.7699496,0.0005385891,0.00009981955,0.0002804007,0.000652539,0.001971717,0.006547383],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0146362,"threshold_uncertainty_score":0.04896295,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2923023063","doi":"","title":"Modeling the Long Term Future in Model-Based Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Reinforcement learning; Term (time); Computer science; Artificial intelligence","authors":[{"name":"Nan Rosemary Ke","is_ca":true},{"name":"Amanpreet Singh","is_ca":false},{"name":"Abdelaziz Touati","is_ca":true},{"name":"Anirudh Goyal","is_ca":true},{"name":"Yoshua Bengio","is_ca":true},{"name":"Devi Parikh","is_ca":false},{"name":"Dhruv Batra","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05336023462993137,"gpt":0.3395181485785783,"spread":0.2861579139486469,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001515609,0.0005987287,0.0009521006,0.0004287819,0.0003537154,0.001281627,0.001262801,0.001148651,0.002614483],"category_scores_gemma":[0.006533797,0.0005099331,0.0004560767,0.0005126983,0.001030904,0.00235754,0.00106726,0.001867951,0.0002447881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001234292,"about_ca_system_score_gemma":0.000968948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008656397,"about_ca_topic_score_gemma":0.008916649,"domain_scores_codex":[0.9995641,0.0002041249,0.00002087786,0.00009369943,0.00006094865,0.00005635479],"domain_scores_gemma":[0.997852,0.001520175,0.000212989,0.0001046416,0.0001953218,0.0001148597],"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":[0.00004797834,0.00002301572,0.0005217587,0.00002988103,0.00002090517,0.00003467367,0.00004240293,0.9583411,0.0002089687,0.03267341,0.0003193416,0.007736503],"study_design_scores_gemma":[0.000006006694,0.000009444351,0.00003693736,0.000003446316,0.000004091029,0.000004182461,0.00000364058,0.98544,0.00003962165,0.01435796,0.00009193231,0.000002745026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08642178,0.0007325049,0.9076887,0.00100227,0.00009572246,0.00003256849,0.0001690775,0.0002471446,0.003610187],"genre_scores_gemma":[0.9663367,0.0003112814,0.03040026,0.00008139247,0.0000318125,0.00008269882,0.0001069782,0.0000321661,0.002616769],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008656397,"threshold_uncertainty_score":0.01721197,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963200642","doi":"","title":"Sparsely-Connected Neural Networks: Towards Efficient VLSI Implementation of Deep Neural Networks","year":2016,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":18,"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":"MNIST database; Computer science; Artificial neural network; Deep learning; Convolutional neural network; Artificial intelligence; Energy consumption","authors":[{"name":"Arash Ardakani","is_ca":true},{"name":"Carlo Condo","is_ca":true},{"name":"Warren J. Gross","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05047194812276975,"gpt":0.3403865215796997,"spread":0.2899145734569299,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002542085,0.0005460451,0.0002641449,0.000386537,0.0001567091,0.0005252082,0.001340124,0.0004530387,0.003468424],"category_scores_gemma":[0.0007702286,0.0002591617,0.0002101761,0.0005067781,0.0002586026,0.0009850365,0.0003781471,0.000588636,0.00075435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005052689,"about_ca_system_score_gemma":0.0006175148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002220602,"about_ca_topic_score_gemma":0.005092838,"domain_scores_codex":[0.9998042,0.000033288,0.00001291293,0.00002799252,0.00009633626,0.00002538269],"domain_scores_gemma":[0.9997936,0.00006203964,0.00002290877,0.00003997863,0.00007097674,0.00001048943],"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":[0.0003432179,0.0001530622,0.0009622047,0.0007079932,0.0001185461,0.0002425331,0.0001368827,0.2086551,0.116277,0.04586663,0.01429107,0.6122458],"study_design_scores_gemma":[0.00004099083,0.0001905214,0.0002959158,0.0000376181,0.00003399731,0.0001159246,0.00002279852,0.9409618,0.03406373,0.01120441,0.01301761,0.00001464235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04707813,0.002247253,0.9373922,0.0004895764,0.0001535637,0.00009506222,0.0002023209,0.003913736,0.008428113],"genre_scores_gemma":[0.5642166,0.0013409,0.4277595,0.0003208525,0.00007991892,0.0001527691,0.0005532532,0.0001473458,0.005428973],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003468424,"threshold_uncertainty_score":0.01160306,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2995128076","doi":"","title":"A Closer Look at the Optimization Landscapes of Generative Adversarial Networks","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Concatenation (mathematics); Computer science; Adversarial system; Generative grammar; Generator (circuit theory); Saddle point; Point (geometry); Visualization; Artificial intelligence; Field (mathematics); Deep learning; Bridge (graph theory); Machine learning; Theoretical computer science; Mathematical optimization; Mathematics","authors":[{"name":"Hugo Berard","is_ca":true},{"name":"Gauthier Gidel","is_ca":true},{"name":"Amjad Almahairi","is_ca":false},{"name":"Pascal Vincent","is_ca":true},{"name":"Simon Lacoste-Julien","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0342901584745485,"gpt":0.28078537204376,"spread":0.2464952135692115,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001337065,0.0008377203,0.0006761324,0.0008418008,0.0004532429,0.00157295,0.0005243624,0.00109008,0.005655858],"category_scores_gemma":[0.005179167,0.0004255806,0.0004797374,0.0003624085,0.00133486,0.002070949,0.001173267,0.002349032,0.000488629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009735067,"about_ca_system_score_gemma":0.0003557454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001772329,"about_ca_topic_score_gemma":0.001450281,"domain_scores_codex":[0.9995856,0.0002384072,0.00001155025,0.00005388452,0.00006933586,0.00004120334],"domain_scores_gemma":[0.9986614,0.0009904881,0.00008770292,0.00008887835,0.00009436828,0.00007706965],"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":[0.00006019635,0.00003599614,0.001092623,0.00008258431,0.00003515095,0.0001716343,0.0002240592,0.755788,0.003078099,0.2197618,0.003637857,0.01603188],"study_design_scores_gemma":[0.000009307613,0.00003287309,0.0005379569,0.00003688465,0.000004600736,0.0000659851,0.00005446313,0.8792903,0.0005033264,0.1169787,0.00247009,0.00001550888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1186862,0.003652316,0.8237022,0.005599346,0.0001654629,0.00009154528,0.0003119075,0.0005829511,0.04720822],"genre_scores_gemma":[0.9203123,0.001899496,0.06734965,0.0006482746,0.0001155771,0.0001365269,0.0002541197,0.0004558411,0.008828393],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005655858,"threshold_uncertainty_score":0.01892072,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963202404","doi":"","title":"FigureQA: An Annotated Figure Dataset for Visual Reasoning","year":2017,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Computer science; Plot (graphics); Visual reasoning; Artificial intelligence; Task (project management); Intersection (aeronautics); Bar chart; Scatter plot; Bounding overwatch; Minimum bounding box; Natural language processing; Smoothness; Baseline (sea); Machine learning; Line (geometry); Image (mathematics); Mathematics","authors":[{"name":"Samira Ebrahimi Kahou","is_ca":true},{"name":"Adam Atkinson","is_ca":false},{"name":"Vincent Michalski","is_ca":true},{"name":"Ákos Kádár","is_ca":false},{"name":"Adam Trischler","is_ca":false},{"name":"Yoshua Bengio","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07102971897405239,"gpt":0.4403949223429446,"spread":0.3693652033688922,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000887662,0.002859113,0.0008636091,0.00413312,0.000972986,0.002063973,0.003536033,0.003981805,0.05281039],"category_scores_gemma":[0.009019935,0.0006298453,0.001817731,0.003233308,0.0008155882,0.003155672,0.002465477,0.002173652,0.02749192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002067883,"about_ca_system_score_gemma":0.001280613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02321013,"about_ca_topic_score_gemma":0.04934249,"domain_scores_codex":[0.9985121,0.0003153567,0.0001631056,0.0004886497,0.0004116543,0.0001092068],"domain_scores_gemma":[0.9968162,0.001543822,0.000179866,0.0006713833,0.0005897286,0.0001989086],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000449345,0.0002777582,0.002923449,0.003242444,0.0001158704,0.0009652507,0.0005255375,0.004305814,0.004877331,0.00543032,0.9136586,0.0632283],"study_design_scores_gemma":[0.0004486044,0.0001859416,0.0108782,0.0008809539,0.00008508272,0.001377722,0.001109469,0.0424518,0.007539399,0.01567934,0.9192148,0.0001486458],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.02027204,0.003567093,0.02773508,0.001529988,0.0005371179,0.0009825759,0.8837571,0.03978894,0.02183005],"genre_scores_gemma":[0.03110679,0.0005694341,0.04995626,0.0005693065,0.0000579706,0.0008408542,0.9091921,0.001631282,0.006075907],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.05281039,"threshold_uncertainty_score":0.1766683,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2994886105","doi":"","title":"Progressive Memory Banks for Incremental Domain Adaptation","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta; University of Waterloo","funders":"","keywords":"Computer science; Recurrent neural network; Domain adaptation; Parameterized complexity; Domain (mathematical analysis); Artificial intelligence; Artificial neural network; Adaptation (eye); Machine learning; Algorithm","authors":[{"name":"Nabiha Asghar","is_ca":true},{"name":"Lili Mou","is_ca":true},{"name":"Kira A. Selby","is_ca":true},{"name":"Kevin D. Pantasdo","is_ca":true},{"name":"Pascal Poupart","is_ca":true},{"name":"Xin Jiang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09777329092838097,"gpt":0.3433704679106314,"spread":0.2455971769822504,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009435122,0.001018469,0.0009135128,0.0007924926,0.0004594618,0.0007431553,0.002408102,0.00115157,0.002772266],"category_scores_gemma":[0.004024582,0.0005767486,0.0008373325,0.0008388838,0.0008090175,0.003420115,0.001702027,0.00217897,0.001228379],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007234056,"about_ca_system_score_gemma":0.0009433383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004860214,"about_ca_topic_score_gemma":0.005527752,"domain_scores_codex":[0.999582,0.000092485,0.00002964179,0.0001738727,0.00007029054,0.00005166698],"domain_scores_gemma":[0.9988728,0.0005354689,0.0000742906,0.0003191598,0.0001465001,0.00005177943],"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":[0.0003122349,0.000326269,0.001685189,0.0001806144,0.0001207438,0.0003096831,0.0003367018,0.3457144,0.01408054,0.01956015,0.006245875,0.6111276],"study_design_scores_gemma":[0.00001564778,0.00004356652,0.0001618222,0.00001218387,0.00002327886,0.0000637807,0.00002088318,0.9816913,0.003777375,0.01228581,0.001891911,0.0000124683],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02886549,0.000967464,0.9648544,0.0002344726,0.00009692126,0.00009901079,0.0001319584,0.002771157,0.001979181],"genre_scores_gemma":[0.7043431,0.0008431091,0.287635,0.0005982668,0.0001206841,0.0003664138,0.0006538995,0.0002736608,0.005165849],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004860214,"threshold_uncertainty_score":0.00966388,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2753228334","doi":"","title":"Online Bayesian Transfer Learning for Sequential Data Modeling","year":2017,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":14,"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":"Hidden Markov model; Computer science; Artificial intelligence; Sequence (biology); Population; Context (archaeology); Machine learning; Sequence learning; Bayesian probability; Pattern recognition (psychology)","authors":[{"name":"Priyank Jaini","is_ca":true},{"name":"Zhitang Chen","is_ca":false},{"name":"Pablo Carbajal","is_ca":false},{"name":"Edith Law","is_ca":true},{"name":"Laura E. Middleton","is_ca":true},{"name":"Kayla Regan","is_ca":true},{"name":"Mike Schaekermann","is_ca":true},{"name":"George Trimponias","is_ca":false},{"name":"James Tung","is_ca":true},{"name":"Pascal Poupart","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2214864104494036,"gpt":0.4322454878549099,"spread":0.2107590774055063,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00747863,0.001837058,0.00273781,0.001824617,0.0008320981,0.001865192,0.00390738,0.003234309,0.005677306],"category_scores_gemma":[0.02968171,0.001245609,0.001793356,0.002638944,0.00195939,0.003916284,0.003019061,0.004901827,0.001551729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002824052,"about_ca_system_score_gemma":0.002255108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01004375,"about_ca_topic_score_gemma":0.006652008,"domain_scores_codex":[0.9969362,0.001476661,0.0001676421,0.0007202107,0.0004841964,0.0002151122],"domain_scores_gemma":[0.9841232,0.01311468,0.0007377313,0.000937207,0.0007982743,0.0002889995],"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":[0.0001678047,0.0001807312,0.001326908,0.000185921,0.0001569626,0.0001798728,0.0001912937,0.8470299,0.0005403212,0.05633838,0.002167618,0.09153435],"study_design_scores_gemma":[0.000005743058,0.00001088392,0.00005105335,0.000006359812,0.000004521069,0.000008724192,0.000005488255,0.9701882,0.00008268643,0.02939962,0.000231505,0.000005255305],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004699987,0.0004012566,0.9931242,0.0004754849,0.00004682488,0.00006052624,0.0001407964,0.0005002994,0.0005507089],"genre_scores_gemma":[0.6164488,0.001427287,0.3684823,0.0007763086,0.0005452365,0.001377535,0.001582673,0.0003833541,0.00897634],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01004375,"threshold_uncertainty_score":0.0395512,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2786406308","doi":"","title":"Espresso: Efficient Forward Propagation for Binary Deep Neural Networks","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; CUDA; Convolutional neural network; Memory footprint; Parallel computing; Binary number; Deep learning; Artificial neural network; Matrix multiplication; Artificial intelligence; Operating system; Arithmetic","authors":[{"name":"Fabrizio Pedersoli","is_ca":true},{"name":"George Tzanetakis","is_ca":true},{"name":"Andrea Tagliasacchi","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0384290167936386,"gpt":0.3438460892558937,"spread":0.3054170724622551,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006872264,0.001272044,0.0004609347,0.0007413328,0.0003968635,0.001124572,0.002531779,0.000824743,0.01764983],"category_scores_gemma":[0.002621573,0.0006988714,0.0006905721,0.0008378772,0.0004299179,0.002040342,0.001464563,0.001335,0.006633596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007496604,"about_ca_system_score_gemma":0.001334009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0040186,"about_ca_topic_score_gemma":0.005349453,"domain_scores_codex":[0.9995408,0.00006577196,0.00004502825,0.0000713664,0.0001994382,0.00007751937],"domain_scores_gemma":[0.9994447,0.0002024449,0.00005956333,0.0001128092,0.0001472289,0.0000332035],"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":[0.001285438,0.0003352942,0.002000808,0.001369281,0.0001987085,0.0004260538,0.0002327191,0.1110218,0.03841546,0.04433609,0.1607168,0.6396616],"study_design_scores_gemma":[0.0001967663,0.0001320174,0.0005626509,0.0001075114,0.0000389801,0.0001925562,0.00003405776,0.8854188,0.04559506,0.02052299,0.04715153,0.00004708871],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02100972,0.001000613,0.8614811,0.0003201776,0.0003407892,0.0001544896,0.002409518,0.09921192,0.01407167],"genre_scores_gemma":[0.2020267,0.000817914,0.7535855,0.000549641,0.0001142572,0.0005585788,0.01011372,0.01026825,0.02196538],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01764983,"threshold_uncertainty_score":0.05904454,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3012851896","doi":"","title":"Convergence of Gradient Methods on Bilinear Zero-Sum Games","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":13,"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":"Convergence (economics); Bilinear interpolation; Zero (linguistics); Applied mathematics; Adversarial system; Computer science; Mathematical optimization; Generative grammar; Zero-sum game; Mathematics; Algorithm; Artificial intelligence; Nash equilibrium","authors":[{"name":"Guojun Zhang","is_ca":true},{"name":"Yaoliang Yu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3522170929303683,"gpt":0.5526990798639185,"spread":0.2004819869335502,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005609209,0.002260897,0.001804334,0.001193805,0.0007496004,0.002292368,0.002017443,0.001890107,0.006948904],"category_scores_gemma":[0.02923418,0.0008079389,0.001193251,0.0007412642,0.003203561,0.004297947,0.004583231,0.004341471,0.001158413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001898542,"about_ca_system_score_gemma":0.001836886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002111071,"about_ca_topic_score_gemma":0.00190631,"domain_scores_codex":[0.9978045,0.001236541,0.00009517493,0.0002929009,0.0003321339,0.0002387785],"domain_scores_gemma":[0.9873784,0.01031341,0.0004674549,0.0004780417,0.0008737647,0.0004889847],"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":[0.0002161406,0.0001272954,0.0007964975,0.0003436111,0.00008406398,0.000107972,0.0002677524,0.3030055,0.001439838,0.6589468,0.004382215,0.03028226],"study_design_scores_gemma":[0.00002265292,0.00004131397,0.00007145225,0.00004380131,0.000009715684,0.00002253636,0.00003262904,0.7698758,0.0003890302,0.2285933,0.0008839746,0.00001394581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01883336,0.0008735126,0.9678403,0.0008402973,0.0001339969,0.0001315702,0.0001152783,0.0001993594,0.01103232],"genre_scores_gemma":[0.6800381,0.002328644,0.2865889,0.001138479,0.0003446126,0.001033155,0.0004341694,0.0008622916,0.02723163],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006948904,"threshold_uncertainty_score":0.0296647,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3130843035","doi":"","title":"Conservative Safety Critics for Exploration","year":2021,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":12,"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":"Reinforcement learning; Computer science; Convergence (economics); Task (project management); Suite; Upper and lower bounds; Artificial intelligence; Machine learning; Mathematical optimization; Engineering; Mathematics; Law","authors":[{"name":"Homanga Bharadhwaj","is_ca":false},{"name":"Aviral Kumar","is_ca":false},{"name":"Nicholas Rhinehart","is_ca":false},{"name":"Sergey Levine","is_ca":false},{"name":"Florian Shkurti","is_ca":false},{"name":"Animesh Garg","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.117497022015405,"gpt":0.379141317792146,"spread":0.261644295776741,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003427426,0.001523781,0.001264877,0.0008666893,0.0007102448,0.001498278,0.0018139,0.001676376,0.003260151],"category_scores_gemma":[0.02140095,0.0007500566,0.0007847692,0.0003562761,0.003185916,0.002227191,0.003132825,0.004427667,0.0006799951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001290597,"about_ca_system_score_gemma":0.002000398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001510068,"about_ca_topic_score_gemma":0.001651699,"domain_scores_codex":[0.9981446,0.0006519448,0.00008949143,0.0003346818,0.0005892685,0.000190067],"domain_scores_gemma":[0.9866975,0.009744322,0.001006267,0.001162457,0.0009308944,0.0004585662],"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":[0.0001447386,0.00004372089,0.001080569,0.0001141378,0.00003647535,0.0001221385,0.0001487666,0.8891531,0.002065313,0.08092644,0.001588472,0.02457607],"study_design_scores_gemma":[0.00001976943,0.00004340584,0.00007399048,0.00002237949,0.000007249618,0.00003090813,0.00001062101,0.9561567,0.0007106579,0.04228693,0.0006281428,0.000009310877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01274006,0.000181563,0.9832035,0.0003787286,0.00004586706,0.00004418065,0.00004437142,0.0005418358,0.002819842],"genre_scores_gemma":[0.8612038,0.0002989043,0.1312736,0.0004854281,0.0001128172,0.0003865905,0.0001891605,0.0002779422,0.005771711],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003427426,"threshold_uncertainty_score":0.01812619,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2907134525","doi":"","title":"Gradient-based Optimization of Neural Network Architecture.","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research; University of Toronto","funders":"","keywords":"Computer science; Artificial neural network; Architecture; Artificial intelligence","authors":[{"name":"Will Grathwohl","is_ca":false},{"name":"Elliot Creager","is_ca":true},{"name":"Seyed Kamyar Seyed Ghasemipour","is_ca":false},{"name":"Richard S. Zemel","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03574961797958973,"gpt":0.3145263233935287,"spread":0.2787767054139389,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001290663,0.001016731,0.0008961043,0.0005453239,0.0003256397,0.0007387256,0.001150145,0.001531252,0.004199507],"category_scores_gemma":[0.00623714,0.0006798024,0.0003764261,0.0006536252,0.0005978571,0.001445896,0.0008597854,0.00168823,0.001140644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009011845,"about_ca_system_score_gemma":0.00125889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005446339,"about_ca_topic_score_gemma":0.007393405,"domain_scores_codex":[0.999706,0.0001351829,0.00001350111,0.00004364335,0.00006448691,0.00003719027],"domain_scores_gemma":[0.9991516,0.0004738728,0.00005897878,0.00005831912,0.0002146891,0.00004263277],"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":[0.0001024341,0.00004910279,0.0003999877,0.0001020428,0.00005078546,0.00003105765,0.00003737603,0.9069675,0.001131745,0.0140573,0.007664398,0.06940638],"study_design_scores_gemma":[0.000007719022,0.00001065736,0.00003798552,0.000006628567,0.000003701469,0.00000443634,0.000003092962,0.9951093,0.0001717937,0.004291412,0.0003516155,0.000001639419],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01738615,0.001324759,0.9720078,0.0007498192,0.000213695,0.00008136482,0.0001300065,0.0007792942,0.007327026],"genre_scores_gemma":[0.612082,0.0008392542,0.3704646,0.0004207963,0.0001723432,0.0003918863,0.0005383296,0.0006413658,0.01444944],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005446339,"threshold_uncertainty_score":0.01404876,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2908176537","doi":"","title":"STOCHASTIC GRADIENT LANGEVIN DYNAMICS THAT EXPLOIT NEURAL NETWORK STRUCTURE","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":8,"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":"Langevin dynamics; Exploit; Computer science; Artificial neural network; Dynamics (music); Statistical physics; Langevin equation; Artificial intelligence; Physics","authors":[{"name":"Zachary Nado","is_ca":false},{"name":"Jasper Snoek","is_ca":false},{"name":"Roger Grosse","is_ca":true},{"name":"David Duvenaud","is_ca":true},{"name":"Bowen Xu","is_ca":false},{"name":"James Martens","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04822018521992996,"gpt":0.3171347456967895,"spread":0.2689145604768595,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006904783,0.0005660939,0.0008443032,0.0004001271,0.0004002794,0.0009884142,0.001159399,0.001418218,0.002772211],"category_scores_gemma":[0.002652388,0.0004777723,0.0005413236,0.0004271745,0.001009733,0.001699492,0.001390734,0.001595237,0.0003974504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006603465,"about_ca_system_score_gemma":0.0008072309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001743258,"about_ca_topic_score_gemma":0.002486574,"domain_scores_codex":[0.9998536,0.00004745358,0.000006246795,0.0000224027,0.00005031867,0.00002005371],"domain_scores_gemma":[0.9994171,0.0002961573,0.00005985711,0.00006327201,0.00009607019,0.00006772771],"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":[0.00004715104,0.00006544252,0.0004042109,0.00005209811,0.00004574405,0.00007129319,0.00005431013,0.6873221,0.003101622,0.29302,0.001735068,0.0140808],"study_design_scores_gemma":[0.000003445308,0.000004996984,0.0000213929,0.000001817143,0.000001810556,0.000005778119,0.000002261389,0.9834714,0.000114393,0.01612896,0.0002403644,0.000003386004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04843853,0.0003553477,0.9399002,0.0008102317,0.0003910808,0.00004665337,0.00007471415,0.0002558026,0.009727491],"genre_scores_gemma":[0.8449886,0.0006580426,0.1326717,0.000308926,0.0001983788,0.0001501666,0.0001833951,0.0002952629,0.02054547],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002772211,"threshold_uncertainty_score":0.009273946,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963359059","doi":"","title":"Variational Message Passing with Structured Inference Networks.","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Inference; Graphical model; Computer science; Message passing; Theoretical computer science; Approximate inference; Variable elimination; Probabilistic logic; Algorithm; Artificial intelligence; Programming language","authors":[{"name":"Lin Wu","is_ca":true},{"name":"Nicolas Hubacher","is_ca":false},{"name":"Mohammad Emtiyaz Khan","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02879153737919618,"gpt":0.3079606261640736,"spread":0.2791690887848774,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004250643,0.001726022,0.001483373,0.001318289,0.0006896806,0.001674892,0.003509962,0.002714617,0.005148088],"category_scores_gemma":[0.0153968,0.00146032,0.001729877,0.001289437,0.002271336,0.004002621,0.003211066,0.004590097,0.0009937203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002541747,"about_ca_system_score_gemma":0.002230251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005334593,"about_ca_topic_score_gemma":0.007839497,"domain_scores_codex":[0.9981281,0.0009805523,0.00008834814,0.0003571116,0.0003232917,0.0001225158],"domain_scores_gemma":[0.9938508,0.004799758,0.0003408215,0.0005307423,0.0002993856,0.0001784101],"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":[0.00007646004,0.00005317088,0.0004197734,0.000124672,0.0001168108,0.00007604489,0.0001125361,0.662225,0.0008071132,0.2901669,0.002557486,0.04326401],"study_design_scores_gemma":[0.000008385926,0.000008975977,0.00002055564,0.000007480252,0.00000814022,0.00001168443,0.000003462743,0.9048937,0.0002423279,0.09409431,0.00069602,0.000004951289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00137434,0.0001659044,0.9971784,0.0002142038,0.00003092516,0.00003343673,0.00006368224,0.0002279844,0.0007110005],"genre_scores_gemma":[0.2563048,0.0007288526,0.7331628,0.0006880799,0.0003291746,0.0005904001,0.000755826,0.000470913,0.006969178],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005334593,"threshold_uncertainty_score":0.02247983,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2786478526","doi":"","title":"Adversarial Policy Gradient for Alternating Markov Games","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"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; Artificial neural network; Computer science; Markov decision process; Markov chain; Gradient descent; Mathematical optimization; Temporal difference learning; Artificial intelligence; Markov process; Machine learning; Mathematics; Statistics","authors":[{"name":"Chao Gao","is_ca":true},{"name":"Martin Mueller","is_ca":true},{"name":"Ryan Hayward","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05030579220343445,"gpt":0.3677090667664834,"spread":0.317403274563049,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001828367,0.00120504,0.001253356,0.0005399686,0.0003984932,0.0008780608,0.001063143,0.001212926,0.003692609],"category_scores_gemma":[0.007792008,0.000496726,0.000555927,0.0003530013,0.001671767,0.001162728,0.001379933,0.001903667,0.0004538065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0016767,"about_ca_system_score_gemma":0.00154991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004118285,"about_ca_topic_score_gemma":0.003329647,"domain_scores_codex":[0.9991131,0.000464157,0.00003379303,0.0001444243,0.0001523318,0.00009210389],"domain_scores_gemma":[0.9965191,0.002739364,0.0002177434,0.000127071,0.0002333358,0.0001633551],"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":[0.00006494252,0.00003125739,0.0002983768,0.00004999825,0.0000195218,0.00004271531,0.00004191282,0.9352189,0.0004969276,0.05240951,0.0007614577,0.01056438],"study_design_scores_gemma":[0.000005016308,0.000008715378,0.00001898787,0.000003119792,0.000001553768,0.000003681557,0.000002162266,0.9887982,0.0000904999,0.01089428,0.0001714936,0.000002252687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02031145,0.0002300542,0.9742187,0.0003856224,0.00006183327,0.00006990109,0.00005318905,0.0003344929,0.004334744],"genre_scores_gemma":[0.8357289,0.0003065134,0.1534143,0.00035602,0.00007336227,0.0004107601,0.0001769059,0.000179639,0.009353611],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004118285,"threshold_uncertainty_score":0.01235294,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963633076","doi":"","title":"Learning to encode motion using spatio-temporal synchrony","year":2014,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":7,"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; ENCODE; Motion (physics); Motion estimation; Margin (machine learning); Task (project management); Sequence (biology); Machine learning; Pattern recognition (psychology); Computer vision; Fraction (chemistry)","authors":[{"name":"Kishore Konda","is_ca":false},{"name":"Roland Memisevic","is_ca":true},{"name":"Vincent Michalski","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04797624201467336,"gpt":0.3647122563108589,"spread":0.3167360142961855,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007849363,0.0005707133,0.0004588233,0.0004059705,0.0001936721,0.0005534329,0.0006620517,0.0006292513,0.001434098],"category_scores_gemma":[0.003918289,0.0002781678,0.0003468986,0.0005062478,0.0006761865,0.001726256,0.001131736,0.001137696,0.0003231871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004364157,"about_ca_system_score_gemma":0.0004553684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001432685,"about_ca_topic_score_gemma":0.001321607,"domain_scores_codex":[0.9997423,0.00006811078,0.0000148627,0.00009383033,0.00004450788,0.00003641006],"domain_scores_gemma":[0.9990133,0.0005220553,0.0001938095,0.000116285,0.0000750904,0.00007947603],"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":[0.0004930427,0.0002142568,0.005687809,0.000116319,0.00009665645,0.0002056717,0.0001632411,0.6123445,0.05593847,0.02940922,0.002017051,0.2933138],"study_design_scores_gemma":[0.000007882385,0.00004681456,0.0005097616,0.000005820149,0.000006106961,0.00002529284,0.000009574888,0.9852604,0.003972413,0.009922896,0.0002278275,0.000005282126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1411099,0.0002426266,0.8566272,0.0003906523,0.00005264065,0.00002925175,0.00008745561,0.000330857,0.001129344],"genre_scores_gemma":[0.9540981,0.000182179,0.04410202,0.0000844847,0.00005565092,0.00002581833,0.0001281071,0.00004182975,0.001281832],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001434098,"threshold_uncertainty_score":0.004797518,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3041421878","doi":"","title":"Solving ODE with Universal Flows: Approximation Theory for Flow-Based Models","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Simulation Techniques and Applications","field":"Decision Sciences","cited_by":6,"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":"Ode; Computer science; Flow (mathematics); Applied mathematics; Mathematical optimization; Mathematical economics; Mathematics; Geometry","authors":[{"name":"Chin-Wei Huang","is_ca":true},{"name":"Laurent Dinh","is_ca":false},{"name":"Aaron Courville","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2281806528029223,"gpt":0.4208250527881581,"spread":0.1926443999852357,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002069979,0.001015992,0.001711624,0.001291667,0.0006681653,0.001905423,0.001548291,0.001785283,0.002153166],"category_scores_gemma":[0.008822869,0.0006769926,0.00153017,0.001085374,0.001790878,0.003499482,0.003278958,0.002691253,0.0002747749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001417336,"about_ca_system_score_gemma":0.001771229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00566016,"about_ca_topic_score_gemma":0.003501806,"domain_scores_codex":[0.9992544,0.00029924,0.00005470325,0.0001311157,0.0001856332,0.00007492638],"domain_scores_gemma":[0.9975419,0.001548705,0.0002070263,0.0002313727,0.0003287798,0.0001422069],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002955084,0.00003920469,0.0003974536,0.0001089931,0.00004181094,0.00003156278,0.00008444906,0.5762966,0.0006113126,0.4001697,0.001040463,0.02114888],"study_design_scores_gemma":[0.00000218229,0.000005145844,0.00001787839,0.00000727901,0.000004143003,0.000005289238,0.000005162428,0.9400667,0.00009072289,0.05947552,0.000316941,0.000003005374],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005252313,0.000231444,0.9925408,0.0001937471,0.00003923439,0.00001479876,0.00003434973,0.00006791843,0.001625279],"genre_scores_gemma":[0.6128586,0.001746298,0.3724415,0.0004143254,0.0002900396,0.0003122853,0.0004352952,0.0002442535,0.01125735],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00566016,"threshold_uncertainty_score":0.01125443,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2966262171","doi":"","title":"Reproducibility in Machine Learning for Health","year":2019,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":6,"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; Field (mathematics); Reproducibility; Machine learning; Scale (ratio); Artificial intelligence; Data science; Human health; Medicine","authors":[{"name":"Matthew B. A. McDermott","is_ca":false},{"name":"Shirly Wang","is_ca":true},{"name":"Nikki Marinsek","is_ca":false},{"name":"Rajesh Ranganath","is_ca":false},{"name":"Marzyeh Ghassemi","is_ca":true},{"name":"Luca Foschini","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.088447391195338,"gpt":0.3988270749660196,"spread":0.3103796837706816,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4609308,0.001360204,0.003361754,0.008808844,0.004230001,0.02047279,0.006945753,0.005893373,0.01025856],"category_scores_gemma":[0.8098052,0.001540337,0.003979392,0.009165728,0.02012133,0.01848185,0.01279689,0.008120709,0.003726515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005418624,"about_ca_system_score_gemma":0.01611867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001973735,"about_ca_topic_score_gemma":0.001443039,"domain_scores_codex":[0.4879948,0.3565743,0.04082423,0.03209327,0.07976238,0.002750929],"domain_scores_gemma":[0.07676753,0.6981449,0.02725886,0.1577353,0.03817299,0.001920545],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001736158,0.0003718343,0.0529915,0.01507469,0.004242722,0.0006110572,0.009603457,0.01059423,0.00230904,0.2839007,0.04954547,0.5690191],"study_design_scores_gemma":[0.0006588788,0.001141802,0.02577298,0.01055612,0.001687618,0.001127398,0.002409906,0.02145392,0.01304608,0.6874776,0.2341982,0.000469326],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.04686713,0.0867136,0.6601108,0.1125983,0.0139036,0.002909661,0.006030561,0.00539396,0.06547231],"genre_scores_gemma":[0.6441832,0.01378927,0.2882324,0.02092542,0.01011424,0.005556368,0.005322288,0.003079429,0.008797452],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.5390692,"threshold_uncertainty_score":0.6647683,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2903153676","doi":"","title":"Leveraging Constraint Logic Programming for Neural Guided Program Synthesis.","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research; University of Toronto","funders":"","keywords":"Computer science; Logic programming; Programming language; Constraint programming; Concurrent constraint logic programming; Constraint logic programming; Logic program; Constraint satisfaction; Constraint (computer-aided design); Inductive programming; Theoretical computer science; Artificial intelligence; Functional logic programming; Programming paradigm; Mathematical optimization; Mathematics","authors":[{"name":"Lisa Zhang","is_ca":true},{"name":"Gregory Rosenblatt","is_ca":false},{"name":"Ethan Fetaya","is_ca":true},{"name":"Renjie Liao","is_ca":true},{"name":"William E. Byrd","is_ca":false},{"name":"Raquel Urtasun","is_ca":false},{"name":"Richard S. Zemel","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1236522775266924,"gpt":0.3885364596589281,"spread":0.2648841821322356,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000793537,0.0007880935,0.0005463319,0.0006592454,0.0004068303,0.001115567,0.001478301,0.0009289826,0.005522368],"category_scores_gemma":[0.00450811,0.0004524004,0.0008259738,0.0007989804,0.0009076907,0.00162135,0.001357966,0.001867104,0.0008215808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008192378,"about_ca_system_score_gemma":0.001684528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005831415,"about_ca_topic_score_gemma":0.01626067,"domain_scores_codex":[0.9994258,0.0001688356,0.00003921653,0.0001295727,0.0001588168,0.00007784989],"domain_scores_gemma":[0.9984272,0.001128382,0.0000927398,0.0001495123,0.0001564103,0.00004581597],"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":[0.0001504207,0.0001839415,0.0006190416,0.0003042453,0.00009254133,0.000163125,0.0001165693,0.6733792,0.007826538,0.06418832,0.005737187,0.2472389],"study_design_scores_gemma":[0.00001150855,0.00001942579,0.00002751497,0.00001514504,0.00001153867,0.00001343575,0.00001471426,0.9659635,0.00146483,0.03124493,0.001209846,0.000003648644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01388949,0.0003353458,0.9763525,0.0003287884,0.00005464397,0.0001140958,0.0002147106,0.001362287,0.007348033],"genre_scores_gemma":[0.378216,0.0003296268,0.6159045,0.0003581035,0.00003636904,0.000311691,0.0006812328,0.0004147929,0.003747722],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005831415,"threshold_uncertainty_score":0.01847416,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2787038193","doi":"","title":"Boundary Seeking GANs","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; University of Waterloo","funders":"","keywords":"Discriminator; Generator (circuit theory); Boundary (topology); Measure (data warehouse); Computer science; Decision boundary; Image (mathematics); Differentiable function; Stability (learning theory); Generative grammar; Scale (ratio); Artificial intelligence; Character (mathematics); Pattern recognition (psychology); Algorithm; Mathematics; Machine learning; Data mining; Mathematical analysis; Geometry; Power (physics)","authors":[{"name":"R Devon Hjelm","is_ca":false},{"name":"Athul Paul Jacob","is_ca":true},{"name":"Adam Trischler","is_ca":false},{"name":"Gerry Che","is_ca":false},{"name":"Kyunghyun Cho","is_ca":false},{"name":"Yoshua Bengio","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04253164387224141,"gpt":0.3256573984082439,"spread":0.2831257545360025,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008319003,0.0008167734,0.0007452843,0.0004325836,0.0002759363,0.0007119888,0.001108278,0.0009667676,0.005238963],"category_scores_gemma":[0.002893675,0.0003344947,0.0005771052,0.0003347049,0.0008307192,0.001077156,0.001193631,0.001736383,0.001151007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006477652,"about_ca_system_score_gemma":0.0004387069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001079121,"about_ca_topic_score_gemma":0.001737916,"domain_scores_codex":[0.9996055,0.0001366436,0.00001384195,0.0001111743,0.00008990645,0.00004308085],"domain_scores_gemma":[0.9993384,0.0003903788,0.000046268,0.00009805898,0.00008876676,0.00003807056],"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":[0.0001234542,0.00005887496,0.000742422,0.0001034104,0.0000415122,0.0001375297,0.000113589,0.79557,0.008342671,0.09443355,0.008331484,0.09200147],"study_design_scores_gemma":[0.000008405067,0.00001636263,0.00006448467,0.000008968992,0.000003641482,0.00003444802,0.000006014941,0.9713201,0.001228536,0.02567627,0.001627713,0.000005034028],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01146229,0.0002647038,0.9812191,0.0002362223,0.00006724251,0.00005587262,0.0001636661,0.000941597,0.005589338],"genre_scores_gemma":[0.6681926,0.0004136353,0.3149268,0.0007106976,0.0001167628,0.0002866832,0.001007418,0.0006348336,0.01371047],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005238963,"threshold_uncertainty_score":0.01752603,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964469479","doi":"","title":"Understanding the Relation Between Maximum-Entropy Inverse Reinforcement Learning and Behaviour Cloning.","year":2019,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"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; Principle of maximum entropy; Cloning (programming); Artificial intelligence; Computer science; Relation (database); Inverse; Entropy (arrow of time); Mathematics; Machine learning; Data mining; Physics; Thermodynamics","authors":[{"name":"Seyed Kamyar Seyed Ghasemipour","is_ca":true},{"name":"Shane Gu","is_ca":false},{"name":"Richard S. Zemel","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0945946462711303,"gpt":0.3266313768676395,"spread":0.2320367305965092,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001423015,0.0003764164,0.0005857456,0.0004956975,0.0004130627,0.001466989,0.001509281,0.001372467,0.003745248],"category_scores_gemma":[0.01488439,0.0005112981,0.0005555482,0.0003766083,0.002431075,0.00373569,0.00158099,0.002203366,0.0003348285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001088368,"about_ca_system_score_gemma":0.0008043373,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002052657,"about_ca_topic_score_gemma":0.001838586,"domain_scores_codex":[0.9992329,0.0003098939,0.00004043762,0.0001757301,0.0001566294,0.00008449442],"domain_scores_gemma":[0.9930681,0.004860662,0.0007528689,0.0006064227,0.0004369791,0.0002749385],"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":[0.0001222992,0.0001241358,0.002878579,0.000169793,0.00009196407,0.0001462829,0.0003235787,0.272945,0.004688954,0.6668865,0.001304212,0.0503188],"study_design_scores_gemma":[0.00000820924,0.00003634731,0.0006175287,0.00001546159,0.00001051116,0.00004449149,0.00002320916,0.5136353,0.0006543813,0.4844929,0.000450441,0.00001136844],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.053229,0.0006498378,0.9341862,0.001338179,0.00007746276,0.00003841288,0.00006988194,0.0001559196,0.01025504],"genre_scores_gemma":[0.9333039,0.0003341891,0.06209532,0.0002185119,0.00005084621,0.00007349517,0.00008371508,0.00006023264,0.003779752],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003745248,"threshold_uncertainty_score":0.01252913,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2995372087","doi":"","title":"Learning the Arrow of Time for Problems in Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"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":"Arrow; Arrow of time; Computer science; Reinforcement learning; Markov decision process; Reachability; Artificial intelligence; Machine learning; Class (philosophy); Function (biology); Markov process; Selection (genetic algorithm); Process (computing); Theoretical computer science; Mathematics","authors":[{"name":"Nasim Rahaman","is_ca":false},{"name":"Steffen Wolf","is_ca":false},{"name":"Anirudh Goyal","is_ca":true},{"name":"Roman Remme","is_ca":false},{"name":"Yoshua Bengio","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05955057235187068,"gpt":0.3172682931974696,"spread":0.2577177208455989,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002553545,0.0008242182,0.0008684381,0.0006171106,0.0006274078,0.001780859,0.001101288,0.001621792,0.003550589],"category_scores_gemma":[0.01387671,0.0004120594,0.0008505912,0.0006235651,0.002704767,0.005086039,0.001807498,0.00458183,0.0003341021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001867161,"about_ca_system_score_gemma":0.001176526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002410463,"about_ca_topic_score_gemma":0.002255719,"domain_scores_codex":[0.9990543,0.0004534036,0.00005860139,0.0002395171,0.0001253738,0.00006882441],"domain_scores_gemma":[0.9949659,0.003940517,0.000415997,0.0002753604,0.0001965755,0.0002058043],"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":[0.0001799698,0.00009638528,0.001496673,0.0002318705,0.00006269703,0.00007176805,0.0002536391,0.4776212,0.001802988,0.461256,0.00142641,0.05550043],"study_design_scores_gemma":[0.00001481261,0.00003956532,0.0001389681,0.00002447399,0.000006924173,0.00001245537,0.00002338092,0.6537325,0.0003882343,0.3446155,0.0009920171,0.00001122537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0172671,0.0005251392,0.9798452,0.0008020037,0.0000380623,0.00002315368,0.00004201003,0.0001154161,0.001341876],"genre_scores_gemma":[0.6324654,0.001295026,0.3617703,0.000275282,0.0001841842,0.0002069498,0.0001983078,0.0001239662,0.003480573],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003550589,"threshold_uncertainty_score":0.01354724,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2995040055","doi":"","title":"Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"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":"Reinforcement learning; Computer science; Context (archaeology); Generalization; Artificial intelligence; Decomposition; State (computer science); Machine learning; Mathematics","authors":[{"name":"Anirudh Goyal","is_ca":true},{"name":"Shagun Sodhani","is_ca":true},{"name":"Jonathan Binas","is_ca":false},{"name":"Xue Bin Peng","is_ca":false},{"name":"Sergey Levine","is_ca":false},{"name":"Yoshua Bengio","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03585979767524092,"gpt":0.2877329669438369,"spread":0.251873169268596,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002080761,0.0007965983,0.001149424,0.000374803,0.0004258653,0.0009927446,0.001670972,0.00100905,0.002191281],"category_scores_gemma":[0.006785824,0.0004788376,0.0005067021,0.0003340623,0.001462568,0.001696157,0.00163521,0.001553625,0.0003118448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001382437,"about_ca_system_score_gemma":0.001459161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004258293,"about_ca_topic_score_gemma":0.003978863,"domain_scores_codex":[0.9988752,0.0003721208,0.00006275684,0.0002356628,0.0002723764,0.0001819181],"domain_scores_gemma":[0.9969845,0.001455346,0.0003934198,0.0004373956,0.0003612055,0.0003681829],"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":[0.0002035694,0.0001322902,0.0009853044,0.00004165158,0.00004937849,0.00006647327,0.00008453937,0.9475821,0.00281169,0.02088561,0.0005588253,0.0265986],"study_design_scores_gemma":[0.00001801032,0.00003935879,0.00007648888,0.000002341392,0.000004580063,0.000006184674,0.000004636787,0.9928604,0.0003468688,0.006516262,0.0001206621,0.000004331596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2262359,0.0002340944,0.7651577,0.0006098082,0.00007493919,0.0001411488,0.00007087168,0.0008173859,0.006658184],"genre_scores_gemma":[0.9661897,0.00004267916,0.0321318,0.00009137716,0.00001576966,0.0000784876,0.00004150745,0.00002352323,0.001384983],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004258293,"threshold_uncertainty_score":0.01100421,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2908074561","doi":"","title":"An Evaluation of Fisher Approximations Beyond Kronecker Factorization","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":5,"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":"Kronecker delta; Factorization; Approximations of π; Computer science; Mathematics; Algorithm; Applied mathematics; Physics","authors":[{"name":"César Laurent","is_ca":true},{"name":"Thomas George","is_ca":false},{"name":"Xavier Bouthillier","is_ca":true},{"name":"Nicolas Ballas","is_ca":true},{"name":"Pascal Vincent","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08524321913795825,"gpt":0.3911625733095208,"spread":0.3059193541715626,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005220151,0.001026226,0.001002364,0.001206967,0.0006389073,0.001842174,0.001328638,0.001728802,0.00642648],"category_scores_gemma":[0.0281716,0.0002671164,0.0005324528,0.001059073,0.0007829264,0.004621959,0.001680955,0.001284811,0.001008538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001040534,"about_ca_system_score_gemma":0.001210819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006288447,"about_ca_topic_score_gemma":0.00846199,"domain_scores_codex":[0.9983089,0.0007930597,0.00007092327,0.0001887555,0.0005218965,0.0001165148],"domain_scores_gemma":[0.9901441,0.006682599,0.0002433684,0.001269943,0.001409177,0.0002507654],"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":[0.002772999,0.0004974296,0.003468223,0.0006689678,0.0003032793,0.0001784975,0.0002108921,0.4345647,0.004995816,0.1156699,0.02323592,0.4134335],"study_design_scores_gemma":[0.00004315781,0.0001580277,0.0004024293,0.00005544676,0.00003257036,0.00006292139,0.00005055191,0.9692774,0.001534581,0.02669273,0.001675803,0.00001445356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1956012,0.007331418,0.7672409,0.002313644,0.0008881685,0.0001677914,0.001235761,0.003134359,0.02208672],"genre_scores_gemma":[0.7313046,0.001607323,0.2573695,0.0004165311,0.0002151158,0.00007585198,0.002657426,0.000489532,0.005864133],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00642648,"threshold_uncertainty_score":0.02760708,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2787849668","doi":"","title":"Extending the Framework of Equilibrium Propagation to General Dynamics","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":5,"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; Backpropagation; Feed forward; Generalization; Function (biology); Learning rule; Artificial neural network; Simple (philosophy); Degree (music); Algorithm; Point (geometry); Symmetry (geometry); Artificial intelligence; Mathematics; Physics","authors":[{"name":"Benjamin Scellier","is_ca":false},{"name":"Anirudh Goyal","is_ca":true},{"name":"Jonathan Binas","is_ca":false},{"name":"Thomas Mésnard","is_ca":false},{"name":"Yoshua Bengio","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06141614500765161,"gpt":0.3636815414519436,"spread":0.302265396444292,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001322258,0.0008043415,0.0005407089,0.0006483958,0.0004192505,0.0010116,0.001306428,0.001139766,0.002114667],"category_scores_gemma":[0.004678624,0.0003958092,0.0006585565,0.0004740682,0.001292893,0.002054547,0.001489334,0.001388001,0.000467351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008871361,"about_ca_system_score_gemma":0.0009201374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003851691,"about_ca_topic_score_gemma":0.00253827,"domain_scores_codex":[0.9995769,0.0001564227,0.00002068661,0.00008264052,0.0001236744,0.00003959611],"domain_scores_gemma":[0.9991701,0.0004225999,0.00007472939,0.0001082407,0.0001884309,0.00003594751],"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":[0.00002095352,0.00002054409,0.0002674026,0.00006159223,0.00002650221,0.00008153523,0.000086777,0.608792,0.002703323,0.3570876,0.0006797081,0.03017209],"study_design_scores_gemma":[0.000003874781,0.000008572777,0.00003200532,0.00000343263,0.000002337988,0.00001326445,0.000002860571,0.9289194,0.0002386155,0.06987169,0.0008997141,0.00000407664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003719616,0.00008314349,0.9945074,0.0001116275,0.00001948937,0.00001125654,0.00001297343,0.0000968042,0.001437838],"genre_scores_gemma":[0.4352582,0.0008747284,0.5559901,0.0001771162,0.0001494089,0.0002062142,0.000103982,0.0002578103,0.006982345],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003851691,"threshold_uncertainty_score":0.007658541,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}