{"meta":{"query_hash":"0738d2126206","filters":{"venue":"International Conference on Learning Representations"},"cohort_total":80,"direct_labels_cover":0,"predictions_cover":80,"exported":80,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/0738d2126206","api":"https://metacan.xera.ac/api/v1/cohort?venue=International+Conference+on+Learning+Representations"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.08007162583441403,"score_gpt":0.35911400772572205,"score_spread":0.27904238189130803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2750933313","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003326474,0.0000025585862,0.96762484,0.002297752,0.00060098764,0.0002812279,0.00003258543,0.00030381078,0.025529735],"genre_scores_gemma":[0.70612127,0.000008581649,0.29238847,0.000050478153,0.000059480604,0.00005980489,0.00022857406,0.000016254618,0.0010670803],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823004,0.00009106645,0.0003743034,0.00055014016,0.000518096,0.00023634153],"domain_scores_gemma":[0.99741155,0.00013262714,0.000560761,0.0008626862,0.0009269862,0.00010540107],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00018936043,0.000195645,0.00016275051,0.0002949791,0.001078124,0.001440318,0.0015179005,0.00009151713,0.0008622464],"category_scores_gemma":[0.0015278208,0.00021289614,0.00007445255,0.0002123238,0.00013737915,0.0014811622,0.00033361473,0.00029787322,0.000050224324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012554414,0.00013252799,0.0043354584,0.0000045526813,0.00007767584,0.000007299893,0.000788675,0.5831189,0.00061323715,0.40832716,0.00022317309,0.0023587472],"study_design_scores_gemma":[0.00036499972,0.000040217452,0.0039764936,0.00004411042,0.000009361835,0.000012070261,0.000105298626,0.99003595,0.0004701712,0.0044340855,0.0002909507,0.0002162613],"about_ca_topic_score_codex":0.0000660471,"about_ca_topic_score_gemma":0.000008406027,"teacher_disagreement_score":0.7027948,"about_ca_system_score_codex":0.0001397017,"about_ca_system_score_gemma":0.00015142499,"threshold_uncertainty_score":0.9995963},"labels":[],"label_agreement":null},{"id":"W2751220357","doi":"","title":"Recurrent Normalization Propagation","year":2017,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Normalization (sociology); Initialization; Computer science; Computation; Parametrization (atmospheric modeling); Artificial intelligence; Generative grammar; Machine learning; Algorithm","score_opus":0.08877434203423155,"score_gpt":0.3726418993060283,"score_spread":0.28386755727179674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2751220357","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029882558,0.000004647066,0.81146806,0.011780725,0.001449764,0.00017680101,0.0000020905688,0.00020507471,0.14503026],"genre_scores_gemma":[0.9908104,0.00002475907,0.0055834875,0.0000708797,0.00014408451,0.000038823808,0.000027596529,0.000006380716,0.0032935939],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878687,0.00006528804,0.00021338527,0.00037017107,0.00043039085,0.00013391432],"domain_scores_gemma":[0.99861985,0.00004599878,0.00028959286,0.0006157782,0.00037488787,0.000053860444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019738033,0.00009517844,0.000075280295,0.00013046326,0.00062883674,0.001002525,0.0011905383,0.000039805014,0.00013410849],"category_scores_gemma":[0.00067874626,0.00009734544,0.00004362774,0.000051602663,0.000043320913,0.001103678,0.00022869329,0.0002110507,0.0001736804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008450425,0.00004939771,0.011159467,0.0000032666942,0.000019422667,0.0000064017186,0.001012934,0.0069264052,0.0008104977,0.90988296,0.0001765323,0.06994423],"study_design_scores_gemma":[0.00027222995,0.000050069728,0.027732855,0.00005231322,0.0000032393493,0.000006492397,0.00008449262,0.9585074,0.000682722,0.01027299,0.0021941033,0.0001410748],"about_ca_topic_score_codex":0.00007408525,"about_ca_topic_score_gemma":0.000017166494,"teacher_disagreement_score":0.96092784,"about_ca_system_score_codex":0.00005803447,"about_ca_system_score_gemma":0.00007165373,"threshold_uncertainty_score":0.96673715},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.027347600635553772,"score_gpt":0.2982712933071036,"score_spread":0.27092369267154987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2751842161","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006258005,0.000011021975,0.9649398,0.0063131903,0.0009801749,0.00014729398,0.000002713923,0.000106855616,0.021240944],"genre_scores_gemma":[0.95088595,0.000017067825,0.045364995,0.00015854185,0.0006397744,0.00003766918,0.000019766298,0.0000159183,0.0028602881],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984215,0.00014186036,0.00017917872,0.00056999235,0.0004245693,0.00026291076],"domain_scores_gemma":[0.9984544,0.00015078692,0.00040675775,0.00059258565,0.00030303033,0.0000924737],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00021926395,0.0002008797,0.00016579885,0.00011061923,0.0015607564,0.00229326,0.0012362656,0.000074629526,0.000078464545],"category_scores_gemma":[0.00030470197,0.00017360186,0.000074376134,0.00008042408,0.000115586045,0.0014284323,0.0003160682,0.0005036902,0.000025293943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001382996,0.00009559592,0.0060495157,0.0000039715515,0.0003037454,0.00011908489,0.0030473033,0.77270263,0.0059791524,0.118900865,0.0010167555,0.091643065],"study_design_scores_gemma":[0.00061419094,0.00010477029,0.0066691255,0.00007612257,0.000016330314,0.000017085677,0.00035394606,0.9886411,0.0011478964,0.0012025053,0.00087522087,0.0002817005],"about_ca_topic_score_codex":0.00035971243,"about_ca_topic_score_gemma":0.000107361215,"teacher_disagreement_score":0.944628,"about_ca_system_score_codex":0.00006890718,"about_ca_system_score_gemma":0.00010816987,"threshold_uncertainty_score":0.99973905},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.1464190826716082,"score_gpt":0.4031299499396052,"score_spread":0.256710867267997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2753160622","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024072437,0.0000048021548,0.86823976,0.006817534,0.00048740717,0.00025901882,0.0000037278955,0.00026581483,0.12151471],"genre_scores_gemma":[0.9072876,0.000043648644,0.05643923,0.00026457448,0.00011971916,0.00014532347,0.000083738574,0.000024584611,0.0355916],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980676,0.00010943309,0.00034065067,0.00063114974,0.0005573757,0.00029378623],"domain_scores_gemma":[0.9978196,0.00027363957,0.0005207464,0.00057404744,0.0006788529,0.00013311622],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000421788,0.0001986207,0.00017361974,0.0002514542,0.0016858525,0.0018537592,0.0014988063,0.000091722606,0.00029522824],"category_scores_gemma":[0.0027066767,0.00021750947,0.00013542957,0.00009377798,0.00009893464,0.0012844596,0.00025654017,0.00047178112,0.00017534611],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028817773,0.000038660382,0.00088452274,0.0000030739832,0.000032290747,0.0000036520737,0.0016752855,0.6952714,0.00040848195,0.29334703,0.00012894481,0.0081778625],"study_design_scores_gemma":[0.00073081977,0.00009992647,0.00097235333,0.000043744953,0.000008408187,0.000008465822,0.00039971046,0.9863824,0.0001173739,0.007791327,0.0032111737,0.00023429113],"about_ca_topic_score_codex":0.000059760383,"about_ca_topic_score_gemma":0.000009775063,"teacher_disagreement_score":0.90488034,"about_ca_system_score_codex":0.00007995829,"about_ca_system_score_gemma":0.00019633728,"threshold_uncertainty_score":0.9996138},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.2214864104494036,"score_gpt":0.4322454878549099,"score_spread":0.2107590774055063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2753228334","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009094243,0.0000038309095,0.97250164,0.0074413265,0.00044483665,0.00021795218,0.000122065496,0.00040253234,0.0097715985],"genre_scores_gemma":[0.92295444,0.00003775014,0.07368387,0.00008707881,0.00020791171,0.00005076521,0.0012518188,0.000020261587,0.0017061157],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808466,0.00011689471,0.00031988954,0.00079119415,0.00043918059,0.0002481497],"domain_scores_gemma":[0.9976089,0.00020080798,0.00016106559,0.0015723148,0.00037314254,0.00008375937],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004973911,0.00017200316,0.00016052819,0.00018643981,0.0010192466,0.0014275752,0.0046437494,0.000074368705,0.00008736163],"category_scores_gemma":[0.001503627,0.00018482406,0.000072387294,0.000049919214,0.000079560494,0.0018378982,0.0008540447,0.00054239493,0.000022764534],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010614099,0.00047291984,0.0037250647,0.000025544887,0.00030577686,0.00004460653,0.0027194934,0.07324625,0.0043362076,0.6542604,0.001826239,0.25893137],"study_design_scores_gemma":[0.00037070605,0.00009282017,0.0004502658,0.00007528422,0.000012492994,0.000008776703,0.00012793418,0.98882484,0.0002557001,0.005906337,0.0036806792,0.00019415861],"about_ca_topic_score_codex":0.00029611393,"about_ca_topic_score_gemma":0.00006710414,"teacher_disagreement_score":0.9155786,"about_ca_system_score_codex":0.000045999725,"about_ca_system_score_gemma":0.00013865676,"threshold_uncertainty_score":0.99960905},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.031554453052495206,"score_gpt":0.32419013458969764,"score_spread":0.29263568153720243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2785948534","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017860444,0.0000063233006,0.9243043,0.0035263484,0.0006315684,0.0001796455,0.0000010101314,0.00044095988,0.0530494],"genre_scores_gemma":[0.9871295,0.000015819818,0.005333061,0.0003050997,0.0005668472,0.00002630485,0.000051912102,0.000026355778,0.0065451143],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997707,0.00022551756,0.00034000125,0.00059091055,0.0007317698,0.00040480145],"domain_scores_gemma":[0.998197,0.00020114517,0.0003335754,0.00045617597,0.00067256315,0.00013951343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019919102,0.00024478778,0.00017438391,0.00047633259,0.000558124,0.000728846,0.0011904512,0.00008664132,0.0003598428],"category_scores_gemma":[0.00044200965,0.00022299857,0.00008436919,0.00073660066,0.00023033726,0.0006319091,0.00026240692,0.00078069494,0.00009284297],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030559444,0.000014665001,0.015172842,0.0000017317911,0.00006474299,0.000011689906,0.0009398565,0.86299914,0.00015767121,0.11343006,0.00010227691,0.00707478],"study_design_scores_gemma":[0.00046802318,0.0005168562,0.018056551,0.000040605522,0.000007939104,0.000034679146,0.0002290695,0.97767574,0.00012799885,0.0009978125,0.0015911194,0.00025362772],"about_ca_topic_score_codex":0.00017660244,"about_ca_topic_score_gemma":0.000030029425,"teacher_disagreement_score":0.96926904,"about_ca_system_score_codex":0.00009306435,"about_ca_system_score_gemma":0.00013928994,"threshold_uncertainty_score":0.9093618},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.060654942516671785,"score_gpt":0.3641504852356096,"score_spread":0.3034955427189378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2786263712","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041929656,0.000015656362,0.9742188,0.009353999,0.0012574967,0.0005722903,0.000023152495,0.00029641986,0.010069221],"genre_scores_gemma":[0.95713454,0.00002181044,0.03917479,0.00029487436,0.0006466597,0.00041485718,0.00021007707,0.000020099593,0.0020823034],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823016,0.000088150875,0.00035112837,0.00065456174,0.0003598285,0.00031615281],"domain_scores_gemma":[0.9978947,0.00040965967,0.00026402425,0.00051719835,0.0007961817,0.0001182371],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014098003,0.00019722013,0.00014766134,0.00018276641,0.00055844407,0.00033208184,0.0010642566,0.000084091655,0.000166379],"category_scores_gemma":[0.00036400728,0.00019897973,0.00010883527,0.00045718582,0.00014018125,0.0006195631,0.00018248928,0.00041255658,0.000088526765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000657004,0.0001845354,0.0013398101,0.000004816306,0.00008321337,0.0000020424598,0.0011662261,0.054346666,0.00074938143,0.83758146,0.004697937,0.0997782],"study_design_scores_gemma":[0.00032799612,0.00019294389,0.0020177292,0.000020548927,0.000007820992,0.0000075572457,0.00007149953,0.96812284,0.00020734667,0.010158647,0.01865998,0.00020508732],"about_ca_topic_score_codex":0.0000063498223,"about_ca_topic_score_gemma":0.00001815146,"teacher_disagreement_score":0.95294154,"about_ca_system_score_codex":0.000078959354,"about_ca_system_score_gemma":0.000053594915,"threshold_uncertainty_score":0.8114158},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0384290167936386,"score_gpt":0.3438460892558937,"score_spread":0.30541707246225513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2786406308","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013045955,0.000011972543,0.9729536,0.005693659,0.0008672475,0.0006108079,0.0000051618376,0.00032999052,0.0064816023],"genre_scores_gemma":[0.980784,0.000008944166,0.016835574,0.00029186334,0.00049053127,0.00046945523,0.000088445806,0.000019697805,0.0010114899],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824566,0.00008964004,0.0003332213,0.00063595775,0.0003863193,0.00030918457],"domain_scores_gemma":[0.99800444,0.00039898077,0.0002519253,0.00045345526,0.0007881204,0.00010305957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017340662,0.00017568792,0.00013077083,0.00018896915,0.0005511699,0.0002819451,0.0009481361,0.00006542169,0.00008407126],"category_scores_gemma":[0.00030606618,0.00017640645,0.00009498589,0.0003950857,0.00014158209,0.00038628068,0.00021230278,0.0002686082,0.00007888459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005414596,0.00010009323,0.00048754652,0.0000029530836,0.00003063111,0.0000023668063,0.00056356576,0.6278361,0.0015772459,0.33255675,0.0004935177,0.03629505],"study_design_scores_gemma":[0.00035404981,0.00021268427,0.0018607627,0.000016682947,0.0000072954376,0.000008115101,0.00006966018,0.9901053,0.00059966976,0.0044984557,0.0020872108,0.00018013208],"about_ca_topic_score_codex":0.000008812057,"about_ca_topic_score_gemma":0.000009404709,"teacher_disagreement_score":0.96773803,"about_ca_system_score_codex":0.000079010424,"about_ca_system_score_gemma":0.00003617492,"threshold_uncertainty_score":0.71936464},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.05030579220343445,"score_gpt":0.3677090667664834,"score_spread":0.31740327456304895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2786478526","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063223206,0.0000022429256,0.8893006,0.007155095,0.0017437128,0.00028503055,0.0000054930897,0.00025105663,0.09493446],"genre_scores_gemma":[0.9567552,0.000013554368,0.029750917,0.00036565002,0.0011780227,0.00008053984,0.000047764443,0.000018303821,0.011790022],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981179,0.00009509576,0.00036258425,0.00051870506,0.00057465065,0.00033103404],"domain_scores_gemma":[0.998107,0.0003809718,0.00029164992,0.00039683378,0.00072130834,0.000102228165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030480872,0.00017331747,0.00013928818,0.00040933563,0.00040466443,0.0005135774,0.0011723143,0.000058806923,0.00020703652],"category_scores_gemma":[0.0017395058,0.00018083466,0.00011207079,0.00028396712,0.00012945442,0.0005105786,0.00026384267,0.00026242985,0.00019739395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055874763,0.00005264203,0.003097879,0.000006553353,0.000117819975,0.000005023688,0.0030551874,0.09530484,0.0011727737,0.8742134,0.0016225069,0.021295518],"study_design_scores_gemma":[0.00077692594,0.00037732528,0.0026122169,0.000055243538,0.000007716234,0.000010152297,0.00026141544,0.9709676,0.0008990321,0.0061063445,0.017695343,0.00023068441],"about_ca_topic_score_codex":0.00013709645,"about_ca_topic_score_gemma":0.0000092692735,"teacher_disagreement_score":0.9504329,"about_ca_system_score_codex":0.00015519776,"about_ca_system_score_gemma":0.00019883689,"threshold_uncertainty_score":0.7374223},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.04253164387224141,"score_gpt":0.32565739840824387,"score_spread":0.28312575453600247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2787038193","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048914864,0.0000062869603,0.79039574,0.0060496368,0.0011231896,0.00006960284,0.000002333736,0.00015189154,0.19730987],"genre_scores_gemma":[0.980822,0.000014295862,0.011691254,0.0003725034,0.00053375016,0.000024198354,0.000011887492,0.000007919728,0.0065221535],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988113,0.00011871042,0.0001787445,0.0003754899,0.00033832216,0.00017740582],"domain_scores_gemma":[0.99898374,0.00013015434,0.000102706625,0.0002740466,0.00044664863,0.00006271565],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016854859,0.00010746725,0.00008727701,0.00014204386,0.00040831382,0.0005371855,0.00066822505,0.000035722383,0.0009636235],"category_scores_gemma":[0.00027241837,0.00010592186,0.00005787909,0.00021009534,0.00012576535,0.00053859234,0.00015876799,0.00019945836,0.0005133149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053562704,0.00022613583,0.011251303,0.0000042948636,0.0002592361,0.00004528329,0.009239326,0.010603655,0.03754551,0.77206385,0.0141639365,0.14454389],"study_design_scores_gemma":[0.00028710344,0.0001688373,0.011242269,0.000044070166,0.000006312097,0.000013559559,0.0003528607,0.92698044,0.003725295,0.010972479,0.045968153,0.00023862091],"about_ca_topic_score_codex":0.000057051333,"about_ca_topic_score_gemma":0.00001863999,"teacher_disagreement_score":0.9759306,"about_ca_system_score_codex":0.00004109326,"about_ca_system_score_gemma":0.00008635797,"threshold_uncertainty_score":0.99994963},"labels":[],"label_agreement":null},{"id":"W2787217782","doi":"","title":"Decoupling the Layers in Residual Networks","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Residual; Computer science; Algorithm; Parallelizable manifold; Decoupling (probability); Scaling; Perturbation (astronomy); Mathematical optimization; Mathematics; Geometry; Physics; Engineering","score_opus":0.050020908066392776,"score_gpt":0.3584311460717074,"score_spread":0.30841023800531464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2787217782","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054731186,0.000022107306,0.84840524,0.028820576,0.00088170497,0.0003517649,0.000001770609,0.0002860162,0.06649962],"genre_scores_gemma":[0.99378306,0.00004172962,0.0040326114,0.0004586427,0.00032953618,0.00008836029,0.000010791137,0.00000905284,0.001246242],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987383,0.000092259674,0.00024741358,0.00039807038,0.00030444405,0.00021951397],"domain_scores_gemma":[0.9987151,0.00046026762,0.00012868328,0.0004126704,0.00023669015,0.00004655872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023059947,0.0001065311,0.00007862597,0.00013915298,0.00033559735,0.00022750096,0.0011177474,0.00004090983,0.00013247538],"category_scores_gemma":[0.00022845922,0.000089655034,0.000034426077,0.0004976898,0.000142491,0.00034882867,0.0002150106,0.00042259382,0.00015525629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001933785,0.000052303036,0.0122449305,5.950596e-7,0.000020983856,0.000008079525,0.0013916291,0.2369248,0.00038649526,0.7262277,0.0012079388,0.021515235],"study_design_scores_gemma":[0.00020176635,0.00004902522,0.023470566,0.000024800107,0.000001999971,0.000008942327,0.00023483408,0.95872176,0.00019894223,0.013522283,0.0034410397,0.00012403223],"about_ca_topic_score_codex":0.00004901836,"about_ca_topic_score_gemma":0.00012419058,"teacher_disagreement_score":0.93905187,"about_ca_system_score_codex":0.000059146445,"about_ca_system_score_gemma":0.000050213926,"threshold_uncertainty_score":0.3656026},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.061416145007651614,"score_gpt":0.36368154145194365,"score_spread":0.302265396444292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2787849668","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91587716,9.1054056e-7,0.036239687,0.010744305,0.0013351494,0.00027860494,0.000019922416,0.00007339401,0.03543086],"genre_scores_gemma":[0.99370694,0.000006289699,0.0005569888,0.0005124349,0.0002977154,0.000031627274,0.00001821705,0.000012564897,0.00485722],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873996,0.00013544326,0.00023305195,0.00031977618,0.00042751015,0.00014423797],"domain_scores_gemma":[0.99893755,0.00036902897,0.0001642885,0.00020958547,0.00027357705,0.000045992856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015992034,0.00009446353,0.000080447695,0.00014823972,0.0002131623,0.0001290553,0.00036506713,0.000039672716,0.00036865193],"category_scores_gemma":[0.002194275,0.00007398196,0.0000497976,0.00032168668,0.00015506617,0.00016468985,0.00010702629,0.00024852323,0.00012857388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006754852,0.000042700653,0.0022059747,0.000002488053,0.000008500864,0.000001985102,0.00061907456,0.0044546146,0.29092163,0.6930441,0.00015052273,0.0084807975],"study_design_scores_gemma":[0.00017800575,0.00040673735,0.014546388,0.000089084504,0.000009735578,0.00001637024,0.00038080977,0.88626915,0.069900535,0.026809381,0.0012092679,0.00018452462],"about_ca_topic_score_codex":0.000041578292,"about_ca_topic_score_gemma":0.000015392621,"teacher_disagreement_score":0.88181454,"about_ca_system_score_codex":0.0000621985,"about_ca_system_score_gemma":0.000037127233,"threshold_uncertainty_score":0.40364802},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09295328918588806,"score_gpt":0.3624233461629727,"score_spread":0.26947005697708465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901997113","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06219863,0.0000042187016,0.07413485,0.05760833,0.0018428555,0.00032065721,0.00003528175,0.00043743962,0.80341774],"genre_scores_gemma":[0.97032285,0.000027533662,0.017524255,0.00039614973,0.0001789961,0.00010366675,0.00001114344,0.000013687293,0.011421741],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9981335,0.00011319511,0.00026344648,0.00057192,0.00067294517,0.00024504092],"domain_scores_gemma":[0.99789107,0.00043873317,0.00024118317,0.00084576115,0.0004083387,0.00017491747],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003325211,0.00016459555,0.00016439489,0.00032427508,0.0007593175,0.0014956972,0.0020370178,0.00006336731,0.004040324],"category_scores_gemma":[0.003125869,0.00016752844,0.0001125875,0.000106860316,0.000088186294,0.0007289521,0.00034701574,0.00027898516,0.0026152546],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023381865,0.00013782339,0.0066311182,0.0000035907103,0.00010522902,0.00009531893,0.00086753396,0.000095941155,0.00429979,0.2218988,0.0017310727,0.7641104],"study_design_scores_gemma":[0.001684199,0.00038933687,0.43639773,0.00072137767,0.0000789178,0.0002966625,0.00187464,0.272077,0.12850676,0.04067498,0.115048476,0.0022499394],"about_ca_topic_score_codex":0.00022109825,"about_ca_topic_score_gemma":0.00004806055,"teacher_disagreement_score":0.9081242,"about_ca_system_score_codex":0.000065070926,"about_ca_system_score_gemma":0.00009426342,"threshold_uncertainty_score":0.99954087},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.12365227752669244,"score_gpt":0.3885364596589281,"score_spread":0.26488418213223563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903153676","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032135896,0.000017236494,0.90068626,0.017512552,0.0014124184,0.00107768,0.000011496746,0.0013508648,0.04579559],"genre_scores_gemma":[0.88053733,0.0000021571564,0.11774302,0.00022104465,0.00022495369,0.00037247184,0.0000364542,0.000012710518,0.0008498396],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99827665,0.00012835805,0.00033359474,0.00055422547,0.00036222578,0.00034493222],"domain_scores_gemma":[0.9980715,0.00065366254,0.00022006959,0.00029015017,0.0006686281,0.000095969546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045235903,0.00017423004,0.00015081262,0.00020647272,0.0005182873,0.0006935803,0.0008035755,0.00006324384,0.00013956158],"category_scores_gemma":[0.0011296675,0.00017123092,0.00010130855,0.00021164458,0.00016110213,0.00035022805,0.00012424837,0.00027578327,0.000066061715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005046102,0.0002401875,0.009080806,0.000025663086,0.00015578257,0.000027459431,0.0049046655,0.01282465,0.0012424864,0.39064944,0.0024309845,0.5783674],"study_design_scores_gemma":[0.00037446842,0.00036828138,0.0013047869,0.00014056136,0.000013270634,0.00004277035,0.00049468636,0.977428,0.0009364016,0.006469619,0.012136143,0.0002909734],"about_ca_topic_score_codex":0.00005667821,"about_ca_topic_score_gemma":0.000005243412,"teacher_disagreement_score":0.96460336,"about_ca_system_score_codex":0.000059226102,"about_ca_system_score_gemma":0.00013333032,"threshold_uncertainty_score":0.6982594},"labels":[],"label_agreement":null},{"id":"W2903934645","doi":"","title":"Online variance-reducing optimization","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Metaheuristic Optimization Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Variance (accounting); Business","score_opus":0.074319189957712,"score_gpt":0.38425176134099914,"score_spread":0.3099325713832871,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903934645","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005992728,0.0000037223424,0.8889251,0.006139473,0.0008956659,0.00014621596,0.000008571163,0.0002471805,0.10303483],"genre_scores_gemma":[0.6099212,0.00006274024,0.3756945,0.00030978787,0.0005659872,0.000040114202,0.00015432427,0.000021412718,0.0132299205],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978309,0.00021106274,0.00035056996,0.0005787894,0.00077498105,0.00025364984],"domain_scores_gemma":[0.9976098,0.00021857799,0.00018577867,0.00048044385,0.0013792375,0.00012617264],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00031720885,0.00014687153,0.00012948507,0.00040619203,0.00035129575,0.00055876566,0.0011117567,0.000060923718,0.0023867348],"category_scores_gemma":[0.0014204388,0.00015213722,0.000053712454,0.0006189344,0.00013379693,0.00066375406,0.00025646895,0.0003389431,0.0004288156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002094455,0.00031207933,0.00058424973,0.0000037618554,0.0000773064,0.00001598907,0.0015003408,0.556681,0.0004885334,0.40862614,0.0012236971,0.03046597],"study_design_scores_gemma":[0.0003118248,0.00011596462,0.0011938488,0.00003141371,0.00000373141,0.000013050146,0.00012468,0.9942599,0.00021310999,0.00203694,0.0015451271,0.00015042226],"about_ca_topic_score_codex":0.00006859145,"about_ca_topic_score_gemma":0.0000051099805,"teacher_disagreement_score":0.6093219,"about_ca_system_score_codex":0.000086487584,"about_ca_system_score_gemma":0.00019275722,"threshold_uncertainty_score":0.9985252},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Maxima and minima; Computer science; Artificial intelligence; Mathematics; Mathematical analysis","score_opus":0.0514478710076336,"score_gpt":0.3483785570925074,"score_spread":0.29693068608487383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904014149","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014591397,0.0000019785384,0.8108089,0.0050795823,0.0002584369,0.000087099914,0.0000011501487,0.00045987812,0.16871159],"genre_scores_gemma":[0.91530854,0.0000059101612,0.078551896,0.00041400755,0.00015220756,0.000020875366,0.00001417453,0.000009171077,0.0055232137],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880487,0.00007712637,0.00019082364,0.00039248413,0.00036313105,0.00017158643],"domain_scores_gemma":[0.9989278,0.00011622199,0.00014098547,0.00029248095,0.00046410775,0.000058460555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014957464,0.00011747068,0.00009028044,0.0002339667,0.00027754557,0.0003745242,0.00071065465,0.000039933137,0.00032658636],"category_scores_gemma":[0.000127414,0.00010516283,0.0000349432,0.00025957706,0.00009802163,0.0003720422,0.00013600347,0.00021108621,0.00027663255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011938559,0.00027696794,0.049181912,0.000008984355,0.00022735496,0.00006790343,0.010069911,0.020244172,0.0030319574,0.85189617,0.019087015,0.045788255],"study_design_scores_gemma":[0.00058641314,0.0005294085,0.012464699,0.00014002783,0.000007353925,0.000051318413,0.000228669,0.96236897,0.00517142,0.0057022017,0.012342072,0.0004074706],"about_ca_topic_score_codex":0.000025496656,"about_ca_topic_score_gemma":0.000007007877,"teacher_disagreement_score":0.9421248,"about_ca_system_score_codex":0.000037716854,"about_ca_system_score_gemma":0.00006699921,"threshold_uncertainty_score":0.42884156},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; University of Toronto","funders":"","keywords":"Computer science; Artificial neural network; Architecture; Artificial intelligence","score_opus":0.03574961797958973,"score_gpt":0.31452632339352865,"score_spread":0.2787767054139389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2907134525","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014508779,0.0000060280327,0.9607181,0.006318843,0.0005266394,0.00016065822,0.0000040019595,0.00014742132,0.01760953],"genre_scores_gemma":[0.96238685,0.0000059854833,0.03651797,0.0002692417,0.000248046,0.000035219127,0.000041185784,0.000008203679,0.0004872822],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988335,0.00008990417,0.00025577264,0.00033057694,0.00031607662,0.00017418175],"domain_scores_gemma":[0.99882406,0.00017466946,0.00020741993,0.0003233748,0.00040868975,0.000061810366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011306971,0.00010651556,0.00010187318,0.000130571,0.00021472726,0.00012824174,0.00068487664,0.000035874247,0.00023460393],"category_scores_gemma":[0.000088009896,0.00010262765,0.00006683599,0.00041415915,0.00012850825,0.00017681965,0.000094741314,0.00019155591,0.00003124191],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011276841,0.00004114631,0.0016770641,0.0000011951629,0.000012625338,9.808722e-7,0.00014275657,0.8320982,0.00030106987,0.15896037,0.0004304294,0.0063229254],"study_design_scores_gemma":[0.00020168707,0.00013150403,0.0030372436,0.00002697511,0.000004168931,0.0000035395742,0.000020043526,0.99031836,0.0004982967,0.0045656664,0.0010931421,0.000099375226],"about_ca_topic_score_codex":0.00002855473,"about_ca_topic_score_gemma":0.000012051122,"teacher_disagreement_score":0.94787806,"about_ca_system_score_codex":0.000019528658,"about_ca_system_score_gemma":0.00005060516,"threshold_uncertainty_score":0.4185034},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Class (philosophy); Computer network; Artificial intelligence","score_opus":0.049546841950115175,"score_gpt":0.3549417961186118,"score_spread":0.30539495416849666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2907257898","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05056421,0.000012307304,0.55111486,0.020305725,0.0008069147,0.0001879171,0.0000029603254,0.00028097068,0.37672415],"genre_scores_gemma":[0.9762975,0.000008397379,0.005980692,0.00018011489,0.0002500856,0.00005193225,0.000009423626,0.000015555324,0.017206276],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847203,0.00009674312,0.00020352015,0.0005495957,0.0003815183,0.00029659297],"domain_scores_gemma":[0.99854326,0.00013466484,0.00014441473,0.00071710686,0.0003127749,0.00014775539],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002526576,0.00016869052,0.0001485445,0.00011756035,0.00096099824,0.0010548426,0.0016900172,0.000046476136,0.00015900405],"category_scores_gemma":[0.00026288547,0.00015418742,0.000058173893,0.00012987293,0.00008204305,0.00049246434,0.00021856381,0.00037753218,0.00033689075],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008002238,0.00011072099,0.07368802,0.000007693813,0.00008985251,0.000051960087,0.004140714,0.12047068,0.000101835765,0.7558079,0.0012667078,0.04418391],"study_design_scores_gemma":[0.0013179459,0.0004193759,0.34127873,0.00043273877,0.000015641821,0.000044888962,0.00027642903,0.54243493,0.00015438696,0.0054221908,0.1074971,0.0007056203],"about_ca_topic_score_codex":0.00015504175,"about_ca_topic_score_gemma":0.00032514648,"teacher_disagreement_score":0.9257333,"about_ca_system_score_codex":0.00005226488,"about_ca_system_score_gemma":0.000100254605,"threshold_uncertainty_score":0.9999822},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.11598024182902084,"score_gpt":0.3604810611844719,"score_spread":0.24450081935545104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2907502844","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6782024,0.0000030207784,0.055629488,0.0035382966,0.0006671176,0.0002597945,0.0000029717098,0.00027900463,0.26141796],"genre_scores_gemma":[0.98698324,0.00001049723,0.0007774616,0.00037197015,0.00033059568,0.00004254809,0.00003826415,0.000018932376,0.011426488],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99810946,0.00019144689,0.00027159392,0.0005381445,0.0006620265,0.00022735068],"domain_scores_gemma":[0.9984136,0.0006824746,0.00023506753,0.00016869162,0.00041956035,0.00008055429],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00012365718,0.00017359534,0.00012099486,0.00026084363,0.0004976129,0.00022284532,0.0003406452,0.00005351339,0.0021480122],"category_scores_gemma":[0.0012105887,0.00015036247,0.000050262635,0.0002583821,0.00031792303,0.00045688008,0.0001086641,0.00052094145,0.0004912233],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060364354,0.00027810832,0.031539936,0.000007704701,0.00016009994,0.00006581431,0.011604729,0.48604977,0.07625679,0.38306588,0.00088161125,0.009485914],"study_design_scores_gemma":[0.0014734041,0.0019377277,0.01413643,0.00033547942,0.000026908006,0.00011445343,0.0037076387,0.8689534,0.09104052,0.0027978097,0.014824889,0.00065133575],"about_ca_topic_score_codex":0.000060303137,"about_ca_topic_score_gemma":0.000021803035,"teacher_disagreement_score":0.38290364,"about_ca_system_score_codex":0.00007622087,"about_ca_system_score_gemma":0.00008275975,"threshold_uncertainty_score":0.99876416},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Kronecker delta; Factorization; Approximations of π; Computer science; Mathematics; Algorithm; Applied mathematics; Physics","score_opus":0.08524321913795825,"score_gpt":0.3911625733095208,"score_spread":0.3059193541715626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2908074561","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6217246,0.0000018633646,0.09809952,0.0006983052,0.0007588482,0.00028167933,0.000030083309,0.000042908545,0.2783622],"genre_scores_gemma":[0.99694693,0.0000015841825,0.00055618625,0.00002096013,0.00050321955,0.000049212143,0.00048017726,0.000011165982,0.0014305345],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986903,0.00016684287,0.0002523368,0.00025488588,0.0005322024,0.00010342953],"domain_scores_gemma":[0.99832517,0.00004215252,0.00020043063,0.00019000436,0.0011875595,0.000054698678],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00023494358,0.000097336495,0.000089011795,0.00013660663,0.00016465827,0.00008028906,0.00016446656,0.00003472101,0.012393479],"category_scores_gemma":[0.00005039925,0.00009828547,0.000050371422,0.00016106853,0.000090451285,0.0003775902,0.000018880854,0.00015621123,0.000086049324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009838449,0.0008504645,0.112605885,0.000004717007,0.00027480326,2.708152e-7,0.0064961365,0.092364356,0.029153585,0.58037835,0.001922755,0.17585027],"study_design_scores_gemma":[0.0005901091,0.00013802227,0.017273763,0.000025002046,0.00004852127,7.218534e-7,0.0016451168,0.94730306,0.0066508087,0.025175342,0.0009801147,0.00016945093],"about_ca_topic_score_codex":0.00007779894,"about_ca_topic_score_gemma":0.000006258455,"teacher_disagreement_score":0.8549387,"about_ca_system_score_codex":0.00002964905,"about_ca_system_score_gemma":0.00008172578,"threshold_uncertainty_score":0.9885093},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04822018521992996,"score_gpt":0.31713474569678946,"score_spread":0.26891456047685947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2908176537","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14187416,0.000022615639,0.8064275,0.018137459,0.0026350485,0.00044460056,0.000036534908,0.00055349345,0.029868603],"genre_scores_gemma":[0.99415857,0.000007992114,0.0026578375,0.00036931562,0.000598754,0.000044401295,0.00009611907,0.000012847164,0.0020541502],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860865,0.00007595161,0.00019814876,0.0004615302,0.00038861058,0.0002671123],"domain_scores_gemma":[0.9989308,0.00015857645,0.00015816979,0.00039076435,0.0002626246,0.00009902647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007962803,0.00015270614,0.00011507388,0.000099281424,0.00038550966,0.0003680972,0.0009041183,0.000050754938,0.00030439225],"category_scores_gemma":[0.00006431549,0.00014414973,0.00006224822,0.00030073055,0.00010746413,0.00034034712,0.00021471707,0.00034271966,0.0001264253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015850643,0.000052398587,0.0036629154,0.0000019077813,0.000048292426,0.000007870463,0.0008317984,0.10742745,0.00022443288,0.8538458,0.0039497004,0.029931605],"study_design_scores_gemma":[0.00016554318,0.00008806729,0.006243217,0.000028810222,0.000006162889,0.000020054946,0.00017168936,0.97445434,0.00004334424,0.017154276,0.0014540593,0.00017040195],"about_ca_topic_score_codex":0.0000419896,"about_ca_topic_score_gemma":0.00013841657,"teacher_disagreement_score":0.8670269,"about_ca_system_score_codex":0.00007109128,"about_ca_system_score_gemma":0.000037072452,"threshold_uncertainty_score":0.58782554},"labels":[],"label_agreement":null},{"id":"W2908509829","doi":"","title":"Reconstructing evolutionary trajectories of mutations in cancer","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Mutation; Genetics; Computational biology; Evolutionary biology; Biology; Gene","score_opus":0.036413581597422716,"score_gpt":0.35180776098204875,"score_spread":0.31539417938462605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2908509829","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9765862,0.00004458749,0.0005026603,0.00056006253,0.00047150976,0.000076602264,0.000048938866,0.000007226739,0.021702208],"genre_scores_gemma":[0.997942,0.00014816826,0.00069853646,0.00003851932,0.00026829535,0.000035659887,0.00011936255,0.000007630834,0.0007418354],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99938774,0.000032413478,0.00019134741,0.00019137117,0.000109724,0.00008737868],"domain_scores_gemma":[0.9993924,0.000053382497,0.00010537468,0.00010133152,0.0003232941,0.000024254881],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000601903,0.00006309609,0.00006601342,0.00010308755,0.000065207256,0.000017768929,0.000119498305,0.000042806154,0.0003200771],"category_scores_gemma":[0.00043361427,0.000072073126,0.00003436786,0.00009748541,0.00014589484,0.000007138352,0.00003901101,0.000087065484,0.000007722614],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016716596,0.00013749619,0.7712505,0.000008276925,0.000102443424,0.0000025868133,0.0015222122,0.009699026,0.17835881,0.02870292,0.00078802806,0.009260526],"study_design_scores_gemma":[0.003197238,0.0014165235,0.6928153,0.0004072567,0.00005907044,0.000046142188,0.009969965,0.052682012,0.20165525,0.013296654,0.02352489,0.0009297067],"about_ca_topic_score_codex":0.00042802325,"about_ca_topic_score_gemma":0.00038674893,"teacher_disagreement_score":0.07843522,"about_ca_system_score_codex":0.00003113628,"about_ca_system_score_gemma":0.0001642289,"threshold_uncertainty_score":0.35046196},"labels":[],"label_agreement":null},{"id":"W2910279493","doi":"","title":"Designing Efficient Neural Attention Systems Towards Achieving Human-level Sharp Vision","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial neural network; Artificial intelligence; Machine vision; Computer vision","score_opus":0.10085423005369301,"score_gpt":0.3803689614535364,"score_spread":0.2795147313998434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910279493","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21770453,0.000016145059,0.74569553,0.0046376605,0.0013238102,0.00036525965,0.000007721484,0.00039135705,0.029857961],"genre_scores_gemma":[0.9928837,0.0000061582145,0.003513531,0.00010104935,0.00042157236,0.000083142935,0.000052522555,0.000014712527,0.002923605],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980078,0.00016188771,0.00037417325,0.00060174114,0.00059045776,0.00026395533],"domain_scores_gemma":[0.9986958,0.00012544714,0.00024856484,0.00039639996,0.00043229817,0.000101515165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030040488,0.00017151755,0.000136979,0.00022334247,0.00078535377,0.0008749242,0.00092510675,0.000059639562,0.00011333195],"category_scores_gemma":[0.000105367886,0.0001663493,0.00008719084,0.00035751596,0.000101842954,0.00041578998,0.0002652168,0.00033588638,0.00023111788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029305169,0.000355634,0.0050752414,0.000013578679,0.00009876703,0.000021957867,0.0017713624,0.11674313,0.14162561,0.68383414,0.0023473515,0.048083927],"study_design_scores_gemma":[0.0002768061,0.00016854693,0.029392296,0.000114951006,0.000007655138,0.0000200642,0.00020381012,0.9673198,0.0006464989,0.0006254664,0.0010133203,0.00021079589],"about_ca_topic_score_codex":0.00014117193,"about_ca_topic_score_gemma":0.000008243068,"teacher_disagreement_score":0.85057664,"about_ca_system_score_codex":0.0000789999,"about_ca_system_score_gemma":0.00004488203,"threshold_uncertainty_score":0.8436914},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.030354844997369082,"score_gpt":0.3326982328008643,"score_spread":0.30234338780349523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911248322","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10899653,0.0000044185863,0.66471875,0.022196008,0.00078819954,0.000258786,0.000007618108,0.0007879594,0.20224176],"genre_scores_gemma":[0.9616747,0.000004494149,0.012562295,0.00052684924,0.00039896352,0.000053983516,0.000059760125,0.000019015843,0.02469995],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976991,0.00021137187,0.00025318417,0.0006570443,0.0008598489,0.00031944332],"domain_scores_gemma":[0.9982767,0.00026093668,0.00016466244,0.00031519867,0.0008047437,0.00017774712],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00029446927,0.00020373904,0.00015660147,0.0003728735,0.0006326417,0.000591451,0.0009284702,0.00005957093,0.00064725266],"category_scores_gemma":[0.00061494816,0.00018525816,0.000060790615,0.0004504758,0.00014701915,0.00048476737,0.00023345498,0.000708896,0.0014658639],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013467751,0.00020418824,0.03761658,0.0000075692838,0.00021122639,0.000087839835,0.011405233,0.09083288,0.0032065418,0.7975172,0.0021649844,0.05661108],"study_design_scores_gemma":[0.0012205337,0.0026261955,0.05205874,0.00016858299,0.000017887098,0.0001817984,0.0029097346,0.8354447,0.0018262437,0.0111048855,0.09159653,0.0008441579],"about_ca_topic_score_codex":0.00012437602,"about_ca_topic_score_gemma":0.00004368557,"teacher_disagreement_score":0.8526782,"about_ca_system_score_codex":0.000071860195,"about_ca_system_score_gemma":0.00015602837,"threshold_uncertainty_score":0.9993116},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Rewriting; Computer science; Programming language; Natural language processing; Information retrieval","score_opus":0.046905022059950514,"score_gpt":0.360655210535885,"score_spread":0.3137501884759345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914442349","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016445585,0.000060664366,0.88829035,0.016282307,0.0009542419,0.00023304495,0.00001075705,0.0017242956,0.07599878],"genre_scores_gemma":[0.90981394,0.000011132218,0.085837446,0.00036761197,0.00024847392,0.000030579788,0.000027546019,0.000010265059,0.003652986],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985344,0.00009311931,0.00023763151,0.00046433127,0.00045829188,0.00021224061],"domain_scores_gemma":[0.9983631,0.00024883254,0.00016491459,0.00036707608,0.0007852142,0.00007091125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022288648,0.00013201639,0.00010302689,0.00024230045,0.00030024274,0.0004766367,0.0011873816,0.0000644734,0.00030332603],"category_scores_gemma":[0.0013841138,0.0001286258,0.00005551616,0.0003162138,0.00012361367,0.00060983386,0.00028426346,0.00037266995,0.00038937075],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028789687,0.000114115646,0.016207233,0.0000062854797,0.000057310404,0.000041555566,0.0025789074,0.00006962722,0.016202841,0.8851615,0.004341892,0.07518992],"study_design_scores_gemma":[0.0018070855,0.00088159274,0.018778376,0.0005838709,0.00002250962,0.00019643131,0.0012507212,0.6728545,0.10295299,0.16133091,0.037907183,0.0014338631],"about_ca_topic_score_codex":0.00008371406,"about_ca_topic_score_gemma":0.000018957684,"teacher_disagreement_score":0.89336836,"about_ca_system_score_codex":0.00006462355,"about_ca_system_score_gemma":0.000076773584,"threshold_uncertainty_score":0.5245208},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Reinforcement learning; Term (time); Computer science; Artificial intelligence","score_opus":0.05336023462993137,"score_gpt":0.3395181485785783,"score_spread":0.2861579139486469,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2923023063","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022364546,0.0000068754734,0.9443343,0.0053693927,0.0005962415,0.00023402543,3.3172103e-7,0.00019278828,0.02690149],"genre_scores_gemma":[0.99102056,0.000027519127,0.0040627695,0.0004029264,0.00029843624,0.00006261072,0.000038432274,0.000019145022,0.004067599],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99760765,0.00019271462,0.000478996,0.0005234884,0.000834597,0.00036254327],"domain_scores_gemma":[0.9985235,0.00016308326,0.00020881023,0.00052868883,0.000499045,0.00007691718],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050632824,0.00021718588,0.00015119107,0.00035923487,0.00051763334,0.00056117866,0.0014540895,0.00008671531,0.00020383946],"category_scores_gemma":[0.0003475939,0.00018553913,0.00009041037,0.00041409268,0.000118270735,0.0005557809,0.00028184656,0.00091501843,0.00017475509],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018679137,0.000020690892,0.0075202994,0.0000033409253,0.00002029792,0.0000061644523,0.0019422547,0.9346972,0.00016215653,0.053045616,0.000029290437,0.002533969],"study_design_scores_gemma":[0.0004504243,0.00012735702,0.0024030972,0.00008758438,0.000005412826,0.000003825444,0.0003157911,0.99559313,0.00014094084,0.0004990416,0.00017274564,0.00020063134],"about_ca_topic_score_codex":0.00006324796,"about_ca_topic_score_gemma":0.000039805593,"teacher_disagreement_score":0.968656,"about_ca_system_score_codex":0.00017103976,"about_ca_system_score_gemma":0.0002157337,"threshold_uncertainty_score":0.75660664},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Optimization algorithm; Algorithm; Mathematical optimization; Mathematics","score_opus":0.04493808541385731,"score_gpt":0.3381104561314346,"score_spread":0.2931723707175773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2923289556","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00067829597,0.000008499437,0.87449175,0.008504178,0.0008317069,0.00031849465,0.000004096541,0.00030612163,0.11485684],"genre_scores_gemma":[0.6021023,0.00017470066,0.18133925,0.0007133868,0.0002675867,0.00007548089,0.00023891398,0.00004102979,0.21504734],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99767417,0.00018377326,0.00037866685,0.00065046124,0.0008150934,0.00029781536],"domain_scores_gemma":[0.9983796,0.00023045913,0.00022407206,0.0004684504,0.0005105902,0.00018682229],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002664274,0.0001926355,0.00017674324,0.00046959863,0.00019505931,0.0007662723,0.001055901,0.000101026235,0.0041226116],"category_scores_gemma":[0.00029547652,0.00019667207,0.00010544441,0.0006416918,0.000035606183,0.0009998586,0.00022776461,0.0005148779,0.0011985829],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014044564,0.000090157395,0.0043659313,0.000004623503,0.00005804302,0.000006903191,0.0016269928,0.75925934,0.0002558879,0.20757696,0.00234053,0.0244006],"study_design_scores_gemma":[0.0008975734,0.00016182427,0.0015284349,0.000047073758,0.0000048312327,0.000009516308,0.00026713937,0.9873877,0.000114127564,0.0017966082,0.007555102,0.00023005749],"about_ca_topic_score_codex":0.00013729699,"about_ca_topic_score_gemma":0.0000062732593,"teacher_disagreement_score":0.6931525,"about_ca_system_score_codex":0.000109539265,"about_ca_system_score_gemma":0.00031062798,"threshold_uncertainty_score":0.9995791},"labels":[],"label_agreement":null},{"id":"W2934497975","doi":"","title":"Classifier with Hierarchical Topographical Maps as Internal Representation.","year":2015,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Artificial intelligence; Classifier (UML); Pattern recognition (psychology); Machine learning; Data mining","score_opus":0.07523832574978477,"score_gpt":0.35001370036302765,"score_spread":0.27477537461324286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2934497975","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.072731175,0.00001842969,0.42655498,0.06797805,0.0009757893,0.00050373754,0.000011936661,0.000659711,0.43056622],"genre_scores_gemma":[0.9835867,0.000021993068,0.0068702833,0.0005848144,0.00022984776,0.00012995384,0.00007010152,0.00001524065,0.008491017],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99779814,0.00016430096,0.00031157196,0.0006398621,0.00083095167,0.0002551856],"domain_scores_gemma":[0.99828553,0.0002432583,0.00016325995,0.00048596528,0.0005331439,0.00028881503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018537036,0.00017934854,0.00015250797,0.00024952038,0.00020486274,0.0005574159,0.0010454301,0.00006919792,0.00018484119],"category_scores_gemma":[0.00023367019,0.0001525186,0.00008402476,0.0005515086,0.00016655083,0.0005704535,0.00022794586,0.0006222304,0.00032733558],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008257253,0.00014764395,0.010428431,0.0000011352151,0.00006541207,0.000057882462,0.0008157798,0.006180368,0.00022254483,0.9679254,0.0052983006,0.008774513],"study_design_scores_gemma":[0.0037837133,0.0014458674,0.031941973,0.00019994877,0.000043865726,0.0006640528,0.002490573,0.5521878,0.0011789816,0.305799,0.099050745,0.0012134849],"about_ca_topic_score_codex":0.00014079914,"about_ca_topic_score_gemma":0.000024660341,"teacher_disagreement_score":0.9108556,"about_ca_system_score_codex":0.000059253594,"about_ca_system_score_gemma":0.00017628033,"threshold_uncertainty_score":0.6219528},"labels":[],"label_agreement":null},{"id":"W2941011530","doi":"","title":"Reward Estimation for Variance Reduction in Deep Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Variance reduction; Reduction (mathematics); Computer science; Variance (accounting); Estimation; Artificial intelligence; Reinforcement; Machine learning; Statistics; Econometrics; Psychology; Mathematics; Engineering; Economics; Social psychology","score_opus":0.050061910459263996,"score_gpt":0.3514664291660533,"score_spread":0.3014045187067893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2941011530","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002523527,0.0000038316425,0.9629498,0.0023364895,0.0010383397,0.000390612,3.5136165e-7,0.00022060916,0.030536426],"genre_scores_gemma":[0.9528331,0.000029124656,0.038642287,0.000085683474,0.00022732583,0.00016183939,0.00008436644,0.00001744572,0.0079187825],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979142,0.0001416655,0.0005085344,0.00056343275,0.00055551325,0.00031664225],"domain_scores_gemma":[0.9983661,0.00023520784,0.0003558306,0.00035132543,0.00062068336,0.00007085899],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005266555,0.00018093985,0.00015729728,0.00044262077,0.0003647114,0.000399239,0.00072638545,0.00008665099,0.00019464169],"category_scores_gemma":[0.0013387975,0.00020433681,0.00007214658,0.00041789367,0.00009674174,0.0008841581,0.00014845174,0.00043453352,0.00020710085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035922138,0.000022514421,0.0009021045,0.000006721565,0.000022406311,0.0000016806978,0.0021735965,0.82472324,0.0006026715,0.16426854,0.0001000622,0.007140503],"study_design_scores_gemma":[0.00062066974,0.0003707816,0.0014450029,0.00009933899,0.0000057364746,0.000010101881,0.00035098428,0.9904602,0.00076098286,0.0032892718,0.0023843127,0.000202627],"about_ca_topic_score_codex":0.00006449973,"about_ca_topic_score_gemma":0.0000072247167,"teacher_disagreement_score":0.95030963,"about_ca_system_score_codex":0.00023378403,"about_ca_system_score_gemma":0.00011390149,"threshold_uncertainty_score":0.8332614},"labels":[],"label_agreement":null},{"id":"W2941951382","doi":"","title":"Jointly Learning \"What\" and \"How\" from Instructions and Goal-States.","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Complex Systems and Decision Making","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Goal orientation; Human–computer interaction; Psychology","score_opus":0.1641833945764254,"score_gpt":0.4275655808461489,"score_spread":0.2633821862697235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2941951382","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9403447,0.00015835644,0.017771378,0.008284732,0.001756757,0.00018167477,0.000022234892,0.00012454284,0.031355638],"genre_scores_gemma":[0.98104376,0.00009490349,0.0012330362,0.0001350119,0.0003582817,0.000016527392,0.000020542262,0.0000141962655,0.017083723],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99711293,0.0003328616,0.00046473922,0.0007602377,0.0011359208,0.00019330748],"domain_scores_gemma":[0.996274,0.001844411,0.0003700617,0.00031811572,0.0010411107,0.00015232601],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007385377,0.00017206692,0.00024073712,0.00049105164,0.0007423528,0.0032051383,0.00038710696,0.000071859584,0.0019510115],"category_scores_gemma":[0.0041856114,0.00014725905,0.00006484365,0.00035591825,0.00034435463,0.001049864,0.00031281047,0.00041395746,0.00028551396],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021212727,0.00009792085,0.22358236,0.0000044164944,0.0002258796,0.00004063794,0.020525323,0.002365078,0.0068927105,0.27160153,0.010448347,0.46400368],"study_design_scores_gemma":[0.0012275252,0.00035234395,0.23108481,0.00024981756,0.000024442985,0.00010248967,0.054019302,0.31695,0.00020032228,0.22659093,0.16867077,0.0005272561],"about_ca_topic_score_codex":0.0003179748,"about_ca_topic_score_gemma":0.00019130314,"teacher_disagreement_score":0.46347642,"about_ca_system_score_codex":0.000034668705,"about_ca_system_score_gemma":0.00005434317,"threshold_uncertainty_score":0.9989613},"labels":[],"label_agreement":null},{"id":"W2942197587","doi":"","title":"Evaluating visual \"common sense\" using fine-grained classification and captioning tasks.","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Human Pose and Action Recognition","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of Toronto; University of British Columbia","funders":"","keywords":"Closed captioning; Computer science; Natural language processing; Artificial intelligence; Image (mathematics)","score_opus":0.20220410973093644,"score_gpt":0.46163012006877796,"score_spread":0.2594260103378415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2942197587","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8806478,0.0000047743238,0.09833544,0.0017868782,0.0004934396,0.00015161345,0.0000033147226,0.00019943334,0.018377349],"genre_scores_gemma":[0.9899624,0.000007861821,0.008567022,0.00014892718,0.00030633932,0.000020615651,0.000057927173,0.000010452978,0.0009184496],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846375,0.00019570041,0.00029907853,0.000451038,0.0004224119,0.00016804312],"domain_scores_gemma":[0.99875975,0.00017817208,0.00024242503,0.00018262344,0.00056525675,0.000071768874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032960664,0.00012991564,0.000108490036,0.00029382677,0.00058230106,0.0005064412,0.0002032241,0.000058564478,0.00029511677],"category_scores_gemma":[0.00033741049,0.0001404571,0.000042599775,0.00022517708,0.00010682117,0.00067292404,0.00010840755,0.00025120945,0.0001403246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101245416,0.0003044332,0.018790916,0.000019954266,0.00020076119,0.000028307588,0.009175794,0.004574153,0.3283166,0.3597327,0.00040840774,0.27834675],"study_design_scores_gemma":[0.0003577681,0.00017320711,0.024869602,0.000070513546,0.00001146997,0.000045929577,0.00045842727,0.9665447,0.0016657583,0.005371021,0.000261186,0.00017045494],"about_ca_topic_score_codex":0.0001039217,"about_ca_topic_score_gemma":0.000035911682,"teacher_disagreement_score":0.9619705,"about_ca_system_score_codex":0.00007277438,"about_ca_system_score_gemma":0.00007570521,"threshold_uncertainty_score":0.57276744},"labels":[],"label_agreement":null},{"id":"W2943085977","doi":"","title":"Brief Report: Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks","year":2019,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Parsing; Artificial intelligence; Language model; Syntax; Tree structure; Tree (set theory); Recurrent neural network; Natural language processing; Artificial neural network; Machine learning; Algorithm; Binary tree; Mathematics","score_opus":0.024539682217917903,"score_gpt":0.3385625186261699,"score_spread":0.31402283640825196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943085977","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09055555,0.00029941273,0.8559458,0.011360823,0.0039906977,0.0007432439,0.000004448293,0.0018762241,0.035223775],"genre_scores_gemma":[0.9449385,0.000016447506,0.052780148,0.00027129616,0.00013833497,0.000038855258,0.00008719413,0.000018560584,0.0017106872],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977809,0.00018325844,0.0004544722,0.00073751574,0.000585811,0.00025799667],"domain_scores_gemma":[0.998147,0.00027248604,0.00040886312,0.00057422306,0.0005125023,0.000084913576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023499558,0.00022723748,0.00019354702,0.00026945464,0.00020976507,0.000743412,0.001306431,0.000093579794,0.00023452827],"category_scores_gemma":[0.001038403,0.0002075057,0.00009866436,0.00036878246,0.000063278334,0.0007745196,0.00037920623,0.00089569564,0.000028149847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043784526,0.00008460508,0.015302365,0.0000167035,0.0000703297,0.00020598879,0.0023623693,0.010993593,0.0037079034,0.6618797,0.0008518897,0.30448076],"study_design_scores_gemma":[0.00029947277,0.00015673992,0.0034920268,0.00010563143,0.0000067061405,0.0001660562,0.00025637032,0.95826435,0.0006999454,0.035135247,0.0011043159,0.0003131583],"about_ca_topic_score_codex":0.00023865722,"about_ca_topic_score_gemma":0.000053723837,"teacher_disagreement_score":0.94727075,"about_ca_system_score_codex":0.000091683214,"about_ca_system_score_gemma":0.00009382104,"threshold_uncertainty_score":0.84618366},"labels":[],"label_agreement":null},{"id":"W2962719937","doi":"","title":"SELF-INFORMED NEURAL NETWORK STRUCTURE LEARNING","year":2015,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Artificial intelligence; Classifier (UML); Artificial neural network; Cognitive neuroscience of visual object recognition; Visualization; Pattern recognition (psychology); Machine learning; Task (project management); Similarity (geometry); Object (grammar); Image (mathematics)","score_opus":0.06063609321300034,"score_gpt":0.35074877230090973,"score_spread":0.2901126790879094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962719937","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13820878,0.00011196018,0.26099035,0.043732125,0.006768119,0.00090187165,0.000025653324,0.004832135,0.544429],"genre_scores_gemma":[0.9797304,0.000023960141,0.015271497,0.00021611962,0.00034681777,0.000022386977,0.00028482513,0.000014419992,0.0040895613],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99793136,0.00028477266,0.00031813758,0.0004883841,0.00068770506,0.00028964382],"domain_scores_gemma":[0.9983962,0.00026428173,0.0002790391,0.00040273077,0.0004688669,0.00018888329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031349983,0.00018187331,0.00014414091,0.00018772151,0.00031944437,0.0006441672,0.0010100924,0.000082437226,0.0001580568],"category_scores_gemma":[0.0011912601,0.00017649728,0.00006092328,0.00037778966,0.00004119168,0.0008435655,0.00024046648,0.00081478147,0.00025264753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041590523,0.00007920656,0.08234302,0.000008843573,0.00009685988,0.000020642297,0.006271688,0.35047066,0.00019460716,0.5274937,0.0051112254,0.02786794],"study_design_scores_gemma":[0.0005020733,0.00014318162,0.01514921,0.000022570252,0.000007684496,0.000031909294,0.0004894131,0.91018116,0.000037502236,0.0045807133,0.068624206,0.00023036652],"about_ca_topic_score_codex":0.00005857461,"about_ca_topic_score_gemma":0.000024212606,"teacher_disagreement_score":0.8415216,"about_ca_system_score_codex":0.00012112621,"about_ca_system_score_gemma":0.00025044775,"threshold_uncertainty_score":0.719735},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.10429671052686768,"score_gpt":0.37495094648723215,"score_spread":0.2706542359603645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962876041","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11583887,0.0000027845106,0.86265296,0.01672734,0.00033658216,0.000111796,0.0000032386533,0.00008056028,0.0042458447],"genre_scores_gemma":[0.9830117,0.000016202719,0.01576108,0.0001848437,0.00012385321,0.000043486874,0.000004059839,0.000007296859,0.00084748433],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858016,0.0001492535,0.00026396205,0.0003689985,0.0004962398,0.00014137277],"domain_scores_gemma":[0.9987567,0.000252541,0.00014319053,0.00041384733,0.00036540395,0.00006833099],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024697933,0.000096579985,0.00009297267,0.00011830212,0.00013425137,0.00015459774,0.0010681308,0.000026384792,0.00007527637],"category_scores_gemma":[0.00036153715,0.00006391116,0.000044286688,0.00017828135,0.00005252846,0.0013335603,0.00014666801,0.00012324331,0.00008730679],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024640523,0.00009173237,0.010976443,0.00000202764,0.000042142052,0.0000070612687,0.007217684,0.043412328,0.032438062,0.7676459,0.00009066498,0.13805133],"study_design_scores_gemma":[0.001072137,0.0005702073,0.057950348,0.00031543348,0.000013216481,0.000014796312,0.004116753,0.8480596,0.015687652,0.06769388,0.003925782,0.00058017205],"about_ca_topic_score_codex":0.00008961965,"about_ca_topic_score_gemma":0.000019711106,"teacher_disagreement_score":0.86717284,"about_ca_system_score_codex":0.000047375797,"about_ca_system_score_gemma":0.00006599554,"threshold_uncertainty_score":0.26062214},"labels":[],"label_agreement":null},{"id":"W2962985403","doi":"","title":"Universal Successor Representations for Transfer Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Initialization; Successor cardinal; Artificial intelligence; Set (abstract data type); Transfer of learning; Focus (optics); Function (biology); Machine learning; Reinforcement; Value (mathematics); Mathematics; Programming language","score_opus":0.057285571163360936,"score_gpt":0.34720038236061634,"score_spread":0.28991481119725543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962985403","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036328144,0.0000029047396,0.8863748,0.004339714,0.00095436507,0.00045273502,0.0000033174929,0.0003920005,0.10384736],"genre_scores_gemma":[0.9568276,0.000031920667,0.008169136,0.00023008611,0.00034065277,0.00013241897,0.00015923055,0.000028944893,0.034080014],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973381,0.00017380917,0.0005313139,0.0007311915,0.0007895802,0.00043599244],"domain_scores_gemma":[0.9974065,0.0005294795,0.00021168438,0.00051777874,0.001185457,0.00014909756],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00038601106,0.00025544403,0.00020553869,0.0004556193,0.0008462836,0.0006392947,0.0013106087,0.00010182606,0.0008189778],"category_scores_gemma":[0.0008723523,0.00027665013,0.00016976547,0.0004440285,0.00020531089,0.0010206131,0.00020976788,0.00051051215,0.0003443466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006226524,0.000039983137,0.002302328,0.0000068646973,0.00011753479,0.0000052177566,0.003105864,0.5506719,0.0014649142,0.43927875,0.000797132,0.0021472506],"study_design_scores_gemma":[0.001153241,0.000639581,0.0017249709,0.000061501596,0.00002424736,0.000009384714,0.0010123497,0.96703345,0.002136154,0.0016233239,0.024234792,0.00034702301],"about_ca_topic_score_codex":0.00010048675,"about_ca_topic_score_gemma":0.000016340671,"teacher_disagreement_score":0.9531948,"about_ca_system_score_codex":0.0001619587,"about_ca_system_score_gemma":0.0001924054,"threshold_uncertainty_score":0.9999686},"labels":[],"label_agreement":null},{"id":"W2963117168","doi":"","title":"Negative eigenvalues of the Hessian in deep neural networks","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Hessian matrix; Eigenvalues and eigenvectors; Deep learning; Artificial neural network; Deep neural networks; Function (biology); Computer science; Hessian equation; Artificial intelligence; Matrix (chemical analysis); Work (physics); Applied mathematics; Mathematical optimization; Mathematics; Engineering; Mathematical analysis; Physics","score_opus":0.03369257548278821,"score_gpt":0.3082430648912333,"score_spread":0.2745504894084451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963117168","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85795003,0.000026331034,0.024113212,0.00079240464,0.0010065605,0.00021240358,0.0000034755114,0.00026560208,0.11562995],"genre_scores_gemma":[0.9992937,0.000014557148,0.0003450987,0.000037932652,0.00010520465,0.000011999873,0.0000045104944,0.000010770184,0.00017626652],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993836,0.00006588502,0.00016988885,0.00011918365,0.00016025316,0.00010115314],"domain_scores_gemma":[0.9995311,0.00009304995,0.000059134316,0.00015069771,0.0001483278,0.000017722288],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000053942,0.00007837459,0.000080358855,0.000096235584,0.000061339124,0.000034106386,0.0002449695,0.00003798195,0.00017861961],"category_scores_gemma":[0.00011757048,0.000065673245,0.000041087693,0.0001621212,0.00012569186,0.000083379484,0.000045355817,0.00024147046,0.000008036674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041138217,0.000056574365,0.0628048,0.0000039202473,0.00009133478,0.000006579926,0.0043749935,0.87291753,0.0076997895,0.032066558,0.00055651413,0.019380275],"study_design_scores_gemma":[0.00010230515,0.000027048402,0.05571064,0.00005937039,0.0000034076565,0.000002236458,0.00033083124,0.9335391,0.007282823,0.0027753697,0.00009930532,0.00006757713],"about_ca_topic_score_codex":0.00010603569,"about_ca_topic_score_gemma":0.000120282115,"teacher_disagreement_score":0.1413436,"about_ca_system_score_codex":0.000030385045,"about_ca_system_score_gemma":0.0000091424145,"threshold_uncertainty_score":0.26780772},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.05047194812276975,"score_gpt":0.3403865215796997,"score_spread":0.28991457345692995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963200642","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09134344,0.000023285182,0.8986691,0.006798029,0.00077313173,0.00040942055,0.000010353427,0.00028349148,0.0016897205],"genre_scores_gemma":[0.9962163,0.000046620073,0.002865635,0.00018638649,0.00021984243,0.00015902078,0.000061786945,0.000024110872,0.00022029142],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973571,0.00022615823,0.00065824087,0.00072571595,0.0006061238,0.00042667252],"domain_scores_gemma":[0.9975248,0.0005663675,0.0005405812,0.0005834406,0.00063670025,0.00014809165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002072884,0.0002601242,0.00023945377,0.00025787315,0.00025473008,0.00015977619,0.0011738201,0.000081615835,0.00039590552],"category_scores_gemma":[0.00019859795,0.00021737025,0.00014231408,0.0006380718,0.00014721681,0.00052008685,0.00032391842,0.00032842948,0.000026779737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032449814,0.00007259606,0.0048054364,0.000002081341,0.00004664224,0.000005883775,0.00030522616,0.7098384,0.0011357953,0.097551174,0.00008025337,0.1861241],"study_design_scores_gemma":[0.00072007347,0.0001461811,0.027275817,0.000023270082,0.000014476243,0.000012847884,0.00018841239,0.96932304,0.00062257826,0.0013143867,0.00012544286,0.00023349561],"about_ca_topic_score_codex":0.00006965066,"about_ca_topic_score_gemma":0.000051518833,"teacher_disagreement_score":0.90487283,"about_ca_system_score_codex":0.00011903569,"about_ca_system_score_gemma":0.00004523897,"threshold_uncertainty_score":0.8864102},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.07102971897405239,"score_gpt":0.44039492234294464,"score_spread":0.3693652033688922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963202404","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2190443,0.00000939625,0.69070774,0.039500576,0.0013969627,0.0012871212,0.0009371951,0.00086714915,0.04624958],"genre_scores_gemma":[0.9740696,0.0000062763706,0.020351157,0.00019872717,0.00020628508,0.0002615113,0.0031358493,0.000020479483,0.0017501244],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981803,0.00012016045,0.00028579668,0.0007332156,0.0004147912,0.0002657225],"domain_scores_gemma":[0.99757487,0.0002649681,0.0004320012,0.0010982217,0.00048436972,0.00014556714],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00034573182,0.00018694285,0.00015517557,0.00017652108,0.0014764948,0.0015582578,0.0023045058,0.00007969995,0.00023130665],"category_scores_gemma":[0.0018609014,0.00019709878,0.00007019724,0.00009035876,0.000097819044,0.0013144641,0.0002846577,0.00043972261,0.00020582163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000105752915,0.0005289077,0.042169616,0.00001534549,0.0001772226,0.000022415208,0.0023045668,0.021828309,0.008557227,0.8562774,0.0056559485,0.062357273],"study_design_scores_gemma":[0.0005948783,0.00015790132,0.114010684,0.000040308038,0.000009454819,0.0000082522565,0.00011492965,0.8674757,0.00038065534,0.003798467,0.0131649,0.0002438993],"about_ca_topic_score_codex":0.00070076785,"about_ca_topic_score_gemma":0.000044334793,"teacher_disagreement_score":0.8524789,"about_ca_system_score_codex":0.000053515592,"about_ca_system_score_gemma":0.0001124493,"threshold_uncertainty_score":0.99982345},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.05905441561582941,"score_gpt":0.3606030764095502,"score_spread":0.3015486607937208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963285940","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01116927,0.000009296609,0.9562113,0.013093712,0.000589182,0.00037316373,0.000009444575,0.00031729703,0.018227285],"genre_scores_gemma":[0.96643335,0.000015298996,0.029357385,0.0004957281,0.0005815353,0.00019053176,0.000056746703,0.000016894446,0.0028525419],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984921,0.00008194859,0.00022737899,0.0005552695,0.00035385636,0.00028940136],"domain_scores_gemma":[0.9983958,0.00041860738,0.00011173447,0.0004244012,0.00054570334,0.00010377518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013355835,0.00014783656,0.00011082742,0.00019391674,0.00042832948,0.00024798175,0.0010777495,0.000053945318,0.000116089606],"category_scores_gemma":[0.00017247003,0.00014542663,0.00009445792,0.00038158867,0.00013715275,0.00031249705,0.00018382892,0.0003584044,0.00010857697],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004636589,0.00006735951,0.001137678,0.000002688743,0.000045373683,0.0000032218682,0.0010480939,0.07746403,0.0017101995,0.8357261,0.0018083354,0.080940574],"study_design_scores_gemma":[0.00040146327,0.00023474559,0.0024795595,0.000022748995,0.0000057481225,0.000021870399,0.00010309602,0.91988826,0.0007478315,0.06268867,0.013182084,0.00022392238],"about_ca_topic_score_codex":0.000012798145,"about_ca_topic_score_gemma":0.000016919403,"teacher_disagreement_score":0.9552641,"about_ca_system_score_codex":0.000036817382,"about_ca_system_score_gemma":0.000048544684,"threshold_uncertainty_score":0.5930326},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.028791537379196184,"score_gpt":0.3079606261640736,"score_spread":0.2791690887848774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963359059","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027137958,0.000005058921,0.95272565,0.0030419377,0.0006490547,0.00011098136,0.00000387599,0.00014110275,0.040608525],"genre_scores_gemma":[0.96257013,0.000011250584,0.03511761,0.00026597033,0.0005221129,0.00004070061,0.000035636323,0.000011769818,0.001424793],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983064,0.00017773977,0.00023999621,0.0005173182,0.0005160583,0.00024247241],"domain_scores_gemma":[0.9983031,0.00028983186,0.00020613695,0.000330989,0.0007793015,0.000090654474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018091881,0.00017807512,0.00013873646,0.00016146938,0.00046413814,0.00067444664,0.0007298024,0.000059239526,0.0008890122],"category_scores_gemma":[0.00029465646,0.00015216376,0.00004865457,0.0003552059,0.00016618712,0.00076122384,0.00015487116,0.00029631561,0.00007373423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008930377,0.00010448167,0.014228767,0.0000023595833,0.00023593186,0.000024336665,0.0020141352,0.29160997,0.0017420484,0.646888,0.0012966454,0.041763987],"study_design_scores_gemma":[0.0003554166,0.0001630265,0.027602173,0.000044100256,0.000009162437,0.000009867151,0.00011954248,0.96421826,0.0005987037,0.004691644,0.0019721522,0.00021597718],"about_ca_topic_score_codex":0.00006273153,"about_ca_topic_score_gemma":0.00005391594,"teacher_disagreement_score":0.95985633,"about_ca_system_score_codex":0.000056351673,"about_ca_system_score_gemma":0.00014807565,"threshold_uncertainty_score":0.973406},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Embedding; Sentence; Computer science; Natural language processing; Artificial intelligence; Logical consequence; Regularization (linguistics)","score_opus":0.05458417324847135,"score_gpt":0.3661503131841141,"score_spread":0.31156613993564275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963386218","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20733437,0.000009337242,0.61912674,0.01932611,0.0028440699,0.000321693,0.000009187956,0.00065918156,0.15036929],"genre_scores_gemma":[0.97295785,0.000016305514,0.023332516,0.00012730162,0.00013965726,0.000027745775,0.000009214751,0.0000085149195,0.003380905],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984345,0.00007258538,0.00022501407,0.0005461299,0.00051537156,0.00020642507],"domain_scores_gemma":[0.9982703,0.00009588754,0.00031014747,0.0008310878,0.0004087544,0.00008387479],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00016096939,0.00013870822,0.00011854371,0.0001438523,0.00072068436,0.001207229,0.0019680345,0.000052137028,0.0001747201],"category_scores_gemma":[0.00056964334,0.0001399169,0.00007505622,0.000056604644,0.00006472192,0.0009221535,0.0004465283,0.00034919815,0.00015785913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001917215,0.00012093693,0.05404845,0.000007798694,0.00019221491,0.0000850249,0.0075552133,0.011844891,0.0035887947,0.8878938,0.00043858847,0.0342051],"study_design_scores_gemma":[0.0003974006,0.000037815335,0.048741177,0.000053764586,0.0000071725653,0.000022069587,0.00039609495,0.935191,0.000536455,0.0130770495,0.0013325,0.00020750705],"about_ca_topic_score_codex":0.00013930745,"about_ca_topic_score_gemma":0.000018146853,"teacher_disagreement_score":0.9233461,"about_ca_system_score_codex":0.00006897849,"about_ca_system_score_gemma":0.00009412341,"threshold_uncertainty_score":0.9998296},"labels":[],"label_agreement":null},{"id":"W2963487749","doi":"","title":"Selecting the Best in GANs Family: a Post Selection Inference Framework","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Technology and Data Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Selection (genetic algorithm); Inference; Artificial intelligence","score_opus":0.041525398226821275,"score_gpt":0.3655370502695997,"score_spread":0.32401165204277843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963487749","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32556278,0.00001356281,0.63218963,0.0161112,0.00051187613,0.00016750074,0.0000059713707,0.00032933019,0.02510817],"genre_scores_gemma":[0.9933248,0.000023370994,0.005485474,0.00037091112,0.000113991526,0.000040917013,0.000017122335,0.0000062085196,0.00061720813],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986127,0.00015756056,0.00025164374,0.00043921807,0.0003239202,0.00021496328],"domain_scores_gemma":[0.99840885,0.00052149215,0.00014665638,0.0003555677,0.00053274207,0.00003470831],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029712275,0.00011940466,0.000105305975,0.00038970055,0.0004278996,0.0003180524,0.0011233978,0.000104340324,0.00017470185],"category_scores_gemma":[0.0018580394,0.000101243655,0.000059125312,0.0010614628,0.0001553112,0.00049757893,0.00021227414,0.0007393187,0.0003600671],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021014297,0.0001257074,0.14078471,0.0000016696441,0.00008643981,0.000008342975,0.0038637097,0.0016230978,0.0038159036,0.8242366,0.00013933508,0.025293516],"study_design_scores_gemma":[0.0004738575,0.0005429689,0.17639358,0.00021959515,0.00003356926,0.000042755823,0.0059192358,0.7291161,0.002370147,0.08133508,0.003049591,0.0005035591],"about_ca_topic_score_codex":0.00065930263,"about_ca_topic_score_gemma":0.0005790605,"teacher_disagreement_score":0.74290144,"about_ca_system_score_codex":0.00006796458,"about_ca_system_score_gemma":0.00012732306,"threshold_uncertainty_score":0.46280542},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.047976242014673355,"score_gpt":0.3647122563108589,"score_spread":0.31673601429618553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963633076","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058808804,0.0000018139064,0.9198969,0.0031282052,0.00054190296,0.00012165363,0.000001015326,0.00026098435,0.01723873],"genre_scores_gemma":[0.9277166,0.0000039412284,0.06977465,0.0003335742,0.00014208912,0.000016923597,0.000029961247,0.000014696993,0.001967576],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981516,0.00022059254,0.0003000799,0.00054640777,0.00054004416,0.00024125501],"domain_scores_gemma":[0.99881285,0.00016574096,0.0001882005,0.00030292157,0.00038918326,0.00014107351],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003159226,0.00015860701,0.00013873038,0.00036304022,0.0003755477,0.00042195353,0.00065387186,0.000041787483,0.00027156735],"category_scores_gemma":[0.0010247753,0.00017011618,0.0000663254,0.00033498657,0.0000374312,0.00076386845,0.00023290818,0.00031926364,0.00031718513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000305861,0.00009869099,0.050154496,0.000007394112,0.00003860229,0.000011448596,0.0052486514,0.52893734,0.008452409,0.15217373,0.00023087118,0.25461575],"study_design_scores_gemma":[0.00024246443,0.0001069022,0.0060892887,0.00006968275,0.000003188878,0.00001125055,0.0003699681,0.9843838,0.00073103,0.0025755782,0.005223584,0.00019324411],"about_ca_topic_score_codex":0.00010000005,"about_ca_topic_score_gemma":0.000010115791,"teacher_disagreement_score":0.8689078,"about_ca_system_score_codex":0.00011883627,"about_ca_system_score_gemma":0.000060406073,"threshold_uncertainty_score":0.69371367},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04670941002473038,"score_gpt":0.3662012404771157,"score_spread":0.31949183045238533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963682248","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022738125,0.000005546925,0.59263295,0.014520062,0.0016143512,0.00015398028,0.000002579719,0.00044178515,0.36789063],"genre_scores_gemma":[0.9661712,0.000015979831,0.027540918,0.00017118281,0.00020089318,0.000031651518,0.000020800531,0.000017971684,0.00582941],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979672,0.00014447825,0.00034591137,0.0006469178,0.00060928264,0.00028623646],"domain_scores_gemma":[0.997697,0.00023169638,0.0005984521,0.0010245884,0.000343352,0.00010490553],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00038637992,0.00019190258,0.00017010418,0.00020169733,0.0012462068,0.0013905637,0.0027408379,0.00007704328,0.00059424364],"category_scores_gemma":[0.002230436,0.0001980306,0.00010852527,0.00009381909,0.00015090856,0.0013425582,0.00063467765,0.0006974728,0.00022753395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032493397,0.00006287186,0.12853564,0.000005127403,0.00010961254,0.000107471475,0.0027201038,0.022949701,0.00058067177,0.8219168,0.0006477999,0.022331696],"study_design_scores_gemma":[0.00043134467,0.000053859505,0.03527179,0.00008483288,0.00000684076,0.000017492746,0.0003151324,0.9465137,0.000156162,0.014787261,0.0021025096,0.00025906588],"about_ca_topic_score_codex":0.00019280514,"about_ca_topic_score_gemma":0.000025345633,"teacher_disagreement_score":0.94343305,"about_ca_system_score_codex":0.00010778943,"about_ca_system_score_gemma":0.0001172507,"threshold_uncertainty_score":0.99964607},"labels":[],"label_agreement":null},{"id":"W2963742410","doi":"","title":"DOM-Q-NET: Grounded RL on Structured Language","year":2019,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Reinforcement learning; Artificial intelligence; Task (project management); Machine learning; The Internet; String (physics); Graph; Natural language processing; Theoretical computer science; World Wide Web","score_opus":0.021628009855171406,"score_gpt":0.34219214213863863,"score_spread":0.32056413228346725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963742410","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62262386,0.0000070784395,0.044819307,0.013972667,0.0010985447,0.0005676306,0.000016059254,0.00071843545,0.31617638],"genre_scores_gemma":[0.9865697,0.000005119861,0.004932993,0.0004285628,0.00011463829,0.00007123241,0.000098967255,0.000019612451,0.0077591776],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99802047,0.00016649002,0.00027144217,0.0006624539,0.0006439083,0.00023522817],"domain_scores_gemma":[0.9984275,0.0003359741,0.00020839348,0.00071092666,0.00022071833,0.00009646684],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00017071687,0.0001926039,0.0001554879,0.0002977721,0.00019440973,0.0004183274,0.0012334333,0.0000751849,0.0013699309],"category_scores_gemma":[0.0002951385,0.00018916801,0.00009010274,0.00030198504,0.00005464852,0.00034296289,0.00018489323,0.00064873847,0.0025618544],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028582208,0.00010277187,0.01172502,0.0000045996867,0.00005831782,0.000008548047,0.0026607406,0.025638279,0.01025158,0.9303633,0.00025366124,0.0189046],"study_design_scores_gemma":[0.0012834499,0.0002845776,0.33273754,0.0000818638,0.000009285497,0.000023730763,0.0008105892,0.6405316,0.0015789767,0.017253954,0.0048898403,0.0005146061],"about_ca_topic_score_codex":0.00049764145,"about_ca_topic_score_gemma":0.000023424021,"teacher_disagreement_score":0.91310936,"about_ca_system_score_codex":0.000102150916,"about_ca_system_score_gemma":0.00007744149,"threshold_uncertainty_score":0.99954295},"labels":[],"label_agreement":null},{"id":"W2964191424","doi":"","title":"Multimodal Transitions for Generative Stochastic Networks","year":2013,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Markov chain; Estimator; Autoregressive model; Computer science; Hidden Markov model; Consistency (knowledge bases); Operator (biology); Probabilistic logic; Artificial intelligence; Probability distribution; Markov model; Cumulative distribution function; Algorithm; Probability density function; Machine learning; Mathematics; Statistics","score_opus":0.05055424772446704,"score_gpt":0.3297161774337315,"score_spread":0.27916192970926446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964191424","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034921025,0.000007038663,0.98125905,0.009196506,0.00044945188,0.00034672854,0.000008413047,0.00019027358,0.0050504156],"genre_scores_gemma":[0.9671878,0.00000626717,0.029841647,0.00034021318,0.00015395704,0.0004940016,0.00007760626,0.000011048518,0.0018874555],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875766,0.00007911661,0.00024883103,0.00043075247,0.00025345178,0.00023018925],"domain_scores_gemma":[0.9986397,0.0002558208,0.000100460544,0.00023367263,0.0006657253,0.00010459996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001114426,0.0001447203,0.00011968122,0.00014319188,0.00031290657,0.0004948159,0.00058391574,0.00006583193,0.00029505862],"category_scores_gemma":[0.0001731683,0.00014411754,0.00009022401,0.00014856044,0.000058229743,0.0005542832,0.00005474592,0.00028623288,0.00015151183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000075680846,0.00007433305,0.000070482536,0.0000013176892,0.000045810484,0.0000010623177,0.0011878799,0.505258,0.0012849966,0.4746953,0.00081280427,0.016560439],"study_design_scores_gemma":[0.00030649808,0.000087894055,0.0006998637,0.000025220937,0.0000055170813,0.0000050391004,0.00019797534,0.9739788,0.00010534335,0.0243496,0.00008097865,0.00015728216],"about_ca_topic_score_codex":0.000081522325,"about_ca_topic_score_gemma":0.000009122877,"teacher_disagreement_score":0.9636957,"about_ca_system_score_codex":0.00004203094,"about_ca_system_score_gemma":0.000080957965,"threshold_uncertainty_score":0.5876943},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03925941227028947,"score_gpt":0.3147329136198822,"score_spread":0.27547350134959275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964335273","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010792982,0.0000070665214,0.93498635,0.023759808,0.0011251697,0.000094048475,7.8568314e-7,0.00016131459,0.029072486],"genre_scores_gemma":[0.98755556,0.0000049614173,0.009368742,0.0010656206,0.00026315605,0.000027507,0.00001441607,0.0000078562925,0.0016921917],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986789,0.00011780894,0.00017761278,0.0004373162,0.00037763786,0.00021071252],"domain_scores_gemma":[0.9989928,0.00018431773,0.00013427911,0.00026502932,0.00029793967,0.00012563329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016880214,0.00012755775,0.00011473522,0.00016178054,0.00022906705,0.00097462075,0.0007609122,0.000038914804,0.00010032843],"category_scores_gemma":[0.0004743663,0.0001240069,0.00005428129,0.00023466183,0.000049327904,0.0004448814,0.00019053926,0.00030107607,0.000050043018],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010413382,0.00003604565,0.0038782575,0.0000035137282,0.000025030407,0.0000048412207,0.0012743564,0.052045602,0.00035215187,0.3646266,0.0011625742,0.57658064],"study_design_scores_gemma":[0.00017953762,0.00007159698,0.0026115559,0.000034881985,0.000002858238,0.000012672323,0.00015909245,0.98676467,0.000110431065,0.0021180667,0.0077806474,0.00015397755],"about_ca_topic_score_codex":0.000013554659,"about_ca_topic_score_gemma":0.000009008383,"teacher_disagreement_score":0.9767626,"about_ca_system_score_codex":0.000035039313,"about_ca_system_score_gemma":0.00003137244,"threshold_uncertainty_score":0.93982905},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0945946462711303,"score_gpt":0.3266313768676395,"score_spread":0.2320367305965092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964469479","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048949543,0.000005737455,0.8974964,0.0041039265,0.00059405214,0.00039213875,7.9944937e-7,0.00023072911,0.0482267],"genre_scores_gemma":[0.9870116,0.000052448235,0.0019364149,0.00011107472,0.00008419365,0.00002151569,0.00006707069,0.000018028335,0.010697624],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99774057,0.00023444448,0.00041385,0.0004937571,0.0008252705,0.0002921347],"domain_scores_gemma":[0.99841577,0.00055862626,0.00039105717,0.0003441362,0.00019761837,0.0000927928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052074785,0.00020121303,0.00016474964,0.00026847332,0.0005541941,0.00070662843,0.00067786773,0.000089624606,0.00036245646],"category_scores_gemma":[0.0003753715,0.0001778774,0.00007485493,0.00027639698,0.0000992838,0.00073336274,0.00036403848,0.00091857126,0.00028793621],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009659366,0.000006086881,0.23044664,0.000004130556,0.000058253707,0.0000033067786,0.0021151006,0.54755455,0.00028359654,0.21904193,0.00007723915,0.00039948858],"study_design_scores_gemma":[0.0006801739,0.0002447456,0.058515605,0.00009689059,0.000025224586,0.000010491998,0.0023871688,0.93109566,0.000087137225,0.005112426,0.0014758524,0.00026865205],"about_ca_topic_score_codex":0.00005631406,"about_ca_topic_score_gemma":0.0000031934057,"teacher_disagreement_score":0.9380621,"about_ca_system_score_codex":0.00025620655,"about_ca_system_score_gemma":0.00008076348,"threshold_uncertainty_score":0.72536296},"labels":[],"label_agreement":null},{"id":"W2965212561","doi":"","title":"Neural Graph Evolution: Towards Efficient Automatic Robot Design","year":2019,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Robot; Graph; Artificial intelligence; Artificial neural network; Theoretical computer science; Machine learning","score_opus":0.05089747332137666,"score_gpt":0.3173870093774977,"score_spread":0.266489536056121,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965212561","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015418723,0.000009225609,0.9432251,0.0029132508,0.0015249171,0.00037853295,0.000001105713,0.00046051675,0.036068656],"genre_scores_gemma":[0.97344095,0.0000057482403,0.019472,0.00014070094,0.00006767406,0.000047555055,0.000021111768,0.00001688628,0.006787351],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99738294,0.00027512317,0.0004213848,0.0005807266,0.0010085638,0.00033125046],"domain_scores_gemma":[0.9982754,0.00031345309,0.0002816424,0.0005910952,0.0004280072,0.00011039103],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003845127,0.00021767525,0.00018855602,0.00041391473,0.00023010261,0.0005400017,0.0013209941,0.00007465209,0.0009237478],"category_scores_gemma":[0.00039874975,0.00021758105,0.0001252372,0.0004819162,0.00006915499,0.00045455,0.00027762662,0.0004975863,0.0013470969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000072093276,0.000038562623,0.0023004557,0.000005024675,0.00003980055,0.0000067726887,0.0005979454,0.8749052,0.0005706135,0.11865961,0.00013092524,0.002737848],"study_design_scores_gemma":[0.00041837376,0.00018664905,0.01787419,0.00005651185,0.0000074126697,0.000019447387,0.00020463251,0.97933215,0.0001673986,0.0013204989,0.00018814203,0.00022456686],"about_ca_topic_score_codex":0.000052059793,"about_ca_topic_score_gemma":8.072806e-7,"teacher_disagreement_score":0.95802224,"about_ca_system_score_codex":0.0001883881,"about_ca_system_score_gemma":0.00019538618,"threshold_uncertainty_score":0.99998957},"labels":[],"label_agreement":null},{"id":"W2965465046","doi":"","title":"Learning proposals for sequential importance samplers using reinforced variational inference.","year":2019,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Inference; Computer science; Artificial intelligence; Machine learning","score_opus":0.05752040479871633,"score_gpt":0.3716738520567237,"score_spread":0.31415344725800737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965465046","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12860405,0.0000054864345,0.84717345,0.0025939152,0.0015157696,0.00064312684,0.00001578074,0.00041999828,0.019028446],"genre_scores_gemma":[0.94212586,0.000008361312,0.045689028,0.00013511581,0.00025598955,0.00007336694,0.0002233366,0.000023960642,0.011464956],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99758536,0.00018282532,0.00047821816,0.00069928187,0.0007005974,0.00035372307],"domain_scores_gemma":[0.99785703,0.0005879533,0.00043058398,0.000352106,0.0006646382,0.00010767175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005146963,0.00023220613,0.00022801544,0.00031403577,0.00040614602,0.00059674005,0.0008635344,0.000098469885,0.00078583445],"category_scores_gemma":[0.001162338,0.00023931114,0.00015113525,0.00030268737,0.00005097192,0.0007894666,0.00019112276,0.0006246603,0.00017282789],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004203055,0.00003557541,0.03720502,0.000015223648,0.00010463901,0.0000044421427,0.0013951028,0.45228675,0.0066869087,0.49769986,0.00008048894,0.004443946],"study_design_scores_gemma":[0.0007411995,0.00021050066,0.002629823,0.00005904821,0.000009633781,0.000013217544,0.0003013427,0.98855424,0.00030038596,0.004696483,0.0021957431,0.000288358],"about_ca_topic_score_codex":0.00014221415,"about_ca_topic_score_gemma":0.000004567565,"teacher_disagreement_score":0.81352186,"about_ca_system_score_codex":0.00013488717,"about_ca_system_score_gemma":0.00036715143,"threshold_uncertainty_score":0.97588253},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.088447391195338,"score_gpt":0.3988270749660196,"score_spread":0.3103796837706816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966262171","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38155305,0.00009703071,0.45417625,0.078633755,0.0027608394,0.0024555332,0.00001680848,0.00078833476,0.0795184],"genre_scores_gemma":[0.9870693,0.00003059558,0.0045011225,0.00036534754,0.000057158803,0.00009942318,0.000051910753,0.000012784505,0.007812345],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972726,0.00025974785,0.00046835106,0.0012992498,0.00038580192,0.00031422588],"domain_scores_gemma":[0.9979575,0.0004835168,0.00023998128,0.000899038,0.00034214085,0.00007777596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017864986,0.00013877949,0.00019594116,0.00031091445,0.00018008657,0.000244988,0.00082232896,0.000047068173,0.0002963558],"category_scores_gemma":[0.0024901992,0.00014901417,0.00008144734,0.00036983343,0.00003674125,0.00057624717,0.00017669739,0.00047456525,0.00033236024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008671122,0.00026222624,0.20282486,0.0000282133,0.00003372753,0.0000067473306,0.005980202,0.111216746,0.0022683276,0.6442588,0.00027128402,0.03276218],"study_design_scores_gemma":[0.00038114388,0.00035946927,0.022180138,0.000081827995,0.0000013525436,0.00000574378,0.0008062394,0.9491829,0.0017577036,0.016752565,0.008263385,0.0002275199],"about_ca_topic_score_codex":0.00071900175,"about_ca_topic_score_gemma":0.00021089899,"teacher_disagreement_score":0.83796614,"about_ca_system_score_codex":0.00019392755,"about_ca_system_score_gemma":0.00019914865,"threshold_uncertainty_score":0.6076622},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Latent variable; Generative grammar; Computer science; Latent variable model; Variable (mathematics); Artificial intelligence; Mathematics","score_opus":0.17610585578987872,"score_gpt":0.3340231839156236,"score_spread":0.15791732812574485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966574105","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12096861,0.0000056106346,0.7889301,0.0034176935,0.0007070298,0.00024831793,0.0000033498604,0.00009898303,0.0856203],"genre_scores_gemma":[0.9817831,0.000010051415,0.013032527,0.0001869812,0.000034323653,0.0000286766,0.000014320835,0.000008025383,0.0049020043],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986269,0.000107789514,0.0002585895,0.00044396956,0.00037778524,0.00018496596],"domain_scores_gemma":[0.9992688,0.00013971997,0.00010659494,0.00028008473,0.00015531678,0.0000495139],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002110538,0.00011047948,0.00012316467,0.0002611708,0.0000850083,0.00031346673,0.000542112,0.000049644048,0.00030215766],"category_scores_gemma":[0.000071426606,0.00011636264,0.000035440997,0.00024220705,0.000018286128,0.00070510485,0.0001781761,0.00026854844,0.00011860574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007841905,0.00002450966,0.00505066,0.0000018415783,0.000013310603,0.000005759282,0.0014545589,0.34480882,0.0017723547,0.6465956,0.000022825749,0.00024194364],"study_design_scores_gemma":[0.00039992316,0.00004186925,0.0009041129,0.00005986789,0.000001445092,0.000006731809,0.00047640438,0.93590736,0.00013772552,0.061886016,0.000058410817,0.00012011922],"about_ca_topic_score_codex":0.0001288772,"about_ca_topic_score_gemma":0.000025118405,"teacher_disagreement_score":0.86081445,"about_ca_system_score_codex":0.00026946323,"about_ca_system_score_gemma":0.00013657048,"threshold_uncertainty_score":0.47451305},"labels":[],"label_agreement":null},{"id":"W2966697812","doi":"","title":"Reproducibility and Stability Analysis in Metric-Based Few-Shot Learning.","year":2019,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; HEC Montréal","funders":"","keywords":"Reproducibility; Metric (unit); Computer science; Stability (learning theory); Artificial intelligence; Mathematics; Machine learning; Statistics; Engineering","score_opus":0.07488014056526597,"score_gpt":0.34860978593865394,"score_spread":0.27372964537338795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966697812","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82114136,0.000030715808,0.111190274,0.005156448,0.00038661272,0.00042674327,0.0000044349913,0.0003010098,0.061362382],"genre_scores_gemma":[0.9940574,0.000016700122,0.003750503,0.00016366508,0.000022811137,0.00003463073,0.000058781912,0.000010430553,0.0018850676],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99623054,0.00065311947,0.00050535036,0.0016530732,0.0006882145,0.0002697241],"domain_scores_gemma":[0.99726254,0.00089415425,0.00027766873,0.0010391889,0.00040924244,0.000117220356],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002206817,0.00019217785,0.00030258475,0.0010287742,0.00016478964,0.00043107613,0.0006349269,0.00008051328,0.0011597956],"category_scores_gemma":[0.0034631703,0.00020184765,0.00013724917,0.0018923439,0.00008510314,0.00055009965,0.0001906586,0.0007412714,0.00015003816],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046958994,0.00015578826,0.84806156,0.00000927258,0.00011236771,0.000007643929,0.0019996879,0.10148247,0.0010315368,0.039541245,0.000011441122,0.0075400253],"study_design_scores_gemma":[0.0005167928,0.00009360855,0.38450307,0.000016152148,0.000016964106,0.000001473962,0.0007054044,0.6119155,0.0002871461,0.0008694209,0.0008913936,0.00018304861],"about_ca_topic_score_codex":0.00031270782,"about_ca_topic_score_gemma":0.000089130066,"teacher_disagreement_score":0.510433,"about_ca_system_score_codex":0.00014323491,"about_ca_system_score_gemma":0.0001468033,"threshold_uncertainty_score":0.9997533},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09777329092838097,"score_gpt":0.3433704679106314,"score_spread":0.24559717698225045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994886105","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0144689465,0.000021294463,0.91367644,0.025018167,0.0005103875,0.0005965792,0.000014189228,0.00040617073,0.045287825],"genre_scores_gemma":[0.94591194,0.0000065702343,0.051198304,0.0011728625,0.00021808298,0.00020606066,0.00014907311,0.000017950193,0.0011191727],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813294,0.0001602349,0.00034517105,0.000564079,0.00056773954,0.00022984411],"domain_scores_gemma":[0.9986583,0.00028282238,0.00027777557,0.00019306771,0.00042629975,0.00016172527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023638323,0.00016993968,0.00014789203,0.00015618495,0.00032589352,0.0004533116,0.00073557266,0.00006061395,0.00038351052],"category_scores_gemma":[0.0006663388,0.0001810866,0.00010954288,0.0002616862,0.000064983695,0.0006696894,0.00013712869,0.00032622847,0.00019826429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002257306,0.00016603348,0.00168161,0.000022190407,0.00017587347,0.00004633839,0.031753376,0.03945927,0.009276599,0.8443804,0.0015964416,0.07121614],"study_design_scores_gemma":[0.0014971602,0.0003741612,0.0028807775,0.000045770725,0.000010100743,0.00001354231,0.0060789823,0.97066456,0.00093781156,0.0063438085,0.0108313365,0.0003219724],"about_ca_topic_score_codex":0.000016740742,"about_ca_topic_score_gemma":0.0000028991437,"teacher_disagreement_score":0.931443,"about_ca_system_score_codex":0.00006940841,"about_ca_system_score_gemma":0.00013912533,"threshold_uncertainty_score":0.7384497},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.035859797675240924,"score_gpt":0.28773296694383693,"score_spread":0.251873169268596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995040055","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033179766,0.000002275644,0.82088596,0.0045742323,0.000097303724,0.00022020335,0.000002427266,0.00018847494,0.17071116],"genre_scores_gemma":[0.9880551,0.0000277035,0.010564056,0.00035894677,0.000040243216,0.000027293534,0.000101880665,0.000009455542,0.0008152847],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808735,0.00012880653,0.0004905353,0.0002948297,0.00078867783,0.00020981325],"domain_scores_gemma":[0.9980388,0.00032725467,0.000540937,0.00020565747,0.00076678913,0.00012052774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015253644,0.00018664148,0.00020588803,0.00022274333,0.00018872548,0.0002795904,0.00073898234,0.000049070877,0.0003145221],"category_scores_gemma":[0.00079910725,0.00017564466,0.00007086123,0.0003477122,0.00015617337,0.001181583,0.00019881927,0.00048153274,0.00012548313],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042433392,0.000012053047,0.0030236722,0.000011746066,0.00007806011,0.0000039936644,0.005840524,0.642129,0.00050258,0.3469694,0.00003193253,0.0013546122],"study_design_scores_gemma":[0.0009839728,0.0008597904,0.003833747,0.00015417289,0.000014567056,0.000009849221,0.0049645044,0.98224777,0.002497911,0.00019855196,0.003961774,0.00027336672],"about_ca_topic_score_codex":0.000027263706,"about_ca_topic_score_gemma":0.0000012737279,"teacher_disagreement_score":0.98473716,"about_ca_system_score_codex":0.0000481561,"about_ca_system_score_gemma":0.00020016517,"threshold_uncertainty_score":0.7162581},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.279971621243436,"score_gpt":0.48483052989203934,"score_spread":0.20485890864860334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995122033","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18985574,0.00002436405,0.6462003,0.03767588,0.0009152503,0.0025203591,0.00018286117,0.0031302287,0.11949501],"genre_scores_gemma":[0.9781236,0.000051485087,0.015434331,0.0003079081,0.00031105668,0.00037462532,0.0003079486,0.00006205786,0.0050269603],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99767816,0.00019478648,0.00056015566,0.00065204664,0.00060743163,0.00030743645],"domain_scores_gemma":[0.99681425,0.0016087723,0.00043725743,0.00026832975,0.00068372354,0.00018767553],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022989268,0.0002813541,0.0003031041,0.00017324653,0.00041167316,0.00020898871,0.00048118635,0.00011355768,0.0011758658],"category_scores_gemma":[0.007471581,0.0002710768,0.0001751348,0.00023654167,0.000123843,0.00045821525,0.00013919761,0.0006730023,0.00010094175],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000807004,0.00037573642,0.014420477,0.000091227404,0.00033401433,0.000035201832,0.014887475,0.006120584,0.041218244,0.89101,0.018440971,0.012259071],"study_design_scores_gemma":[0.0049834005,0.0027256901,0.0032880728,0.00084232446,0.00026488962,0.00004452811,0.031201864,0.34150648,0.039805204,0.5321841,0.041088037,0.002065397],"about_ca_topic_score_codex":0.000020547714,"about_ca_topic_score_gemma":0.000008112226,"teacher_disagreement_score":0.7882679,"about_ca_system_score_codex":0.00011496853,"about_ca_system_score_gemma":0.00009060157,"threshold_uncertainty_score":0.99997413},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0342901584745485,"score_gpt":0.28078537204376,"score_spread":0.24649521356921147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995128076","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002092613,0.000025715599,0.96533453,0.018329158,0.00040339064,0.00015785746,0.000006985263,0.000053067655,0.013596652],"genre_scores_gemma":[0.98882,0.00007021487,0.009157435,0.00056750426,0.0003750098,0.000035320343,0.000053494747,0.000008395968,0.0009125831],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868596,0.00024054766,0.00025581298,0.00034185205,0.00034348524,0.00013236611],"domain_scores_gemma":[0.9988963,0.00026643652,0.00022404615,0.00020095812,0.00034899334,0.000063263775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001370555,0.00012128705,0.00013189155,0.00005041752,0.00024544916,0.00016008655,0.00059942564,0.000045524754,0.0008141882],"category_scores_gemma":[0.00033078427,0.00009321832,0.00008820007,0.0002349506,0.0000715011,0.00032085326,0.0002485867,0.0002054201,0.000035240595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041061972,0.000020485464,0.0007638909,9.564237e-7,0.000066137036,0.0000023204755,0.0014418932,0.9757748,0.00067234505,0.017553369,0.0018032957,0.0018593994],"study_design_scores_gemma":[0.00031604312,0.00008367646,0.00046820316,0.00001118356,0.000010661327,0.0000016474149,0.00023605862,0.99576324,0.0013994029,0.00018853186,0.0014254262,0.00009594798],"about_ca_topic_score_codex":0.000035970774,"about_ca_topic_score_gemma":0.000017695698,"teacher_disagreement_score":0.9867274,"about_ca_system_score_codex":0.000031000025,"about_ca_system_score_gemma":0.000060819708,"threshold_uncertainty_score":0.89147896},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06320326867818603,"score_gpt":0.3032700120988561,"score_spread":0.24006674342067008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995291884","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00043884057,0.0000046172613,0.9272605,0.016818093,0.00025441073,0.0003082803,0.000005340498,0.00048443113,0.05442548],"genre_scores_gemma":[0.88577825,0.000015439482,0.11139618,0.0017517996,0.00011033065,0.00014760566,0.00009090768,0.000021256012,0.0006882107],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99802,0.0001480536,0.0003337112,0.0006021139,0.0006866247,0.00020951802],"domain_scores_gemma":[0.9985223,0.00037164512,0.00022845788,0.0003629738,0.0003955539,0.00011908274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019175661,0.00018691359,0.00014257507,0.0001861039,0.00032244466,0.000503227,0.0012549318,0.00006385004,0.00019909817],"category_scores_gemma":[0.0013525332,0.00016445809,0.00009417839,0.00049525435,0.000081368555,0.00041114222,0.00022101248,0.0004088208,0.0001007115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020996145,0.000058433394,0.0001341532,0.000002571952,0.000029734274,0.0000035138494,0.0017543932,0.5620769,0.00009895205,0.4330623,0.0014071065,0.0013509329],"study_design_scores_gemma":[0.00034498062,0.00018091277,0.0001511923,0.00003179136,0.0000070489564,0.000006362327,0.0002617584,0.9956653,0.00021611365,0.0026436937,0.0003231193,0.00016772204],"about_ca_topic_score_codex":0.00001666061,"about_ca_topic_score_gemma":6.2273955e-7,"teacher_disagreement_score":0.88533944,"about_ca_system_score_codex":0.00006945648,"about_ca_system_score_gemma":0.00009741548,"threshold_uncertainty_score":0.67064065},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.05955057235187068,"score_gpt":0.3172682931974696,"score_spread":0.2577177208455989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995372087","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007360958,0.000011021354,0.94549435,0.013171172,0.0002168591,0.0007088621,0.000001067367,0.00020374586,0.032831986],"genre_scores_gemma":[0.990382,0.000040953997,0.0021306237,0.0002251217,0.00008191261,0.00012148531,0.000056756526,0.00001920282,0.006941912],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977693,0.00023726911,0.0005993201,0.00044952228,0.0006563553,0.00028823118],"domain_scores_gemma":[0.9980472,0.0007191609,0.0004989118,0.0002456129,0.0004087607,0.00008036873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005441699,0.00018394878,0.00021994063,0.00019669112,0.00025170544,0.0002440646,0.001162859,0.000065185,0.00022476114],"category_scores_gemma":[0.0021369306,0.00016309008,0.000103936625,0.0004311133,0.00008864843,0.00040905343,0.0002710261,0.00079912547,0.00012073608],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002243277,0.000017358561,0.0066027334,0.000016681219,0.000042746477,0.0000015838665,0.0061372924,0.9505544,0.0030733885,0.031840567,0.00012703841,0.001563802],"study_design_scores_gemma":[0.00059210125,0.0005697722,0.0012608626,0.00008935545,0.000007452999,0.0000021325607,0.00071241014,0.9905544,0.0005023136,0.00043891705,0.005105117,0.00016518784],"about_ca_topic_score_codex":0.000049743172,"about_ca_topic_score_gemma":0.0000029029145,"teacher_disagreement_score":0.9830211,"about_ca_system_score_codex":0.00007002158,"about_ca_system_score_gemma":0.00012306492,"threshold_uncertainty_score":0.66506207},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.08250555733982355,"score_gpt":0.3510375405511749,"score_spread":0.26853198321135135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996067004","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007542129,0.000008076632,0.9818614,0.0054417867,0.00029406187,0.00018404501,0.0000029706227,0.0003131048,0.004352426],"genre_scores_gemma":[0.9681268,0.000015664522,0.030745087,0.0007685212,0.00011642167,0.000033479682,0.00007537912,0.000013187723,0.00010550888],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984488,0.00016638126,0.0003780089,0.00042408978,0.00043515328,0.00014758854],"domain_scores_gemma":[0.998717,0.00010166043,0.00027326972,0.00027389085,0.0005111152,0.00012304183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013127393,0.0001351424,0.00014709088,0.00016495753,0.0000999498,0.00017559266,0.0007951525,0.000041850883,0.00021760802],"category_scores_gemma":[0.0003583629,0.0001413284,0.00006304714,0.0003961961,0.000054982625,0.00061536726,0.00014582412,0.00020751014,0.00001638034],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000081086055,0.000041488776,0.0017287853,0.0000022003717,0.000017217419,0.0000022712013,0.0009353567,0.5710766,0.0011643596,0.42240793,0.00008383945,0.002531901],"study_design_scores_gemma":[0.00028815778,0.00020200569,0.0012879453,0.000018969356,0.0000067825567,0.000004952465,0.00007738733,0.9932674,0.00095682486,0.0037177277,0.0000443369,0.00012751487],"about_ca_topic_score_codex":0.00003468486,"about_ca_topic_score_gemma":0.0000024805267,"teacher_disagreement_score":0.96058464,"about_ca_system_score_codex":0.0000325418,"about_ca_system_score_gemma":0.00004535435,"threshold_uncertainty_score":0.57632047},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09059197135597538,"score_gpt":0.3557337931421951,"score_spread":0.2651418217862197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996068536","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08404621,0.000011871485,0.808919,0.023188101,0.00035086076,0.00010596547,0.0000030802335,0.00039068292,0.0829842],"genre_scores_gemma":[0.98751587,0.000011487547,0.0104664005,0.00078112853,0.00018679613,0.0000151626255,0.000018340195,0.000008035045,0.0009967835],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988035,0.000058571037,0.00019849172,0.0004023962,0.00039372535,0.00014333417],"domain_scores_gemma":[0.99938333,0.000095687756,0.000053873693,0.000219698,0.00014641297,0.000100985955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009236257,0.000096049655,0.00008843452,0.00008081189,0.00011219422,0.00026935787,0.00079961645,0.000033965945,0.0002493892],"category_scores_gemma":[0.00032133912,0.0001011003,0.000055007873,0.0001575389,0.000021260168,0.00034304647,0.00016235554,0.00030909435,0.00022751727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021538433,0.000083655286,0.017109519,0.0000111583,0.000108741835,0.000121939695,0.034891956,0.09222154,0.027247014,0.7350851,0.00068626786,0.092411555],"study_design_scores_gemma":[0.00014724267,0.000043008447,0.00181133,0.000021062779,0.0000033239696,0.0000057281577,0.0011319658,0.992832,0.0013454056,0.001062648,0.0014533722,0.00014288083],"about_ca_topic_score_codex":0.000044195636,"about_ca_topic_score_gemma":0.0000050568906,"teacher_disagreement_score":0.9034697,"about_ca_system_score_codex":0.000028434393,"about_ca_system_score_gemma":0.000054820957,"threshold_uncertainty_score":0.41227505},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.07105698301146753,"score_gpt":0.32163291283718065,"score_spread":0.25057592982571314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996091952","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6719767,0.0000106172765,0.31121442,0.01365289,0.0007635036,0.00039695017,0.000008154304,0.00021284557,0.0017639691],"genre_scores_gemma":[0.98237985,0.0000055342075,0.016137898,0.00038843448,0.0005633308,0.00026885504,0.000026279826,0.000026181995,0.00020360686],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981653,0.00015684722,0.00029155964,0.00054548593,0.00051990664,0.00032092052],"domain_scores_gemma":[0.9987429,0.00045218406,0.00023174248,0.00020394694,0.0002561381,0.00011312498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031065842,0.0001773322,0.00015389023,0.000046389272,0.00041516463,0.0005642874,0.00073986547,0.000032542768,0.0007340028],"category_scores_gemma":[0.00086972007,0.0001304454,0.00005829665,0.00017904268,0.00017856825,0.000288777,0.00015978259,0.0003242474,0.00006664963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014689782,0.000026724136,0.0037201187,0.000010721142,0.000021117365,0.000009325643,0.002345581,0.85765594,0.12594512,0.005521872,0.00009194157,0.0045046518],"study_design_scores_gemma":[0.00034510996,0.0001357335,0.002766065,0.000023886958,0.0000157745,0.000013654624,0.0007443212,0.98782265,0.007347053,0.00015247196,0.00045942792,0.0001738498],"about_ca_topic_score_codex":0.000055349923,"about_ca_topic_score_gemma":0.000005136592,"teacher_disagreement_score":0.31040323,"about_ca_system_score_codex":0.000037555037,"about_ca_system_score_gemma":0.00003522939,"threshold_uncertainty_score":0.8036816},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.0703062179486579,"score_gpt":0.34140394478371966,"score_spread":0.2710977268350617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996151541","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37987766,0.000013861113,0.5453901,0.0569152,0.0010840846,0.0005162417,0.00011603448,0.0002690737,0.01581773],"genre_scores_gemma":[0.9977198,0.000012073506,0.0014650876,0.00033728694,0.00012575873,0.00003415426,0.000023944855,0.000004912448,0.00027695173],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902713,0.00008179976,0.00021860494,0.00026599164,0.00030902785,0.00009743637],"domain_scores_gemma":[0.99919075,0.00007468516,0.00019484303,0.00019882651,0.00029304874,0.000047826088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000058569567,0.000075979566,0.000075859134,0.000025767711,0.00021600512,0.000109584274,0.0006320665,0.000031726584,0.000046572473],"category_scores_gemma":[0.00015056728,0.00006117869,0.000063984335,0.0003329173,0.00010938205,0.00025458832,0.00017596783,0.00018166873,0.000017178027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000164056,0.00006469475,0.04170839,0.000006075878,0.000056354627,0.0000011520439,0.0045358012,0.06824885,0.0160945,0.85746056,0.001478123,0.010329073],"study_design_scores_gemma":[0.0003158169,0.000060362127,0.0675515,0.000032044773,0.0000058592755,0.0000071288223,0.0005851603,0.91976494,0.0036110524,0.005408243,0.0025604137,0.00009747663],"about_ca_topic_score_codex":0.00002162365,"about_ca_topic_score_gemma":0.000006683121,"teacher_disagreement_score":0.85205233,"about_ca_system_score_codex":0.000018803434,"about_ca_system_score_gemma":0.000039560124,"threshold_uncertainty_score":0.24947944},"labels":[],"label_agreement":null},{"id":"W2996170846","doi":"","title":"Training Recurrent Neural Networks Online by Learning Explicit State Variables","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Recurrent neural network; Computer science; Truncation (statistics); Computation; Focus (optics); Machine learning; Artificial intelligence; Variety (cybernetics); Artificial neural network; Online learning; Algorithm; Mathematical optimization; Mathematics","score_opus":0.11405124960379914,"score_gpt":0.3407093050386591,"score_spread":0.22665805543485995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996170846","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025193155,0.00007166671,0.94162387,0.015099595,0.000754414,0.00022913131,0.000014735979,0.0007414087,0.016272005],"genre_scores_gemma":[0.9910021,0.00015158227,0.00502457,0.0013053084,0.00021991,0.000037804693,0.0003212127,0.000029402374,0.001908146],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972682,0.00037866642,0.0005091439,0.0007608499,0.0006800468,0.00040309952],"domain_scores_gemma":[0.99836886,0.00043512558,0.00035990818,0.0002239048,0.00032621567,0.00028599577],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027992233,0.00026301196,0.00024367863,0.00016445057,0.00041369646,0.00085837615,0.0010043558,0.00007187914,0.0005468108],"category_scores_gemma":[0.00084069377,0.00028418907,0.00011252337,0.00042963837,0.000056185112,0.0008795665,0.00024735305,0.0012095781,0.00011286123],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006201787,0.00012060331,0.0021892649,0.000006567843,0.00010112272,0.00003086738,0.014352709,0.67382485,0.0022256891,0.043271977,0.001205074,0.26260927],"study_design_scores_gemma":[0.00053962186,0.0002006177,0.0009876038,0.000049678554,0.000006627648,0.000008416614,0.002495111,0.97810596,0.000041226325,0.0003971029,0.016883329,0.00028471943],"about_ca_topic_score_codex":0.00004106988,"about_ca_topic_score_gemma":0.0000049931,"teacher_disagreement_score":0.9658089,"about_ca_system_score_codex":0.00006363125,"about_ca_system_score_gemma":0.00009243545,"threshold_uncertainty_score":0.999961},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.019646100709941154,"score_gpt":0.2979189959929102,"score_spread":0.27827289528296906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996680032","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01354594,0.000048243117,0.9298532,0.037556317,0.00020608988,0.00016063894,0.0000115464945,0.0005138617,0.018104156],"genre_scores_gemma":[0.90797025,0.000079613405,0.09063323,0.0010821375,0.00010372859,0.000029397519,0.000022176073,0.0000057574844,0.00007371716],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990683,0.000042608146,0.00019818466,0.0002750703,0.0003090713,0.00010671889],"domain_scores_gemma":[0.9992748,0.00008797596,0.00012863577,0.00013964067,0.00027389394,0.00009505299],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000092126946,0.00010200819,0.000081153805,0.00012583299,0.00020452825,0.0005023628,0.000357259,0.00004511972,0.000036055506],"category_scores_gemma":[0.00046979912,0.00010385626,0.00001734977,0.00018105627,0.000058505946,0.0013231619,0.00031422274,0.0003022097,0.0000150895385],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056845478,0.00006221163,0.012422748,0.000059080015,0.00006503222,0.0000103073835,0.02317927,0.010761343,0.0069349697,0.8365655,0.001467044,0.10841564],"study_design_scores_gemma":[0.00021316193,0.00007154164,0.006006434,0.000027495775,0.0000033405054,0.000011623014,0.00072915707,0.9822553,0.0001863676,0.00593637,0.004452943,0.00010630447],"about_ca_topic_score_codex":0.000007047091,"about_ca_topic_score_gemma":4.1275484e-7,"teacher_disagreement_score":0.9714939,"about_ca_system_score_codex":0.000021038011,"about_ca_system_score_gemma":0.000038937986,"threshold_uncertainty_score":0.48442957},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.35221709293036835,"score_gpt":0.5526990798639185,"score_spread":0.20048198693355018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012851896","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1087376,0.000042400123,0.80924517,0.029689062,0.0014751112,0.00059804885,0.00010713806,0.00017909889,0.049926348],"genre_scores_gemma":[0.9831194,0.000053551616,0.011219879,0.00027084802,0.000120600766,0.000033195407,0.000026384756,0.000016223594,0.005139867],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99551946,0.0006446224,0.00072515686,0.0007358527,0.002138214,0.0002367073],"domain_scores_gemma":[0.9944951,0.0030653337,0.00041300408,0.00042449436,0.0013945701,0.00020749144],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011506117,0.0001668606,0.0002910095,0.00040313945,0.00015221545,0.00017286441,0.0011769912,0.0000617754,0.0039604004],"category_scores_gemma":[0.019843373,0.00013803766,0.00015813143,0.00080061407,0.00027245187,0.0002947562,0.00022130583,0.0005466045,0.0008289014],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011137006,0.0006898414,0.04408732,0.000023952163,0.00035222978,0.00008701502,0.013940642,0.38224906,0.04386877,0.19790706,0.011677864,0.30400255],"study_design_scores_gemma":[0.0011555201,0.0011121987,0.020764176,0.0000832807,0.000015499798,0.000008549847,0.0053947982,0.8362018,0.03966288,0.05318099,0.041988473,0.00043182715],"about_ca_topic_score_codex":0.000041060197,"about_ca_topic_score_gemma":0.000003230278,"teacher_disagreement_score":0.87438184,"about_ca_system_score_codex":0.000053491956,"about_ca_system_score_gemma":0.00014695484,"threshold_uncertainty_score":0.9999491},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Ode; Computer science; Flow (mathematics); Applied mathematics; Mathematical optimization; Mathematical economics; Mathematics; Geometry","score_opus":0.22818065280292232,"score_gpt":0.42082505278815807,"score_spread":0.19264439998523575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041421878","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00904134,0.0000027207684,0.94913894,0.012485632,0.000063237,0.00048188047,0.000054755048,0.00021652208,0.028515002],"genre_scores_gemma":[0.95493907,0.0000025534562,0.042562872,0.00059086486,0.0001056367,0.0001760011,0.00017536237,0.000019155075,0.0014284819],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99784315,0.00015075154,0.00040974404,0.00055500795,0.000886265,0.00015510237],"domain_scores_gemma":[0.9966366,0.0015595118,0.00027797752,0.00028322416,0.0011287933,0.000113888156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005743437,0.00014348315,0.00016064236,0.00023002987,0.0003260234,0.00039020294,0.0006107568,0.000061132414,0.0008232688],"category_scores_gemma":[0.0015901546,0.00012040226,0.00010566024,0.00041798066,0.00007493944,0.0005122639,0.00005159248,0.00021488039,0.000087074186],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018182705,0.00003972593,0.00042929623,0.0000022158983,0.000021670816,8.4326854e-7,0.0011189064,0.65073043,0.0006498086,0.33618528,0.00063363387,0.010006373],"study_design_scores_gemma":[0.0005406751,0.00011715655,0.00020185258,0.000019953342,0.000012203618,7.741707e-7,0.00180891,0.90963316,0.00053303357,0.08373632,0.003262216,0.00013375247],"about_ca_topic_score_codex":0.000013496451,"about_ca_topic_score_gemma":0.0000073517936,"teacher_disagreement_score":0.94589776,"about_ca_system_score_codex":0.000053611344,"about_ca_system_score_gemma":0.00015248406,"threshold_uncertainty_score":0.90142155},"labels":[],"label_agreement":null},{"id":"W3122339903","doi":"","title":"Fast convergence of stochastic subgradient method under interpolation","year":2021,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Subgradient method; Interpolation (computer graphics); Mathematical optimization; Parameterized complexity; Mathematics; Stochastic gradient descent; Rate of convergence; Applied mathematics; Convergence (economics); Convex optimization; Convex function; Minification; Regular polygon; Computer science; Algorithm; Artificial intelligence; Artificial neural network; Geometry","score_opus":0.04650407779978084,"score_gpt":0.341509292915698,"score_spread":0.29500521511591715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122339903","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06370027,0.000035864257,0.90557647,0.00037293072,0.0006025411,0.00007509891,0.000010304456,0.0002520359,0.029374454],"genre_scores_gemma":[0.9932159,0.000027261443,0.0058977366,0.000030032954,0.000042321677,0.00001252701,0.00006056713,0.0000147406745,0.0006988869],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999194,0.0000674071,0.00022664684,0.00018275899,0.00022791541,0.00010122954],"domain_scores_gemma":[0.9991932,0.00015069214,0.000071518065,0.00016402401,0.00038416695,0.000036416484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006687787,0.00009799075,0.00011992727,0.00013241872,0.000044685672,0.000042860265,0.00013739544,0.000042712283,0.00065168773],"category_scores_gemma":[0.00012933853,0.00011005497,0.000059791073,0.00014365924,0.00003653554,0.00010000505,0.00004019935,0.00020571945,0.000026627955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019848501,0.00006541637,0.0011441673,0.00000861377,0.00017465826,0.000012358134,0.0015383031,0.6942421,0.16040096,0.13576052,0.0005661495,0.006066899],"study_design_scores_gemma":[0.00016372434,0.000032431602,0.0040541203,0.00013221802,0.00001676644,0.000017918706,0.0010427681,0.94422364,0.04298987,0.0069988864,0.00018570707,0.0001419708],"about_ca_topic_score_codex":0.000036331534,"about_ca_topic_score_gemma":0.000015123915,"teacher_disagreement_score":0.92951566,"about_ca_system_score_codex":0.000038391205,"about_ca_system_score_gemma":0.000035634526,"threshold_uncertainty_score":0.7135524},"labels":[],"label_agreement":null},{"id":"W3125085017","doi":"","title":"Leaky Tiling Activations: A Simple Approach to Learning Sparse Representations Online","year":2021,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Reinforcement learning; Regularization (linguistics); Simple (philosophy); Artificial neural network; Online algorithm; Artificial intelligence; Algorithm; Deep learning; Function (biology); Pattern recognition (psychology)","score_opus":0.1131943599475023,"score_gpt":0.3721155278946628,"score_spread":0.25892116794716047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125085017","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03745668,0.0000248045,0.7700796,0.007973978,0.0005330917,0.00035684282,0.00001678851,0.0006776455,0.18288054],"genre_scores_gemma":[0.9144657,0.000051831452,0.05996735,0.00087288284,0.00022458595,0.00013336723,0.00081042864,0.00003773319,0.023436103],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963187,0.0005003831,0.000629587,0.0011236747,0.0009858138,0.00044184653],"domain_scores_gemma":[0.9969359,0.00060202763,0.00031742954,0.000668745,0.0011944606,0.0002814213],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039488374,0.00029115222,0.00027711166,0.00056598126,0.0007878482,0.0010039825,0.0009841816,0.0001068339,0.0006951997],"category_scores_gemma":[0.0034709391,0.0003359381,0.00017279614,0.0013162334,0.000058979575,0.0009870438,0.0004443726,0.0010174307,0.00048695772],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005828708,0.0008185004,0.0078365505,0.000014644524,0.00020332597,0.00006530481,0.010172886,0.50894266,0.013178746,0.42786682,0.002270381,0.028571885],"study_design_scores_gemma":[0.0011220437,0.00013870937,0.033198394,0.00009839188,0.000026080019,0.00008873638,0.014855025,0.87210214,0.0016266693,0.0057424954,0.07029265,0.0007086401],"about_ca_topic_score_codex":0.00010294305,"about_ca_topic_score_gemma":0.000032007454,"teacher_disagreement_score":0.87700903,"about_ca_system_score_codex":0.0001589648,"about_ca_system_score_gemma":0.0003652719,"threshold_uncertainty_score":0.9999093},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.05821540092947535,"score_gpt":0.34313833311950254,"score_spread":0.2849229321900272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127129507","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11281158,0.000060287384,0.77001995,0.0076736,0.001219807,0.0002808157,0.0000026451503,0.00046896716,0.10746237],"genre_scores_gemma":[0.9840883,0.00006357382,0.010426512,0.00025578518,0.0000974249,0.000045303423,0.00016063005,0.000023392344,0.0048390827],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970813,0.00056531775,0.0004873026,0.000734827,0.00079205923,0.0003392085],"domain_scores_gemma":[0.99837923,0.00036678178,0.00028147455,0.0003304014,0.0005164876,0.00012561868],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00042357921,0.00022215421,0.00021478807,0.00042946663,0.00032889593,0.00062678487,0.000617152,0.00009790132,0.0012116192],"category_scores_gemma":[0.0012403004,0.0002631466,0.000102209604,0.00081349857,0.00006177299,0.00083504955,0.0002503374,0.0008047812,0.000381577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000787325,0.00045283447,0.07750378,0.000018492345,0.00013388305,0.0002989361,0.015358984,0.21027046,0.061711155,0.5972294,0.00014391102,0.036799382],"study_design_scores_gemma":[0.001129232,0.000104240135,0.0517048,0.00010008445,0.000008060953,0.000053262276,0.0041308794,0.9327525,0.0036215214,0.0022404136,0.0037542463,0.0004007769],"about_ca_topic_score_codex":0.00012329087,"about_ca_topic_score_gemma":0.00014621347,"teacher_disagreement_score":0.87127674,"about_ca_system_score_codex":0.00019383633,"about_ca_system_score_gemma":0.00020359135,"threshold_uncertainty_score":0.99998206},"labels":[],"label_agreement":null},{"id":"W3127501635","doi":"","title":"Universal approximation power of deep residual neural networks via nonlinear control theory","year":2021,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Controllability; Residual; Uniform norm; Artificial neural network; Function approximation; Mathematics; Applied mathematics; Monotonic function; Mathematical optimization; Computer science; Nonlinear system; Discrete mathematics; Algorithm; Artificial intelligence; Mathematical analysis","score_opus":0.01787769868776137,"score_gpt":0.2882457914256486,"score_spread":0.27036809273788726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127501635","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18249583,0.000021490143,0.7518427,0.0017993549,0.0007832074,0.0001772132,0.000028433573,0.000060551025,0.062791266],"genre_scores_gemma":[0.9969128,0.0000048839106,0.00041462854,0.00006520332,0.0002833906,0.000012630229,0.0002818727,0.000012511165,0.0020121008],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988672,0.0002257521,0.00025977395,0.00025623155,0.00025370548,0.00013731827],"domain_scores_gemma":[0.9989481,0.00020154896,0.0001927295,0.00015850701,0.00044239013,0.000056734712],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00011621633,0.00011391385,0.00013781711,0.000080436665,0.00011801885,0.000062671264,0.00014878402,0.000042556872,0.0041795042],"category_scores_gemma":[0.000046004796,0.00011771488,0.000098907825,0.00013421284,0.00007446544,0.00017886801,0.00003999006,0.00034504748,0.000016616608],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020463397,0.00023014321,0.01259575,0.0000027345084,0.00023373294,0.000008311216,0.00082837476,0.64181626,0.002140968,0.31675667,0.00017242227,0.02501],"study_design_scores_gemma":[0.0006929231,0.00004457728,0.0022705323,0.00001638013,0.000023997516,0.000004410086,0.0017608135,0.9894236,0.00081440934,0.0046343207,0.00019458855,0.000119449796],"about_ca_topic_score_codex":0.000029682244,"about_ca_topic_score_gemma":0.0000026190528,"teacher_disagreement_score":0.81441694,"about_ca_system_score_codex":0.000018212997,"about_ca_system_score_gemma":0.000043585373,"threshold_uncertainty_score":0.9967308},"labels":[],"label_agreement":null},{"id":"W3128624754","doi":"","title":"Neural representation and generation for RNA secondary structures","year":2021,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; RNA; Computational biology; Theoretical computer science; Folding (DSP implementation); Graph; Encoding (memory); Artificial intelligence; Biology; Engineering; Genetics; Gene","score_opus":0.05482078782626408,"score_gpt":0.34202032152011785,"score_spread":0.28719953369385376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128624754","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9683977,0.00011180833,0.020060295,0.0026154981,0.0006180702,0.00023177142,0.000039453273,0.000023087992,0.007902333],"genre_scores_gemma":[0.991424,0.000110293186,0.0027092213,0.00021746161,0.00038531955,0.00008242873,0.0009171604,0.0000134379625,0.0041406383],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99914306,0.00009666009,0.00015454953,0.00036871646,0.00014040607,0.00009663134],"domain_scores_gemma":[0.9993749,0.000043740496,0.00008535064,0.00015425896,0.0002999077,0.00004181996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000085885265,0.000091447815,0.00007471223,0.000045935743,0.00016199313,0.00012951109,0.00008891361,0.00006874667,0.0002444182],"category_scores_gemma":[0.00050734443,0.000097364835,0.000055449716,0.000040557537,0.000032464708,0.000014896796,0.000048097983,0.000087582775,0.000003809931],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000472097,0.000015712165,0.00083234254,0.0000039320025,0.000049756934,0.0000030687838,0.000119681456,0.0008321376,0.95979,0.01571588,0.0005457345,0.02204455],"study_design_scores_gemma":[0.0007369547,0.00019125246,0.0060758414,0.0000129534765,0.000020804704,0.000051089482,0.0006641126,0.019539174,0.960251,0.0064481623,0.005789374,0.0002192893],"about_ca_topic_score_codex":0.000010648284,"about_ca_topic_score_gemma":0.00001915522,"teacher_disagreement_score":0.023026355,"about_ca_system_score_codex":0.00000832497,"about_ca_system_score_gemma":0.000066602624,"threshold_uncertainty_score":0.39704227},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.11749702201540502,"score_gpt":0.379141317792146,"score_spread":0.261644295776741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3130843035","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038618478,0.0000055406927,0.9230995,0.020756116,0.0007723424,0.00017681353,0.00000884677,0.00016544528,0.054629173],"genre_scores_gemma":[0.91065323,0.00007504399,0.063025914,0.00085632846,0.0001613198,0.00012611448,0.00037160687,0.000018582341,0.024711857],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984492,0.00014256693,0.00034237228,0.00042550347,0.0004452711,0.0001950974],"domain_scores_gemma":[0.997215,0.0007006772,0.00017196058,0.0003388001,0.0015064784,0.00006711167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002116543,0.00013028337,0.00012903499,0.00012538106,0.00031064372,0.00047878874,0.0005230504,0.000056929937,0.00022313885],"category_scores_gemma":[0.0020706852,0.00014762346,0.000086422544,0.0002454846,0.00007975584,0.00083432184,0.00014779862,0.00026327826,0.000106882755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014894974,0.00003472692,0.00064505904,0.000005101281,0.000046703546,0.000009367834,0.0012168812,0.25148338,0.0006253039,0.7428561,0.000745949,0.0023165403],"study_design_scores_gemma":[0.0006166069,0.00011281522,0.0011096634,0.000056398963,0.0000094078,0.000011231806,0.0016148782,0.95872253,0.0027204065,0.015282397,0.019538995,0.0002046517],"about_ca_topic_score_codex":0.000015437403,"about_ca_topic_score_gemma":0.00001086767,"teacher_disagreement_score":0.91026706,"about_ca_system_score_codex":0.00009041642,"about_ca_system_score_gemma":0.0002562981,"threshold_uncertainty_score":0.601991},"labels":[],"label_agreement":null},{"id":"W3131453904","doi":"","title":"HalentNet: Multimodal Trajectory Forecasting with Hallucinative Intents","year":2021,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Autonomous Vehicle Technology and Safety","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Trajectory; Computer science; Discriminative model; Artificial intelligence; Machine learning; Motion (physics); Feature learning; Robot; Key (lock); Representation (politics)","score_opus":0.04119373225655152,"score_gpt":0.2768955204699636,"score_spread":0.23570178821341206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131453904","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7321735,0.000057196783,0.03787368,0.0019346189,0.0005359059,0.00018278707,0.000025982512,0.00092187466,0.22629443],"genre_scores_gemma":[0.99556494,0.000038965736,0.0017374356,0.000035523564,0.00004474831,0.000041181356,0.000088323606,0.00002266452,0.0024262376],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915123,0.000042714753,0.00018106958,0.00025143006,0.00020429966,0.0001692555],"domain_scores_gemma":[0.99937916,0.00010480182,0.000052611595,0.00014412755,0.00027506115,0.000044258122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006230555,0.00013168229,0.00011708079,0.00012387426,0.0001310157,0.000050223967,0.00017160807,0.000075853255,0.00061167014],"category_scores_gemma":[0.00015357991,0.00013276815,0.00004390974,0.00014125333,0.00010148391,0.0001616361,0.000038060614,0.0005059165,0.00007660239],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015738978,0.0003425514,0.08070753,0.0000464498,0.0010923066,0.00067500543,0.006585112,0.71755576,0.015942538,0.0840201,0.00065016176,0.09222509],"study_design_scores_gemma":[0.0009125507,0.00009947155,0.053451363,0.00015239713,0.00002309674,0.00011980532,0.0030897711,0.92893815,0.0098382225,0.0014284545,0.0016116165,0.00033508177],"about_ca_topic_score_codex":0.000017329441,"about_ca_topic_score_gemma":0.0000750331,"teacher_disagreement_score":0.2633914,"about_ca_system_score_codex":0.00009036379,"about_ca_system_score_gemma":0.000055008204,"threshold_uncertainty_score":0.6697359},"labels":[],"label_agreement":null},{"id":"W3132255199","doi":"","title":"C-Learning: Horizon-Aware Cumulative Accessibility Estimation","year":2021,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reachability; Reinforcement learning; Computer science; Motion planning; Time horizon; Generalization; Sample (material); Reliability (semiconductor); Set (abstract data type); Path (computing); Code (set theory); Field (mathematics); Machine learning; Artificial intelligence; Mathematical optimization; Robot; Theoretical computer science; Mathematics","score_opus":0.06374053049019669,"score_gpt":0.3772116194799136,"score_spread":0.31347108898971693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132255199","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020225877,0.000006459585,0.89342767,0.0039435094,0.00079655397,0.00015637891,0.000002503164,0.00042897474,0.081012055],"genre_scores_gemma":[0.97135603,0.00003110097,0.012156782,0.00011341897,0.00009398664,0.000039764178,0.00021089103,0.000017435967,0.015980579],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971392,0.00040647484,0.00048110067,0.00075668225,0.0009282992,0.00028824815],"domain_scores_gemma":[0.99726117,0.00053255307,0.00036736001,0.0005558718,0.0011598624,0.00012319292],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034270828,0.00021784953,0.00019677951,0.00022128073,0.00043905055,0.00089830207,0.0009341544,0.00009922024,0.00087126],"category_scores_gemma":[0.0023883507,0.00023661328,0.00012043117,0.0005405361,0.000084212006,0.001143502,0.00043106053,0.00081205025,0.00041206976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010917045,0.000066484194,0.009806041,0.0000071433046,0.00006589598,0.00003526615,0.0015221755,0.8531891,0.0004937368,0.1201723,0.00018793823,0.014442975],"study_design_scores_gemma":[0.00037727278,0.00016579941,0.015191111,0.00006286294,0.00000947195,0.000016807517,0.0006901455,0.9762689,0.0011984883,0.0042728744,0.0015055772,0.00024070371],"about_ca_topic_score_codex":0.000032049236,"about_ca_topic_score_gemma":0.0000047842477,"teacher_disagreement_score":0.95113015,"about_ca_system_score_codex":0.00017644178,"about_ca_system_score_gemma":0.00031734203,"threshold_uncertainty_score":0.96488094},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03819528323690188,"score_gpt":0.31948798933381134,"score_spread":0.2812927060969095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138602767","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026695512,0.000006163908,0.9203491,0.0038759434,0.00051609916,0.00011520244,0.0000051130833,0.000049040915,0.048387796],"genre_scores_gemma":[0.9721096,0.0000072090497,0.027063012,0.00008362857,0.00015780781,0.000023642253,0.000010808029,0.0000047854414,0.00053950987],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998781,0.00012858861,0.00030171755,0.00029115874,0.000359726,0.00013775393],"domain_scores_gemma":[0.9990875,0.00019229835,0.00018976007,0.00017373354,0.00032133143,0.00003535631],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022332589,0.00008993857,0.00010573272,0.00020800377,0.000119228964,0.00011564306,0.00045836234,0.000028718026,0.0005809174],"category_scores_gemma":[0.00029487186,0.00008965715,0.000047176713,0.00025511277,0.000081726444,0.00036625692,0.00013063457,0.00013369677,0.00003635418],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051850133,0.00032221075,0.12311205,0.0000059544545,0.00012711136,0.000012237829,0.011365543,0.16329852,0.007944396,0.67067105,0.0006252543,0.02246386],"study_design_scores_gemma":[0.00028113445,0.00009514495,0.03428851,0.00004328583,0.0000028646068,0.0000019865565,0.00046241572,0.95626765,0.0023467455,0.005701827,0.00041138558,0.000097055185],"about_ca_topic_score_codex":0.00015563621,"about_ca_topic_score_gemma":0.000058447895,"teacher_disagreement_score":0.94541407,"about_ca_system_score_codex":0.000045552642,"about_ca_system_score_gemma":0.00007610318,"threshold_uncertainty_score":0.6360638},"labels":[],"label_agreement":null},{"id":"W3153191490","doi":"","title":"I❤LA: Compilable Markdown for Linear Algebra","year":2021,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Mathematics, Computing, and Information Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Linear algebra; Algebra over a field; Mathematics; Computer science; Pure mathematics; Applied mathematics; Mathematical optimization; Geometry","score_opus":0.05767489961279243,"score_gpt":0.3520611637380513,"score_spread":0.29438626412525887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153191490","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032643713,0.000011079573,0.83405596,0.0032715218,0.00043416038,0.00009967246,0.000004936797,0.00017118032,0.15868714],"genre_scores_gemma":[0.872863,0.000026439844,0.10943465,0.0005623007,0.00014364427,0.000052138996,0.00010950771,0.000012558193,0.016795782],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987338,0.00008349212,0.00035328147,0.0003058107,0.00035265737,0.00017091319],"domain_scores_gemma":[0.99806833,0.0004943811,0.00022413555,0.00027229748,0.0008769916,0.00006388409],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033261985,0.000114901886,0.0001307886,0.00013962295,0.00029168546,0.0005820483,0.00056685426,0.000053597665,0.00041854446],"category_scores_gemma":[0.0009329112,0.000120447796,0.00008300348,0.00020811679,0.000041466537,0.0005235733,0.00017545432,0.00023223397,0.00013871331],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000056621006,0.000072643714,0.00046036957,0.0000340703,0.000044363835,0.0000068459103,0.0030304776,0.004450713,0.0003858536,0.9657641,0.002319029,0.023425847],"study_design_scores_gemma":[0.00043460424,0.000031955682,0.00053808856,0.000096055395,0.0000053546923,0.000038076618,0.0007299991,0.9344569,0.0018315485,0.024216723,0.037450485,0.0001702499],"about_ca_topic_score_codex":0.000005750245,"about_ca_topic_score_gemma":0.000001846914,"teacher_disagreement_score":0.9415474,"about_ca_system_score_codex":0.00004149432,"about_ca_system_score_gemma":0.00022173453,"threshold_uncertainty_score":0.56127053},"labels":[],"label_agreement":null},{"id":"W3165914412","doi":"","title":"Pretraining Reward-Free Representations for Data-Efficient Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal; Université de Montréal","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Cognitive psychology; Machine learning; Human–computer interaction; Psychology; Social psychology","score_opus":0.12765188971660188,"score_gpt":0.378776401532506,"score_spread":0.2511245118159041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165914412","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008749011,0.000021466141,0.90021336,0.0074079116,0.0011776414,0.0004214643,0.000014820151,0.00042820166,0.08944021],"genre_scores_gemma":[0.884539,0.00008089446,0.07542964,0.00031830842,0.0002937571,0.00021019648,0.0015566044,0.000047988906,0.037523605],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995858,0.00029929535,0.0007976148,0.0012754073,0.0012451452,0.0005245395],"domain_scores_gemma":[0.9947122,0.0010996283,0.00052508555,0.0021307473,0.0013519109,0.00018047068],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008302111,0.0003024425,0.00028405094,0.00035329827,0.00081384525,0.0010657,0.0030433177,0.000116176496,0.0005129276],"category_scores_gemma":[0.007916275,0.0003422202,0.00016458235,0.0005912839,0.00010713934,0.00083207974,0.0017102647,0.0007976589,0.000142205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001893182,0.00005730783,0.0012436332,0.00001230989,0.00013139876,0.000021764694,0.001854016,0.8096831,0.0006250926,0.18109268,0.0019920226,0.0032677483],"study_design_scores_gemma":[0.0010382213,0.0001482398,0.00081856316,0.00010611192,0.000030466645,0.000030169562,0.001398453,0.9768035,0.00060787913,0.0015335903,0.017138638,0.00034619044],"about_ca_topic_score_codex":0.00005232038,"about_ca_topic_score_gemma":0.000010187309,"teacher_disagreement_score":0.88366413,"about_ca_system_score_codex":0.00017402685,"about_ca_system_score_gemma":0.0004939393,"threshold_uncertainty_score":0.9999713},"labels":[],"label_agreement":null},{"id":"W3204811657","doi":"","title":"LOCO: Adaptive exploration in reinforcement learning via local estimation of contraction coefficients","year":2021,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Reinforcement learning; Contraction (grammar); Computer science; Reinforcement; Artificial intelligence; Control theory (sociology); Mathematics; Mathematical optimization; Engineering; Structural engineering","score_opus":0.053273948608731185,"score_gpt":0.33253110950232107,"score_spread":0.2792571608935899,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204811657","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00653691,0.0000071216978,0.9782869,0.00090507517,0.00045225138,0.0002120989,6.589449e-7,0.00009987496,0.013499058],"genre_scores_gemma":[0.99195963,0.000040248688,0.0058501093,0.000053514705,0.000028957333,0.00004986242,0.00015881931,0.000012365324,0.0018464846],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99755704,0.0002883665,0.00063681434,0.00045354795,0.0008396455,0.00022458777],"domain_scores_gemma":[0.9980517,0.00031790257,0.00048275324,0.0002908312,0.00079331885,0.00006348991],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035669256,0.00016868705,0.00020080527,0.00038096184,0.0001554432,0.0001841462,0.00040584942,0.000086676984,0.0002022287],"category_scores_gemma":[0.0006276535,0.00019615827,0.00006454011,0.0005529226,0.0000805369,0.0011201423,0.00016170192,0.0005508849,0.00009713359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034153836,0.00007615142,0.0009881787,0.0000062947706,0.00003230035,0.000015532009,0.0015798168,0.91308177,0.0015540491,0.05724219,0.000015996078,0.025373563],"study_design_scores_gemma":[0.0006808459,0.00022452795,0.00237476,0.00013083237,0.0000073186375,0.0000098113405,0.0014987296,0.9890459,0.0045945486,0.001087324,0.00018163126,0.00016372732],"about_ca_topic_score_codex":0.00014521668,"about_ca_topic_score_gemma":0.000024083085,"teacher_disagreement_score":0.98542273,"about_ca_system_score_codex":0.00024157342,"about_ca_system_score_gemma":0.00020028272,"threshold_uncertainty_score":0.79991025},"labels":[],"label_agreement":null},{"id":"W3205221690","doi":"","title":"How Chaotic Are Recurrent Neural Networks","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Recurrent neural network; Computer science; Chaotic; CHAOS (operating system); Work (physics); Process (computing); Artificial neural network; Artificial intelligence; Engineering","score_opus":0.07907329506073459,"score_gpt":0.3174880274877981,"score_spread":0.2384147324270635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205221690","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012540493,0.00004002487,0.6833879,0.29353523,0.00088334386,0.00031413243,0.00000709566,0.00049713324,0.008794652],"genre_scores_gemma":[0.9960828,0.00004858137,0.0010158747,0.0012765,0.00040424737,0.00006539871,0.0000349528,0.00001052011,0.0010611247],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867374,0.00008558608,0.00018646405,0.00049833575,0.00035195754,0.00020389882],"domain_scores_gemma":[0.9990269,0.00013000947,0.00019712024,0.00025750714,0.00022544588,0.00016301165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000055813307,0.00014257335,0.0001238146,0.00006525608,0.00022059733,0.0007269154,0.00091548526,0.000042286854,0.00008189809],"category_scores_gemma":[0.0001714241,0.00013854126,0.00008372888,0.00033872286,0.000044592525,0.00043541085,0.00020431523,0.0004639147,0.00006200264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028048287,0.00014190163,0.009166384,0.000007747298,0.00007600636,0.000045676905,0.0012268005,0.22396295,0.00061686256,0.66527027,0.007930215,0.09152712],"study_design_scores_gemma":[0.00018123483,0.0000677125,0.0042607784,0.000017522627,0.000004114536,0.0000059685376,0.00017472633,0.9881989,0.000043177926,0.0008541436,0.006046937,0.00014480513],"about_ca_topic_score_codex":0.0000064961364,"about_ca_topic_score_gemma":0.000003615658,"teacher_disagreement_score":0.9835423,"about_ca_system_score_codex":0.00002549895,"about_ca_system_score_gemma":0.00002190408,"threshold_uncertainty_score":0.7009662},"labels":[],"label_agreement":null}]}