{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":5,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":5,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"22fa33f7ea39","filters":{"venue":"neural information processing systems"}},"results":[{"id":"W2136836265","doi":"","title":"Adaptive dropout for training deep neural networks","year":2013,"lang":"en","type":"article","venue":"neural information processing systems","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":280,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Dropout (neural networks); MNIST database; Computer science; Artificial intelligence; Artificial neural network; Feature (linguistics); Boltzmann machine; Deep belief network; Restricted Boltzmann machine; Stochastic gradient descent; Pattern recognition (psychology); Convolutional neural network; Machine learning; Gradient descent; Deep learning; Backpropagation","authors":[{"name":"Jimmy Ba","is_ca":false},{"name":"Brendan J. Frey","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03198876176642353,"gpt":0.2623541483614051,"spread":0.2303653865949816,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002532988,0.00163039,0.001390848,0.0007825632,0.0004931596,0.0007281076,0.002410142,0.001743993,0.002599454],"category_scores_gemma":[0.009215246,0.0008076783,0.0008850672,0.001163765,0.0008317434,0.001702418,0.001184674,0.002890878,0.0009752566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00208935,"about_ca_system_score_gemma":0.00138793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007458387,"about_ca_topic_score_gemma":0.009496566,"domain_scores_codex":[0.9990265,0.0003035218,0.00007445418,0.0001907642,0.0003011811,0.0001035908],"domain_scores_gemma":[0.9981797,0.001068271,0.0001724509,0.0002107065,0.0003099995,0.00005899304],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001855017,0.00009602705,0.001215815,0.0002279037,0.000106024,0.0001091253,0.00007202156,0.7541853,0.003640156,0.01371893,0.005606814,0.2208365],"study_design_scores_gemma":[0.000008567491,0.00001251579,0.00008281985,0.000009818968,0.000004526226,0.000009035216,0.000002355215,0.993558,0.001087368,0.004687907,0.00053352,0.000003544253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007589848,0.0007353236,0.9880284,0.0002754466,0.00005882711,0.00005295054,0.0001704069,0.002399314,0.0006894648],"genre_scores_gemma":[0.4366782,0.001072215,0.5525709,0.000482965,0.0001572557,0.0005980167,0.001540378,0.0006039467,0.006296165],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007458387,"threshold_uncertainty_score":0.01515937,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2162124943","doi":"","title":"Automatic Generation of Social Tags for Music Recommendation","year":2007,"lang":"en","type":"article","venue":"neural information processing systems","topic":"Music and Audio Processing","field":"Computer Science","cited_by":184,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; CMC Microsystems (Canada)","funders":"","keywords":"Recommender system; Computer science; Information retrieval; Set (abstract data type); Baseline (sea); World Wide Web; Resource (disambiguation); Space (punctuation); Social web; Component (thermodynamics); Social media","authors":[{"name":"Douglas Eck","is_ca":true},{"name":"Paul Lamere","is_ca":false},{"name":"Thierry Bertin-Mahieux","is_ca":false},{"name":"Stephen Green","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06320323338863898,"gpt":0.294099101272341,"spread":0.230895867883702,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008098643,0.0007873744,0.000594289,0.00245588,0.0007019604,0.0009317625,0.0009474471,0.00109874,0.002134195],"category_scores_gemma":[0.004356659,0.0003603437,0.0007173113,0.001774466,0.000326475,0.001243797,0.0007483168,0.0008692308,0.003539399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007322888,"about_ca_system_score_gemma":0.0007542986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007290555,"about_ca_topic_score_gemma":0.02383797,"domain_scores_codex":[0.9989443,0.0002696712,0.0000537621,0.0002891798,0.0003174701,0.0001256739],"domain_scores_gemma":[0.9975771,0.0008728913,0.0001768653,0.0004407816,0.0008279922,0.0001043925],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005868218,0.0005039651,0.02248252,0.0002410658,0.0002204461,0.0002768603,0.0003943761,0.02534584,0.0415266,0.004889013,0.02922503,0.8743074],"study_design_scores_gemma":[0.00006069087,0.0001472151,0.009521491,0.00003429352,0.00009708119,0.000248689,0.0002157333,0.9234076,0.04138378,0.0106063,0.01421578,0.00006142438],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1295759,0.0008535698,0.846418,0.0005157756,0.0004194652,0.000398199,0.00359002,0.009299411,0.008929669],"genre_scores_gemma":[0.5972756,0.0003324725,0.384872,0.0001866982,0.0002384157,0.0002853884,0.007128368,0.0003756392,0.009305431],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007290555,"threshold_uncertainty_score":0.01449621,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2107741520","doi":"","title":"Weighted importance sampling for off-policy learning with linear function approximation","year":2014,"lang":"en","type":"article","venue":"neural information processing systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":100,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Weighting; Computer science; Importance sampling; Sampling (signal processing); Convergence (economics); Function (biology); Bridging (networking); Artificial intelligence; Mathematical optimization; Machine learning; Function approximation; Mathematics; Statistics; Artificial neural network","authors":[{"name":"A. Rupam Mahmood","is_ca":true},{"name":"Hado P. van Hasselt","is_ca":true},{"name":"Richard S. Sutton","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02050125081507167,"gpt":0.2586979979424325,"spread":0.2381967471273608,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003871777,0.001036859,0.001519142,0.0007723552,0.0004654666,0.0009972792,0.001582514,0.001238514,0.00247525],"category_scores_gemma":[0.01506721,0.0006548598,0.0006075407,0.0007096122,0.001491298,0.001559958,0.001529916,0.002218682,0.0004343321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001454449,"about_ca_system_score_gemma":0.001721152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003799199,"about_ca_topic_score_gemma":0.002948301,"domain_scores_codex":[0.9983357,0.0007954943,0.00007223223,0.0002013136,0.00046619,0.0001292071],"domain_scores_gemma":[0.9948004,0.003931496,0.0002417963,0.0003939313,0.0004869859,0.0001453537],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001379119,0.0001134671,0.0007565156,0.00009343355,0.00004127,0.00007150257,0.00005880834,0.8944612,0.00114141,0.04464915,0.0008608595,0.05761454],"study_design_scores_gemma":[0.000006589455,0.00001343828,0.00002424642,0.000003260468,0.000002175327,0.000005213354,0.000001674112,0.9923093,0.0001810288,0.007292121,0.0001590086,0.000001794239],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005933413,0.0001403208,0.9926208,0.00008012487,0.00002959891,0.00003960179,0.00001124571,0.0001601256,0.0009846879],"genre_scores_gemma":[0.6960257,0.0003789738,0.2987357,0.0002635636,0.000102109,0.00041985,0.0001569149,0.0001849333,0.00373229],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003871777,"threshold_uncertainty_score":0.02047622,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2163976407","doi":"","title":"Lower Bounds on Rate of Convergence of Cutting Plane Methods","year":2010,"lang":"en","type":"article","venue":"neural information processing systems","topic":"Advanced Numerical Analysis Techniques","field":"Engineering","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Support vector machine; Cutting-plane method; Hinge loss; Convergence (economics); Rate of convergence; Conjecture; Plane (geometry); Computer science; Algorithm; Function (biology); Mathematical optimization; Mathematics; Applied mathematics; Artificial intelligence; Combinatorics; Geometry","authors":[{"name":"Xinhua Zhang","is_ca":true},{"name":"Ankan Saha","is_ca":false},{"name":"S. V. N. Vishwanathan","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01068978264807512,"gpt":0.2954642392651482,"spread":0.2847744566170731,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02437544,0.004975929,0.003683838,0.003446759,0.002180244,0.004559478,0.006181982,0.006272803,0.01347722],"category_scores_gemma":[0.183176,0.001914697,0.003193169,0.002950609,0.005158517,0.009609666,0.007596761,0.01651826,0.007618246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003106679,"about_ca_system_score_gemma":0.002256985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001765052,"about_ca_topic_score_gemma":0.001254543,"domain_scores_codex":[0.9810228,0.007462696,0.001257684,0.002335115,0.006299627,0.001622224],"domain_scores_gemma":[0.8282341,0.1400365,0.00439525,0.0117747,0.01359229,0.001967164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.003069826,0.0006110242,0.008216838,0.002506607,0.0006072765,0.0007144543,0.001139829,0.3105389,0.01072228,0.4245299,0.0295462,0.2077969],"study_design_scores_gemma":[0.0001624142,0.0004237655,0.001070561,0.0007462286,0.0001114681,0.0004257106,0.0001504089,0.7942753,0.006231549,0.1825322,0.01376253,0.0001079354],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01589902,0.01474954,0.9340407,0.004728172,0.0009393955,0.000425143,0.0005434653,0.00162594,0.02704867],"genre_scores_gemma":[0.2608341,0.01440721,0.6849862,0.003159203,0.002128764,0.002800746,0.002360891,0.005842899,0.02348001],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02437544,"threshold_uncertainty_score":0.1289112,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2770008080","doi":"","title":"Efficient Sublinear-Regret Algorithms for Online Sparse Linear Regression with Limited Observation","year":2017,"lang":"en","type":"article","venue":"neural information processing systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Regret; Sublinear function; Computer science; Algorithm; Linear regression; Constraint (computer-aided design); Task (project management); Exponential function; Mathematical optimization; Mathematics; Machine learning; Discrete mathematics","authors":[{"name":"Shinji Ito","is_ca":false},{"name":"Daisuke Hatano","is_ca":false},{"name":"Hanna Sumita","is_ca":false},{"name":"Akihiro Yabe","is_ca":false},{"name":"Takuro Fukunaga","is_ca":false},{"name":"Naonori Kakimura","is_ca":true},{"name":"Ken Kawarabayashi","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2585063217238566,"gpt":0.4470429972754272,"spread":0.1885366755515706,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004788409,0.002609702,0.00272475,0.0009935412,0.000985996,0.002176426,0.004165528,0.002415461,0.006199688],"category_scores_gemma":[0.02137628,0.001042621,0.001557403,0.002032443,0.001452624,0.004132302,0.002869697,0.005756326,0.003016435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002434317,"about_ca_system_score_gemma":0.003959764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004659403,"about_ca_topic_score_gemma":0.007428977,"domain_scores_codex":[0.9966831,0.001145777,0.0001897925,0.0006921306,0.0008159478,0.0004734298],"domain_scores_gemma":[0.9847705,0.01151758,0.001050729,0.001361694,0.0009540385,0.0003454364],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006542719,0.0006742729,0.001297315,0.0004103185,0.0001279858,0.0001157875,0.0001699787,0.7161039,0.0019342,0.04373357,0.02121115,0.2135672],"study_design_scores_gemma":[0.00004629526,0.00003686842,0.00009719327,0.00001195195,0.00001146491,0.00002886454,0.00001442852,0.9830344,0.0005305242,0.01555267,0.0006278062,0.000007537173],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006763617,0.0009622475,0.9870401,0.0008543076,0.0001041278,0.000132441,0.0002114431,0.001477947,0.002453763],"genre_scores_gemma":[0.2606055,0.001252423,0.7270392,0.001202241,0.0005542599,0.0008837296,0.001749039,0.0007104936,0.006003232],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006199688,"threshold_uncertainty_score":0.02532387,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}