{"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"},"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0001742303,0.0002409663,0.0002513643,0.0001332559,0.0005361879,0.001099221,0.0007374412,0.0001033319,0.000003246236],"category_scores_gemma":[0.00004398571,0.0002144411,0.00007649128,0.0005951151,0.00005497367,0.008921999,0.0001023381,0.000213284,0.0000488699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007187587,"about_ca_system_score_gemma":0.00003559096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001756599,"about_ca_topic_score_gemma":0.000001609815,"domain_scores_codex":[0.9981577,0.00004346713,0.0007097769,0.000276028,0.0002867118,0.0005263464],"domain_scores_gemma":[0.998305,0.0001530632,0.0005425934,0.0003658377,0.0004783446,0.0001551675],"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":[0.0000064519,0.000009153422,0.00002730403,0.00006638201,0.000006723537,2.754708e-7,0.001690027,0.4083112,0.00003837342,0.01029106,0.000878065,0.578675],"study_design_scores_gemma":[0.000289654,0.00006830336,0.00008848021,0.00002963092,0.000004844844,0.00004508556,0.000522561,0.9957029,0.00001889275,0.0006666981,0.00231625,0.000246656],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001684411,0.0002447148,0.9939305,0.0006971702,0.0006547029,0.00141096,0.000002594391,0.0006021471,0.0007728419],"genre_scores_gemma":[0.9786201,0.000002413998,0.01889288,0.0009002767,0.0002740725,0.001178846,0.0000297021,0.00001675906,0.00008499255],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9769356,"threshold_uncertainty_score":0.9999377,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008937056,0.0001118661,0.0001685806,0.0001946566,0.0003506072,0.0004276312,0.000233123,0.00007871951,0.000006745347],"category_scores_gemma":[0.00005605614,0.000102881,0.00004540184,0.0003854236,0.0000229113,0.00445299,0.00003292842,0.00006461768,0.000005912831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005741855,"about_ca_system_score_gemma":0.00007033005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006955217,"about_ca_topic_score_gemma":0.000001663368,"domain_scores_codex":[0.998639,0.00002407027,0.0007668139,0.0001201699,0.0002412377,0.0002086494],"domain_scores_gemma":[0.9986271,0.00004129551,0.0007965032,0.0001000889,0.0003980815,0.00003690423],"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":[0.00000441552,0.00001380187,0.00001955559,0.0008027273,0.000004614978,8.116378e-8,0.005054919,0.0002532348,0.002103581,0.004461475,0.003582013,0.9836996],"study_design_scores_gemma":[0.0003432028,0.00003758072,0.000268636,0.00005249053,0.000006043378,0.00001063856,0.0003016938,0.9861856,0.003630516,0.00008066795,0.00895167,0.0001312938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05010068,0.00003010116,0.946924,0.0004890517,0.0007533237,0.0003284406,0.000003336189,0.0001730332,0.001198004],"genre_scores_gemma":[0.9887086,3.151767e-7,0.01032235,0.0005552922,0.0002702517,0.00003058556,0.00006606636,0.000005655536,0.00004091623],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9859324,"threshold_uncertainty_score":0.4195366,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006400385,0.0001996109,0.0002096474,0.0002836304,0.0005195138,0.0009234643,0.0003451941,0.00009606953,8.648817e-7],"category_scores_gemma":[0.0002227671,0.0001652715,0.00004030316,0.0006244434,0.0000281705,0.005227198,0.00004706143,0.00021901,0.00002373346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001005635,"about_ca_system_score_gemma":0.0001149565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001019537,"about_ca_topic_score_gemma":4.99597e-7,"domain_scores_codex":[0.9982738,0.00005976248,0.0006617876,0.0002116586,0.0004620257,0.0003309453],"domain_scores_gemma":[0.9981285,0.00009550097,0.0008989705,0.0002714287,0.0005299504,0.00007563071],"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":[0.00002303111,0.000004573265,0.0005843919,0.0004843734,0.000008453634,5.330334e-8,0.0007866694,0.9183554,0.00007266143,0.01171112,0.00006408319,0.06790516],"study_design_scores_gemma":[0.000516156,0.0002619887,0.0002286585,0.0001289379,0.00000884387,0.00001668186,0.000121129,0.9689828,0.00009761469,0.00006849843,0.02936201,0.0002067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003359515,0.00004528818,0.9933459,0.0002346482,0.0003094954,0.0005470256,5.696735e-7,0.0005928659,0.001564703],"genre_scores_gemma":[0.9599105,0.000003391262,0.0388323,0.0003278566,0.0003431948,0.0001290645,0.000106194,0.00001915083,0.000328407],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.956551,"threshold_uncertainty_score":0.8904988,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003361153,0.000110121,0.0002427431,0.000137709,0.00003713807,0.00003488444,0.0001335511,0.00007156354,0.00001037015],"category_scores_gemma":[0.0001120731,0.00009358524,0.00004112421,0.0003106939,0.0000462021,0.0008932666,0.00001320193,0.0001915634,0.000005381365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000014905,"about_ca_system_score_gemma":0.0000106667,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001608217,"about_ca_topic_score_gemma":4.331247e-7,"domain_scores_codex":[0.9990296,0.00002643758,0.0006253236,0.00005926737,0.0001378242,0.0001215923],"domain_scores_gemma":[0.9992622,0.00007064686,0.0003195159,0.000148907,0.0001637719,0.00003492607],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005791719,0.00004013918,0.0007205899,0.004010851,0.00005862546,0.00000105156,0.001538082,0.1786106,0.6019474,0.002095567,0.0005264884,0.2103927],"study_design_scores_gemma":[0.0001033364,0.00005761757,0.0001458239,0.0001433227,0.00001223644,0.000006555427,0.0001088818,0.7309598,0.2636175,0.00009797753,0.004601468,0.0001454348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4811383,0.0001164723,0.5115623,0.00002710022,0.00103541,0.0002571329,0.00001255806,0.0006096274,0.005241045],"genre_scores_gemma":[0.9880815,0.000004720722,0.01180649,0.00002671043,0.00002687339,0.00001349656,0.000009244621,0.000009301122,0.00002167621],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5523492,"threshold_uncertainty_score":0.3816295,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002274249,0.0003218286,0.0004885221,0.0005060181,0.001776069,0.003127303,0.001309996,0.0001847632,0.00001120056],"category_scores_gemma":[0.004896169,0.0001957884,0.00009859134,0.0006779463,0.0002326,0.004613444,0.0001784435,0.0003298494,0.0000541893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001248813,"about_ca_system_score_gemma":0.0002437004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005906789,"about_ca_topic_score_gemma":0.00001503334,"domain_scores_codex":[0.9949041,0.0001075914,0.001371098,0.000465812,0.002604946,0.0005464558],"domain_scores_gemma":[0.9924403,0.0004285552,0.002135972,0.001119859,0.003659756,0.0002155705],"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":[0.0007516705,0.0001569789,0.002441657,0.0003710793,0.00002244177,0.000008401428,0.001241548,0.4708841,0.0001824421,0.00009444678,0.002654012,0.5211912],"study_design_scores_gemma":[0.001505864,0.0002177994,0.003530876,0.0002833797,0.000009897922,0.00003426371,0.0008152613,0.9730873,0.0003388921,0.00006304462,0.01984886,0.0002646107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3114899,0.0001963521,0.6813874,0.002549924,0.001465746,0.002172421,0.0002690699,0.0002801139,0.000189163],"genre_scores_gemma":[0.968922,0.000007079455,0.02724859,0.0001950921,0.0007165697,0.0002013537,0.0003934506,0.00004125137,0.002274651],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6574321,"threshold_uncertainty_score":0.9995235,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}