{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":559,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":559,"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":"532ca883ae4d","filters":{"topic":"Machine Learning and Data Classification"}},"results":[{"id":"W2095705004","doi":"","title":"Dropout: a simple way to prevent neural networks from overfitting","year":2014,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":34279,"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":"Overfitting; Dropout (neural networks); Computer science; Artificial intelligence; Artificial neural network; Machine learning; Benchmark (surveying); Deep neural networks; Regularization (linguistics)","authors":[{"name":"Nitish Srivastava","is_ca":true},{"name":"Geoffrey E. Hinton","is_ca":true},{"name":"Alex Krizhevsky","is_ca":true},{"name":"Ilya Sutskever","is_ca":true},{"name":"Ruslan Salakhutdinov","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01136010837867235,"gpt":0.2537860031689929,"spread":0.2424258947903206,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007399546,0.003175213,0.002476552,0.001213895,0.001552035,0.002131637,0.005329866,0.004265398,0.00720394],"category_scores_gemma":[0.02451395,0.001352779,0.002521613,0.001165287,0.002012588,0.003653186,0.003461487,0.006102899,0.002641639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0015359,"about_ca_system_score_gemma":0.002730993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002662425,"about_ca_topic_score_gemma":0.00375493,"domain_scores_codex":[0.997254,0.0007695961,0.0003592201,0.0004388804,0.0009016429,0.0002767438],"domain_scores_gemma":[0.994581,0.002185311,0.0006114065,0.001165108,0.001187783,0.0002693239],"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":[0.0016224,0.001049367,0.00755663,0.001531799,0.001236919,0.001176019,0.0006106283,0.3473644,0.03488646,0.04651832,0.07451293,0.4819342],"study_design_scores_gemma":[0.0002933075,0.0004245605,0.001147357,0.0001871633,0.0001863999,0.0002968073,0.00005962023,0.9320658,0.02768456,0.02638475,0.01119809,0.00007152299],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01637033,0.0009023724,0.9681464,0.001398033,0.0003667193,0.0003409812,0.0004985436,0.009519537,0.002457043],"genre_scores_gemma":[0.3683977,0.001387717,0.6043078,0.003449407,0.0006766606,0.002006396,0.00336059,0.003041689,0.01337204],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007399546,"threshold_uncertainty_score":0.03913301,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2913668833","doi":"","title":"Proceedings of the 25th international conference on Machine learning","year":2008,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":5550,"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":"Presentation (obstetrics); Library science; Computer science; Medical education; Artificial intelligence; Medicine","authors":[{"name":"William W. Cohen","is_ca":false},{"name":"Andrew McCallum","is_ca":false},{"name":"Sam T. Roweis","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04098708239380094,"gpt":0.2591540437091648,"spread":0.2181669613153638,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003742557,0.001600298,0.002117145,0.002029026,0.0008741611,0.006129342,0.002375599,0.002160638,0.1049251],"category_scores_gemma":[0.008888099,0.0003557306,0.001107056,0.001694025,0.001337568,0.004348736,0.002839121,0.003984428,0.06765388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001167257,"about_ca_system_score_gemma":0.002456774,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001301833,"about_ca_topic_score_gemma":0.001480856,"domain_scores_codex":[0.9947248,0.001409539,0.0004758287,0.0009564207,0.002071843,0.000361477],"domain_scores_gemma":[0.9953478,0.001434829,0.0002274279,0.000941503,0.001624577,0.0004237778],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001509529,0.00009008645,0.001013982,0.0006983528,0.0001522534,0.0001365744,0.0001062741,0.00149607,0.001472305,0.01410835,0.5722674,0.4083073],"study_design_scores_gemma":[0.00001694073,0.00008773024,0.0009862002,0.0002946162,0.00004108517,0.0003018338,0.00008761661,0.004457255,0.0008179299,0.01392849,0.9789463,0.00003396485],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.01197277,0.1491677,0.2494867,0.03605902,0.1050109,0.001268021,0.01215599,0.009224354,0.4256546],"genre_scores_gemma":[0.1089245,0.08688647,0.1242955,0.01141207,0.03039398,0.001393962,0.03805171,0.002282021,0.5963597],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.1049251,"threshold_uncertainty_score":0.3510096,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1479807131","doi":"10.7551/mitpress/9780262033589.001.0001","title":"Semi-Supervised Learning","year":2006,"lang":"en","type":"book","venue":"The MIT Press eBooks","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4308,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Artificial intelligence; Machine learning; Benchmark (surveying); Field (mathematics); Unsupervised learning; Semi-supervised learning; Graph; Taxonomy (biology); Theoretical computer science; Mathematics","authors":[{"name":"Olivier Chapelle","is_ca":false},{"name":"Alexander Zien","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02696831639417286,"gpt":0.2417254804910513,"spread":0.2147571640968785,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001804952,0.001219969,0.001356841,0.002030413,0.0005980677,0.002772866,0.001714791,0.001410365,0.01530845],"category_scores_gemma":[0.006000304,0.0007007151,0.0009540411,0.004052365,0.001105121,0.004253955,0.001408897,0.002541024,0.01881181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001176813,"about_ca_system_score_gemma":0.001453117,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001347758,"about_ca_topic_score_gemma":0.002156172,"domain_scores_codex":[0.9970578,0.0005797268,0.0002027046,0.0006058806,0.001474304,0.00007960972],"domain_scores_gemma":[0.99691,0.001641954,0.0001750346,0.0003353727,0.0008415708,0.00009614216],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003192655,0.00004735275,0.000349763,0.001595537,0.0001050377,0.00008208559,0.0001265248,0.01121193,0.001192811,0.03106459,0.280255,0.6739375],"study_design_scores_gemma":[0.00001544432,0.0000664722,0.0008132012,0.0007538288,0.00003848019,0.0005990342,0.0001215161,0.03523439,0.001762521,0.08701818,0.8735059,0.00007107812],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002157961,0.1989104,0.7132853,0.006788527,0.005450598,0.0002002536,0.002367884,0.004262991,0.06657606],"genre_scores_gemma":[0.06209954,0.3013301,0.4329523,0.007031417,0.01085381,0.0008113203,0.01919561,0.002689438,0.1630365],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01530845,"threshold_uncertainty_score":0.05121183,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3045004532","doi":"10.1016/j.neucom.2020.07.061","title":"On hyperparameter optimization of machine learning algorithms: Theory and practice","year":2020,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3145,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Hyperparameter; Computer science; Machine learning; Algorithm; Artificial intelligence; Optimization algorithm; Mathematical optimization; Mathematics","authors":[{"name":"Li Yang","is_ca":true},{"name":"Abdallah Shami","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02419853204666712,"gpt":0.2728189988463539,"spread":0.2486204667996868,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01125334,0.002771612,0.003393744,0.002554583,0.001091463,0.005208133,0.003089451,0.00460006,0.003976587],"category_scores_gemma":[0.05171193,0.002009453,0.001869798,0.005188411,0.006030949,0.0071283,0.004664945,0.007793642,0.001476727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001919422,"about_ca_system_score_gemma":0.001860868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002451713,"about_ca_topic_score_gemma":0.001495049,"domain_scores_codex":[0.9911151,0.005890127,0.0004394715,0.0008536134,0.001494506,0.0002071397],"domain_scores_gemma":[0.9708409,0.02448813,0.0007325882,0.002009409,0.001660302,0.0002686299],"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":[0.0001127461,0.0001216704,0.001066097,0.0006206417,0.000257719,0.0000624621,0.0002474031,0.4669122,0.0008083108,0.333029,0.007847111,0.1889147],"study_design_scores_gemma":[0.0000333729,0.00004267815,0.0002069985,0.0002094377,0.00003620995,0.00004207106,0.00003436393,0.6249124,0.0004873748,0.3683329,0.005631073,0.00003109845],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00166202,0.009244694,0.9847494,0.0009388772,0.0001563757,0.00002925674,0.00002062765,0.00009622494,0.003102527],"genre_scores_gemma":[0.2224419,0.03019469,0.7341421,0.001474263,0.002871629,0.0006349798,0.0002666294,0.0006652426,0.00730856],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01125334,"threshold_uncertainty_score":0.05951405,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4213308398","doi":"10.1007/978-3-030-05318-5","title":"Automated Machine Learning","year":2019,"lang":"en","type":"book","venue":"˜The œSpringer series on challenges in machine learning","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1396,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"BrainLinks-BrainTools; Deutsche Forschungsgemeinschaft; Institut national de recherche en informatique et en automatique (INRIA); Generalitat de Catalunya; Natural Sciences and Engineering Research Council of Canada; European Commission; Centres de Recerca de Catalunya","keywords":"Computer science; Artificial intelligence; Machine learning","authors":[{"name":"Frank Hutter","is_ca":false},{"name":"Lars Kotthoff","is_ca":false},{"name":"Joaquin Vanschoren","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03342894053342584,"gpt":0.2644895588843254,"spread":0.2310606183508996,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001809128,0.001435698,0.001140903,0.003519031,0.0008673051,0.004379843,0.002232953,0.00134037,0.07616359],"category_scores_gemma":[0.005112745,0.0008293991,0.001045088,0.003225059,0.000978743,0.003650521,0.002629527,0.002067741,0.09774896],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001134428,"about_ca_system_score_gemma":0.001161586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006637343,"about_ca_topic_score_gemma":0.001044537,"domain_scores_codex":[0.9976246,0.0003416686,0.0001190182,0.0004544973,0.00135509,0.0001052305],"domain_scores_gemma":[0.9978209,0.0007619247,0.00008568438,0.0007759101,0.0004934893,0.00006220368],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000195623,0.00003603404,0.0002966875,0.0005843667,0.00004189952,0.0000609331,0.00005280129,0.002191344,0.001566394,0.05806967,0.3170305,0.6200498],"study_design_scores_gemma":[0.000007357258,0.0000199471,0.000521916,0.0002464077,0.0000124001,0.0003761144,0.00003323837,0.01262613,0.003165315,0.1044511,0.8785084,0.00003169982],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002167664,0.04462499,0.6117795,0.004521884,0.004135024,0.0003400348,0.008018492,0.01945346,0.304959],"genre_scores_gemma":[0.03138822,0.03428026,0.4763355,0.002370747,0.003205785,0.0006485888,0.02765382,0.003310726,0.4208063],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07616359,"threshold_uncertainty_score":0.2547926,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2102539288","doi":"10.1145/2487575.2487629","title":"Auto-WEKA","year":2013,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1321,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Hyperparameter; Machine learning; Computer science; MNIST database; Artificial intelligence; Hyperparameter optimization; Bayesian optimization; Classifier (UML); Feature selection; Data mining; Artificial neural network; Support vector machine","authors":[{"name":"Chris Thornton","is_ca":true},{"name":"Frank Hutter","is_ca":true},{"name":"Holger H. Hoos","is_ca":true},{"name":"Kevin Leyton‐Brown","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01031152393134421,"gpt":0.2275537245930732,"spread":0.217242200661729,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00171496,0.002150835,0.001377062,0.002842343,0.0007363696,0.002812748,0.003716246,0.001187634,0.03907871],"category_scores_gemma":[0.00786593,0.001740336,0.00328384,0.002164066,0.0004775175,0.003324462,0.002034691,0.003189442,0.05152514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009149109,"about_ca_system_score_gemma":0.002259629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005561791,"about_ca_topic_score_gemma":0.007629293,"domain_scores_codex":[0.9982027,0.0003402189,0.0002557402,0.0005548175,0.0004723359,0.0001742808],"domain_scores_gemma":[0.9965238,0.001374025,0.0002310621,0.0009795949,0.0008113242,0.00008018479],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007671122,0.0003887365,0.002996098,0.002393909,0.0009859578,0.0003622044,0.0004073048,0.03902,0.006297181,0.01963878,0.6539994,0.2727432],"study_design_scores_gemma":[0.0006501588,0.0001580991,0.003661982,0.0003922644,0.0004383406,0.000617261,0.0002353177,0.2439542,0.0171737,0.0502198,0.682175,0.0003237825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.00842645,0.00160789,0.3787124,0.0008377904,0.0004571459,0.00128067,0.03300551,0.547622,0.02805026],"genre_scores_gemma":[0.08808607,0.003082911,0.6862742,0.001558658,0.0001834944,0.004261015,0.1007922,0.07314222,0.04261926],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.03907871,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2125943921","doi":"10.1145/1401890.1401965","title":"Get another label? improving data quality and data mining using multiple, noisy labelers","year":2008,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1114,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Computer science; Quality (philosophy); Sequence labeling; Set (abstract data type); Crowdsourcing; Artificial intelligence; Imperfect; Focus (optics); Machine learning; Outsourcing; Labeled data; Data quality; Data mining; Task (project management); Engineering","authors":[{"name":"Victor S. Sheng","is_ca":false},{"name":"Foster Provost","is_ca":false},{"name":"Panagiotis G. Ipeirotis","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3107738534872337,"gpt":0.3854225652339457,"spread":0.07464871174671206,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0533477,0.001870645,0.004226172,0.002902847,0.002759279,0.005474885,0.00561529,0.005733274,0.001407121],"category_scores_gemma":[0.2065193,0.001772843,0.002245947,0.004026951,0.006119312,0.01644064,0.007519447,0.005497869,0.00112703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002807251,"about_ca_system_score_gemma":0.003057901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003152638,"about_ca_topic_score_gemma":0.004161607,"domain_scores_codex":[0.9527618,0.02493188,0.002514974,0.009207833,0.009316074,0.001267407],"domain_scores_gemma":[0.7619519,0.1498884,0.01834544,0.05373462,0.0140682,0.002011444],"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":[0.003048622,0.001307522,0.06509171,0.001938647,0.001354966,0.0006406903,0.005913186,0.1618992,0.02504838,0.04951632,0.009231757,0.6750091],"study_design_scores_gemma":[0.0003331303,0.0009017854,0.01203851,0.000379039,0.0004264354,0.0009377563,0.001500675,0.7234598,0.03792428,0.2099879,0.01182162,0.0002890115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05885515,0.001062335,0.934046,0.003378188,0.0000778621,0.0001509867,0.0002091013,0.001351374,0.0008690184],"genre_scores_gemma":[0.3994365,0.0004214309,0.5965488,0.001056486,0.0002192036,0.0002825489,0.0005853832,0.0004156631,0.001033847],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0533477,"threshold_uncertainty_score":0.282133,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1437335841","doi":"10.1088/1749-4699/8/1/014008","title":"Hyperopt: a Python library for model selection and hyperparameter optimization","year":2015,"lang":"en","type":"article","venue":"Computational Science & Discovery","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1041,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Rowland Institute at Harvard; Office of the Director; National Science Foundation","keywords":"Bayesian optimization; MNIST database; Computer science; Hyperparameter; Python (programming language); Machine learning; Hyperparameter optimization; Artificial intelligence; Model selection; Algorithm; Support vector machine; Deep learning; Programming language","authors":[{"name":"James Bergstra","is_ca":true},{"name":"Brent Komer","is_ca":true},{"name":"Chris Eliasmith","is_ca":true},{"name":"Dan Yamins","is_ca":false},{"name":"David Cox","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03402540472736977,"gpt":0.2792169580267524,"spread":0.2451915532993826,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002091973,0.002708688,0.001735213,0.001657881,0.000942704,0.002977864,0.0042578,0.001620155,0.05773329],"category_scores_gemma":[0.008712323,0.001832355,0.002838458,0.002110415,0.0009560871,0.003373142,0.003387208,0.004873738,0.0410476],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001209131,"about_ca_system_score_gemma":0.00369421,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003891611,"about_ca_topic_score_gemma":0.007128664,"domain_scores_codex":[0.9984208,0.0003890562,0.0001609165,0.0002988855,0.0005777068,0.000152616],"domain_scores_gemma":[0.9976694,0.001172363,0.0001804498,0.0004663185,0.0003888831,0.0001225295],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003875437,0.0002591257,0.003089599,0.002446422,0.0004761206,0.0003891572,0.000351733,0.08982325,0.007001043,0.0420488,0.546996,0.3067313],"study_design_scores_gemma":[0.0002623142,0.00007850827,0.001619129,0.0002425429,0.00008077191,0.00032387,0.00007326825,0.6261686,0.01417569,0.1091807,0.2476301,0.000164469],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.001305637,0.0003033563,0.6918371,0.0003832737,0.0001125267,0.000208556,0.00974494,0.2895569,0.00654768],"genre_scores_gemma":[0.03569096,0.0008933934,0.8001385,0.001278686,0.0001574676,0.002135542,0.02975333,0.1177427,0.01220939],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.05773329,"threshold_uncertainty_score":0.1931371,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2613634265","doi":"","title":"Scaling learning algorithms towards AI","year":2007,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":930,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Artificial intelligence; Computer science; Machine learning; Kernel (algebra); Curse of dimensionality; Kernel method; Algorithm; Support vector machine; Mathematics","authors":[{"name":"Yoshua Bengio","is_ca":true},{"name":"Yann LeCun","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01827361657636038,"gpt":0.3036296303033375,"spread":0.2853560137269771,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002834962,0.001495271,0.001066078,0.001561628,0.0008954604,0.003898137,0.001819417,0.002118774,0.01094009],"category_scores_gemma":[0.01736227,0.0005787492,0.0009587603,0.001508083,0.003704966,0.005455918,0.004199128,0.005095726,0.004219627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001711958,"about_ca_system_score_gemma":0.001401972,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001493463,"about_ca_topic_score_gemma":0.0009151624,"domain_scores_codex":[0.9977902,0.0008032434,0.0001337732,0.0005133428,0.0006418658,0.0001174908],"domain_scores_gemma":[0.9940334,0.003383626,0.000231488,0.001353994,0.0008038139,0.0001936179],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004285008,0.00004764888,0.0004553194,0.0003784308,0.00006185223,0.00005269595,0.0001820489,0.05605276,0.0007841455,0.7954887,0.01478993,0.1316637],"study_design_scores_gemma":[0.00002109004,0.00003108576,0.0001572298,0.0001015499,0.00001221894,0.00004078795,0.00003522122,0.1265555,0.0003329465,0.8330415,0.03965468,0.00001620197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006731946,0.01477947,0.8837968,0.007520991,0.001309495,0.0001619715,0.0002943105,0.001758593,0.08364643],"genre_scores_gemma":[0.2941294,0.01954335,0.6407195,0.003060006,0.003531572,0.001095566,0.0009626205,0.0009457788,0.03601228],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01094009,"threshold_uncertainty_score":0.03659832,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2409550820","doi":"10.48550/arxiv.1605.08803","title":"Density Estimation Using Real NVP","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":793,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Latent variable; Inference; Computer science; Artificial intelligence; Unsupervised learning; Sampling (signal processing); Machine learning; Probabilistic logic; Computation; Set (abstract data type); Bayesian inference; Latent variable model; Bayesian probability; Algorithm","authors":[{"name":"Laurent Dinh","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09837519305503026,"gpt":0.2189231448305726,"spread":0.1205479517755423,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00324183,0.0007316808,0.0009300187,0.0009850271,0.0005674392,0.00183571,0.002090792,0.001251451,0.002593561],"category_scores_gemma":[0.01928101,0.0005966327,0.0009823153,0.0008494318,0.002169169,0.003409432,0.002927315,0.003095252,0.0006882127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001672274,"about_ca_system_score_gemma":0.001434768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003410663,"about_ca_topic_score_gemma":0.003283798,"domain_scores_codex":[0.998058,0.001122775,0.00007175371,0.0003160184,0.0003575686,0.0000738764],"domain_scores_gemma":[0.9931881,0.004572396,0.0004474826,0.001114867,0.0005285484,0.0001485768],"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":[0.00008753867,0.00005554212,0.001345303,0.0001109185,0.00004572052,0.0001301196,0.000221908,0.662335,0.002177524,0.2529472,0.002706579,0.07783659],"study_design_scores_gemma":[0.00000423735,0.000006496988,0.00005224823,0.000005319919,0.00000121826,0.00002125704,0.000008128132,0.9288274,0.0004303533,0.07004339,0.0005949837,0.000004969006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004676104,0.00005611271,0.9939955,0.0001527488,0.00001234416,0.00002372602,0.00005527908,0.0003149063,0.0007132619],"genre_scores_gemma":[0.3869121,0.0002575354,0.607407,0.0002463905,0.00008972988,0.0003498567,0.0007435858,0.0005528955,0.003440966],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003410663,"threshold_uncertainty_score":0.01714468,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4245055982","doi":"10.1017/cbo9780511921803","title":"Evaluating Learning Algorithms","year":2011,"lang":"en","type":"book","venue":"Cambridge University Press eBooks","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":753,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Resampling; Interdependence; Field (mathematics); Process (computing); Classifier (UML); Algorithm; Management science; Engineering; Mathematics","authors":[{"name":"Nathalie Japkowicz","is_ca":false},{"name":"Mohak Shah","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06511601777908724,"gpt":0.2686649979806887,"spread":0.2035489802016015,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01587596,0.001892937,0.001758145,0.002992241,0.0007804467,0.007575775,0.002308666,0.002569759,0.01758493],"category_scores_gemma":[0.08062258,0.0003756514,0.0008944256,0.002667618,0.001598647,0.005764205,0.002193948,0.001846805,0.008212416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002123566,"about_ca_system_score_gemma":0.001652628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006026435,"about_ca_topic_score_gemma":0.0007153722,"domain_scores_codex":[0.970924,0.01184547,0.001464337,0.002001899,0.01329857,0.0004657268],"domain_scores_gemma":[0.959121,0.0292467,0.00124702,0.003490392,0.006388702,0.0005061199],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002081909,0.0001117295,0.001713662,0.001189584,0.0001808502,0.00006863488,0.0002046612,0.03990015,0.00154532,0.1320376,0.04448029,0.7783593],"study_design_scores_gemma":[0.0001654658,0.001042941,0.003216753,0.002799228,0.0003205527,0.0008626026,0.0007128069,0.2703566,0.01603126,0.3452406,0.3591016,0.0001497141],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01797654,0.03165271,0.748911,0.004192261,0.003019235,0.0007701178,0.001315385,0.002806231,0.1893566],"genre_scores_gemma":[0.1730005,0.02180362,0.7438771,0.001520088,0.001637775,0.001235932,0.003992847,0.001896223,0.0510359],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01758493,"threshold_uncertainty_score":0.08396113,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2294059674","doi":"","title":"Maxout Networks","year":2013,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":607,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"MNIST database; Dropout (neural networks); Leverage (statistics); Computer science; Benchmark (surveying); Artificial intelligence; Machine learning; Set (abstract data type); Deep learning","authors":[{"name":"Ian Goodfellow","is_ca":true},{"name":"David Warde-Farley","is_ca":true},{"name":"Mehdi Mirza","is_ca":true},{"name":"Aaron Courville","is_ca":true},{"name":"Yoshua Bengio","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.007273672343883744,"gpt":0.2085233568947044,"spread":0.2012496845508207,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002514733,0.001766477,0.001164197,0.0005750207,0.0005423483,0.001290798,0.003133566,0.001791055,0.005484845],"category_scores_gemma":[0.006042056,0.0006803698,0.0007980711,0.0006438967,0.001071575,0.004107276,0.001783605,0.002074238,0.001357966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001115644,"about_ca_system_score_gemma":0.0008306282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001738528,"about_ca_topic_score_gemma":0.003255449,"domain_scores_codex":[0.9991898,0.0003183031,0.00003393152,0.0002463771,0.0001298606,0.00008173118],"domain_scores_gemma":[0.9984564,0.0008680179,0.0001455295,0.0002615415,0.0001881405,0.00008034359],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000430395,0.0001486841,0.001589289,0.0002707732,0.0001402465,0.0001669142,0.0001642873,0.7081127,0.004056572,0.08421587,0.01375791,0.1869463],"study_design_scores_gemma":[0.00000987064,0.00004570771,0.00006591673,0.00001455465,0.00001323863,0.00002397659,0.000007351793,0.9674914,0.001270789,0.02920766,0.001842187,0.000007364311],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01312935,0.0006179748,0.9797759,0.0005973642,0.0001148012,0.00005601552,0.000353159,0.001124815,0.004230666],"genre_scores_gemma":[0.7397595,0.0008603594,0.2366387,0.001303751,0.0002429455,0.000452723,0.001500534,0.0004196918,0.01882187],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005484845,"threshold_uncertainty_score":0.01834863,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2113145584","doi":"","title":"Multi-Task Bayesian Optimization","year":2013,"lang":"en","type":"article","venue":"Digital Access to Scholarship at Harvard (DASH) (Harvard University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":452,"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":"Defense Advanced Research Projects Agency","keywords":"Bayesian optimization; Hyperparameter; Computer science; Gaussian process; Machine learning; Bayesian probability; Artificial intelligence; Task (project management); Gaussian","authors":[{"name":"Kevin Swersky","is_ca":true},{"name":"Jasper Snoek","is_ca":false},{"name":"Ryan P. Adams","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02370578556113782,"gpt":0.2429140372040699,"spread":0.2192082516429321,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003467985,0.001705018,0.002868802,0.001180053,0.000889656,0.00223144,0.00207944,0.003299042,0.01589182],"category_scores_gemma":[0.01153356,0.001378669,0.001242265,0.001798547,0.001533456,0.002329072,0.002274693,0.003221979,0.003693469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001609496,"about_ca_system_score_gemma":0.003685431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01260275,"about_ca_topic_score_gemma":0.01185318,"domain_scores_codex":[0.9987699,0.0005942078,0.00005431941,0.0002847633,0.0001421965,0.0001545621],"domain_scores_gemma":[0.9956326,0.003332843,0.0001777529,0.000189813,0.0004742894,0.0001926713],"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":[0.0004030266,0.0001551188,0.000935645,0.0003293927,0.000186147,0.0001603115,0.00009841257,0.8213432,0.0005054951,0.06021282,0.02912201,0.08654851],"study_design_scores_gemma":[0.00005794598,0.00002956353,0.0001953837,0.00004252603,0.00002040853,0.00002735848,0.00001648645,0.958937,0.0001540475,0.03778923,0.002711743,0.00001839709],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009784828,0.002325469,0.9671981,0.002774805,0.0002784506,0.0001789103,0.00109933,0.0007248953,0.01563519],"genre_scores_gemma":[0.4938356,0.002388556,0.4399266,0.001796669,0.0009038614,0.001049384,0.004940798,0.0008598241,0.05429874],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01589182,"threshold_uncertainty_score":0.05316341,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3037950864","doi":"","title":"Maxout Networks","year":2013,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":451,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"MNIST database; Dropout (neural networks); Leverage (statistics); Computer science; Benchmark (surveying); Artificial intelligence; Machine learning; Set (abstract data type); Simple (philosophy); Deep learning","authors":[{"name":"Ian Goodfellow","is_ca":true},{"name":"David Warde-Farley","is_ca":true},{"name":"Mehdi Mirza","is_ca":true},{"name":"Aaron Courville","is_ca":true},{"name":"Yoshua Bengio","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02043164376349244,"gpt":0.2569974981647503,"spread":0.2365658544012578,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002658545,0.00180552,0.001196451,0.0006014925,0.0005493592,0.001375678,0.003158782,0.001877742,0.005650114],"category_scores_gemma":[0.006604165,0.0006946854,0.000828852,0.0006881593,0.001119443,0.004223297,0.001873801,0.002171112,0.001445224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001137832,"about_ca_system_score_gemma":0.0008281285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001671946,"about_ca_topic_score_gemma":0.003090969,"domain_scores_codex":[0.9991103,0.0003515838,0.00003698122,0.0002722979,0.000141742,0.00008722217],"domain_scores_gemma":[0.9983394,0.0009352417,0.0001559102,0.0002889738,0.0001940454,0.00008639791],"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":[0.0004525942,0.0001536539,0.001659652,0.0002951912,0.0001491463,0.0001710549,0.0001742803,0.6908231,0.004121291,0.094193,0.01491846,0.1928885],"study_design_scores_gemma":[0.00001035121,0.00004705697,0.00007111918,0.00001606453,0.00001400927,0.0000252894,0.000007877175,0.9614906,0.00133038,0.03493638,0.002043119,0.000007778967],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01296263,0.0006568772,0.9797356,0.0006495826,0.0001206781,0.00005606153,0.0003809491,0.001136305,0.004301247],"genre_scores_gemma":[0.7312678,0.0009411536,0.2436024,0.001411885,0.0002735992,0.0004734402,0.001649119,0.0004662451,0.01991436],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005650114,"threshold_uncertainty_score":0.01890147,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1798702550","doi":"10.48550/arxiv.1502.05700","title":"Scalable Bayesian Optimization Using Deep Neural Networks","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":440,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Office of Science; National Energy Research Scientific Computing Center; Canadian Institute for Advanced Research; FAS Division of Science, Harvard University; U.S. Department of Energy; Harvard University; National Science Foundation","keywords":"Computer science; Bayesian optimization; Hyperparameter; Artificial intelligence; Artificial neural network; Convolutional neural network; Machine learning; Gaussian process; Global Positioning System; Deep learning; Benchmark (surveying); Optimization problem; Scalability; Surrogate model; Scale (ratio); Gaussian; Algorithm","authors":[{"name":"Jasper Snoek","is_ca":false},{"name":"Oren Rippel","is_ca":false},{"name":"Kevin Swersky","is_ca":true},{"name":"Ryan Kiros","is_ca":true},{"name":"Nadathur Satish","is_ca":false},{"name":"Narayanan Sundaram","is_ca":false},{"name":"Mostofa Patwary","is_ca":false},{"name":"Ryan P. Adams","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07416914068091068,"gpt":0.2071218247056708,"spread":0.1329526840247601,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001930585,0.00156252,0.002038095,0.0009905688,0.0005635048,0.001452558,0.002017426,0.001811696,0.004145322],"category_scores_gemma":[0.006563195,0.001360619,0.001143889,0.001340431,0.00120934,0.002158467,0.002220128,0.002767872,0.001195585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00236139,"about_ca_system_score_gemma":0.002973829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01453932,"about_ca_topic_score_gemma":0.02334828,"domain_scores_codex":[0.9989173,0.0003557847,0.00004917206,0.0002295051,0.0003305807,0.00011761],"domain_scores_gemma":[0.9980762,0.001179119,0.0001539135,0.0002101334,0.0002874469,0.0000930902],"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":[0.00004348134,0.0000307339,0.0002407832,0.00005491327,0.0000401026,0.00002451572,0.00001874698,0.9533207,0.0006125519,0.01245147,0.002117141,0.03104487],"study_design_scores_gemma":[0.000004097907,0.000002366,0.00001590354,0.000002403459,0.000001305978,0.000001555218,0.000001429213,0.9946346,0.00009152688,0.005064409,0.000178684,0.000001655873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008189522,0.0003965056,0.9858584,0.0003773559,0.00003949622,0.00004117652,0.0001464465,0.001438228,0.00351283],"genre_scores_gemma":[0.4215743,0.0006021329,0.5660248,0.0005680663,0.0001637628,0.000401121,0.001185553,0.001158212,0.008322083],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01453932,"threshold_uncertainty_score":0.02890939,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963371670","doi":"","title":"Learning to Reweight Examples for Robust Deep Learning","year":2018,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":418,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Hyperparameter; Overfitting; Computer science; Artificial intelligence; Machine learning; Regularization (linguistics); Deep learning; Gradient descent; Artificial neural network; Set (abstract data type); Deep neural networks; Supervised learning","authors":[{"name":"Mengye Ren","is_ca":true},{"name":"Wenyuan Zeng","is_ca":true},{"name":"Bin Yang","is_ca":false},{"name":"Raquel Urtasun","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06198251208780124,"gpt":0.3196849676050122,"spread":0.257702455517211,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003014941,0.001648032,0.001435648,0.0009686974,0.0004882924,0.0009747415,0.002878403,0.001764908,0.002397225],"category_scores_gemma":[0.01215782,0.001018628,0.0007445737,0.000812158,0.001190686,0.002409206,0.002192374,0.002521112,0.001623657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007359701,"about_ca_system_score_gemma":0.0009697113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00128318,"about_ca_topic_score_gemma":0.002356709,"domain_scores_codex":[0.9986085,0.0003745376,0.0001005571,0.0004126229,0.0004045675,0.00009927544],"domain_scores_gemma":[0.9973658,0.0007671358,0.0003576148,0.0008569427,0.000574527,0.00007801061],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000387677,0.0001780349,0.001764616,0.0002018033,0.0001400272,0.0001054679,0.0001410884,0.4014745,0.029572,0.01451483,0.007002268,0.5445177],"study_design_scores_gemma":[0.0000213669,0.00005419519,0.0001696784,0.00002024808,0.00001407779,0.00004607942,0.00001236142,0.9790543,0.009618066,0.009448349,0.001530014,0.00001121626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01268174,0.000233727,0.9844466,0.0001227315,0.00004572638,0.00005527987,0.00004582364,0.001794783,0.0005737263],"genre_scores_gemma":[0.2854782,0.0002370739,0.7093232,0.0003492083,0.0000828271,0.0002777519,0.0004043261,0.0006217023,0.003225652],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003014941,"threshold_uncertainty_score":0.01594472,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2950277768","doi":"","title":"Scalable Bayesian Optimization Using Deep Neural Networks","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":376,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Hyperparameter; Bayesian optimization; Artificial intelligence; Artificial neural network; Convolutional neural network; Deep learning; Gaussian process; Global Positioning System; Machine learning; Benchmark (surveying); Optimization problem; Scalability; Surrogate model; Gaussian; Algorithm","authors":[{"name":"Jasper Snoek","is_ca":false},{"name":"Oren Rippel","is_ca":false},{"name":"Kevin Swersky","is_ca":true},{"name":"Ryan Kiros","is_ca":true},{"name":"Nadathur Satish","is_ca":false},{"name":"Narayanan Sundaram","is_ca":false},{"name":"Md. Mostofa Ali Patwary","is_ca":false},{"name":"Ryan P. Adams","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07416914068091068,"gpt":0.2071218247056708,"spread":0.1329526840247601,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001930585,0.00156252,0.002038095,0.0009905688,0.0005635048,0.001452558,0.002017426,0.001811696,0.004145322],"category_scores_gemma":[0.006563195,0.001360619,0.001143889,0.001340431,0.00120934,0.002158467,0.002220128,0.002767872,0.001195585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00236139,"about_ca_system_score_gemma":0.002973829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01453932,"about_ca_topic_score_gemma":0.02334828,"domain_scores_codex":[0.9989173,0.0003557847,0.00004917206,0.0002295051,0.0003305807,0.00011761],"domain_scores_gemma":[0.9980762,0.001179119,0.0001539135,0.0002101334,0.0002874469,0.0000930902],"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":[0.00004348134,0.0000307339,0.0002407832,0.00005491327,0.0000401026,0.00002451572,0.00001874698,0.9533207,0.0006125519,0.01245147,0.002117141,0.03104487],"study_design_scores_gemma":[0.000004097907,0.000002366,0.00001590354,0.000002403459,0.000001305978,0.000001555218,0.000001429213,0.9946346,0.00009152688,0.005064409,0.000178684,0.000001655873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008189522,0.0003965056,0.9858584,0.0003773559,0.00003949622,0.00004117652,0.0001464465,0.001438228,0.00351283],"genre_scores_gemma":[0.4215743,0.0006021329,0.5660248,0.0005680663,0.0001637628,0.000401121,0.001185553,0.001158212,0.008322083],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01453932,"threshold_uncertainty_score":0.02890939,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W114730584","doi":"","title":"An Efficient Approach for Assessing Hyperparameter Importance","year":2014,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":314,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Hyperparameter; Computer science; Hyperparameter optimization; Machine learning; Leverage (statistics); Bayesian optimization; Artificial intelligence; Random forest; Bayesian probability; Support vector machine","authors":[{"name":"Frank Hutter","is_ca":false},{"name":"Holger H. Hoos","is_ca":true},{"name":"Kevin Leyton‐Brown","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02586691008238868,"gpt":0.2989415350621249,"spread":0.2730746249797362,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01070331,0.003160426,0.001790833,0.005341672,0.001099919,0.003535323,0.002669491,0.003144415,0.007074399],"category_scores_gemma":[0.0890836,0.001271816,0.001557654,0.003404744,0.001488607,0.004167059,0.003449043,0.005504897,0.002471001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001433889,"about_ca_system_score_gemma":0.00361039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00198332,"about_ca_topic_score_gemma":0.00261152,"domain_scores_codex":[0.9917971,0.003491798,0.0007456425,0.0009915335,0.002693662,0.0002802043],"domain_scores_gemma":[0.9665054,0.02341781,0.002015558,0.004241972,0.003501061,0.0003181015],"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":[0.0003403104,0.0003479894,0.007708289,0.0005372876,0.0003641377,0.0001499866,0.0003118684,0.3111908,0.01494983,0.0578674,0.009310917,0.5969211],"study_design_scores_gemma":[0.0001031322,0.0001280199,0.002153191,0.0001048319,0.00007886083,0.000241258,0.00008986645,0.915205,0.01016405,0.06613997,0.005502308,0.00008942719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003868575,0.0002834476,0.9932268,0.0001501521,0.00003778779,0.0001846324,0.0001419893,0.001063837,0.00104286],"genre_scores_gemma":[0.1024783,0.0003182008,0.8941746,0.000165097,0.00008795151,0.0008644534,0.0004616659,0.00058545,0.0008642647],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01070331,"threshold_uncertainty_score":0.05660522,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2164921999","doi":"10.1162/089976600300015178","title":"Boosting Neural Networks","year":2000,"lang":"en","type":"article","venue":"Neural Computation","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":303,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Boosting (machine learning); AdaBoost; Computer science; Artificial intelligence; Artificial neural network; Machine learning; Resampling; Weighting; Decision tree; Gradient boosting; Overfitting; Benchmark (surveying); Pattern recognition (psychology); Random forest; Classifier (UML)","authors":[{"name":"Holger Schwenk","is_ca":false},{"name":"Yoshua Bengio","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01889837284029754,"gpt":0.2679592206379307,"spread":0.2490608477976331,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002402864,0.001452723,0.00262314,0.001663072,0.0007050195,0.001905532,0.002168657,0.001833486,0.006827388],"category_scores_gemma":[0.005741045,0.000780189,0.001410815,0.001870437,0.0006784992,0.001370505,0.001336068,0.001677862,0.004916257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007703787,"about_ca_system_score_gemma":0.000689169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001606836,"about_ca_topic_score_gemma":0.001454526,"domain_scores_codex":[0.9983909,0.0004491268,0.00009002443,0.0002671239,0.0006568567,0.0001460351],"domain_scores_gemma":[0.998759,0.0004722782,0.0001140362,0.0001894785,0.0004019078,0.0000632406],"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":[0.0001674785,0.0001438909,0.001905802,0.000612637,0.0004513842,0.0001272027,0.00006269873,0.3178453,0.004915778,0.03771656,0.02361008,0.6124411],"study_design_scores_gemma":[0.00006370788,0.0001166299,0.0008053204,0.0001100041,0.00009640266,0.0001502097,0.00001511891,0.9136986,0.003453392,0.04652826,0.03492052,0.00004179958],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005729985,0.00458816,0.9728804,0.0003526117,0.0005699989,0.000228315,0.0002310468,0.002079939,0.01333955],"genre_scores_gemma":[0.3458728,0.008896823,0.6155522,0.001434449,0.001576639,0.001076082,0.001885218,0.0004540814,0.02325171],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006827388,"threshold_uncertainty_score":0.0228399,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2112364454","doi":"10.25080/majora-14bd3278-006","title":"Hyperopt-Sklearn: Automatic Hyperparameter Configuration for Scikit-Learn","year":2014,"lang":"en","type":"article","venue":"Proceedings of the Python in Science Conferences","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":298,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"MNIST database; Hyperparameter; Computer science; Artificial intelligence; Preprocessor; Machine learning; Benchmarking; Classifier (UML); Support vector machine; Pattern recognition (psychology); Data mining; Deep learning","authors":[{"name":"Brent Komer","is_ca":true},{"name":"James Bergstra","is_ca":true},{"name":"Chris Eliasmith","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02458341355120219,"gpt":0.2767362059639611,"spread":0.252152792412759,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005664534,0.005132728,0.002487261,0.003883565,0.001080408,0.003849433,0.007976645,0.004311373,0.05109996],"category_scores_gemma":[0.03129011,0.002847017,0.003213817,0.002771943,0.001128767,0.005325556,0.005578367,0.007904643,0.05881105],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001720243,"about_ca_system_score_gemma":0.002878956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002540538,"about_ca_topic_score_gemma":0.005510845,"domain_scores_codex":[0.9963265,0.001103962,0.0004969759,0.0008148384,0.000952078,0.0003056406],"domain_scores_gemma":[0.9911089,0.004711919,0.0004215411,0.002161069,0.001192277,0.000404273],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001203991,0.0008000963,0.006309112,0.002255243,0.0007873792,0.0004421727,0.0005048895,0.0388262,0.007114233,0.009392462,0.4976523,0.434712],"study_design_scores_gemma":[0.001299699,0.0002835487,0.003089009,0.0005765711,0.0002160005,0.0004493054,0.0002238714,0.7489264,0.0359644,0.07540168,0.1331803,0.0003892129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.005988665,0.0006245574,0.3039908,0.0002716188,0.0003452025,0.0004292746,0.004883424,0.6777152,0.005751205],"genre_scores_gemma":[0.09153431,0.0007119813,0.6414686,0.001601793,0.00026677,0.005479333,0.03079169,0.2163929,0.01175252],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.05109996,"threshold_uncertainty_score":0.1709464,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2120501001","doi":"","title":"Lifelong Machine Learning Systems: Beyond Learning Algorithms","year":2013,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":292,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Acadia University","funders":"","keywords":"Computer science; Lifelong learning; Listing (finance); Artificial intelligence; Field (mathematics); Task (project management); Machine learning; Remainder; Key (lock); Position paper; Psychology; Engineering","authors":[{"name":"Daniel Silver","is_ca":true},{"name":"Qiang Yang","is_ca":false},{"name":"Lianghao Li","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01263382449279777,"gpt":0.2323464850853059,"spread":0.2197126605925082,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008643749,0.0009026986,0.001691502,0.001599649,0.002012311,0.009142326,0.004171193,0.005213353,0.006888526],"category_scores_gemma":[0.027457,0.0006396503,0.0007911925,0.002245049,0.01148636,0.03072037,0.006128125,0.009112135,0.002337522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00336433,"about_ca_system_score_gemma":0.002200438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001913613,"about_ca_topic_score_gemma":0.001591573,"domain_scores_codex":[0.9953108,0.002397117,0.0003086178,0.000720525,0.000988669,0.0002741748],"domain_scores_gemma":[0.9703,0.01966698,0.001190464,0.005270907,0.002454638,0.001117045],"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":[0.00002886224,0.00006429042,0.0009753848,0.0002590341,0.00003008253,0.00006205007,0.0004839909,0.008933012,0.0002104708,0.9137287,0.006167118,0.06905697],"study_design_scores_gemma":[0.000008454743,0.00002966379,0.0002010537,0.0001099423,0.00000594765,0.0000583384,0.0001428202,0.0440488,0.0002569681,0.9289782,0.02613732,0.00002246372],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0139414,0.03323919,0.8453633,0.0668123,0.001115709,0.0001676303,0.0002428863,0.0008651252,0.03825242],"genre_scores_gemma":[0.568266,0.02571165,0.3661694,0.01066343,0.006654037,0.0006915281,0.0005384573,0.0005049349,0.02080058],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009142326,"threshold_uncertainty_score":0.04571307,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2740333758","doi":"10.24963/ijcai.2017/352","title":"Learning Feature Engineering for Classification","year":2017,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":282,"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":"Feature engineering; Feature (linguistics); Computer science; Feature selection; Artificial intelligence; Feature vector; Machine learning; Transformation (genetics); Aggregate (composite); Set (abstract data type); Artificial neural network; Process (computing); Data mining; Pattern recognition (psychology); Deep learning","authors":[{"name":"Fatemeh Nargesian","is_ca":true},{"name":"Horst Samulowitz","is_ca":false},{"name":"Udayan Khurana","is_ca":false},{"name":"Elias B. Khalil","is_ca":false},{"name":"Deepak S. Turaga","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02701836804495996,"gpt":0.2871792180817002,"spread":0.2601608500367402,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00285409,0.002138925,0.001512761,0.003362869,0.0006681767,0.001670084,0.00184614,0.001365755,0.002931072],"category_scores_gemma":[0.01489632,0.0004311401,0.001708967,0.00320961,0.001032304,0.003000912,0.001691467,0.002781697,0.001998874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001076173,"about_ca_system_score_gemma":0.001276334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002405414,"about_ca_topic_score_gemma":0.00306387,"domain_scores_codex":[0.9974371,0.0007423261,0.0002288519,0.0008463067,0.0005973463,0.0001479558],"domain_scores_gemma":[0.9935661,0.003697731,0.0005259338,0.001304735,0.0007946849,0.0001109265],"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":[0.0002536078,0.0003389782,0.007504433,0.0004273543,0.0002001069,0.0001495385,0.0001291835,0.1352067,0.00810233,0.0147477,0.01705341,0.8158866],"study_design_scores_gemma":[0.00004116557,0.0001639375,0.001381531,0.00006348327,0.00004968908,0.0001358974,0.00006109448,0.9301842,0.006521249,0.05252884,0.008830156,0.00003862282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01697602,0.0008882463,0.9750992,0.0004843797,0.0000804936,0.0001600162,0.0009727722,0.003805742,0.001533082],"genre_scores_gemma":[0.3136094,0.0007152075,0.6773009,0.0003800904,0.0001756193,0.0006577505,0.00521054,0.0003729555,0.00157751],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003362869,"threshold_uncertainty_score":0.0150941,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1982723861","doi":"10.1145/2746539.2746580","title":"Preserving Statistical Validity in Adaptive Data Analysis","year":2015,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":265,"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":"National Science Foundation","keywords":"Spurious relationship; Computer science; Statistical inference; Statistical hypothesis testing; Inference; Data mining; Machine learning; Statistical analysis; Data collection; Data science; Artificial intelligence; Statistics; Mathematics","authors":[{"name":"Cynthia Dwork","is_ca":false},{"name":"Vitaly Feldman","is_ca":false},{"name":"Moritz Hardt","is_ca":false},{"name":"Toniann Pitassi","is_ca":true},{"name":"Omer Reingold","is_ca":false},{"name":"Aaron Roth","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3190507828462666,"gpt":0.3803631002506314,"spread":0.06131231740436482,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3153098,0.00270875,0.004944179,0.005841988,0.003687107,0.009346747,0.008212823,0.006346032,0.002656762],"category_scores_gemma":[0.707212,0.003133912,0.004145336,0.006106342,0.03301642,0.01192173,0.01676875,0.01729901,0.0009878281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003651798,"about_ca_system_score_gemma":0.01366499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002393279,"about_ca_topic_score_gemma":0.001468515,"domain_scores_codex":[0.5915508,0.3375226,0.01747462,0.02450914,0.02694451,0.001998379],"domain_scores_gemma":[0.1888938,0.7083583,0.01327981,0.07394217,0.01395229,0.00157372],"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":[0.001042547,0.0002649288,0.01635722,0.002331981,0.002153899,0.001162664,0.005549012,0.05474374,0.002928523,0.6843786,0.005684813,0.2234022],"study_design_scores_gemma":[0.0002533577,0.00023089,0.001200268,0.0004024568,0.0001354536,0.0002811208,0.0002109517,0.07587625,0.001585073,0.9141186,0.005629152,0.00007638751],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002862438,0.001050102,0.990262,0.003709746,0.0002366005,0.0002814292,0.00009652582,0.0002624104,0.001238747],"genre_scores_gemma":[0.1736735,0.001352459,0.8138074,0.004738664,0.001348085,0.003405704,0.0003643459,0.0004512386,0.0008585543],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3153098,"threshold_uncertainty_score":0.844345,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2891021639","doi":"10.1609/aaai.v33i01.33013714","title":"MixUp as Locally Linear Out-of-Manifold Regularization","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":265,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; National Research Council Canada","funders":"National Key Research and Development Program of China; Beijing Advanced Innovation Center for Big Data and Brain Computing; National Natural Science Foundation of China","keywords":"Computer science; Regularization (linguistics); Manifold (fluid mechanics); Artificial neural network; Benchmark (surveying); Artificial intelligence; Machine learning; Mixing (physics); Nonlinear dimensionality reduction; Algorithm; Dimensionality reduction","authors":[{"name":"Hongyu Guo","is_ca":true},{"name":"Yongyi Mao","is_ca":true},{"name":"Richong Zhang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05000555547855106,"gpt":0.29572975316366,"spread":0.2457241976851089,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003547559,0.001880651,0.001535537,0.0009971253,0.0007742886,0.001579799,0.003284661,0.002438632,0.002387439],"category_scores_gemma":[0.007702904,0.001109407,0.001338793,0.0009267264,0.002225545,0.003019148,0.005379437,0.004540794,0.001199007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00111927,"about_ca_system_score_gemma":0.001220108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001494465,"about_ca_topic_score_gemma":0.002296479,"domain_scores_codex":[0.9984075,0.0007069752,0.00007935652,0.0003507232,0.0003333669,0.0001219797],"domain_scores_gemma":[0.9976706,0.001001208,0.0002285649,0.000690654,0.0002625796,0.0001463773],"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":[0.0005145665,0.0002950891,0.00359957,0.0003674467,0.0003000371,0.0002478311,0.0004390044,0.6598876,0.01350846,0.0537295,0.0118996,0.2552112],"study_design_scores_gemma":[0.00001585377,0.00007355284,0.0001104186,0.00001597844,0.00001239727,0.00003284136,0.00001318764,0.9857668,0.002395124,0.01005105,0.001500506,0.00001229848],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02621372,0.0006348087,0.968236,0.0004158118,0.00006158227,0.0001223885,0.00014884,0.002734759,0.001431991],"genre_scores_gemma":[0.4985226,0.0004941036,0.4901173,0.000931118,0.0001628358,0.0006859364,0.001157534,0.0009908316,0.006937818],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003547559,"threshold_uncertainty_score":0.01876152,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2548122763","doi":"10.14778/2994509.2994514","title":"ActiveClean","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":244,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"MNIST database; Computer science; Context (archaeology); Support vector machine; Data mining; Convergence (economics); Process (computing); Class (philosophy); Iterative and incremental development; Machine learning; Artificial intelligence; Deep learning","authors":[{"name":"Sanjay Krishnan","is_ca":false},{"name":"Jiannan Wang","is_ca":true},{"name":"Eugene Wu","is_ca":false},{"name":"Michael J. Franklin","is_ca":false},{"name":"Ken Goldberg","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.009115700324434017,"gpt":0.2121947867126384,"spread":0.2030790863882044,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005524416,0.003281085,0.002910606,0.003398271,0.002098419,0.007996758,0.007369641,0.003558987,0.04162381],"category_scores_gemma":[0.02294586,0.002480949,0.003860537,0.003341832,0.001404523,0.007642557,0.007066833,0.00456045,0.03641694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008763244,"about_ca_system_score_gemma":0.003094282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003690959,"about_ca_topic_score_gemma":0.007741269,"domain_scores_codex":[0.9951501,0.001209463,0.0004006198,0.001279485,0.001660123,0.0003001515],"domain_scores_gemma":[0.990415,0.004144664,0.0003539688,0.003346487,0.0014871,0.0002528988],"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":[0.0005766489,0.0002924403,0.004378524,0.001855119,0.0006870286,0.0004468172,0.0008711849,0.05785158,0.006938002,0.04163717,0.4085335,0.475932],"study_design_scores_gemma":[0.0001804244,0.0001143024,0.0008681212,0.0002539227,0.0001296521,0.0006816341,0.0004368314,0.435555,0.01938186,0.1141362,0.4281086,0.0001533892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00346497,0.001361244,0.8787732,0.001261081,0.000674281,0.0003527406,0.006805339,0.09451578,0.01279131],"genre_scores_gemma":[0.06609979,0.002148384,0.8232331,0.002652606,0.0003656152,0.001181668,0.04470693,0.03090976,0.02870207],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04162381,"threshold_uncertainty_score":0.1392455,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4405907339","doi":"10.1109/tpami.2024.3524377","title":"Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":237,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Natural Science Foundation of Beijing Municipality; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Object detection; Hypergraph; Computer vision; Computation; Object (grammar); Cognitive neuroscience of visual object recognition; Visualization; Pattern recognition (psychology); Mathematics; Algorithm","authors":[{"name":"Yifan Feng","is_ca":false},{"name":"Jiangang Huang","is_ca":false},{"name":"Shaoyi Du","is_ca":false},{"name":"Shihui Ying","is_ca":false},{"name":"Jun‐Hai Yong","is_ca":false},{"name":"Yipeng Li","is_ca":false},{"name":"Guiguang Ding","is_ca":false},{"name":"Rongrong Ji","is_ca":true},{"name":"Yue Gao","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01839729713418404,"gpt":0.286248052880697,"spread":0.267850755746513,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001178233,0.001404482,0.001236929,0.002292317,0.0008165988,0.002583856,0.002933974,0.0017229,0.003990557],"category_scores_gemma":[0.005514436,0.0007630661,0.0009033215,0.001445751,0.00131925,0.006176492,0.003200949,0.001747764,0.001824272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001483756,"about_ca_system_score_gemma":0.00179026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01219375,"about_ca_topic_score_gemma":0.01880462,"domain_scores_codex":[0.9992286,0.0001404477,0.0000306424,0.0003003742,0.0001831586,0.0001168252],"domain_scores_gemma":[0.9986005,0.0004997056,0.000119809,0.0004070574,0.0002763096,0.0000965908],"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":[0.0007838522,0.0004018756,0.008049675,0.0005013911,0.0003121082,0.0003980901,0.0004990344,0.2534674,0.02486361,0.05282407,0.03282822,0.6250707],"study_design_scores_gemma":[0.00002296651,0.00005738549,0.0006263161,0.00002465019,0.00002603037,0.00005805639,0.00007209933,0.9677143,0.00498175,0.02164842,0.004750635,0.00001743894],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02641531,0.0006917698,0.9579489,0.0004832165,0.0001145074,0.0002097813,0.0005277104,0.008101963,0.005506787],"genre_scores_gemma":[0.4792367,0.000699552,0.5030815,0.001164423,0.0002383541,0.0005178393,0.003308587,0.001198897,0.01055416],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01219375,"threshold_uncertainty_score":0.0242455,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2047003964","doi":"10.1145/2076450.2076469","title":"Programming by optimization","year":2012,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":226,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Programming language","authors":[{"name":"Holger H. Hoos","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03999092086229857,"gpt":0.3033604240854069,"spread":0.2633695032231084,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002302106,0.001762719,0.000916209,0.0009164551,0.0006007935,0.001723606,0.001312165,0.0008777355,0.0077256],"category_scores_gemma":[0.007838326,0.0006463342,0.001057389,0.00112754,0.00184833,0.001745925,0.002087391,0.002932572,0.002341715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008011108,"about_ca_system_score_gemma":0.00203097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001064198,"about_ca_topic_score_gemma":0.001793966,"domain_scores_codex":[0.9981453,0.0008243388,0.00009545336,0.0003385284,0.0004776461,0.0001187704],"domain_scores_gemma":[0.9975132,0.001791611,0.0001415198,0.0003465083,0.0001535404,0.00005370444],"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":[0.00008069759,0.0001171836,0.000631406,0.0005562712,0.000122304,0.0000914542,0.0001497364,0.3192759,0.002978945,0.418823,0.01999417,0.237179],"study_design_scores_gemma":[0.00005250968,0.00005502096,0.00008531352,0.00009232097,0.00002911893,0.00006203258,0.00003326561,0.5519335,0.001891568,0.4212334,0.02451346,0.00001841165],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001353763,0.0002731346,0.9906131,0.0004207484,0.00006679607,0.00008200768,0.00004056455,0.0004107131,0.00673914],"genre_scores_gemma":[0.07120201,0.0008514299,0.917836,0.0004752086,0.0001487475,0.0006331189,0.000235329,0.0008420941,0.007776],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0077256,"threshold_uncertainty_score":0.02584469,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2303810353","doi":"10.1007/978-3-319-25388-6","title":"Lectures on the Nearest Neighbor Method","year":2015,"lang":"en","type":"book","venue":"Springer series in the data sciences","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":224,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"k-nearest neighbors algorithm; Nearest neighbor search; Computer science; Artificial intelligence","authors":[{"name":"Gérard Biau","is_ca":false},{"name":"Luc Devroye","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1236141954165152,"gpt":0.3532936935617726,"spread":0.2296794981452575,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001119216,0.001276794,0.001480591,0.001531896,0.0005651788,0.001608075,0.0009959859,0.001197818,0.01903697],"category_scores_gemma":[0.002919683,0.0007066248,0.001059117,0.002483159,0.001166258,0.003017837,0.001199834,0.003915372,0.01629596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009023653,"about_ca_system_score_gemma":0.0008795547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001691715,"about_ca_topic_score_gemma":0.001697725,"domain_scores_codex":[0.9990658,0.0001265247,0.00005790917,0.0002102679,0.0004958085,0.00004373632],"domain_scores_gemma":[0.9992843,0.0003449127,0.00002686553,0.00008989891,0.0002084457,0.00004545509],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004730739,0.00007600172,0.0002183713,0.000561107,0.00005535723,0.00009004949,0.0001560116,0.006258049,0.00169063,0.280766,0.1842822,0.5257989],"study_design_scores_gemma":[0.00001536021,0.00005061543,0.0006204342,0.0003278775,0.00003110461,0.0004422725,0.00003897309,0.0115123,0.0008891396,0.344216,0.6418033,0.00005266024],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001916536,0.1839974,0.5269834,0.005209669,0.01950552,0.0000835761,0.00116911,0.001114429,0.2600204],"genre_scores_gemma":[0.03806967,0.1261989,0.5209541,0.003094977,0.01526143,0.0002421115,0.002223059,0.001178336,0.2927774],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01903697,"threshold_uncertainty_score":0.06368506,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1471542436","doi":"10.1016/j.artint.2016.04.003","title":"ASlib: A benchmark library for algorithm selection","year":2016,"lang":"en","type":"article","venue":"Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":213,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Deutsche Forschungsgemeinschaft; Microsoft","keywords":"Computer science; Selection (genetic algorithm); Benchmark (surveying); Exploit; Task (project management); Set (abstract data type); Variety (cybernetics); Data mining; Selection algorithm; Range (aeronautics); Algorithm; Machine learning; Artificial intelligence","authors":[{"name":"Bernd Bischl","is_ca":false},{"name":"Pascal Kerschke","is_ca":false},{"name":"Lars Kotthoff","is_ca":true},{"name":"Marius Lindauer","is_ca":false},{"name":"Yuri Malitsky","is_ca":false},{"name":"Alexandre Fréchette","is_ca":true},{"name":"Holger H. Hoos","is_ca":true},{"name":"Frank Hutter","is_ca":false},{"name":"Kevin Leyton‐Brown","is_ca":true},{"name":"Kevin Tierney","is_ca":false},{"name":"Joaquin Vanschoren","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03557090669313157,"gpt":0.2896685730587838,"spread":0.2540976663656522,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003632026,0.004083215,0.001940365,0.005574837,0.00108087,0.003465727,0.006065022,0.002636231,0.02917494],"category_scores_gemma":[0.01839225,0.001315071,0.002112807,0.008753804,0.0006638374,0.003174958,0.002139326,0.002766719,0.02193213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00135894,"about_ca_system_score_gemma":0.003677071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005246897,"about_ca_topic_score_gemma":0.007185344,"domain_scores_codex":[0.9959049,0.001368114,0.0006313844,0.000468453,0.001215743,0.0004115051],"domain_scores_gemma":[0.9906844,0.005167089,0.000381245,0.001546416,0.001877998,0.0003428987],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001080231,0.0007177115,0.001828908,0.003827329,0.0004664825,0.0002142019,0.0001095981,0.04588515,0.002494574,0.007018102,0.6180547,0.318303],"study_design_scores_gemma":[0.003520534,0.0009133805,0.002826098,0.0009418671,0.0005174764,0.0008820263,0.0002182718,0.5151961,0.03220281,0.03740518,0.4051512,0.0002250927],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05930647,0.01963295,0.3810522,0.00249454,0.002415851,0.001975762,0.1136165,0.32293,0.0965757],"genre_scores_gemma":[0.09621303,0.00627061,0.6434432,0.001503926,0.0004366471,0.002881761,0.1890014,0.03720484,0.02304456],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02917494,"threshold_uncertainty_score":0.09759986,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964273174","doi":"10.1109/icdm.2016.0121","title":"Learning Deep Networks from Noisy Labels with Dropout Regularization","year":2016,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":188,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Canadian Institute for Advanced Research; National Science Foundation","keywords":"Softmax function; Dropout (neural networks); Computer science; Artificial intelligence; MNIST database; Regularization (linguistics); Stochastic gradient descent; Deep neural networks; Deep learning; Artificial neural network; Noise (video); Machine learning; Pattern recognition (psychology); Gradient descent; Underdetermined system; Algorithm","authors":[{"name":"Ishan Jindal","is_ca":false},{"name":"Matthew Nokleby","is_ca":false},{"name":"Xuewen Chen","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.00550017393021877,"gpt":0.2010668505581302,"spread":0.1955666766279114,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004124372,0.002165323,0.001639591,0.0009457637,0.0008925131,0.001659548,0.002915758,0.002500703,0.001529895],"category_scores_gemma":[0.01551701,0.001054913,0.0008838262,0.001124127,0.001737772,0.003890995,0.002879795,0.004595137,0.0009535739],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002361618,"about_ca_system_score_gemma":0.001866254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007111995,"about_ca_topic_score_gemma":0.01228655,"domain_scores_codex":[0.9986945,0.0004889708,0.00006538151,0.0002915215,0.0003052526,0.0001544891],"domain_scores_gemma":[0.9959649,0.002192337,0.0004638798,0.0006592741,0.0005818657,0.0001376963],"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":[0.0003050747,0.0001356306,0.002340259,0.0001361134,0.00009135314,0.0001402643,0.0001610004,0.8435615,0.002540585,0.01442457,0.00755156,0.1286121],"study_design_scores_gemma":[0.000008853637,0.00001491993,0.00008241028,0.000009683878,0.000004512789,0.000006790237,0.000005948662,0.9897774,0.0006434848,0.009187313,0.000254511,0.000004159129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04716791,0.0005016171,0.9469503,0.0008528848,0.00008484699,0.00007058173,0.0002931016,0.002577137,0.001501661],"genre_scores_gemma":[0.7204784,0.0005881925,0.2679587,0.0009633003,0.0002158867,0.0004740025,0.002429316,0.0004159714,0.006476248],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007111995,"threshold_uncertainty_score":0.02181202,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964096266","doi":"","title":"Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks","year":2017,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":186,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Robustness (evolution); Discriminative model; Artificial intelligence; Inference; Convolutional neural network; Deep neural networks; Pattern recognition (psychology); Machine learning; Noise (video); Training set; Graphical model; Artificial neural network; Noise measurement; Image (mathematics); Noise reduction","authors":[{"name":"Arash Vahdat","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0666042164439337,"gpt":0.2991574030539693,"spread":0.2325531866100355,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01270445,0.002558243,0.002446637,0.001386195,0.001195142,0.002601301,0.003828435,0.003287358,0.001091059],"category_scores_gemma":[0.05570972,0.001835593,0.001199221,0.001608805,0.003432492,0.005630956,0.005742977,0.007066675,0.000804974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002514095,"about_ca_system_score_gemma":0.001905029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004507687,"about_ca_topic_score_gemma":0.00629003,"domain_scores_codex":[0.9927893,0.003550938,0.0002981987,0.001626106,0.001294522,0.0004409188],"domain_scores_gemma":[0.9700409,0.0207071,0.002265053,0.004767334,0.001790982,0.0004287212],"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":[0.0009956151,0.0002404562,0.004809876,0.0002959676,0.0002319857,0.0001945835,0.0003356329,0.7899922,0.009684678,0.02429932,0.005394794,0.163525],"study_design_scores_gemma":[0.00002500711,0.00004521221,0.0002369122,0.00001940986,0.00001523649,0.00002763011,0.00002017675,0.9748253,0.002812689,0.02154587,0.0004175395,0.000008909649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03078092,0.0004921588,0.9647859,0.0007337268,0.00005692046,0.00005208174,0.0001927116,0.002037569,0.0008679305],"genre_scores_gemma":[0.643769,0.0004823609,0.3483629,0.001296074,0.0002315476,0.00038952,0.001946567,0.0007671797,0.002754842],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01270445,"threshold_uncertainty_score":0.06718832,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W14214433","doi":"","title":"A fast decision tree learning algorithm","year":2006,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":162,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Decision tree; Algorithm; Speedup; Incremental decision tree; Naive Bayes classifier; Tree (set theory); Time complexity; ID3 algorithm; Benchmark (surveying); Machine learning; Artificial intelligence; Decision tree learning; Mathematics","authors":[{"name":"Su Jiang","is_ca":true},{"name":"Harry Zhang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.006777359616075056,"gpt":0.2358982322015854,"spread":0.2291208725855104,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002779506,0.0009826289,0.001507859,0.001927806,0.0009861464,0.001500657,0.002124104,0.002024318,0.006244821],"category_scores_gemma":[0.008818517,0.0005850348,0.001254952,0.002564276,0.0005066504,0.002825207,0.001776695,0.002191291,0.004117779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000724408,"about_ca_system_score_gemma":0.002069622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002430716,"about_ca_topic_score_gemma":0.002245752,"domain_scores_codex":[0.9971254,0.0007308511,0.0002228307,0.0005356708,0.001147169,0.0002379643],"domain_scores_gemma":[0.996707,0.001440102,0.0001365893,0.0003255146,0.001254181,0.0001364752],"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":[0.0002624981,0.000183125,0.0009873112,0.0002012313,0.00009481247,0.0001294211,0.00008002145,0.08235342,0.004053415,0.01897129,0.01919477,0.8734886],"study_design_scores_gemma":[0.0001394363,0.0001255606,0.0002777126,0.00003947617,0.0000400057,0.000251112,0.00003010134,0.9485661,0.003333028,0.03105658,0.01611217,0.0000287661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004557027,0.0005407251,0.9911236,0.0002853323,0.0001497113,0.00013236,0.0002588378,0.001304225,0.00164829],"genre_scores_gemma":[0.05246555,0.0003817405,0.9427873,0.0002649941,0.0001236489,0.0002601808,0.001115426,0.0001323438,0.002468653],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006244821,"threshold_uncertainty_score":0.02089095,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3032150799","doi":"10.1109/jproc.2020.2989782","title":"Towards Robust Pattern Recognition: A Review","year":2020,"lang":"en","type":"review","venue":"Proceedings of the IEEE","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":153,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"Chinese Academy of Sciences; National Natural Science Foundation of China; China Association for Science and Technology","keywords":"Computer science; Robustness (evolution); Artificial intelligence; Perspective (graphical); Machine learning; Pattern recognition (psychology)","authors":[{"name":"Xu-Yao Zhang","is_ca":false},{"name":"Cheng‐Lin Liu","is_ca":false},{"name":"Ching Y. Suen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09618442242372488,"gpt":0.3118657382337085,"spread":0.2156813158099836,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00179673,0.001286777,0.001723121,0.004098346,0.0004045767,0.002059579,0.002077748,0.001683092,0.004132013],"category_scores_gemma":[0.004029189,0.0007574178,0.0009141559,0.005370026,0.001068534,0.003796717,0.00112225,0.002011099,0.004932178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008609999,"about_ca_system_score_gemma":0.002066017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001918693,"about_ca_topic_score_gemma":0.001440523,"domain_scores_codex":[0.9991739,0.0001186331,0.0001253398,0.0001920232,0.0003415804,0.00004851127],"domain_scores_gemma":[0.9976084,0.001314847,0.0001728635,0.0001129257,0.0007096444,0.00008127377],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003470258,0.00006559799,0.0002860599,0.01278462,0.00009875357,0.00008129098,0.0000637587,0.0009098377,0.00101119,0.007557415,0.02953887,0.947568],"study_design_scores_gemma":[0.00001281584,0.0001375929,0.0009284038,0.005025269,0.0001526022,0.0009620348,0.00008275874,0.001229579,0.00124713,0.008459552,0.9817016,0.00006064675],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001826673,0.9924313,0.004500563,0.0006023477,0.0003839803,0.0000157121,0.00004292187,0.00005850342,0.001781916],"genre_scores_gemma":[0.001294961,0.993101,0.00387299,0.0003527264,0.0005537508,0.00002196668,0.0001142691,0.00001434816,0.0006739163],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.004132013,"threshold_uncertainty_score":0.01382291,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2042053856","doi":"10.1016/j.patcog.2008.03.027","title":"A dynamic overproduce-and-choose strategy for the selection of classifier ensembles","year":2008,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":152,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Defence Research and Development Canada; Quest University Canada; École de Technologie Supérieure","funders":"","keywords":"Classifier (UML); Computer science; Artificial intelligence; Selection (genetic algorithm); Machine learning; Population; Pattern recognition (psychology)","authors":[{"name":"Eulanda M. dos Santos","is_ca":true},{"name":"Robert Sabourin","is_ca":true},{"name":"Patrick Maupin","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05774142430184379,"gpt":0.2844336532926083,"spread":0.2266922289907645,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0109792,0.001404866,0.002448179,0.003008538,0.002230129,0.003037214,0.004604416,0.002759139,0.01026291],"category_scores_gemma":[0.03357337,0.0009422217,0.001332149,0.002433299,0.001946766,0.003482279,0.005186295,0.00363537,0.002545435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001108371,"about_ca_system_score_gemma":0.002351681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001417896,"about_ca_topic_score_gemma":0.00373789,"domain_scores_codex":[0.9922044,0.003875684,0.0003987848,0.0008921973,0.002031134,0.0005977894],"domain_scores_gemma":[0.9817933,0.009696995,0.0006017453,0.004230012,0.002792263,0.0008856183],"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":[0.001395369,0.0008192018,0.006994763,0.0002083862,0.0004934434,0.000453234,0.0006347911,0.1229501,0.01622714,0.09499764,0.01835789,0.736468],"study_design_scores_gemma":[0.0001567921,0.0002346851,0.0006351357,0.00004014893,0.0001294199,0.0003037894,0.0001316715,0.9117404,0.007089869,0.07422519,0.005248757,0.0000641134],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02914557,0.0003600812,0.962926,0.0008922006,0.0001528082,0.0004154074,0.0001318434,0.001128389,0.00484771],"genre_scores_gemma":[0.431301,0.0002165176,0.5553299,0.0008729829,0.0003431324,0.0008674318,0.0004900144,0.0006837695,0.009895335],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0109792,"threshold_uncertainty_score":0.05806428,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2186489521","doi":"","title":"Unsupervised and Transfer Learning Challenge: a Deep Learning Approach","year":2011,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":147,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Transfer of learning; Artificial intelligence; Computer science; Unsupervised learning; Machine learning; Deep learning; Classifier (UML); Competitive learning; Semi-supervised learning; Task (project management)","authors":[{"name":"Grégoire Mesnil","is_ca":true},{"name":"Yann Dauphin","is_ca":true},{"name":"Xavier Glorot","is_ca":true},{"name":"Salah Rifai","is_ca":true},{"name":"Yoshua Bengio","is_ca":true},{"name":"Ian Goodfellow","is_ca":true},{"name":"Erick Lavoie","is_ca":true},{"name":"Xavier Muller","is_ca":true},{"name":"Guillaume Desjardins","is_ca":true},{"name":"David Warde-Farley","is_ca":true},{"name":"Pascal Vincent","is_ca":true},{"name":"Aaron Courville","is_ca":true},{"name":"James Bergstra","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0682199232260771,"gpt":0.275857866333464,"spread":0.2076379431073869,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007351813,0.00160286,0.00192075,0.001036175,0.001229522,0.002454197,0.004127303,0.005211365,0.001892246],"category_scores_gemma":[0.0162389,0.0006088496,0.001348186,0.001564818,0.002716885,0.005175709,0.004565401,0.007827694,0.0007030549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001883187,"about_ca_system_score_gemma":0.002376356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003113645,"about_ca_topic_score_gemma":0.003404893,"domain_scores_codex":[0.9960707,0.001607553,0.00016949,0.0009456675,0.0009667077,0.000239973],"domain_scores_gemma":[0.9908798,0.005359355,0.0003098494,0.001718011,0.001252474,0.0004805777],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004813469,0.000752744,0.00472146,0.0007123381,0.0003831723,0.0004372807,0.0006209317,0.1661556,0.006940723,0.1606938,0.08485372,0.5732468],"study_design_scores_gemma":[0.00005247274,0.0001347994,0.001160666,0.00005648631,0.00002474236,0.0001672135,0.000169355,0.6961474,0.004327734,0.281808,0.01590117,0.00004997128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0216308,0.002083413,0.9548503,0.01397996,0.0004703874,0.0002225573,0.001023204,0.001042022,0.004697385],"genre_scores_gemma":[0.4195784,0.002147623,0.5539837,0.004117147,0.001801099,0.0009587276,0.00383928,0.0004700864,0.0131039],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007351813,"threshold_uncertainty_score":0.03888059,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2490023472","doi":"10.5555/2946645.3007063","title":"Are random forests truly the best classifiers","year":2016,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":135,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Genomics; University of Toronto","funders":"","keywords":"Random forest; Support vector machine; Random subspace method; Artificial intelligence; Machine learning; Computer science; Classifier (UML); Artificial neural network; Pattern recognition (psychology); Data mining","authors":[{"name":"Michael Wainberg","is_ca":true},{"name":"Babak Alipanahi","is_ca":true},{"name":"Brendan J. Frey","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08091568562646898,"gpt":0.3714797027783613,"spread":0.2905640171518924,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03270388,0.001205931,0.002318471,0.002235428,0.001737315,0.004935264,0.001475485,0.003191055,0.003539073],"category_scores_gemma":[0.11923,0.0006850528,0.001888322,0.002084875,0.001768812,0.0113095,0.000942665,0.003905374,0.004586917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001288601,"about_ca_system_score_gemma":0.001919494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001874938,"about_ca_topic_score_gemma":0.004684045,"domain_scores_codex":[0.9757118,0.01324609,0.001250231,0.003669101,0.005083793,0.001038938],"domain_scores_gemma":[0.9380649,0.04065282,0.002592866,0.009441436,0.007903337,0.00134456],"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":[0.003006274,0.0003892775,0.05076744,0.001445883,0.001752232,0.0002793353,0.0008955449,0.02337026,0.002425702,0.05884807,0.2144305,0.6423895],"study_design_scores_gemma":[0.0008417536,0.001499274,0.02816766,0.002883185,0.001512446,0.00132608,0.002694088,0.1482531,0.01326493,0.6103843,0.1888004,0.0003726654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.281067,0.08437066,0.4143722,0.1153967,0.01006159,0.0004583756,0.01415788,0.004089523,0.07602616],"genre_scores_gemma":[0.8290455,0.007614397,0.1310744,0.01401012,0.003328765,0.0002668266,0.006613622,0.001328157,0.006718055],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03270388,"threshold_uncertainty_score":0.1729568,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3146200671","doi":"10.1109/iccit.2007.4420473","title":"Investigating the Performance of Naive- Bayes Classifiers and K- Nearest Neighbor Classifiers","year":2007,"lang":"en","type":"article","venue":"2007 International Conference on Convergence Information Technology (ICCIT 2007)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":126,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"","keywords":"Naive Bayes classifier; Artificial intelligence; k-nearest neighbors algorithm; Computer science; Bayes error rate; Machine learning; Classifier (UML); Bayes classifier; Pattern recognition (psychology); Random subspace method; Bayesian probability; Bayes' theorem; Data mining; Support vector machine","authors":[{"name":"Mohammed Jahirul Islam","is_ca":true},{"name":"Q. M. Jonathan Wu","is_ca":true},{"name":"Majid Ahmadi","is_ca":true},{"name":"M.A. Sid-Ahmed","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02361376314223779,"gpt":0.2723399187404118,"spread":0.248726155598174,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02529873,0.001721731,0.002490754,0.004416841,0.001910139,0.003924645,0.001969807,0.002868794,0.001942975],"category_scores_gemma":[0.1014981,0.0006384532,0.001171691,0.003288578,0.001271853,0.0075209,0.001042202,0.001648775,0.001260272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002840949,"about_ca_system_score_gemma":0.002247396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01466184,"about_ca_topic_score_gemma":0.0117313,"domain_scores_codex":[0.9717779,0.00922172,0.002028905,0.003479799,0.01256224,0.000929488],"domain_scores_gemma":[0.9166707,0.06020813,0.002845148,0.003679312,0.01587223,0.0007245174],"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":[0.002682743,0.0006956996,0.04053821,0.00125658,0.0009666167,0.0002252029,0.0008841181,0.2255046,0.002508153,0.02420464,0.01275031,0.6877831],"study_design_scores_gemma":[0.00008448183,0.0007176748,0.009430393,0.0001843656,0.0001923057,0.0002499676,0.0005297582,0.9598077,0.003200358,0.02055613,0.004921972,0.0001249202],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.404068,0.02989454,0.5219258,0.003411538,0.002095178,0.001080956,0.001785187,0.00249506,0.03324367],"genre_scores_gemma":[0.7796537,0.00323768,0.2107958,0.0004261406,0.0004733659,0.0002529971,0.001486866,0.0002163415,0.003457246],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02529873,"threshold_uncertainty_score":0.1337941,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2113635748","doi":"","title":"Quickly Boosting Decision Trees - Pruning Underachieving Features Early","year":2013,"lang":"en","type":"article","venue":"CaltechAUTHORS (California Institute of Technology)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":123,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Army Research Office; Natural Sciences and Engineering Research Council of Canada; Office of Naval Research; Multidisciplinary University Research Initiative; Gordon and Betty Moore Foundation; National Aeronautics and Space Administration","keywords":"Boosting (machine learning); Computer science; Exploit; Machine learning; Artificial intelligence; Decision tree; Gradient boosting; Pruning; Classifier (UML); Training set; Random forest","authors":[{"name":"Ron D. Appel","is_ca":false},{"name":"Thomas J. Fuchs","is_ca":false},{"name":"Piotr Dollár","is_ca":false},{"name":"Pietro Perona","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01134313802980673,"gpt":0.2474545042656787,"spread":0.236111366235872,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005843605,0.001254486,0.002443466,0.001055864,0.0007764787,0.001296227,0.001733808,0.001546422,0.002126242],"category_scores_gemma":[0.0219975,0.0007709184,0.001040686,0.001191538,0.0008807665,0.002018762,0.001787146,0.002545093,0.001487827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005955987,"about_ca_system_score_gemma":0.001406443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001453294,"about_ca_topic_score_gemma":0.002084586,"domain_scores_codex":[0.9967173,0.001220618,0.0001496288,0.0003409119,0.001178609,0.0003930515],"domain_scores_gemma":[0.9893589,0.006601408,0.0004434226,0.00149305,0.001806262,0.0002968613],"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":[0.0008600804,0.0003512521,0.007500792,0.0003079185,0.000164034,0.0004265742,0.0003458266,0.2824166,0.02872876,0.0331948,0.01369293,0.6320104],"study_design_scores_gemma":[0.00006340617,0.0001545014,0.000730326,0.00004313559,0.00004371617,0.0001992191,0.00002416994,0.9555122,0.009807078,0.0288264,0.004579436,0.00001646391],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03243421,0.0008544754,0.963203,0.000312834,0.0001550118,0.0001307847,0.00005650617,0.001179783,0.001673432],"genre_scores_gemma":[0.4144006,0.0004042531,0.5801194,0.0005261321,0.0002654262,0.0002571388,0.0003966938,0.0003479267,0.003282398],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005843605,"threshold_uncertainty_score":0.03090435,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2164092299","doi":"10.1287/opre.1060.0360","title":"Classification and Regression via Integer Optimization","year":2007,"lang":"en","type":"article","venue":"Operations Research","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":116,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Integer (computer science); Regression; Integer programming; Regression analysis; Computer science; Optimization problem; Mathematics; Mathematical optimization; Data mining; Artificial intelligence; Statistics; Machine learning","authors":[{"name":"Dimitris Bertsimas","is_ca":false},{"name":"Romy Shioda","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08721332552102332,"gpt":0.419794869743731,"spread":0.3325815442227077,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005159746,0.001915054,0.00200739,0.001915286,0.0006910675,0.003427498,0.001310788,0.001205739,0.004927121],"category_scores_gemma":[0.01604348,0.0006905707,0.001565696,0.002837959,0.00157866,0.002751569,0.002011555,0.003000261,0.001673136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001170108,"about_ca_system_score_gemma":0.001647299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001847592,"about_ca_topic_score_gemma":0.001509577,"domain_scores_codex":[0.9960611,0.002192551,0.0002184756,0.0006251088,0.0006956701,0.000206974],"domain_scores_gemma":[0.992749,0.005630966,0.0006063614,0.0004330316,0.0004552894,0.0001253407],"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":[0.0001283675,0.00009543295,0.00123009,0.0002674632,0.0001046786,0.00009494447,0.00008256853,0.6717206,0.001009657,0.1524097,0.006091412,0.1667651],"study_design_scores_gemma":[0.00001006267,0.00001532792,0.00008249745,0.00001681213,0.000007311737,0.00001686515,0.00000971638,0.9378298,0.0002719972,0.05974868,0.001984278,0.000006704651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001644767,0.0003079804,0.9958902,0.0003283115,0.00005222837,0.00003400432,0.00008408866,0.0001895504,0.001468859],"genre_scores_gemma":[0.09499459,0.0009385675,0.8988137,0.0003768214,0.0003265574,0.0005953587,0.0006566748,0.0002908589,0.003006838],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005159746,"threshold_uncertainty_score":0.02728772,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2296059279","doi":"10.1609/aaai.v29i1.9375","title":"Efficient Benchmarking of Hyperparameter Optimizers via Surrogates","year":2015,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":113,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Deutsche Forschungsgemeinschaft","keywords":"Hyperparameter; Hyperparameter optimization; Machine learning; Computer science; Artificial intelligence; Benchmarking; Regression; Algorithm; Support vector machine; Mathematics; Statistics","authors":[{"name":"Katharina Eggensperger","is_ca":false},{"name":"Frank Hutter","is_ca":false},{"name":"Holger H. Hoos","is_ca":true},{"name":"Kevin Leyton‐Brown","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09360323200453574,"gpt":0.298169570383572,"spread":0.2045663383790363,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007550742,0.001992469,0.001544704,0.001649624,0.0005557712,0.002391089,0.00187154,0.002274132,0.002511709],"category_scores_gemma":[0.03503464,0.0006933365,0.001122291,0.001602403,0.001220081,0.002230847,0.00161563,0.002827196,0.001217901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001234834,"about_ca_system_score_gemma":0.001516987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002554331,"about_ca_topic_score_gemma":0.002316374,"domain_scores_codex":[0.9950994,0.002558748,0.0003101296,0.0004800984,0.001227773,0.0003239263],"domain_scores_gemma":[0.9857498,0.008414847,0.0009686523,0.002727645,0.001845439,0.0002936151],"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":[0.0001965116,0.0001599785,0.002062761,0.0001665968,0.00008428016,0.00005682919,0.00005013017,0.9612257,0.002003234,0.006006783,0.002724118,0.02526314],"study_design_scores_gemma":[0.00002432506,0.00008252126,0.000298037,0.00002728276,0.000007747015,0.00001955772,0.00001915506,0.9938582,0.002016922,0.002895504,0.0007394736,0.00001128898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3088906,0.002781274,0.6650389,0.001136689,0.0003866644,0.0003437468,0.00128062,0.006805492,0.01333605],"genre_scores_gemma":[0.8188611,0.0005197177,0.1752019,0.0002639127,0.00004719876,0.0004545426,0.002118949,0.0009624045,0.001570255],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007550742,"threshold_uncertainty_score":0.03993267,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2029320154","doi":"10.1007/s10732-014-9275-9","title":"Analysing differences between algorithm configurations through ablation","year":2015,"lang":"en","type":"article","venue":"Journal of Heuristics","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":113,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Compute Canada","keywords":"Computer science; Satisfiability; Algorithm; Integer programming","authors":[{"name":"Chris Fawcett","is_ca":true},{"name":"Holger H. Hoos","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08233675307823943,"gpt":0.3237777667160881,"spread":0.2414410136378487,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009226498,0.0006590858,0.0009569346,0.002246433,0.0007954164,0.002417388,0.001559588,0.001768355,0.002231169],"category_scores_gemma":[0.0975994,0.0005488398,0.0008757259,0.002212462,0.00118491,0.003060679,0.001335358,0.002404973,0.0006087402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009523596,"about_ca_system_score_gemma":0.0013022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009357745,"about_ca_topic_score_gemma":0.001038085,"domain_scores_codex":[0.9901068,0.004938975,0.0007742854,0.001232887,0.002217947,0.000729213],"domain_scores_gemma":[0.8483396,0.1301717,0.002692352,0.01138432,0.00646962,0.000942403],"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":[0.007971299,0.002116025,0.07362862,0.001001753,0.001274613,0.0008064486,0.002032962,0.3701016,0.04992733,0.01507995,0.007313864,0.4687456],"study_design_scores_gemma":[0.0003904152,0.001747261,0.01915685,0.00009658874,0.0004979477,0.0006475787,0.0007816268,0.9198545,0.0270957,0.02663872,0.002986689,0.0001061674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9222093,0.0005531128,0.07079773,0.0003179789,0.0001296684,0.0001137295,0.0003116367,0.001607788,0.003959046],"genre_scores_gemma":[0.9524529,0.0000719681,0.04559127,0.00006938042,0.00001783901,0.0001024942,0.0005875677,0.0006048519,0.0005017896],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009226498,"threshold_uncertainty_score":0.04879498,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1589919686","doi":"","title":"Does Unlabeled Data Provably Help? Worst-case Analysis of the Sample Complexity of Semi-Supervised Learning.","year":2008,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Sample complexity; Computer science; Semi-supervised learning; Homogeneous; Distribution (mathematics); Artificial intelligence; Conjecture; Sample (material); Class (philosophy); Labeled data; Supervised learning; Machine learning; Pattern recognition (psychology); Mathematics; Artificial neural network; Discrete mathematics; Combinatorics","authors":[{"name":"Shai Ben-David","is_ca":true},{"name":"Tyler Lu","is_ca":true},{"name":"Dávid Pál","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1094726326608954,"gpt":0.3005835196592879,"spread":0.1911108869983926,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04909202,0.002055194,0.003230908,0.001854699,0.002274829,0.006628438,0.004759783,0.004406094,0.005380261],"category_scores_gemma":[0.2437087,0.001662931,0.002425974,0.002347252,0.006966659,0.01762641,0.006678529,0.008449861,0.0006740681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005287651,"about_ca_system_score_gemma":0.003938376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001770247,"about_ca_topic_score_gemma":0.002176097,"domain_scores_codex":[0.9686936,0.02026018,0.001149181,0.003399631,0.004714407,0.001783043],"domain_scores_gemma":[0.5536621,0.4099721,0.008232041,0.01941536,0.00544474,0.003273695],"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":[0.002027699,0.0005622571,0.01044493,0.0009811625,0.0006080166,0.000640019,0.0008329389,0.4680459,0.002348514,0.4380042,0.01347208,0.06203231],"study_design_scores_gemma":[0.00007958779,0.000131083,0.0005890534,0.00006714119,0.00005694027,0.0001891417,0.00009221874,0.6213314,0.001031848,0.3752761,0.001127078,0.00002841321],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07923751,0.002680105,0.8899365,0.01374921,0.0002869549,0.0003119658,0.00108923,0.0006963228,0.01201226],"genre_scores_gemma":[0.7826052,0.001618824,0.2047564,0.002528409,0.001282519,0.0008575924,0.001588077,0.0005946105,0.004168412],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04909202,"threshold_uncertainty_score":0.2596266,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2914110112","doi":"10.1016/j.patrec.2019.02.009","title":"A new hyperparameters optimization method for convolutional neural networks","year":2019,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":105,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Key Research and Development Program of China; Canadian Institute for Advanced Research","keywords":"Hyperparameter; Hyperparameter optimization; Bayesian optimization; Computer science; Convolutional neural network; Gaussian process; Artificial intelligence; Artificial neural network; Machine learning; Gaussian; Algorithm; Support vector machine","authors":[{"name":"Hua Cui","is_ca":false},{"name":"Jie Bai","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02314881426054435,"gpt":0.2654592914709404,"spread":0.2423104772103961,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001523832,0.001714641,0.001236345,0.0008549592,0.0005121019,0.001172182,0.001967412,0.002065552,0.004370734],"category_scores_gemma":[0.003717768,0.001184529,0.001180583,0.0008956942,0.0006439884,0.001708525,0.001530496,0.00285229,0.001921864],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001041756,"about_ca_system_score_gemma":0.001428242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005933094,"about_ca_topic_score_gemma":0.008907994,"domain_scores_codex":[0.9993194,0.0002303647,0.00004975557,0.0001492417,0.000197129,0.00005396489],"domain_scores_gemma":[0.9992958,0.0003203814,0.00005399558,0.00008690646,0.000204564,0.00003836181],"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":[0.0001714822,0.00009601392,0.0005326255,0.0001539626,0.0002250702,0.00008263619,0.00007843216,0.5779356,0.01314343,0.01753833,0.008992095,0.3810503],"study_design_scores_gemma":[0.00001701384,0.00001426501,0.00007055175,0.00001495021,0.00001681004,0.00001904219,0.000003984036,0.9918481,0.00165863,0.004406101,0.001920784,0.000009656952],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001492423,0.00022496,0.9968946,0.0000800259,0.00005191418,0.00002422687,0.00003395731,0.0005212982,0.0006764996],"genre_scores_gemma":[0.06920583,0.0003957326,0.9193346,0.000289888,0.0001736321,0.0003451779,0.0003512325,0.001167116,0.008736875],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005933094,"threshold_uncertainty_score":0.0146215,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3121928352","doi":"","title":"Get Another Label? Improving Data Quality and Data Mining Using Multiple, Noisy Labelers","year":2008,"lang":"en","type":"article","venue":"The Faculty Digital Archive (New York University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Computer science; Quality (philosophy); Sequence labeling; Set (abstract data type); Imperfect; Crowdsourcing; Artificial intelligence; Focus (optics); Outsourcing; Machine learning; Data quality; Data mining; Task (project management); Engineering; Operations management","authors":[{"name":"Victor S. Sheng","is_ca":false},{"name":"Foster Provost","is_ca":false},{"name":"Panagiotis G. Ipeirotis","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2440212770188994,"gpt":0.3130783756742693,"spread":0.06905709865536985,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05628715,0.001906095,0.003796659,0.002852007,0.003051088,0.0061131,0.005679002,0.005722686,0.001955241],"category_scores_gemma":[0.20369,0.00185468,0.002314649,0.00408371,0.00648598,0.0169351,0.00849425,0.00672916,0.001585853],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003267481,"about_ca_system_score_gemma":0.003679196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004048896,"about_ca_topic_score_gemma":0.005459627,"domain_scores_codex":[0.9503537,0.02573116,0.002402801,0.01028016,0.009889651,0.001342535],"domain_scores_gemma":[0.7609167,0.146386,0.01547831,0.05950804,0.01537152,0.002339518],"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":[0.003302162,0.001344522,0.05830147,0.002085162,0.001303989,0.000647222,0.00639865,0.1422854,0.02625489,0.0629131,0.01593962,0.6792238],"study_design_scores_gemma":[0.0003426763,0.0008195458,0.01019877,0.0004823944,0.0003879555,0.0008330804,0.001612748,0.6743777,0.0377869,0.2540003,0.01886679,0.000291116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05133817,0.001379395,0.9385371,0.004875813,0.000134682,0.0001687281,0.0003282013,0.001922385,0.001315541],"genre_scores_gemma":[0.364316,0.0005151551,0.6300961,0.001499507,0.000273666,0.0002869751,0.0008910986,0.0006470364,0.001474542],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05628715,"threshold_uncertainty_score":0.2976785,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2125592902","doi":"10.1613/jair.1509","title":"Learning From Labeled And Unlabeled Data: An Empirical Study Across Techniques And Domains","year":2005,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Labeled data; Semi-supervised learning; Relevance (law); Independence (probability theory); Selection (genetic algorithm); Empirical research; Bivariate analysis; Process (computing); Selection bias","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.2839496994906822,"gpt":0.524008033142466,"spread":0.2400583336517838,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07462388,0.001142854,0.001248782,0.006404977,0.002042362,0.003164663,0.002321455,0.002626695,0.001118234],"category_scores_gemma":[0.3005234,0.0006709936,0.001561848,0.007555592,0.004770027,0.007988516,0.003250567,0.003153588,0.0006037896],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001657993,"about_ca_system_score_gemma":0.001018512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001996029,"about_ca_topic_score_gemma":0.003070139,"domain_scores_codex":[0.9021531,0.07004455,0.004660438,0.007672345,0.01459388,0.0008755882],"domain_scores_gemma":[0.3241137,0.6103453,0.01903173,0.02687059,0.01784821,0.0017905],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002064988,0.002729457,0.4093144,0.003875118,0.002519568,0.0004555163,0.006322849,0.05768108,0.00202441,0.01907527,0.01400519,0.4799322],"study_design_scores_gemma":[0.0006475797,0.005757357,0.4448055,0.006130484,0.002020629,0.006773097,0.02326671,0.3372336,0.01271522,0.08543523,0.07455759,0.0006569715],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8431463,0.02452665,0.1109241,0.003438853,0.0002914163,0.0008704404,0.001518103,0.0003439657,0.01494016],"genre_scores_gemma":[0.9196181,0.006358972,0.06752194,0.0008059692,0.0002885,0.0004767551,0.003426344,0.0002463437,0.001257105],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07462388,"threshold_uncertainty_score":0.3946535,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4211173503","doi":"10.1515/9783110629453-084","title":"84 Automated machine learning","year":2020,"lang":"en","type":"book-chapter","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":96,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Centre National de la Recherche Scientifique; BrainLinks-BrainTools; Eidgenössische Technische Hochschule Zürich; Deutsche Forschungsgemeinschaft; Institut national de recherche en informatique et en automatique (INRIA); Generalitat de Catalunya; Natural Sciences and Engineering Research Council of Canada; European Commission; Centres de Recerca de Catalunya","keywords":"Computer science; Artificial intelligence","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.02329552522663692,"gpt":0.2429454570042957,"spread":0.2196499317776588,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008728132,0.001263404,0.0007890392,0.002148252,0.000814023,0.003943303,0.001288932,0.001214641,0.06290522],"category_scores_gemma":[0.002555858,0.0007032178,0.0008910801,0.002570945,0.001426062,0.003683132,0.00189246,0.0023153,0.05695007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001499675,"about_ca_system_score_gemma":0.001203522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000987943,"about_ca_topic_score_gemma":0.00150021,"domain_scores_codex":[0.9989441,0.000172426,0.00005629953,0.0002104694,0.0005587668,0.00005794227],"domain_scores_gemma":[0.9991442,0.0003954573,0.00002862153,0.0001829757,0.0002090954,0.00003962142],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001901861,0.00003926982,0.000253092,0.000488259,0.00002536878,0.00005364821,0.0001126207,0.002396533,0.0008307372,0.1187758,0.3918695,0.4851361],"study_design_scores_gemma":[0.000003779136,0.00001177015,0.0003948954,0.0002452009,0.000005757095,0.0001801657,0.00003660963,0.003779999,0.0005585313,0.08428126,0.9104871,0.00001498566],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.001569485,0.07714096,0.2266678,0.005864151,0.004771981,0.0002675671,0.002091543,0.004398038,0.6772284],"genre_scores_gemma":[0.02279544,0.0542586,0.152122,0.00271104,0.003900632,0.0004489221,0.006198792,0.001549629,0.7560149],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.06290522,"threshold_uncertainty_score":0.2104389,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2949431720","doi":"10.48550/arxiv.1208.3719","title":"Auto-WEKA: Combined Selection and Hyperparameter Optimization of Classification Algorithms","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Hyperparameter; Machine learning; Computer science; Hyperparameter optimization; MNIST database; Artificial intelligence; Bayesian optimization; Feature selection; Classifier (UML); Selection (genetic algorithm); Data mining; Artificial neural network; Support vector machine","authors":[{"name":"Chris Thornton","is_ca":true},{"name":"Frank Hutter","is_ca":true},{"name":"Holger H. Hoos","is_ca":true},{"name":"Kevin Leyton‐Brown","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07618852931793457,"gpt":0.2056777942802454,"spread":0.1294892649623109,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006836981,0.002882346,0.002345481,0.004210179,0.0010164,0.002697292,0.003566801,0.002462036,0.00257364],"category_scores_gemma":[0.02274685,0.001677889,0.00256418,0.00333645,0.001133373,0.004164049,0.002634722,0.003778839,0.002532943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001103709,"about_ca_system_score_gemma":0.002559384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003598335,"about_ca_topic_score_gemma":0.006184702,"domain_scores_codex":[0.9921852,0.004292191,0.0005594069,0.001089441,0.001481801,0.0003919935],"domain_scores_gemma":[0.9894966,0.006345101,0.000635116,0.002137338,0.001227431,0.0001584415],"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":[0.0003460154,0.0003534714,0.004002353,0.000362378,0.000809907,0.0001300485,0.0002148423,0.4065019,0.006700126,0.01041023,0.01920761,0.5509611],"study_design_scores_gemma":[0.00007420482,0.00005104319,0.0004196563,0.00003467041,0.00007462658,0.00006025864,0.0000317907,0.9789146,0.003976841,0.01276597,0.003558087,0.00003831985],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007522053,0.0004976325,0.9807993,0.0001983552,0.00005829459,0.0001276997,0.000129626,0.009744068,0.0009229383],"genre_scores_gemma":[0.1304903,0.0003496118,0.8645813,0.0002821184,0.00009969457,0.0007275433,0.0005756029,0.001657225,0.001236549],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006836981,"threshold_uncertainty_score":0.03615785,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2475602767","doi":"10.25080/majora-8b375195-004","title":"SkData: Data Sets and Algorithm Evaluation Protocols in Python","year":2013,"lang":"en","type":"article","venue":"Proceedings of the Python in Science Conferences","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Rowland Institute at Harvard; National Science Foundation","keywords":"Python (programming language); Computer science; Upload; Parsing; Benchmark (surveying); Scripting language; Algorithm; Set (abstract data type); Data mining; Data set; Programming language; Theoretical computer science; Information retrieval; Artificial intelligence; World Wide Web","authors":[{"name":"James Bergstra","is_ca":true},{"name":"Nicolas Pinto","is_ca":false},{"name":"D. J. Cox","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08828722234852654,"gpt":0.368364488690674,"spread":0.2800772663421474,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01204317,0.002803002,0.0018368,0.003372203,0.001798396,0.005701167,0.007386613,0.001549796,0.03932123],"category_scores_gemma":[0.04506695,0.00313847,0.002394933,0.003696571,0.002701435,0.01106906,0.009613873,0.006929241,0.03459992],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003086228,"about_ca_system_score_gemma":0.006665038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00541607,"about_ca_topic_score_gemma":0.004739375,"domain_scores_codex":[0.9867578,0.002868147,0.002638637,0.001802271,0.005111709,0.0008212921],"domain_scores_gemma":[0.975369,0.008780937,0.00124877,0.009666024,0.004108401,0.0008268447],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001787814,0.0006505305,0.00485898,0.001852832,0.0002853379,0.0003061882,0.001063129,0.01586829,0.005545378,0.03811789,0.7944457,0.1352178],"study_design_scores_gemma":[0.0009805107,0.0002506562,0.005718524,0.0005899467,0.0001215021,0.0005059029,0.0004340457,0.1675767,0.06547202,0.1815248,0.5762596,0.0005658076],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"software","genre_scores_codex":[0.003690532,0.0001359772,0.2932478,0.0007814231,0.0002013315,0.001114657,0.05479307,0.6374072,0.008627973],"genre_scores_gemma":[0.08195586,0.0004482093,0.4053994,0.002436567,0.0001731527,0.01361278,0.2168271,0.2655804,0.01356636],"genre_candidate":"software","genre_consensus":"software","teacher_disagreement_score":0.03932123,"threshold_uncertainty_score":0.1315426,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2092353981","doi":"10.1007/s10044-003-0191-0","title":"A brief taxonomy and ranking of creative prototype reduction schemes","year":2003,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; sort; Ranking (information retrieval); Reduction (mathematics); Taxonomy (biology); Set (abstract data type); Data reduction; Artificial intelligence; Class (philosophy); Machine learning; Data mining; Pattern recognition (psychology); Information retrieval; Mathematics","authors":[{"name":"Seo-Yi Kim","is_ca":false},{"name":"B. John Oommen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02025541410322381,"gpt":0.2641137965063549,"spread":0.2438583824031311,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004207567,0.0009526369,0.001336762,0.009041207,0.001933472,0.005862389,0.002626961,0.00142493,0.01396178],"category_scores_gemma":[0.0197023,0.0005262443,0.001065235,0.008858811,0.002034245,0.005317671,0.001643392,0.001725082,0.004143994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001398787,"about_ca_system_score_gemma":0.002004855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001174523,"about_ca_topic_score_gemma":0.001553976,"domain_scores_codex":[0.9946446,0.001229131,0.0007492174,0.0005417593,0.002488447,0.0003468369],"domain_scores_gemma":[0.9889507,0.004419823,0.000990995,0.002125573,0.003116424,0.0003964545],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002520577,0.0002717822,0.002878412,0.001119155,0.00005400884,0.0000841385,0.0003592822,0.00593043,0.005015207,0.169904,0.01311404,0.8010176],"study_design_scores_gemma":[0.0002201929,0.001732029,0.009150252,0.00102835,0.000269865,0.002043131,0.001321882,0.1337457,0.02071448,0.6511027,0.1784001,0.0002713939],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03690996,0.0123612,0.8981025,0.001938581,0.0005252264,0.001515262,0.001711919,0.002738992,0.04419634],"genre_scores_gemma":[0.127306,0.005358188,0.8522362,0.0002325268,0.0002688451,0.0007313204,0.002148558,0.0002542075,0.01146433],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01396178,"threshold_uncertainty_score":0.04670674,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385248297","doi":"10.1145/3571724","title":"The Principles of Data-Centric AI","year":2023,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; TRACE (psycholinguistics); Data science; Philosophy","authors":[{"name":"Mohammad Hossein Jarrahi","is_ca":false},{"name":"Ali Memariani","is_ca":false},{"name":"Shion Guha","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1798954497282311,"gpt":0.3795690690161228,"spread":0.1996736192878917,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0108238,0.0009551484,0.001063297,0.003499368,0.002392616,0.01069806,0.003768305,0.002533977,0.006571941],"category_scores_gemma":[0.02042694,0.0008742764,0.001386358,0.00408256,0.01908518,0.01532885,0.007075816,0.00859076,0.002710153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003725505,"about_ca_system_score_gemma":0.006582365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0047608,"about_ca_topic_score_gemma":0.004010417,"domain_scores_codex":[0.9917548,0.003130665,0.0007021301,0.001613902,0.002361729,0.0004368003],"domain_scores_gemma":[0.9781148,0.01074009,0.0007251545,0.006801172,0.002742471,0.0008763094],"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":[0.000008846389,0.000009665869,0.0001095618,0.00007914467,0.00001142413,0.00001719334,0.0002658375,0.0007836336,0.0001197148,0.9856941,0.002061233,0.01083963],"study_design_scores_gemma":[0.00001001236,0.00001135842,0.00005156895,0.00008241818,0.00000886351,0.0000541195,0.00009920363,0.00358275,0.0003643818,0.9545491,0.04117417,0.00001198397],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002150154,0.00442108,0.8924848,0.01543002,0.0006648221,0.0001823769,0.0003053536,0.0005433722,0.08381796],"genre_scores_gemma":[0.278686,0.007210135,0.6804308,0.007092627,0.001696615,0.001061223,0.0007585994,0.0004829476,0.02258112],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0108238,"threshold_uncertainty_score":0.05724239,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}