{"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"},"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)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002980291,0.0000863981,0.0000926068,0.00003306788,0.000103777,0.0001889761,0.0005670101,0.0000321088,0.0000573143],"category_scores_gemma":[0.00014348,0.00007179914,0.00003014185,0.0001719851,0.000006499203,0.0002028279,0.0002782075,0.0001192241,0.0001167119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001481501,"about_ca_system_score_gemma":0.000005036547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000516352,"about_ca_topic_score_gemma":0.00005901926,"domain_scores_codex":[0.9990335,0.0001120705,0.0001566984,0.0003504219,0.0001478461,0.0001994529],"domain_scores_gemma":[0.9990153,0.0001670671,0.00005534033,0.0006269014,0.00002303371,0.0001123471],"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":[0.000004311024,0.00006573375,0.01051816,0.000003380788,0.000008493594,0.000001086965,0.0003257093,0.02089405,0.0003754538,0.08239655,0.007722992,0.8776841],"study_design_scores_gemma":[0.00007222479,0.00003916358,0.0207656,0.000003790213,0.000001777834,5.435102e-7,0.000006650748,0.9529493,0.00009504422,0.001186239,0.02478058,0.00009910815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04197765,0.00001071321,0.9524139,0.002232736,0.0002118633,0.0000717718,0.00000112539,0.0002305503,0.002849664],"genre_scores_gemma":[0.9660603,7.278398e-7,0.03189301,0.00147494,0.000212245,0.000006763363,0.00002661227,0.000005927012,0.0003194066],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9320552,"threshold_uncertainty_score":0.2927884,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001228121,0.00005142665,0.00005133785,0.00003972058,0.0001058672,0.00003262252,0.0007436085,0.00001870207,0.0000641056],"category_scores_gemma":[0.00009280381,0.00003182023,0.00002509603,0.0001421519,0.00003773272,0.0001711762,0.0001525941,0.0001642974,0.00002695831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001041427,"about_ca_system_score_gemma":0.00002140453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003996149,"about_ca_topic_score_gemma":0.000002034837,"domain_scores_codex":[0.9994281,0.0000121371,0.0001041151,0.0001553771,0.0002330833,0.00006718525],"domain_scores_gemma":[0.999646,0.00001307155,0.000096027,0.0001297673,0.00009512779,0.00002002256],"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":[0.000003912711,0.00003506115,0.04961115,0.000003005371,0.000004596872,2.674352e-7,0.0003592056,0.00004378965,0.002855791,0.9420904,0.0009901052,0.004002699],"study_design_scores_gemma":[0.0002146821,0.00007085153,0.1252935,0.00001983744,0.000001383044,0.00002597398,0.00003614451,0.8545552,0.00349582,0.0006476269,0.01554714,0.00009187099],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.22633,0.00001514456,0.05112806,0.01229279,0.000475425,0.0001662339,0.000003468231,0.0003199859,0.7092689],"genre_scores_gemma":[0.9893543,0.00001931917,0.004448866,0.0001527013,0.00002083868,0.000002352961,0.00000268162,0.000002341291,0.005996609],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9414428,"threshold_uncertainty_score":0.1381822,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000477714,0.0003068577,0.0002656043,0.00007290439,0.000331018,0.0003971389,0.002301281,0.0002283882,0.00001068503],"category_scores_gemma":[0.00004120913,0.0002227172,0.000127955,0.00001860897,0.00009457339,0.00009682404,0.0006122176,0.001126079,0.0001372754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006220192,"about_ca_system_score_gemma":0.0001437172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002144382,"about_ca_topic_score_gemma":0.00001129259,"domain_scores_codex":[0.9981259,0.0002747699,0.0003048638,0.0005548203,0.0004312311,0.000308445],"domain_scores_gemma":[0.9978231,0.000242564,0.0002812413,0.001522402,0.00006884526,0.00006182351],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001101477,0.00002298664,0.00001090563,0.0001430828,0.0001034633,0.00002181999,0.001306182,0.0009333083,0.0001216556,0.4201052,0.3855999,0.1916205],"study_design_scores_gemma":[0.0001394112,0.00002669115,0.00003722912,0.00007406889,0.00003674103,0.00001026847,0.000001349256,0.02710282,0.00004761717,0.00287465,0.9693801,0.0002690331],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.000003568143,0.0005487378,0.06157424,0.0001772744,0.0002211557,0.0002439089,0.000008017809,0.000511959,0.9367111],"genre_scores_gemma":[0.00062358,0.00001241449,0.0009012023,0.0001673128,0.00041565,0.0000390378,0.000138827,0.00004184061,0.9976602],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.5837802,"threshold_uncertainty_score":0.9082143,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006468482,0.00009394666,0.0001153239,0.00005149522,0.0001138102,0.00008524409,0.0002497442,0.00002957093,0.000004107045],"category_scores_gemma":[0.003425969,0.00008774039,0.00002148426,0.0002401763,0.00002268098,0.0002721931,0.0001915581,0.0002782485,0.000007518759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004703759,"about_ca_system_score_gemma":0.00001218736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005617446,"about_ca_topic_score_gemma":3.489929e-8,"domain_scores_codex":[0.9985576,0.000627737,0.0001874094,0.0003426117,0.0001713379,0.0001132791],"domain_scores_gemma":[0.9975276,0.001976226,0.0002049294,0.0001739212,0.00005341085,0.00006390102],"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":[0.00009135167,0.00006156471,0.0004458441,0.00004644527,0.00001487613,0.00001038582,0.001867765,0.5596306,0.001325334,0.05943406,0.00005476355,0.377017],"study_design_scores_gemma":[0.0001961968,0.0002218119,0.0003597135,0.00001271919,0.000006404682,0.00002053635,0.00002866672,0.9968038,0.000175954,0.0001408491,0.001954377,0.00007901464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005179388,0.00006481799,0.9899376,0.002878486,0.00005346368,0.00008036472,6.998654e-7,0.0001653208,0.001639858],"genre_scores_gemma":[0.7729477,0.00001789698,0.2248072,0.002144831,0.00005017155,0.000001316728,0.000006883168,0.00001089634,0.00001319434],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7677683,"threshold_uncertainty_score":0.4101452,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002698435,0.001207998,0.001176738,0.0008609636,0.000727798,0.0005388971,0.003597906,0.0007807134,0.0001154546],"category_scores_gemma":[0.0003929341,0.001005206,0.0003193936,0.000458869,0.0001921317,0.0006728508,0.001688169,0.007542444,0.001370023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004404461,"about_ca_system_score_gemma":0.0003053231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001307269,"about_ca_topic_score_gemma":0.0007333999,"domain_scores_codex":[0.9930906,0.001463451,0.001065281,0.00207798,0.001218872,0.001083762],"domain_scores_gemma":[0.9948285,0.001133376,0.001116401,0.002586914,0.0001467704,0.0001881003],"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":[0.0005035397,0.0005291744,0.005595214,0.002250565,0.000691207,0.0004774805,0.01289146,0.1154228,0.0001400681,0.3078854,0.004275435,0.5493376],"study_design_scores_gemma":[0.0005774241,0.0005107746,0.001750807,0.0004881146,0.00002819413,0.00006153039,0.0000857347,0.3438323,0.000005224452,0.0009481778,0.6507673,0.0009443476],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.000333611,0.04055538,0.006284851,0.01822073,0.003904755,0.002103127,0.00005062839,0.01045014,0.9180968],"genre_scores_gemma":[0.094544,0.02331496,0.003232031,0.0005968749,0.0009148802,0.0001962516,0.0009079819,0.0005389113,0.8757541],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.6464919,"threshold_uncertainty_score":0.9994075,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00006153078,0.00003020221,0.00002723663,0.00002335618,0.00002835719,0.0001347585,0.0003392251,0.00001368166,0.0003824383],"category_scores_gemma":[0.00002307452,0.00002251246,0.00001019217,0.00009195808,0.000006239531,0.000371847,0.00006999714,0.0000425422,0.004206203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004458535,"about_ca_system_score_gemma":0.000008782587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001047795,"about_ca_topic_score_gemma":0.00000164356,"domain_scores_codex":[0.9996622,0.00001711405,0.00005320073,0.0001221123,0.0000693413,0.00007607154],"domain_scores_gemma":[0.9995674,0.00002006533,0.0000158858,0.0003401651,0.00002100991,0.00003540153],"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":[7.102393e-8,0.00001342305,0.001666783,0.000001522143,0.000001381416,2.541816e-7,0.00006687733,0.000005428991,0.001043711,0.3857143,0.03535417,0.5761321],"study_design_scores_gemma":[0.0000777832,0.00001922007,0.1453267,0.000001611551,5.132972e-7,0.000004092837,0.000008660517,0.5324925,0.0002795052,0.004466792,0.317228,0.00009470364],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001495855,0.000008186629,0.8134656,0.007009239,0.00007786651,0.00003832611,7.564475e-8,0.0002995818,0.1776053],"genre_scores_gemma":[0.860584,0.000002226434,0.1119028,0.0009462579,0.00003200832,0.00001298573,0.0000039167,0.000002332955,0.02651357],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8590881,"threshold_uncertainty_score":0.9965692,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001144572,0.0001354229,0.0001571679,0.00006721968,0.000320304,0.0001804056,0.002360988,0.00005525474,0.00001178892],"category_scores_gemma":[0.0006510016,0.0001193671,0.000007542021,0.0002302746,0.00007604952,0.001886358,0.002874427,0.0001437022,0.00001205876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001817751,"about_ca_system_score_gemma":0.00008865914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002244439,"about_ca_topic_score_gemma":0.000236371,"domain_scores_codex":[0.9981223,0.0001627168,0.0002812086,0.0009425608,0.0002467546,0.0002444426],"domain_scores_gemma":[0.9958273,0.0002514737,0.0001612319,0.003645681,0.00004007361,0.00007423348],"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":[0.00002131167,0.0001856654,0.3440276,0.00009520839,0.00005125175,0.00002424286,0.001404675,0.00006588954,0.01666647,0.002693865,0.007980296,0.6267835],"study_design_scores_gemma":[0.0004142925,0.00001049395,0.03039387,0.000008936322,0.00000555634,0.00003126034,0.00005087545,0.9602913,0.00004471561,0.000009382456,0.008549623,0.0001897479],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1731337,0.000172531,0.8241168,0.001256616,0.0001283614,0.0001122892,0.0001209972,0.000261297,0.0006974303],"genre_scores_gemma":[0.4296047,0.00002554131,0.5690429,0.0005633169,0.00006582499,9.757795e-7,0.0003798271,0.00001251704,0.0003043479],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9602253,"threshold_uncertainty_score":0.4867648,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004436551,0.00009921597,0.0000892916,0.0001719199,0.0002817079,0.0009386679,0.0004203226,0.00003207243,0.000001271883],"category_scores_gemma":[0.0002703808,0.00008957973,0.00002418078,0.0006191306,0.0001272402,0.005760056,0.0001845689,0.00006773999,0.000004696565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004855394,"about_ca_system_score_gemma":0.000628821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004691658,"about_ca_topic_score_gemma":5.146525e-7,"domain_scores_codex":[0.9987388,0.00003248614,0.0001615585,0.0004905974,0.0003836499,0.000192965],"domain_scores_gemma":[0.9993203,0.0001070103,0.00008886812,0.00017043,0.0001432326,0.0001701945],"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":[0.0000101663,0.0000261503,0.0005576409,0.000004068712,0.000001496001,1.241629e-7,0.00013824,0.911079,0.0001112031,0.08171629,0.000517221,0.005838435],"study_design_scores_gemma":[0.0002450086,0.00006921262,0.001568681,0.000006501523,0.000003358917,0.00001205653,0.00001600115,0.9729728,0.00007671484,0.02449381,0.0004155581,0.0001202846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02815843,0.00004216473,0.9692352,0.001536202,0.0001358347,0.0001643408,0.00001038513,0.0001617994,0.0005556089],"genre_scores_gemma":[0.5377766,0.000003202393,0.4616437,0.0003146075,0.00003614231,0.00001777911,0.0000501832,0.000006185012,0.0001515579],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5096182,"threshold_uncertainty_score":0.9051596,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00103393,0.00007256208,0.0000686206,0.00008913867,0.0001497095,0.0001588397,0.0004269732,0.0000423195,0.00004157996],"category_scores_gemma":[0.0001590853,0.00006208622,0.0000293487,0.0002910499,0.00001473405,0.0003431106,0.0001323057,0.0002509651,0.0002027912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002133174,"about_ca_system_score_gemma":0.00002652639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001226719,"about_ca_topic_score_gemma":0.000005975241,"domain_scores_codex":[0.9991101,0.00003759133,0.0001540492,0.0002613638,0.0002131891,0.0002237222],"domain_scores_gemma":[0.9994458,0.00007421422,0.00004569911,0.0003006009,0.00005168159,0.00008202123],"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":[0.000001045772,0.0000125593,0.001397877,0.000002529993,0.000002532547,0.000004225189,0.000190144,0.0001433486,0.0003216371,0.04962149,0.0003015993,0.948001],"study_design_scores_gemma":[0.0002165352,0.00005314005,0.04451632,0.000009782725,0.000002715442,0.00002363255,0.00009484292,0.6888559,0.0042266,0.000982984,0.260782,0.0002355442],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001641163,0.00002857794,0.9483253,0.001784205,0.0001744786,0.00003058288,1.185557e-7,0.0004570741,0.04755851],"genre_scores_gemma":[0.8017285,0.000006783285,0.1932346,0.0007531186,0.0001290631,0.000001383839,0.000009617074,0.000006489879,0.004130385],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9477655,"threshold_uncertainty_score":0.2606538,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002810333,0.0001966183,0.0001910303,0.0001853678,0.0001890768,0.0001263643,0.001094609,0.0002111458,0.00001243958],"category_scores_gemma":[0.0000624854,0.0001993636,0.00009320924,0.0002582321,0.00005982301,0.0004726624,0.001270725,0.0003386837,0.000127021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000238562,"about_ca_system_score_gemma":0.0001760746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000392531,"about_ca_topic_score_gemma":0.00002317062,"domain_scores_codex":[0.9985068,0.0001780164,0.0001467357,0.0008640297,0.00008696132,0.0002174452],"domain_scores_gemma":[0.9981106,0.00007764868,0.0002880587,0.001294873,0.0001201629,0.0001086359],"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":[0.00002951172,0.00008308622,0.01784689,0.00009916179,0.00006412606,0.0001406341,0.0002145513,0.1929496,0.000573848,0.7729112,0.0004046129,0.01468282],"study_design_scores_gemma":[0.0001692697,0.00001177417,0.00906796,0.00006751225,0.00002867969,0.000004728742,0.000005424843,0.9454781,0.00008122806,0.04466517,0.0001756673,0.0002445109],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2013023,0.00000604287,0.7952811,0.0001457329,0.0003364702,0.00009903911,0.00000795521,0.0002685189,0.002552793],"genre_scores_gemma":[0.9870773,0.00004869158,0.01204558,0.00002852784,0.00007909149,2.187277e-7,0.0000366932,0.00001007312,0.0006738522],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7857749,"threshold_uncertainty_score":0.8129809,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004684841,0.0003190873,0.0003107706,0.0002241247,0.0003857212,0.0001473995,0.001791785,0.0003044383,0.000003062188],"category_scores_gemma":[0.00006990163,0.0003783625,0.000147407,0.00002985829,0.00009823721,0.0002701113,0.001016922,0.001051895,0.00007684912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002372982,"about_ca_system_score_gemma":0.0003969652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001473396,"about_ca_topic_score_gemma":5.057938e-7,"domain_scores_codex":[0.9979339,0.0003007676,0.0002027626,0.0008211437,0.0004100117,0.0003314186],"domain_scores_gemma":[0.9980848,0.0001271933,0.0004097082,0.001019973,0.0001947658,0.0001635485],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001153271,0.00001108229,0.000003792435,0.00006178255,0.00005428725,0.00007609002,0.0001730849,0.00001824112,0.0000329942,0.8700614,0.03199247,0.09750323],"study_design_scores_gemma":[0.0003080497,0.0001048818,0.00005123437,0.00009775149,0.00006459766,0.00001598514,0.00001135866,0.03308615,0.00005746265,0.00001431677,0.9657724,0.0004158498],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.000008766409,0.00008517462,0.1366786,0.00001414779,0.0002655563,0.0001910844,0.00001729616,0.0005094431,0.86223],"genre_scores_gemma":[0.0001078428,0.00003549962,0.01178545,0.00003476462,0.0001515696,0.000001177773,0.0001453989,0.0000297879,0.9877085],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.9337799,"threshold_uncertainty_score":0.9998668,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00006521659,0.00003189796,0.00002859671,0.00001793098,0.00003733007,0.0001452662,0.0003311286,0.0000174853,0.0002544637],"category_scores_gemma":[0.00001319265,0.00002391579,0.00001062118,0.00009294492,0.000006052836,0.0003115051,0.00007419897,0.0000542525,0.001415975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000380363,"about_ca_system_score_gemma":0.000004738034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001087693,"about_ca_topic_score_gemma":0.000001935744,"domain_scores_codex":[0.9996614,0.00001859806,0.0000551263,0.0001204845,0.00005593236,0.0000884363],"domain_scores_gemma":[0.9995741,0.00002207651,0.00001687156,0.0003302801,0.00001956573,0.00003706962],"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":[1.409669e-7,0.0000134616,0.005168939,0.000001142512,0.00000211014,3.66276e-7,0.00003418587,0.0003341975,0.00008550367,0.3669288,0.0419598,0.5854713],"study_design_scores_gemma":[0.00003561363,0.000007879897,0.07401251,8.739018e-7,2.861466e-7,0.000001975435,0.000003205408,0.8878723,0.00001482654,0.001274123,0.03672893,0.00004742372],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007664722,0.00001713688,0.9440089,0.003077148,0.00009084807,0.00003817017,3.127889e-8,0.0002064066,0.05179484],"genre_scores_gemma":[0.9434403,0.000004511243,0.04974469,0.0008242345,0.00004409297,0.00001046284,0.000003904785,0.000001981727,0.0059258],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9426739,"threshold_uncertainty_score":0.9993615,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0002470483,0.0003795468,0.0003044201,0.0007702154,0.0005687402,0.004759546,0.003684237,0.0001889755,0.0007069896],"category_scores_gemma":[0.0004075156,0.0004137122,0.0001574271,0.001785575,0.00007251638,0.01792828,0.002149191,0.0004297709,0.0111192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003814575,"about_ca_system_score_gemma":0.0001033489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007968314,"about_ca_topic_score_gemma":0.00003255265,"domain_scores_codex":[0.997226,0.0001779758,0.0003363766,0.001089036,0.0005477737,0.0006228571],"domain_scores_gemma":[0.9973358,0.0001201565,0.0002336918,0.001252222,0.0004071482,0.0006509722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003124295,0.001801804,0.6073751,0.0002460676,0.0004470481,0.00039782,0.001602653,0.06974005,0.005651064,0.03902546,0.02756498,0.2458355],"study_design_scores_gemma":[0.001387919,0.0001502185,0.204044,0.00008863234,0.00003438215,0.00002526146,0.0000593938,0.1183657,0.0005619449,0.0002387368,0.6738371,0.001206627],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03914215,0.000005130285,0.9363591,0.00133816,0.0003214839,0.0007867282,0.00009401872,0.0009317293,0.02102148],"genre_scores_gemma":[0.9427283,0.00002182399,0.04517494,0.0009412361,0.00008059952,0.00001360673,0.000386975,0.00004712823,0.0106054],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9035861,"threshold_uncertainty_score":0.9998315,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001944332,0.0001390352,0.000131851,0.0000597472,0.00004999722,0.0005084928,0.001472478,0.0001816316,0.0001621398],"category_scores_gemma":[0.00002909832,0.0001144401,0.00005364594,0.00007795564,0.00001415734,0.000147653,0.001867762,0.0005736002,0.0007250243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002011519,"about_ca_system_score_gemma":0.00004381678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002565797,"about_ca_topic_score_gemma":0.000004806216,"domain_scores_codex":[0.9989518,0.00006878027,0.0001688247,0.0004926275,0.0001489968,0.0001689768],"domain_scores_gemma":[0.9982886,0.00004102246,0.0001161973,0.001430709,0.00005172423,0.00007171222],"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":[6.330401e-7,0.00003552619,0.001379639,0.00003577211,0.00002133736,0.000002589199,0.00009499935,0.01542562,0.000006730078,0.467369,0.07481153,0.4408166],"study_design_scores_gemma":[0.00003271984,0.000005806632,0.00805417,0.0000145115,0.000002369343,0.000001885904,0.000001476341,0.9421701,0.000003612596,0.006170384,0.04338608,0.0001568603],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002459273,0.0001418518,0.953654,0.002567572,0.0008241136,0.0001270999,8.578833e-7,0.000518107,0.04192049],"genre_scores_gemma":[0.691803,0.0001787529,0.2829278,0.001474031,0.0005776205,0.0001215082,0.0002624416,0.00002305137,0.02263187],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9267445,"threshold_uncertainty_score":0.9318963,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003506914,0.0002464372,0.0002308694,0.0002077316,0.0001980157,0.0002762661,0.001398994,0.0002790945,0.00002368492],"category_scores_gemma":[0.00005175125,0.0002907668,0.00009093125,0.0006251398,0.00005628445,0.0005996948,0.001374149,0.0005941226,0.00001512797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002288014,"about_ca_system_score_gemma":0.0001188642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002455984,"about_ca_topic_score_gemma":0.00002274833,"domain_scores_codex":[0.9982349,0.0002505184,0.0001811435,0.0009339853,0.00009110034,0.0003083178],"domain_scores_gemma":[0.9980234,0.00004395564,0.0002963197,0.001231024,0.0002052836,0.0002000464],"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":[0.000008501574,0.00002702648,0.002431117,0.00001484564,0.00001555441,0.0000311177,0.0000474427,0.9851941,0.000001004292,0.01081468,0.0001097092,0.001304829],"study_design_scores_gemma":[0.000215684,0.00001843086,0.0002102396,0.00002310328,0.00003794356,0.000005740778,0.00001752841,0.996922,0.000001118542,0.002138042,0.0001102724,0.0002998871],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00499872,0.00007977828,0.9922126,0.0001019448,0.0006255783,0.0001620863,0.000003665801,0.0003161442,0.001499464],"genre_scores_gemma":[0.9682637,0.00003609151,0.03102631,0.00006817008,0.0001291644,3.979094e-7,0.0001296089,0.00001853732,0.0003279731],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.963265,"threshold_uncertainty_score":0.9999545,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001104122,0.0003417186,0.000283324,0.0004921886,0.0008578479,0.0007642539,0.001607317,0.0001224979,0.0005259847],"category_scores_gemma":[0.002578889,0.0003335354,0.0001183507,0.000404149,0.00007584934,0.0005426779,0.0004260685,0.001086325,0.0007732463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000122681,"about_ca_system_score_gemma":0.00007525834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001557361,"about_ca_topic_score_gemma":0.00009606967,"domain_scores_codex":[0.9969825,0.0003782009,0.0004632231,0.001005114,0.0006498792,0.0005210653],"domain_scores_gemma":[0.9978133,0.0004762481,0.0003456253,0.0004376739,0.0007050349,0.0002221146],"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":[0.0002463089,0.0001225345,0.01958715,0.00002736876,0.0001035929,0.00001371009,0.003924772,0.04834091,0.00546048,0.3564731,0.0005340254,0.565166],"study_design_scores_gemma":[0.0004597359,0.0009559785,0.003699543,0.00007376661,0.000007271814,0.000015706,0.0002015639,0.7772194,0.0002924732,0.0009472693,0.2157677,0.0003596274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01150482,0.0000333766,0.9407945,0.00775772,0.0008638629,0.0003139963,0.000006682665,0.0007742177,0.03795082],"genre_scores_gemma":[0.9147466,0.00004221943,0.07410017,0.0005946079,0.0007036721,0.0000881712,0.0002622531,0.00004621994,0.009416101],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9032418,"threshold_uncertainty_score":0.9999117,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003506914,0.0002464372,0.0002308694,0.0002077316,0.0001980157,0.0002762661,0.001398994,0.0002790945,0.00002368492],"category_scores_gemma":[0.00005175125,0.0002907668,0.00009093125,0.0006251398,0.00005628445,0.0005996948,0.001374149,0.0005941226,0.00001512797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002288014,"about_ca_system_score_gemma":0.0001188642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002455984,"about_ca_topic_score_gemma":0.00002274833,"domain_scores_codex":[0.9982349,0.0002505184,0.0001811435,0.0009339853,0.00009110034,0.0003083178],"domain_scores_gemma":[0.9980234,0.00004395564,0.0002963197,0.001231024,0.0002052836,0.0002000464],"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":[0.000008501574,0.00002702648,0.002431117,0.00001484564,0.00001555441,0.0000311177,0.0000474427,0.9851941,0.000001004292,0.01081468,0.0001097092,0.001304829],"study_design_scores_gemma":[0.000215684,0.00001843086,0.0002102396,0.00002310328,0.00003794356,0.000005740778,0.00001752841,0.996922,0.000001118542,0.002138042,0.0001102724,0.0002998871],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00499872,0.00007977828,0.9922126,0.0001019448,0.0006255783,0.0001620863,0.000003665801,0.0003161442,0.001499464],"genre_scores_gemma":[0.9682637,0.00003609151,0.03102631,0.00006817008,0.0001291644,3.979094e-7,0.0001296089,0.00001853732,0.0003279731],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.963265,"threshold_uncertainty_score":0.9999545,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006258399,0.0000721844,0.00008166577,0.00004092622,0.0001208108,0.0003233979,0.0004963015,0.00003201737,0.00000390051],"category_scores_gemma":[0.00008978233,0.00005649477,0.00002852313,0.0001133083,0.00001497351,0.0003027805,0.00003654727,0.00006123591,0.000007503562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001114919,"about_ca_system_score_gemma":0.00001560333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006570181,"about_ca_topic_score_gemma":4.361496e-7,"domain_scores_codex":[0.9991658,0.00006285815,0.0001273145,0.0003656106,0.0001202554,0.0001581945],"domain_scores_gemma":[0.9990749,0.00008511083,0.00006336314,0.0006731731,0.00004007076,0.00006339457],"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":[0.000005244368,0.0003608505,0.01406741,0.00004111994,0.000007331988,2.262725e-7,0.0002494939,0.02222307,0.002688931,0.5141896,0.001798812,0.4443679],"study_design_scores_gemma":[0.0001186602,0.00003458445,0.006966612,0.000001294606,0.000001869824,0.000002431863,0.0000129717,0.9871507,0.0001328877,0.0002591545,0.005226442,0.00009234191],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01658755,0.000006838259,0.9647276,0.000223147,0.00006981553,0.0001010868,5.291415e-7,0.0002111619,0.01807229],"genre_scores_gemma":[0.5459182,1.153134e-7,0.4537327,0.0002070343,0.00003428168,0.00001392837,0.00001979867,0.000003376706,0.00007062266],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9649277,"threshold_uncertainty_score":0.3118533,"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)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001401394,0.00009837489,0.00008235889,0.00004800043,0.0001900997,0.0002231553,0.0003218617,0.00003733609,0.00003695143],"category_scores_gemma":[0.00002566202,0.00009432388,0.00003408912,0.0002973202,0.00001592471,0.0005476798,0.00004422616,0.00018588,0.0000764053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001601032,"about_ca_system_score_gemma":0.00000724757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003038013,"about_ca_topic_score_gemma":0.000002586887,"domain_scores_codex":[0.9990367,0.0001226569,0.0001833248,0.0002980662,0.0001694215,0.0001897721],"domain_scores_gemma":[0.99951,0.0001019715,0.00006917019,0.0002228385,0.00003702592,0.000059031],"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":[0.000003190552,0.000008525633,0.0005844014,0.000001897574,0.000001145583,0.000002756427,0.00005999833,0.3333887,0.00003319878,0.0007324801,0.0003355005,0.6648482],"study_design_scores_gemma":[0.0001406048,0.00004535497,0.02874751,0.000003544451,0.000002049038,0.00002263558,0.00000249019,0.9693722,0.000009092963,0.0002697782,0.001285671,0.00009914214],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2177902,0.00007809856,0.7756361,0.002049254,0.0003216813,0.0001063083,6.463726e-7,0.0005601298,0.003457513],"genre_scores_gemma":[0.9915951,0.000004061741,0.007361867,0.0006313393,0.0001423136,0.000004115472,0.00005247734,0.000007116707,0.0002015775],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7738049,"threshold_uncertainty_score":0.3846416,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002766201,0.0001282396,0.0001989771,0.0002480168,0.0003463044,0.0005214636,0.002398256,0.00005091596,0.00001175824],"category_scores_gemma":[0.003670558,0.00008663438,0.00005316087,0.001068965,0.0005671994,0.001160683,0.0002416475,0.0001560991,0.000008355416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003361907,"about_ca_system_score_gemma":0.0002576146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005632037,"about_ca_topic_score_gemma":0.000007758607,"domain_scores_codex":[0.9982271,0.00002718711,0.0003911067,0.0004978307,0.0005466033,0.0003102263],"domain_scores_gemma":[0.9985334,0.0002297141,0.0003929795,0.0002951808,0.0004678353,0.00008091439],"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":[0.000009353555,0.00007011255,0.02885951,0.0001274027,0.000003856459,2.712836e-8,0.003515254,0.00007927418,0.04738134,0.7142948,0.0002029471,0.2054562],"study_design_scores_gemma":[0.0004114364,0.0002117205,0.08197734,0.000162689,0.000009170723,0.000006588578,0.0008145511,0.8525357,0.02613023,0.0320619,0.005417144,0.0002615356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9228517,0.00002199644,0.05064991,0.007636225,0.0005931001,0.0006038392,0.000001791718,0.000162175,0.0174792],"genre_scores_gemma":[0.9755748,0.000004943371,0.0240487,0.0001409146,0.00003248458,0.00004739765,6.830213e-7,0.000004212595,0.0001458824],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8524565,"threshold_uncertainty_score":0.5028486,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005961136,0.0001934614,0.000201907,0.0001646273,0.0004048077,0.0008449987,0.0007761957,0.0000861591,0.0002066538],"category_scores_gemma":[0.0002725816,0.0001615152,0.00005398657,0.000407137,0.00002942683,0.00108253,0.0002976034,0.0006402063,0.002089143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003870386,"about_ca_system_score_gemma":0.00003497811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001836736,"about_ca_topic_score_gemma":0.000007924457,"domain_scores_codex":[0.9980732,0.0003212191,0.0003284905,0.0005296424,0.0003669361,0.0003805722],"domain_scores_gemma":[0.9987991,0.000193256,0.0001770495,0.0005239166,0.0001335116,0.0001731891],"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":[0.000003918486,0.0001343261,0.07660656,0.0001078659,0.00007657265,0.00001886606,0.001483384,0.02040699,0.002381451,0.1418464,0.009486262,0.7474474],"study_design_scores_gemma":[0.0001822405,0.00007728177,0.007963277,0.000014477,0.000003628364,0.00002738221,0.0001206824,0.9123219,0.00005991211,0.0001692428,0.07883561,0.0002244234],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005278739,0.0005911687,0.9497042,0.002735524,0.0004817153,0.0002766012,8.281251e-7,0.001443264,0.03948791],"genre_scores_gemma":[0.9294171,0.00006625811,0.04092532,0.0002807303,0.0002161837,0.0000704875,0.00007832713,0.00002678548,0.02891885],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9241383,"threshold_uncertainty_score":0.9986879,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002400364,0.00006130656,0.00005702361,0.00003688507,0.0004599989,0.0005168868,0.000729124,0.00004462316,0.000003149786],"category_scores_gemma":[0.0005196166,0.00005447027,0.00002973063,0.00002933002,0.000008939945,0.0005141649,0.00008482633,0.0001245245,0.00002875132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001306865,"about_ca_system_score_gemma":0.00001367228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001080798,"about_ca_topic_score_gemma":0.000002368397,"domain_scores_codex":[0.9995016,0.00001048667,0.00006527717,0.0002218783,0.00007987792,0.0001208323],"domain_scores_gemma":[0.9990798,0.00005586382,0.00009917479,0.0006806543,0.00004631601,0.00003821532],"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":[0.000003666841,0.00001667678,0.006691854,0.0000268855,0.000009090489,4.91289e-7,0.0001528207,0.0004112232,0.01260167,0.6697097,0.004622946,0.305753],"study_design_scores_gemma":[0.0001139309,0.00002310459,0.08381814,0.000005083786,0.0000015716,0.000001528495,0.000007550541,0.755563,0.0002882028,0.0001826809,0.159921,0.00007422988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009845926,0.00001178769,0.9837308,0.007907567,0.0001941767,0.00008834281,5.891434e-7,0.0002679453,0.006814227],"genre_scores_gemma":[0.8461817,0.000005801857,0.1477183,0.00004613659,0.0001018057,0.0000275538,0.00001917104,0.000006506319,0.005893097],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8451971,"threshold_uncertainty_score":0.4984351,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001059954,0.00005061879,0.0001002531,0.0001223039,0.00002194668,0.0001016904,0.001301625,0.00002190139,0.00003868562],"category_scores_gemma":[0.0006023727,0.00004248962,0.000009477505,0.0007255284,0.00001357452,0.0006083376,0.0008590152,0.0001006292,0.00005861204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002369802,"about_ca_system_score_gemma":0.00006127205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001592023,"about_ca_topic_score_gemma":0.0009583408,"domain_scores_codex":[0.9989426,0.0002061913,0.0001333375,0.0003800171,0.0002203056,0.0001175641],"domain_scores_gemma":[0.9983107,0.000175784,0.00003617435,0.001347391,0.00003948847,0.00009045967],"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":[0.00002398132,0.0002504971,0.3296032,0.00000860834,0.0001152303,0.00003137107,0.000926205,0.005580692,0.00001567882,0.5596707,0.04660619,0.05716764],"study_design_scores_gemma":[0.00008398129,0.00001741521,0.1161936,9.408558e-7,0.00001333386,4.664982e-7,0.00003274236,0.8787134,0.000003075422,0.002438205,0.002449467,0.00005335664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001064715,0.00001032077,0.98783,0.0007514561,0.0000363955,0.00003450806,0.00002409789,0.00007049568,0.01017795],"genre_scores_gemma":[0.7261399,0.000001279177,0.2733295,0.00005470468,0.00001508796,0.000001914146,0.0002168525,0.000001554019,0.0002392577],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8731328,"threshold_uncertainty_score":0.2418764,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005541189,0.0001638984,0.0002206881,0.0001192705,0.00008521361,0.0001265951,0.00199932,0.00009675505,0.00009262513],"category_scores_gemma":[0.0005136003,0.0001259823,0.00008714118,0.0005025837,0.00009998667,0.0004277253,0.0003482146,0.0002511619,0.0004791806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002569992,"about_ca_system_score_gemma":0.0001122369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003899543,"about_ca_topic_score_gemma":0.000004469645,"domain_scores_codex":[0.9982797,0.00002410815,0.0005129222,0.0004562135,0.0005176628,0.0002094174],"domain_scores_gemma":[0.9981741,0.00007522299,0.0005461858,0.0004846951,0.000661285,0.00005852024],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003261459,0.00006171255,0.0005906293,0.00004576101,0.000007551959,8.619432e-8,0.0006860977,0.00007808337,0.078852,0.8918898,0.00005471327,0.02770102],"study_design_scores_gemma":[0.00004123158,0.0003605091,0.0005947843,0.0002782055,0.00001172339,0.000002241122,0.0002725825,0.2510752,0.6250774,0.1211256,0.000931567,0.0002288899],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3311834,0.0000512027,0.515138,0.01792201,0.002716268,0.001697727,0.00001464085,0.0004031312,0.1308737],"genre_scores_gemma":[0.9935583,0.00002005828,0.004504894,0.0001482085,0.00004885949,0.000007322843,0.000002548161,0.00001009711,0.001699744],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7707641,"threshold_uncertainty_score":0.6159057,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002455014,0.00006172685,0.00006522557,0.00003417992,0.00006358518,0.00003427575,0.0009108183,0.00001755708,0.00001058924],"category_scores_gemma":[0.0001236381,0.00002905918,0.0000414636,0.0001489794,0.00003619854,0.0003022806,0.0003272137,0.00004717764,0.00002646544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003386122,"about_ca_system_score_gemma":0.00001160415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009090244,"about_ca_topic_score_gemma":2.792583e-7,"domain_scores_codex":[0.999399,0.000006654332,0.0001172592,0.0001828491,0.0001766334,0.0001175978],"domain_scores_gemma":[0.9995267,0.00003516491,0.0001479358,0.0001874553,0.00007123804,0.00003150084],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000005092331,0.00004358792,0.005162852,0.00001270583,0.00001072455,3.301596e-8,0.0002485394,2.972087e-7,0.3499639,0.3406787,0.002692454,0.3011811],"study_design_scores_gemma":[0.0006386968,0.0001065241,0.07652286,0.0001276876,0.00001114911,0.0000107853,0.00007034253,0.0008733721,0.8030983,0.02366083,0.09468397,0.0001954392],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3562582,0.0002442886,0.2771933,0.1524427,0.001813846,0.001391986,0.00001480555,0.0009568534,0.2096839],"genre_scores_gemma":[0.9882314,0.0000155887,0.01057301,0.00009126191,0.00002797692,0.00001227271,9.592381e-8,0.000003741714,0.001044702],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6319731,"threshold_uncertainty_score":0.1692542,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003631779,0.0002401838,0.0002534977,0.0009971124,0.0003082136,0.0004833101,0.0003011856,0.00008735601,0.00006976633],"category_scores_gemma":[0.000006955946,0.0002099394,0.0002411742,0.001478182,0.00005345367,0.0004547218,0.000006816528,0.000383425,0.0001046649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004412976,"about_ca_system_score_gemma":0.00002385468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001295876,"about_ca_topic_score_gemma":0.001496808,"domain_scores_codex":[0.9981511,0.0001722605,0.00037556,0.000753581,0.0003275126,0.0002199896],"domain_scores_gemma":[0.9991883,0.0001968786,0.0000757747,0.0003569806,0.00006587543,0.0001161645],"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":[0.000007250908,0.00006137764,0.0001626709,0.00002580197,0.0002712152,0.000005309592,0.0003497669,0.01101374,0.001530053,0.0001271555,0.00001227942,0.9864334],"study_design_scores_gemma":[0.00005477849,0.0001685842,0.001234902,0.00003142848,0.0002989867,0.00002842352,0.00003174256,0.9604819,0.03599128,0.0003918493,0.001028708,0.000257358],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005021074,0.0003561012,0.9922403,0.001271968,0.0004625077,0.0001125207,0.00002487471,0.0003913666,0.0001192873],"genre_scores_gemma":[0.9973221,0.0003018247,0.001885439,0.0001905695,0.0000356034,0.00002377837,0.00002808959,0.00001545922,0.0001970657],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9923011,"threshold_uncertainty_score":0.8561078,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0003503661,0.00003924517,0.00004407679,0.00002296037,0.0001944725,0.00003276078,0.02164219,0.00002159912,0.000002840406],"category_scores_gemma":[0.002929226,0.00002921198,0.00002645231,0.000277805,0.00006412171,0.0003389744,0.01038828,0.00009686417,0.00001036619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001298267,"about_ca_system_score_gemma":0.00001323455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002113631,"about_ca_topic_score_gemma":0.000001164199,"domain_scores_codex":[0.9994856,0.000147053,0.0001212929,0.00006366988,0.00009163431,0.00009080237],"domain_scores_gemma":[0.9776353,0.0001221344,0.0001282704,0.02204347,0.00004525594,0.000025547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003707467,0.001098644,0.08322302,0.00003849051,0.00005128481,1.207705e-8,0.003736773,0.00296482,0.004017567,0.4027993,0.1567589,0.3453074],"study_design_scores_gemma":[0.0002846692,0.00002749331,0.02529492,0.00004779175,0.00002786903,0.000007001552,0.0001289631,0.2009111,0.002379858,0.007438128,0.7631907,0.00026156],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001865503,0.004298829,0.8148117,0.1690247,0.0003046033,0.0003872542,0.000008490614,0.0002708913,0.009027991],"genre_scores_gemma":[0.4267831,0.00005878074,0.572966,0.0000647483,0.000006896382,0.00001282144,0.00001939208,0.000002595973,0.00008565681],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6064317,"threshold_uncertainty_score":0.9976155,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.008113025,0.000277129,0.0002303598,0.0001660737,0.0005866836,0.001393992,0.01771542,0.0001169078,0.0000330455],"category_scores_gemma":[0.001281984,0.0001343022,0.00003736129,0.0006026211,0.0006503469,0.001043423,0.002424532,0.0008146859,0.0001474188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000555139,"about_ca_system_score_gemma":0.0007268412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001373862,"about_ca_topic_score_gemma":0.000291833,"domain_scores_codex":[0.996571,0.0006609507,0.0002889086,0.001015695,0.001109781,0.0003536838],"domain_scores_gemma":[0.9940485,0.001187156,0.0002692978,0.00439339,0.0000523641,0.00004932281],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006871702,0.00001856305,0.00003446702,0.00001338054,0.00000850687,0.000008351412,0.001032245,0.0001656653,0.000003906885,0.713353,0.2606696,0.02468532],"study_design_scores_gemma":[0.00004330619,0.0001083398,0.0004264569,0.0000615657,0.000007928331,0.00002019576,0.0001184101,0.009460178,0.000009278472,0.04511518,0.9444109,0.0002182768],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00002767266,0.001781214,0.04567814,0.06748308,0.002277619,0.0008098871,0.0004237778,0.0002670189,0.8812516],"genre_scores_gemma":[0.01240363,0.002011208,0.3802884,0.03392128,0.006487055,0.000423913,0.004212332,0.000223794,0.5600284],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.6837412,"threshold_uncertainty_score":0.9996427,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002515002,0.0001031763,0.00008998041,0.00009371611,0.0001673865,0.0001752378,0.0005738222,0.00005737556,0.00009852841],"category_scores_gemma":[0.0001813281,0.00007481756,0.00005431535,0.0003639259,0.000041376,0.001015928,0.00009440875,0.00006722178,0.0003174016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001947534,"about_ca_system_score_gemma":0.00006029993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001304582,"about_ca_topic_score_gemma":0.000006431769,"domain_scores_codex":[0.9989007,0.00005807035,0.0002506633,0.0004095168,0.0001397089,0.0002413086],"domain_scores_gemma":[0.9991292,0.0003036216,0.00008939322,0.0003409073,0.00005987201,0.00007701524],"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":[0.000005419018,0.00001888919,0.0001010307,0.000002392183,0.000003092917,3.635946e-7,0.00005350524,0.000005301852,0.002409447,0.2513175,0.001362617,0.7447205],"study_design_scores_gemma":[0.00004508579,0.0002651616,0.0006474656,0.00003848242,0.000006659929,0.00001069785,0.00003085025,0.3954738,0.1803393,0.2778217,0.1449877,0.0003330878],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004473719,0.00002938727,0.9918479,0.005884524,0.0003681216,0.0001658798,0.00001370161,0.0004050903,0.0008379957],"genre_scores_gemma":[0.5623511,0.000055587,0.4345994,0.0004863816,0.0005113457,0.0001101284,0.00003027309,0.00002565991,0.001830121],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7443874,"threshold_uncertainty_score":0.4079662,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001768972,0.00009397403,0.00008530374,0.00004370918,0.0001333724,0.000141307,0.0003867616,0.0000544627,0.0000910209],"category_scores_gemma":[0.0000714866,0.00005362626,0.00001554197,0.0002198941,0.00002792046,0.000511492,0.0000969547,0.0001078169,0.0001309173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002280285,"about_ca_system_score_gemma":0.00002005988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007446702,"about_ca_topic_score_gemma":0.00003875147,"domain_scores_codex":[0.9990595,0.0001112033,0.0001247433,0.0003558267,0.0001801235,0.0001686069],"domain_scores_gemma":[0.9991737,0.0001339256,0.00009485608,0.0004732191,0.00006111705,0.00006317623],"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":[0.00001766727,0.00003859728,0.08103498,0.000002690536,0.00002569161,0.000005178054,0.0003058841,0.004294148,0.002811102,0.132617,0.0005612408,0.7782859],"study_design_scores_gemma":[0.0005430392,0.0001260399,0.03401051,0.0000405319,0.000007513262,0.000004177228,0.0000197313,0.9482796,0.0004986901,0.001593956,0.01464716,0.0002290657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004546989,0.00002593495,0.98796,0.002414839,0.00007949709,0.00005421255,5.023887e-7,0.0003795768,0.004538413],"genre_scores_gemma":[0.9369693,0.00001856675,0.05679974,0.0001734768,0.0001034298,0.000006248518,0.00003649425,0.00001017931,0.00588255],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9439855,"threshold_uncertainty_score":0.2186815,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006086789,0.0002028384,0.000244983,0.0001965169,0.0006990519,0.003048989,0.001214363,0.0001045212,7.907429e-7],"category_scores_gemma":[0.0002841445,0.0001769943,0.00003322319,0.0002360636,0.00007036065,0.01052667,0.0001965389,0.0003786645,0.000008833825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007466594,"about_ca_system_score_gemma":0.00005695038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000103772,"about_ca_topic_score_gemma":0.00001734681,"domain_scores_codex":[0.9983118,0.0001160437,0.0006100682,0.0002586684,0.0003444012,0.0003589827],"domain_scores_gemma":[0.9982266,0.00004947923,0.0008543229,0.0005851656,0.0001892288,0.00009523325],"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":[0.000009880215,0.00001821094,0.001296918,0.0001924239,0.000003105962,0.000004933349,0.008231872,0.3069628,0.00001615895,0.001916328,0.00004880345,0.6812985],"study_design_scores_gemma":[0.0004935086,0.00002501046,0.01094786,0.000140525,0.000003107405,0.0000215644,0.001082957,0.9866949,0.000005161824,0.00001324253,0.0003617607,0.0002104245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05892183,0.0001890202,0.932761,0.001877015,0.001246889,0.0003761209,0.000004161994,0.0003243214,0.004299708],"genre_scores_gemma":[0.998104,0.000007067553,0.001363933,0.0002121229,0.0001182733,0.00006036638,0.00007394577,0.000008929559,0.00005131482],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9391822,"threshold_uncertainty_score":0.997986,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002148415,0.0000706823,0.00006579442,0.00007786474,0.0001312057,0.0001786602,0.0003940453,0.0000327804,0.00004021349],"category_scores_gemma":[0.00004241332,0.00005776786,0.00002909295,0.0002523641,0.00001121897,0.0002966454,0.0001072763,0.0001324478,0.0003771536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001715358,"about_ca_system_score_gemma":0.00001788527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002322701,"about_ca_topic_score_gemma":0.00003532636,"domain_scores_codex":[0.9992128,0.00004549724,0.0001343556,0.0002660523,0.0001970964,0.0001442105],"domain_scores_gemma":[0.9994661,0.00009092641,0.00004789422,0.0003272105,0.00003266578,0.00003521386],"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":[5.848904e-7,0.00001903491,0.001271607,6.307678e-7,7.710678e-7,0.000002169864,0.0000196893,0.0004003564,0.0001557089,0.02889637,0.003754711,0.9654784],"study_design_scores_gemma":[0.0001797264,0.00003561286,0.03925005,0.000005105891,0.000001223988,0.00001116071,0.00001076019,0.8599198,0.0001533647,0.003351898,0.09697396,0.0001073302],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001012618,0.0000373958,0.9508733,0.0005629238,0.0000906634,0.00003090042,4.041212e-7,0.0003536367,0.04703812],"genre_scores_gemma":[0.266381,0.000004362469,0.7216412,0.00009646986,0.0001201339,0.000005010876,0.00003194531,0.000006732498,0.01171313],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.965371,"threshold_uncertainty_score":0.4847672,"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)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004984498,0.0002787155,0.0009684623,0.0000617146,0.00007936275,0.0001182087,0.002726281,0.0001160832,0.0000188928],"category_scores_gemma":[0.0003612177,0.0001745049,0.0004255685,0.0008230212,0.0000362553,0.0002656787,0.0004310364,0.0005334901,0.0001580027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004732614,"about_ca_system_score_gemma":0.0001548368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009671883,"about_ca_topic_score_gemma":2.500512e-7,"domain_scores_codex":[0.998309,0.00003586663,0.0005803881,0.0005103661,0.0003934634,0.0001709574],"domain_scores_gemma":[0.9982944,0.00004320944,0.001018446,0.0003682548,0.0002024364,0.00007330052],"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":[1.747868e-7,0.00001027143,8.126111e-7,0.04751834,0.0000221761,2.99565e-7,0.0000202439,1.914001e-8,2.674305e-7,0.0001199097,0.01776052,0.9345469],"study_design_scores_gemma":[0.00003146566,0.00002064963,0.000002068538,0.05554538,0.0002432599,0.00005109117,0.000001213793,0.0001463679,0.000004226818,0.0001256063,0.9436404,0.0001883261],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[7.378881e-8,0.9893895,0.002468451,0.003192271,0.0003693742,0.0005707027,0.00002555522,0.0001182004,0.003865883],"genre_scores_gemma":[0.000001280548,0.9956076,0.003391234,0.0005205276,0.0002250535,0.00009060289,0.00001506345,0.0000220434,0.0001265515],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9343587,"threshold_uncertainty_score":0.7116102,"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)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002228234,0.00007737285,0.00008176827,0.00005938491,0.0001801101,0.00003732959,0.000145056,0.0000414325,0.00001222697],"category_scores_gemma":[0.00007133473,0.00005861499,0.00003485989,0.0001285072,0.00003410119,0.000232983,0.00002828668,0.00009359542,0.000013751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001524168,"about_ca_system_score_gemma":0.00002870615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008139396,"about_ca_topic_score_gemma":0.00004186776,"domain_scores_codex":[0.9993036,0.00006166418,0.0001615707,0.0002475722,0.0001142926,0.0001112493],"domain_scores_gemma":[0.9993647,0.000186758,0.0001287771,0.0001960622,0.00009953366,0.00002420883],"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":[0.00001213499,0.00003642717,0.003887502,0.00003102371,0.0000132663,3.419025e-7,0.0001843792,0.00004061252,0.002412867,0.00009990422,0.00023612,0.9930454],"study_design_scores_gemma":[0.000465452,0.0001750563,0.3561128,0.00003409261,0.00002458812,0.00008239246,0.00004811609,0.6368147,0.003070634,0.001870111,0.001137396,0.0001647179],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2758564,0.00008699008,0.7227053,0.000779262,0.0001117676,0.0002185494,0.00001861832,0.00006050198,0.0001626015],"genre_scores_gemma":[0.9966234,0.000185517,0.002843224,0.00009966787,0.00004045053,0.00005450356,0.00006282827,0.000006586544,0.00008385467],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9928807,"threshold_uncertainty_score":0.239025,"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)","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000774865,0.0003529362,0.000288451,0.0003710363,0.0004618626,0.0003683118,0.001074781,0.0001470572,0.0004336042],"category_scores_gemma":[0.0003459674,0.000335998,0.00009186747,0.0002487408,0.00008940664,0.0006760344,0.0002684541,0.001887527,0.0001337852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004985772,"about_ca_system_score_gemma":0.00004413457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002091321,"about_ca_topic_score_gemma":0.0000182809,"domain_scores_codex":[0.9971542,0.0005618029,0.0003966071,0.0009030992,0.0005834399,0.0004008299],"domain_scores_gemma":[0.998988,0.0001360428,0.0001495576,0.0003325549,0.0002073864,0.0001864113],"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":[0.0001326101,0.0002777015,0.03456064,0.00004656762,0.0001166468,0.0000298896,0.01122034,0.005042204,0.001137524,0.6160211,0.00000688067,0.3314079],"study_design_scores_gemma":[0.0008469226,0.0004778662,0.01439621,0.00005553887,0.00001364269,0.00004396171,0.000521393,0.9717566,0.00007772142,0.00134136,0.01001877,0.0004499635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04580575,0.0003440423,0.6802667,0.002091788,0.0003423129,0.0002678312,0.000003207546,0.001038839,0.2698395],"genre_scores_gemma":[0.9862804,0.0005298889,0.01084093,0.0001347591,0.00009749596,0.00003988918,0.0001280226,0.00003608911,0.001912533],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9667144,"threshold_uncertainty_score":0.9999092,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009731015,0.0001475032,0.0002725107,0.0004709224,0.0006662366,0.0003689397,0.002173047,0.00008771069,0.00005798731],"category_scores_gemma":[0.008756197,0.00006847439,0.000161089,0.0007111454,0.0002283755,0.0006363401,0.0003690451,0.001906703,0.0002066385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001157196,"about_ca_system_score_gemma":0.0001851734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000479245,"about_ca_topic_score_gemma":0.00004838485,"domain_scores_codex":[0.9950869,0.002123189,0.0005166531,0.000285434,0.001487763,0.0005000231],"domain_scores_gemma":[0.9945799,0.003091868,0.0007610859,0.0006452409,0.0007103069,0.0002115689],"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":[0.0004557591,0.0001871516,0.426748,0.00003523226,0.000101808,0.000185274,0.0007025235,0.0007787752,0.00331368,0.007901537,0.01276345,0.5468268],"study_design_scores_gemma":[0.006458111,0.001444164,0.3588566,0.0006174521,0.000030177,0.0007393955,0.0006161663,0.0545474,0.0005055121,0.006710047,0.5690522,0.000422758],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2470242,0.002830813,0.5610548,0.1817753,0.001015578,0.0004486849,0.000006687007,0.0001537965,0.005690136],"genre_scores_gemma":[0.9937351,0.000316445,0.001241814,0.00009478956,0.00038783,0.000006135961,9.166591e-7,0.00001859829,0.004198316],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7467109,"threshold_uncertainty_score":0.9995935,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009936177,0.0002207598,0.0001869347,0.0006401165,0.0002834702,0.0001690679,0.001417419,0.0002386362,0.0002047899],"category_scores_gemma":[0.0005602869,0.0001800488,0.00004357361,0.0006438349,0.0005462368,0.001742013,0.0002616185,0.0005787933,0.0001810306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008580969,"about_ca_system_score_gemma":0.0001719305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004549993,"about_ca_topic_score_gemma":0.00001142714,"domain_scores_codex":[0.9980096,0.00004201339,0.0007381757,0.0003026946,0.0005658516,0.0003416265],"domain_scores_gemma":[0.9979759,0.0001739631,0.0006635797,0.0005108074,0.0005732304,0.0001024831],"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":[0.00003297048,0.00003410734,0.08260646,0.00003450502,0.00004208378,0.000001457887,0.0005756646,0.0001103034,0.0010828,0.7578483,0.001632483,0.1559989],"study_design_scores_gemma":[0.0007850529,0.0004263023,0.1585186,0.0002044736,0.00001446153,0.00005798849,0.002367585,0.7850226,0.008293711,0.004376672,0.03939013,0.0005424284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4916434,0.00009050313,0.4287548,0.01853477,0.003023855,0.000626063,0.00003674972,0.0006295576,0.05666028],"genre_scores_gemma":[0.9915473,0.0002340981,0.006940806,0.0009149933,0.00005544311,0.00002111922,0.00004460684,0.00000671527,0.0002349114],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7849123,"threshold_uncertainty_score":0.7342178,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005125841,0.0002983264,0.0003863828,0.0009209096,0.0004296978,0.0002101044,0.001841768,0.0004273509,0.00001761647],"category_scores_gemma":[0.001395498,0.0002638687,0.0001062267,0.001457202,0.0003111408,0.001048767,0.0007373262,0.0008046816,0.0002437897],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007734878,"about_ca_system_score_gemma":0.00009722253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002740723,"about_ca_topic_score_gemma":0.0000366694,"domain_scores_codex":[0.9977245,0.00004602092,0.0006287515,0.0007053578,0.0003927191,0.0005026453],"domain_scores_gemma":[0.9978309,0.0001055659,0.0004295918,0.001286582,0.000206982,0.0001404017],"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":[0.00000940289,0.00008245546,0.01098438,0.00005029484,0.00002965572,0.00001227268,0.0001321118,0.0005346632,0.01701686,0.1853688,0.001058394,0.7847208],"study_design_scores_gemma":[0.003059146,0.001349158,0.2026611,0.00262132,0.0001367157,0.0004728349,0.0006558906,0.2345501,0.0507776,0.2383214,0.2620247,0.003370041],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3241836,0.0003724204,0.6675875,0.004680851,0.0004551506,0.0003671128,0.00001088568,0.00122001,0.001122582],"genre_scores_gemma":[0.7485701,0.00002938512,0.2510996,0.00008023319,0.00004136566,0.00004763965,0.00001570951,0.00001870796,0.0000971751],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7813507,"threshold_uncertainty_score":0.9999813,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002752336,0.00007202708,0.00006378913,0.000365417,0.0006539227,0.0004083216,0.0003645027,0.00007510655,0.0000380313],"category_scores_gemma":[0.0004073575,0.00005942348,0.00001216683,0.0007983382,0.0000853634,0.0007308076,0.0001715657,0.000325952,0.00008409562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000630334,"about_ca_system_score_gemma":0.00006246378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000101738,"about_ca_topic_score_gemma":0.00010935,"domain_scores_codex":[0.9985433,0.0002376077,0.0002012133,0.0003614417,0.0004198058,0.0002366733],"domain_scores_gemma":[0.9987633,0.0001643792,0.00002021133,0.0005445896,0.0004001378,0.000107389],"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":[0.00002234328,0.0002052472,0.005286505,0.00002347493,0.00001074094,0.000004976075,0.001500619,0.01830131,0.03272191,0.4546293,0.001999539,0.4852941],"study_design_scores_gemma":[0.0001170764,0.0000570824,0.02265082,0.00001343157,8.97644e-7,0.000007967102,0.0001081066,0.9710649,0.0003807138,0.0001876358,0.005335159,0.00007622088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007286594,0.00007085413,0.9819533,0.004181333,0.00007294472,0.0001837597,8.617823e-7,0.00008907128,0.006161234],"genre_scores_gemma":[0.8714819,0.00008611541,0.1268201,0.00004483362,0.00006854746,0.00002262791,0.00006801185,0.000007263478,0.001400646],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9527636,"threshold_uncertainty_score":0.5029511,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009358811,0.0001703651,0.0002435682,0.0001393228,0.00009133948,0.0001238778,0.001660093,0.0000694512,0.00002101288],"category_scores_gemma":[0.0006530402,0.0001244698,0.00009405311,0.0006010922,0.0002397324,0.0001678078,0.0003555384,0.0002307977,0.00004351112],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003737729,"about_ca_system_score_gemma":0.00009373601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009363394,"about_ca_topic_score_gemma":0.000004012429,"domain_scores_codex":[0.9982487,0.00003195002,0.000512542,0.0004073375,0.0005537784,0.0002456784],"domain_scores_gemma":[0.9981665,0.0001248162,0.0005020026,0.0003743677,0.0007267136,0.0001055996],"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":[0.0001131449,0.0002629792,0.001791605,0.00006091316,0.00002541751,3.129235e-7,0.003650097,0.007772421,0.04490424,0.7940158,0.0001563948,0.1472467],"study_design_scores_gemma":[0.00003558059,0.0002010462,0.0003123296,0.000114672,0.00001038138,0.000003686107,0.000383082,0.7691275,0.2097301,0.019866,0.00006149655,0.0001540157],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6821634,0.00005167894,0.2883275,0.004196588,0.001030259,0.0005544879,0.000007563617,0.0001629757,0.0235056],"genre_scores_gemma":[0.9795278,0.00000609329,0.02030265,0.00005251898,0.00003572595,0.0000101281,0.000001004636,0.00000758482,0.00005646035],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7741498,"threshold_uncertainty_score":0.5075731,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004904272,0.00006699231,0.0001625791,0.00009338115,0.00008539103,0.0001811011,0.0003664809,0.00003653246,0.000003750974],"category_scores_gemma":[0.0004508042,0.00005283969,0.00004186761,0.0002462537,0.00002374922,0.0005489103,0.0000336923,0.0001946421,0.00001239276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003553516,"about_ca_system_score_gemma":0.0001258063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001637157,"about_ca_topic_score_gemma":0.000001284036,"domain_scores_codex":[0.9989483,0.0001154688,0.0003875597,0.00009242033,0.0003642836,0.00009191238],"domain_scores_gemma":[0.9986576,0.0001612358,0.0004855218,0.0001954185,0.0004097716,0.0000904344],"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":[0.00001653609,0.0002866023,0.1398834,0.00003179324,0.0002887851,0.0000805415,0.009856646,0.003548621,0.0004390305,0.0794975,0.02123494,0.7448356],"study_design_scores_gemma":[0.0009570065,0.0005387223,0.2691785,0.00007646184,0.0001834254,0.0001445956,0.0004611411,0.6300559,0.0002817792,0.05609059,0.04167579,0.0003561105],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007254543,0.000116644,0.9902336,0.001154872,0.000276837,0.00002102387,0.000004893236,0.00002008642,0.0009175063],"genre_scores_gemma":[0.7697024,0.00002175713,0.2298441,0.00004022306,0.00032554,2.127909e-7,0.00001039297,0.000002910328,0.00005247257],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7624478,"threshold_uncertainty_score":0.215474,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002033402,0.0002366982,0.0005220857,0.0003124982,0.0005521429,0.00006801938,0.00258896,0.000101692,0.0002350741],"category_scores_gemma":[0.003443418,0.0001421227,0.0001543339,0.001610324,0.0006481658,0.00033174,0.0009704476,0.0007906125,0.00001529721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002694965,"about_ca_system_score_gemma":0.0002225597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003713163,"about_ca_topic_score_gemma":0.00006921801,"domain_scores_codex":[0.9962797,0.001651878,0.0005228202,0.000748156,0.0004997643,0.0002976503],"domain_scores_gemma":[0.9950982,0.001306794,0.0006724973,0.002539643,0.0002916398,0.00009123523],"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":[0.0002844102,0.0006297041,0.2683807,0.0001671712,0.001054528,0.00005502323,0.009647001,0.01821464,0.005431186,0.6018642,0.0002038829,0.09406758],"study_design_scores_gemma":[0.0005343439,0.0002254615,0.06798401,0.0001015096,0.0002736543,0.00003210279,0.0008228603,0.9206918,0.0008382852,0.005651091,0.002489695,0.0003551994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6035352,0.00006233552,0.3912469,0.001324412,0.0002269512,0.0003558729,0.0001155962,0.0003044562,0.002828205],"genre_scores_gemma":[0.9932922,0.00005684969,0.005183752,0.0000630356,0.00002581341,0.000008339051,0.0002292578,0.00001469927,0.001126092],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9024771,"threshold_uncertainty_score":0.5795596,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002957406,0.0001437985,0.0001426615,0.0001223814,0.00008693075,0.0001822712,0.0003414708,0.00006284745,0.0001405351],"category_scores_gemma":[0.00004588226,0.0001480232,0.00009238091,0.0001868529,0.00001088963,0.0005321102,0.00005362516,0.000151565,0.0001248093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004217242,"about_ca_system_score_gemma":0.0000211962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005633104,"about_ca_topic_score_gemma":0.000002165954,"domain_scores_codex":[0.9987263,0.0001432055,0.0002342659,0.0004643026,0.0001792709,0.0002526557],"domain_scores_gemma":[0.9990589,0.0003000421,0.0001631403,0.0003185016,0.00006589138,0.00009351464],"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":[0.00002203859,0.00002174772,0.003613602,0.00002193021,0.0000272008,9.080538e-7,0.0001055379,0.3145458,0.0006089715,0.0001240469,0.005816845,0.6750914],"study_design_scores_gemma":[0.000719541,0.0000509312,0.001888637,0.00001535873,0.00001243665,0.00001540355,0.000007625936,0.9956718,0.00004826938,0.00009463955,0.001274659,0.0002006625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00484016,0.00001553714,0.9843998,0.009269175,0.0007878713,0.0004078523,0.0000176864,0.0001823161,0.00007958968],"genre_scores_gemma":[0.131405,0.000005344592,0.8529603,0.01407484,0.0003204732,0.0000803373,0.001030579,0.00002416602,0.000098868],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6811261,"threshold_uncertainty_score":0.6036212,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002636463,0.0001808517,0.0001723223,0.0001208655,0.0005847756,0.0002859009,0.003732926,0.00003799778,0.0000022185],"category_scores_gemma":[0.0002932131,0.0001499315,0.00002342739,0.0004202051,0.0002457277,0.002421164,0.004218226,0.0002097754,0.00001623761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003584612,"about_ca_system_score_gemma":0.0001669117,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001446121,"about_ca_topic_score_gemma":0.0002014252,"domain_scores_codex":[0.9983451,0.0001425151,0.000170777,0.000796638,0.0002565727,0.0002883871],"domain_scores_gemma":[0.9971384,0.0003386252,0.0001918752,0.002172295,0.00002845185,0.0001303365],"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":[0.0002910709,0.0003715764,0.148908,0.00009284961,0.000339101,0.0001655307,0.01348501,0.0005567333,0.003735542,0.01352492,0.02467356,0.7938561],"study_design_scores_gemma":[0.002059513,0.00007296279,0.04969462,0.00005714081,0.00005083129,0.00009488981,0.001481662,0.7209167,0.00002492806,0.0002465003,0.2245797,0.0007204562],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2427137,0.00006598484,0.7464391,0.00174435,0.00009822247,0.0002650571,0.003349422,0.0003179844,0.005006137],"genre_scores_gemma":[0.8227534,0.0000294682,0.1675714,0.000324776,0.0001346353,2.107381e-7,0.004457643,0.00002940139,0.004699119],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7931357,"threshold_uncertainty_score":0.6936767,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008206872,0.000121466,0.0002443503,0.0002469594,0.0005251443,0.0008792608,0.00139676,0.00008331259,0.0000133933],"category_scores_gemma":[0.001129798,0.00009840656,0.00001966051,0.000552252,0.0002145713,0.001691398,0.0009282492,0.001243916,0.00001533494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005180987,"about_ca_system_score_gemma":0.0001243438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002181821,"about_ca_topic_score_gemma":0.0003532617,"domain_scores_codex":[0.9965844,0.001104177,0.000601707,0.0004972544,0.0008395939,0.000372914],"domain_scores_gemma":[0.9976065,0.00076932,0.0002122691,0.0006976732,0.000463475,0.0002507427],"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":[0.0000959222,0.0004789958,0.01767422,0.000004650558,0.00002506583,0.00005771682,0.007070971,0.00004868398,0.004432799,0.0008270133,0.00009016633,0.9691938],"study_design_scores_gemma":[0.0005838975,0.009978671,0.03807912,0.0001810655,0.00004647127,0.0004018891,0.03539537,0.828493,0.02771812,0.01682809,0.04146965,0.0008246821],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9187421,0.0003125917,0.07779205,0.002840231,0.00004998219,0.0001687351,0.000004450316,0.00004600145,0.00004390362],"genre_scores_gemma":[0.9709637,0.0003237753,0.02813894,0.0000260184,0.0004920706,0.000003074904,0.000006676139,0.000009830418,0.00003593014],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9683691,"threshold_uncertainty_score":0.8478733,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001647623,0.000280599,0.0002751074,0.0001259328,0.0001357641,0.0002175056,0.0009583556,0.0001999195,0.0005085701],"category_scores_gemma":[0.00007806365,0.0002503128,0.0000958683,0.00006345321,0.00002695449,0.0001853287,0.0004318779,0.0008277182,0.003356658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003459564,"about_ca_system_score_gemma":0.00006752006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003509866,"about_ca_topic_score_gemma":0.000007595395,"domain_scores_codex":[0.9985313,0.00003956001,0.0002837373,0.0006508888,0.0003275381,0.0001669669],"domain_scores_gemma":[0.9988596,0.00007423946,0.0002288985,0.0006440767,0.00005499529,0.0001381642],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002130108,0.000004630354,0.00002507204,0.00002385115,0.00002620741,0.00002289629,0.00004918149,0.00006318146,0.00003301538,0.9460733,0.0128668,0.04080977],"study_design_scores_gemma":[0.00006974353,0.00004209817,0.00004416303,0.00001900315,0.000007200383,0.000008980674,4.809291e-7,0.4197708,0.000005196047,0.002032965,0.5778008,0.0001985859],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[2.357501e-7,0.0002125338,0.1627278,0.003513978,0.0001660662,0.00009191182,0.000007538456,0.004567079,0.8287129],"genre_scores_gemma":[0.003700036,0.0001171932,0.02500674,0.0008868841,0.0001644654,0.000004218799,0.0005782426,0.00005330221,0.9694889],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.9440403,"threshold_uncertainty_score":0.9999949,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003396549,0.0002054966,0.0002448499,0.000264722,0.000102948,0.00008660265,0.0005728629,0.0002712861,0.00001565576],"category_scores_gemma":[0.00005950807,0.0002340328,0.00006923897,0.0004751303,0.00007090547,0.0005427208,0.0005101436,0.0003841304,0.00001323349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001030023,"about_ca_system_score_gemma":0.0000841686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000885252,"about_ca_topic_score_gemma":0.000005830294,"domain_scores_codex":[0.9985656,0.0002153505,0.0002307143,0.0007004905,0.00009430156,0.000193618],"domain_scores_gemma":[0.998453,0.00009128548,0.0004550969,0.0007024121,0.0001932307,0.0001049253],"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":[0.00006478423,0.0003454348,0.02471143,0.0002264689,0.0001249533,0.000003888461,0.0004745448,0.7407151,0.0006083568,0.2090213,0.0001581599,0.02354559],"study_design_scores_gemma":[0.000304095,0.00004771032,0.0201466,0.00003048053,0.00006131602,0.00000319051,0.00001973377,0.9774168,0.00008316398,0.001395723,0.0002713805,0.0002198066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04579136,0.00004725651,0.9524153,0.0001380446,0.0002900798,0.0002215993,0.000009890858,0.0001976543,0.00088875],"genre_scores_gemma":[0.9647698,0.0001480142,0.03439193,0.00001985298,0.00004444644,0.000001760617,0.0001594441,0.00001283555,0.0004518699],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9189785,"threshold_uncertainty_score":0.954358,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005335463,0.0001165277,0.0001597022,0.0002814754,0.0001399571,0.0006830572,0.003919029,0.0000446549,0.00001188919],"category_scores_gemma":[0.001627509,0.00007965659,0.0000104983,0.001515287,0.0004682746,0.004205823,0.001552465,0.0002015858,0.000006009427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004507761,"about_ca_system_score_gemma":0.00037951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006747979,"about_ca_topic_score_gemma":0.00005403582,"domain_scores_codex":[0.9977264,0.00004239921,0.0003938225,0.0007111608,0.0008542337,0.0002719186],"domain_scores_gemma":[0.9985355,0.00007950728,0.0003285147,0.0005684296,0.0004266641,0.00006136941],"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":[0.000002755375,0.00007844544,0.1982958,0.00005934389,0.000001582383,9.771308e-8,0.00180713,0.0000103511,0.007377317,0.01820861,0.0003006461,0.7738579],"study_design_scores_gemma":[0.0002149621,0.00003357032,0.3685924,0.0001565052,0.000001946725,0.000004121652,0.0003500079,0.615091,0.001435517,0.01361904,0.0003963003,0.000104658],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9401301,0.0001594926,0.01058986,0.01553092,0.000531951,0.01947366,0.00003120963,0.0001735315,0.01337927],"genre_scores_gemma":[0.9719181,0.00001474868,0.02697645,0.00004277349,0.00001491765,0.001006367,0.000003975017,0.000002964601,0.00001969171],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7737532,"threshold_uncertainty_score":0.7282597,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001782221,0.00005783982,0.0001172976,0.0001278878,0.0001092794,0.00005881875,0.00009334963,0.00002045424,0.00001389971],"category_scores_gemma":[0.00001386397,0.00005241771,0.00003096321,0.0005751369,0.00004092342,0.0001156921,0.00002740372,0.00004961284,0.000001788859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005008712,"about_ca_system_score_gemma":0.00001089974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001362164,"about_ca_topic_score_gemma":0.00001094528,"domain_scores_codex":[0.999423,0.00005161445,0.0001428879,0.0002504422,0.00007012237,0.00006195241],"domain_scores_gemma":[0.9994854,0.0000232317,0.0001237096,0.0002803612,0.0000528109,0.00003451736],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00000241212,0.000095957,0.1512158,0.0000379984,0.0002521229,1.021713e-7,0.0003149908,0.00003636082,0.002278652,0.1105338,0.00002429382,0.7352075],"study_design_scores_gemma":[0.001159838,0.0001712842,0.5671945,0.00005254282,0.00123235,0.0000280634,0.0006240052,0.1213181,0.01948551,0.006902289,0.2810299,0.0008016918],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01246238,0.0001308996,0.985604,0.0001926911,0.000003087445,0.0002695846,0.000003665085,0.00002159023,0.001312105],"genre_scores_gemma":[0.9871511,0.00005802764,0.01232689,0.00001996671,0.00001097035,0.0003473592,0.00001914524,0.000002132551,0.00006442167],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9746887,"threshold_uncertainty_score":0.2137532,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0009645508,0.0000385003,0.00005909386,0.00004238415,0.0003589779,0.00003888305,0.07968687,0.00001668948,8.974995e-7],"category_scores_gemma":[0.008738233,0.00002222017,0.00002804703,0.0008319112,0.0001711389,0.0001959937,0.05622783,0.000135407,0.00003075276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006995846,"about_ca_system_score_gemma":0.00006127952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004424748,"about_ca_topic_score_gemma":0.00003313091,"domain_scores_codex":[0.9992136,0.0002373265,0.0002064021,0.000110578,0.0001518835,0.00008021826],"domain_scores_gemma":[0.9348066,0.0009126774,0.0001961891,0.06399283,0.00007850934,0.0000131919],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002598057,0.00009285302,0.01049728,0.00001996107,0.000034042,4.341228e-8,0.0005613671,0.0002863798,0.0006900791,0.8259072,0.07525229,0.08665591],"study_design_scores_gemma":[0.0001067329,0.000009358263,0.1236864,0.00002726251,0.00001189451,0.000001347099,0.00007431437,0.2279606,0.0003151842,0.03329159,0.6144552,0.00006008918],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.00847356,0.00301724,0.01365436,0.9624579,0.0003945488,0.000518128,0.0001100692,0.0003507428,0.01102344],"genre_scores_gemma":[0.913794,0.00175798,0.08327096,0.0001320921,0.00001408613,0.00001581369,0.0001149951,0.000006562826,0.000893549],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.9623258,"threshold_uncertainty_score":0.9996116,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}