{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":529,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":529,"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":"7313441f4fd3","filters":{"topic":"Imbalanced Data Classification Techniques"}},"results":[{"id":"W2999309192","doi":"10.1186/s12864-019-6413-7","title":"The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation","year":2020,"lang":"en","type":"article","venue":"BMC Genomics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":5819,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Tobacco Research Unit; Krembil Foundation","funders":"University of Toronto","keywords":"Binary classification; False positive paradox; Binary number; False positives and false negatives; Correlation; Confusion matrix; Artificial intelligence; Statistics; Pearson product-moment correlation coefficient; False positive rate; Confusion; Correlation coefficient; Matthews correlation coefficient; Computer science; Machine learning; Pattern recognition (psychology); Data mining; Mathematics; Support vector machine; Psychology; Arithmetic","retraction":null,"screen_n_in":null,"score":{"opus":0.06413411072449375,"gpt":0.3027767276479773,"spread":0.2386426169234835,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007043112,0.00009019958,0.00009152911,0.00004315823,0.0001355152,0.00008727822,0.0006583218,0.00005166115,0.000002584675],"category_scores_gemma":[0.0004460215,0.00006166106,0.00002856091,0.0003615876,0.00008994603,0.0002729199,0.0002590761,0.0001157856,0.000006102528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001139803,"about_ca_system_score_gemma":0.0001618144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001136223,"about_ca_topic_score_gemma":0.00002783892,"domain_scores_codex":[0.9987971,0.000199393,0.0003383674,0.0002712177,0.0002774034,0.0001164721],"domain_scores_gemma":[0.998624,0.0002963247,0.0003433118,0.0006099952,0.00009703809,0.00002929274],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001687687,0.0002529022,0.2719513,0.0001640739,0.00002278493,7.383633e-7,0.01108718,0.02218224,0.2837154,0.1964711,0.004517326,0.2094661],"study_design_scores_gemma":[0.0001728143,0.0000196408,0.3863221,0.00001194506,0.000004903224,9.225787e-7,0.00009704454,0.6071351,0.003857108,0.0008521849,0.001467205,0.00005895816],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6175244,0.0002588032,0.378004,0.00273835,0.0001917752,0.001032321,0.00001504597,0.0000659037,0.0001694158],"genre_scores_gemma":[0.9921369,0.0001389624,0.007411905,0.0002066699,0.00001972583,0.00004732059,0.00001608747,0.000007645372,0.00001481582],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5849529,"threshold_uncertainty_score":0.2514465,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1941659294","doi":"10.3233/ida-2002-6504","title":"The class imbalance problem: A systematic study1","year":2002,"lang":"en","type":"article","venue":"Intelligent Data Analysis","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3298,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Class (philosophy); Psychology; Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.0727591430494873,"gpt":0.2990844827479253,"spread":0.226325339698438,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.001486605,0.0002115884,0.0004382351,0.0002785766,0.0003470137,0.0008003945,0.008392807,0.00005787821,0.00004196136],"category_scores_gemma":[0.0003509606,0.0001382619,0.0001474088,0.002871331,0.00009846099,0.0008749968,0.001389827,0.0001848335,0.000589896],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009282968,"about_ca_system_score_gemma":0.00001830545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000468638,"about_ca_topic_score_gemma":0.0001224306,"domain_scores_codex":[0.9969931,0.0002984066,0.0007962006,0.0008533532,0.0006736997,0.0003851985],"domain_scores_gemma":[0.991289,0.0004676279,0.0004067346,0.007562072,0.0001786955,0.00009590537],"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":[0.00001669915,0.001782981,0.01173055,0.003572595,0.01482295,0.0001047954,0.003201379,0.0008829115,0.0008303174,0.4994125,0.3623678,0.1012745],"study_design_scores_gemma":[0.00005485141,0.00003141614,0.0002023973,0.0001510988,0.0006334645,0.000005970133,0.0001331456,0.9621427,0.0006532918,0.001577092,0.03410683,0.0003077343],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00003816581,0.001861458,0.9933605,0.002267629,0.00009480232,0.0005708612,0.00008440602,0.0004189529,0.001303235],"genre_scores_gemma":[0.9004814,0.005007187,0.08777721,0.0008701822,0.0001077753,0.0005569695,0.0004788981,0.00003742308,0.004682956],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9612598,"threshold_uncertainty_score":0.9969723,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2096451472","doi":"10.1109/tkde.2005.50","title":"Using AUC and accuracy in evaluating learning algorithms","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2141,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Machine learning; Computer science; Artificial intelligence; Naive Bayes classifier; Decision tree; Measure (data warehouse); Receiver operating characteristic; Algorithm; Bayes' theorem; Data mining; Support vector machine; Bayesian probability","retraction":null,"screen_n_in":null,"score":{"opus":0.09066818198011457,"gpt":0.3642777199882067,"spread":0.2736095380080922,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004324713,0.0001276593,0.0001235776,0.0002408607,0.000115294,0.0001156627,0.0004013286,0.00005380643,0.000003580371],"category_scores_gemma":[0.00003864769,0.0001392269,0.00001097022,0.0003086899,0.0000167689,0.001447589,0.0000255762,0.0002880872,0.00000661875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005457976,"about_ca_system_score_gemma":0.00003282005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001308241,"about_ca_topic_score_gemma":0.00001194664,"domain_scores_codex":[0.999059,0.0000338975,0.0002060342,0.0004149186,0.00009663967,0.0001895097],"domain_scores_gemma":[0.9991423,0.0001987749,0.00003604428,0.0005336754,0.0000283248,0.00006082984],"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":[0.000002809259,0.00006130484,0.00002767492,0.00004036618,0.00001028785,0.000001983083,0.0006082497,0.03106907,0.01580902,0.0003083105,0.00002559873,0.9520353],"study_design_scores_gemma":[0.0002095673,0.00002559086,0.0001845205,0.00007466973,0.000006041735,0.00001956216,0.00001525022,0.9869223,0.01009867,0.00001192378,0.002280105,0.0001517955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00894332,0.0003533961,0.9901127,0.00006803263,0.0001054274,0.0001086147,0.00001614932,0.0002427346,0.00004968545],"genre_scores_gemma":[0.6860757,0.000179386,0.3136319,0.00001385473,0.00004045405,0.00001263597,0.000007849952,0.0000120493,0.00002610507],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9558532,"threshold_uncertainty_score":0.5677507,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2015452969","doi":"10.1142/s0218001409007326","title":"CLASSIFICATION OF IMBALANCED DATA: A REVIEW","year":2009,"lang":"en","type":"review","venue":"International Journal of Pattern Recognition and Artificial Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1690,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Pattern Discovery Technologies (Canada)","funders":"","keywords":"Artificial intelligence; Computer science; Classifier (UML); Machine learning; One-class classification; Class (philosophy); Data classification","retraction":null,"screen_n_in":null,"score":{"opus":0.3034801403945102,"gpt":0.4311119133602611,"spread":0.1276317729657509,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001192889,0.0002726034,0.0009984187,0.0004976001,0.00003282489,0.0001657512,0.003266857,0.0001541481,0.00004975385],"category_scores_gemma":[0.0004765134,0.0002304243,0.0002362276,0.0003558412,0.00009824874,0.001004826,0.0003238042,0.0004192089,0.00005614442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007842808,"about_ca_system_score_gemma":0.0002451651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005076367,"about_ca_topic_score_gemma":0.00000289537,"domain_scores_codex":[0.9962633,0.0002481194,0.002207529,0.0004457147,0.0006840434,0.0001512601],"domain_scores_gemma":[0.9945721,0.0002649552,0.003180636,0.0007296054,0.001159244,0.00009347257],"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":[0.000003409935,0.00009957133,9.194896e-7,0.001392838,0.00007537229,0.00001565798,0.00002037146,5.614989e-8,0.00001460462,0.0006830986,0.0006055988,0.9970885],"study_design_scores_gemma":[0.00008955945,0.0003093519,0.00003494407,0.1256484,0.0005432328,0.001184706,0.00003884575,0.001633858,0.0005859846,0.02335053,0.8457787,0.000801872],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[9.2152e-7,0.5795948,0.4188398,0.000550981,0.0004851285,0.0002141633,0.000225596,0.00002450516,0.00006406708],"genre_scores_gemma":[0.0001777982,0.988915,0.009767003,0.0003534641,0.0002933676,0.00001119952,0.0004614637,0.00001365789,0.000007045217],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9962866,"threshold_uncertainty_score":0.9396431,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2103614420","doi":"10.1016/j.patcog.2007.04.009","title":"Cost-sensitive boosting for classification of imbalanced data","year":2007,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1430,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Pattern Discovery Technologies (Canada); University of Waterloo","funders":"","keywords":"Boosting (machine learning); Tacking; AdaBoost; Machine learning; Artificial intelligence; Weighting; Computer science; Classifier (UML); Statistical classification; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.1947451742491384,"gpt":0.3649999840489949,"spread":0.1702548097998565,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001182177,0.0001106838,0.0001473327,0.0001436759,0.0000743432,0.00004761008,0.0007465906,0.00007781807,0.000004385553],"category_scores_gemma":[0.000332711,0.0001189986,0.00003289246,0.0002402385,0.00004238904,0.0007889438,0.0001779479,0.00008715973,0.00002726783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005377892,"about_ca_system_score_gemma":0.00003232591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001702305,"about_ca_topic_score_gemma":0.00002251955,"domain_scores_codex":[0.9986179,0.00004446543,0.0004218011,0.0004796897,0.0002013216,0.0002348498],"domain_scores_gemma":[0.997802,0.0003919037,0.0004026185,0.0009583221,0.0003959065,0.00004929896],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001414706,0.00004780411,0.0008317798,0.00003416217,0.000008568783,8.579536e-7,0.0001170677,1.342001e-7,0.05916367,0.000297136,0.000664739,0.9388199],"study_design_scores_gemma":[0.001032438,0.0001606941,0.1327973,0.0002314814,0.00003215969,0.0000243138,0.0002472645,0.1432638,0.7136181,0.005234178,0.002855966,0.0005023165],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006755273,0.000009098921,0.9906428,0.0003115643,0.0001826801,0.0006857865,0.0005032206,0.0002433869,0.0006661333],"genre_scores_gemma":[0.8282302,0.00001276655,0.1690744,0.000228041,0.00008892014,0.00005687682,0.002286038,0.00001206046,0.00001073886],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9383176,"threshold_uncertainty_score":0.4852624,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2023639956","doi":"10.1111/j.0824-7935.2004.t01-1-00228.x","title":"A Multiple Resampling Method for Learning from Imbalanced Data Sets","year":2004,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1022,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Medical Protective Association; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Dalhousie University","keywords":"Undersampling; Oversampling; Resampling; Computer science; Machine learning; Artificial intelligence; Class (philosophy); Scheme (mathematics); Task (project management); Data mining; Pattern recognition (psychology); Mathematics; Bandwidth (computing); Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1485671637564458,"gpt":0.3960542626513615,"spread":0.2474870988949157,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005912044,0.000170555,0.0001904352,0.0001114447,0.0002466361,0.0002240389,0.002510355,0.00007432677,0.000007587821],"category_scores_gemma":[0.001042111,0.0001820849,0.00004833495,0.0003715914,0.0000523561,0.0008704952,0.0006677986,0.0002127445,0.00006528133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001046047,"about_ca_system_score_gemma":0.0001884907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001156245,"about_ca_topic_score_gemma":0.00001310205,"domain_scores_codex":[0.9980307,0.00007360439,0.0004202985,0.0008785095,0.0003250194,0.0002719278],"domain_scores_gemma":[0.996691,0.001698712,0.0002172096,0.001003679,0.0003043317,0.00008505763],"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":[0.00002143019,0.00007855353,0.0002387481,0.00001541981,0.00003085788,0.000003436541,0.000499364,0.7082524,0.001750825,0.138056,0.0005056058,0.1505474],"study_design_scores_gemma":[0.000135511,0.00003150521,0.00060933,0.00003526195,0.000003530049,0.000005079946,0.00002751347,0.7290077,0.008515215,0.2593768,0.002085436,0.0001671906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002567119,0.0001015517,0.9973353,0.0009668512,0.0002035663,0.0003522985,0.0001619051,0.0005615682,0.00006026378],"genre_scores_gemma":[0.2495023,0.00001107783,0.7489188,0.0003085135,0.00005589297,0.00005307359,0.001123354,0.0000128791,0.00001411219],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2492456,"threshold_uncertainty_score":0.7425206,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3126232929","doi":"10.1186/s13040-021-00244-z","title":"The Matthews correlation coefficient (MCC) is more reliable than balanced accuracy, bookmaker informedness, and markedness in two-class confusion matrix evaluation","year":2021,"lang":"en","type":"article","venue":"BioData Mining","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":893,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Krembil Foundation","funders":"Deutsche Forschungsgemeinschaft","keywords":"Confusion matrix; Correlation; False positive paradox; Computer science; Confusion; False positives and false negatives; Classifier (UML); Statistics; Artificial intelligence; Metric (unit); Correlation coefficient; Machine learning; Data mining; Mathematics; Psychology; Operations management","retraction":null,"screen_n_in":null,"score":{"opus":0.02927417731283126,"gpt":0.3307727570661502,"spread":0.3014985797533189,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001762428,0.0001970354,0.0002002522,0.0001260251,0.0003517381,0.0005833707,0.000739908,0.00009551262,0.00003247773],"category_scores_gemma":[0.0006715515,0.0001489541,0.00002999572,0.0006928727,0.0001055955,0.001234671,0.000704595,0.000183002,0.00002834772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001623063,"about_ca_system_score_gemma":0.0003414543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007134146,"about_ca_topic_score_gemma":0.00011563,"domain_scores_codex":[0.9977421,0.0001492541,0.0005368413,0.0005956199,0.0006270448,0.0003491307],"domain_scores_gemma":[0.9976253,0.0003633969,0.0003491719,0.001276071,0.0003178012,0.00006828783],"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":[0.0002876632,0.0003627121,0.1041116,0.0002320732,0.00007303976,0.00005586188,0.01516407,0.0007974996,0.02464442,0.03576079,0.09862348,0.7198868],"study_design_scores_gemma":[0.001067561,0.00003157498,0.05069922,0.0002263046,0.00001611916,0.00003875652,0.001250027,0.8883365,0.007416944,0.0003809202,0.05020287,0.0003331762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5127193,0.002180492,0.4586311,0.01517173,0.002717055,0.003033906,0.0003182659,0.0008298899,0.004398221],"genre_scores_gemma":[0.9420449,0.0007553545,0.0531632,0.001355942,0.00007308814,0.0002808835,0.00098885,0.00003450177,0.001303316],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.887539,"threshold_uncertainty_score":0.607417,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2068258779","doi":"10.1109/acii.2013.47","title":"Facing Imbalanced Data--Recommendations for the Use of Performance Metrics","year":2013,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":806,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute of Mental Health; McMaster University; National Institutes of Health; University of Northern British Columbia","keywords":"Skew; Receiver operating characteristic; Computer science; Artificial intelligence; Machine learning; Precision and recall; Kappa; Pattern recognition (psychology); Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2246192492723406,"gpt":0.3280352919055073,"spread":0.1034160426331666,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002901355,0.00007763216,0.0001002954,0.0001005738,0.0001383054,0.0001901226,0.001967089,0.00002950439,0.00003795454],"category_scores_gemma":[0.0002718711,0.0000508917,0.00002313783,0.000527281,0.00003948212,0.002675552,0.0004935092,0.00006449789,0.00002755129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001913881,"about_ca_system_score_gemma":0.00003309147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007035575,"about_ca_topic_score_gemma":0.00000312963,"domain_scores_codex":[0.9991527,0.00002131998,0.0002682112,0.0002528579,0.0001455939,0.0001593778],"domain_scores_gemma":[0.9969796,0.0007463465,0.0001493209,0.001867273,0.0002295352,0.00002794037],"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":[0.000001555352,0.00005195119,0.001086495,0.00002406276,0.00002630595,2.162765e-8,0.0001047426,0.00007257378,0.002635237,0.07418336,0.2656677,0.656146],"study_design_scores_gemma":[0.00008765133,0.00001984867,0.003095427,0.000006247526,0.000004331695,8.835045e-7,0.0000160127,0.7234131,0.01481984,0.0002564355,0.2581998,0.0000803974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003120379,0.00001573846,0.9938718,0.004707053,0.0001272158,0.0005284835,0.00007924305,0.0001835791,0.0001748128],"genre_scores_gemma":[0.219901,0.0001128902,0.7786322,0.0005493044,0.00001540262,0.0001554946,0.0001141137,0.000005796559,0.0005137876],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7233405,"threshold_uncertainty_score":0.3655374,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2011376672","doi":"10.1145/1007730.1007737","title":"Class imbalances versus small disjuncts","year":2004,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":681,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Class (philosophy); Focus (optics); Classifier (UML); Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.068174256664078,"gpt":0.279847161916715,"spread":0.211672905252637,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002052662,0.0002469015,0.0001971132,0.0002012451,0.000272908,0.0004478452,0.002610336,0.0001151364,0.00002557672],"category_scores_gemma":[0.0003292368,0.0002341337,0.00008341561,0.0007420649,0.000113523,0.002011453,0.0005548025,0.0002468015,0.001054363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001650662,"about_ca_system_score_gemma":0.0001370464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003110094,"about_ca_topic_score_gemma":0.00007739377,"domain_scores_codex":[0.9981174,0.00006877974,0.0003845946,0.0006315607,0.0003687071,0.000428922],"domain_scores_gemma":[0.9968916,0.0001860733,0.0001557384,0.002498135,0.0001435885,0.0001248217],"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":[0.00007889464,0.0005443797,0.0008210528,0.00003678228,0.0001209024,0.00008160621,0.003674977,0.0008715389,0.0477502,0.6932518,0.2174866,0.03528124],"study_design_scores_gemma":[0.006100406,0.0007120852,0.00541481,0.0001284391,0.00006049424,0.00004207194,0.0004895467,0.002268243,0.2297273,0.1501286,0.6026062,0.002321754],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008144988,0.00005157474,0.9044271,0.08279607,0.000939207,0.0003462788,0.00001435182,0.001199726,0.00208074],"genre_scores_gemma":[0.5063142,0.00007157026,0.4810038,0.01114897,0.0004498782,0.0004912788,0.0001699971,0.00003931447,0.0003109741],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5431231,"threshold_uncertainty_score":0.9997234,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2040010062","doi":"10.1145/1007730.1007736","title":"Learning from imbalanced data sets with boosting and data generation","year":2004,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":606,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Boosting (machine learning); Machine learning; Computer science; Artificial intelligence; Benchmarking; Classifier (UML); Training set; Gradient boosting; Ensemble learning; Data mining; Random forest","retraction":null,"screen_n_in":null,"score":{"opus":0.145876779440151,"gpt":0.3158766600273255,"spread":0.1699998805871745,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003222386,0.0001980615,0.0001673559,0.0001056951,0.0003836424,0.0006368018,0.003432518,0.00007286271,0.000008761832],"category_scores_gemma":[0.0004966659,0.0001807002,0.000008969001,0.0003690996,0.00007639533,0.006221595,0.002521853,0.000273184,0.00006503921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000469216,"about_ca_system_score_gemma":0.0001044384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001276227,"about_ca_topic_score_gemma":0.0001409449,"domain_scores_codex":[0.9978958,0.00009588418,0.0003138723,0.001135965,0.0003055945,0.000252875],"domain_scores_gemma":[0.9935837,0.0001469891,0.0001909034,0.005908929,0.00009191391,0.0000775059],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004995339,0.0004140445,0.01311982,0.00004740396,0.0002928872,0.0001422116,0.009118505,0.006061779,0.5167028,0.01936595,0.2208476,0.2138371],"study_design_scores_gemma":[0.00466569,0.0005391771,0.01449964,0.000338661,0.0001584736,0.0001302773,0.0007180895,0.7545464,0.08538315,0.01743417,0.1187609,0.002825395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02282449,0.00006450046,0.9509304,0.02507789,0.0000963905,0.0002634567,0.0001226905,0.0005454391,0.00007473868],"genre_scores_gemma":[0.3785406,0.0000515419,0.6110542,0.002644182,0.0002326781,0.00004877903,0.007379863,0.00002236726,0.00002580333],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7484846,"threshold_uncertainty_score":0.7368741,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4205471456","doi":"10.1016/j.eswa.2021.116429","title":"Financial Fraud: A Review of Anomaly Detection Techniques and Recent Advances","year":2021,"lang":"en","type":"review","venue":"Expert Systems with Applications","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":544,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Alberta Oil Sands Technology and Research Authority; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Credit card fraud; Anomaly detection; Exploit; Computer science; Insider; Artificial intelligence; Business; Finance; Computer security; Credit card; Payment","retraction":null,"screen_n_in":null,"score":{"opus":0.02676344441469306,"gpt":0.3305285859300074,"spread":0.3037651415153144,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003770123,0.000360848,0.001402191,0.0002114428,0.0001346712,0.00008457749,0.0008906742,0.0002189587,0.000003926672],"category_scores_gemma":[0.00005941988,0.0002821191,0.0001165059,0.001375816,0.00009465124,0.0003694074,0.0001962115,0.0002315624,0.000006574034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001355737,"about_ca_system_score_gemma":0.0004200467,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001785881,"about_ca_topic_score_gemma":0.000004159715,"domain_scores_codex":[0.9974954,0.0002144478,0.000951585,0.0008083131,0.0003288712,0.000201356],"domain_scores_gemma":[0.996558,0.0001185803,0.001105014,0.001717729,0.0004294487,0.00007127494],"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":[3.344787e-7,0.00003143739,1.687039e-7,0.02662112,0.00001479639,0.000001463267,0.0000123217,9.796213e-9,0.000003695473,0.008570126,0.001065919,0.9636786],"study_design_scores_gemma":[0.00002994953,0.00004638536,1.955419e-7,0.06113016,0.00004594937,0.0002174881,0.000004973464,0.000006591794,0.0001734806,0.00002901368,0.9380403,0.0002754845],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[2.134898e-9,0.5876225,0.4096781,0.00004685321,0.00004189809,0.001996116,0.00003408633,0.0002409017,0.0003395026],"genre_scores_gemma":[4.899694e-7,0.9339164,0.04987247,0.0000655711,0.0001429529,0.01579303,0.0001191841,0.00002909795,0.00006078505],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9634031,"threshold_uncertainty_score":0.9999631,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4321214126","doi":"10.1186/s13040-023-00322-4","title":"The Matthews correlation coefficient (MCC) should replace the ROC AUC as the standard metric for assessing binary classification","year":2023,"lang":"en","type":"article","venue":"BioData Mining","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":513,"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":"Receiver operating characteristic; Matthews correlation coefficient; Binary classification; Statistics; Confusion matrix; False positive rate; Artificial intelligence; Correlation; Mathematics; Binary number; Sensitivity (control systems); Metric (unit); Classifier (UML); Computer science; Pattern recognition (psychology); Machine learning; Support vector machine; Arithmetic","retraction":null,"screen_n_in":null,"score":{"opus":0.1099873591318314,"gpt":0.3627967148767833,"spread":0.2528093557449519,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004527626,0.0001897326,0.0001500108,0.0002021247,0.002025972,0.001443565,0.002546804,0.0001023849,0.000004457973],"category_scores_gemma":[0.00176413,0.0001014715,0.00007332858,0.002370559,0.0001822049,0.0008307789,0.0005902674,0.0002358752,0.00008865461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001672805,"about_ca_system_score_gemma":0.0002291622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001151915,"about_ca_topic_score_gemma":0.000005820631,"domain_scores_codex":[0.9975507,0.0002870343,0.0004909845,0.0006005724,0.0006539651,0.0004167016],"domain_scores_gemma":[0.9942104,0.002775441,0.0004784605,0.002267737,0.0002188182,0.00004914254],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009181811,0.00006502582,0.001617078,0.00003878062,0.00006402737,0.00000426817,0.002719463,0.0005908711,0.009261704,0.157185,0.4464743,0.3818877],"study_design_scores_gemma":[0.0002458281,0.000102889,0.01393474,0.00005681081,0.00002881783,0.0000147217,0.002323982,0.6029679,0.003380282,0.001024668,0.375668,0.0002514689],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003982812,0.0002232328,0.9644635,0.02789442,0.0008631662,0.001040715,0.0001058182,0.0008031839,0.0006231703],"genre_scores_gemma":[0.9387665,0.0003413442,0.05482959,0.001547972,0.0002815714,0.0009967815,0.0007729403,0.00006939482,0.002393937],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9347836,"threshold_uncertainty_score":0.999593,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1514907448","doi":"","title":"AUC: a statistically consistent and more discriminating measure than accuracy","year":2003,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":502,"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; Western University","funders":"","keywords":"Measure (data warehouse); Receiver operating characteristic; Computer science; Consistency (knowledge bases); Machine learning; Artificial intelligence; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.03047426631467451,"gpt":0.2873676294616058,"spread":0.2568933631469313,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003189974,0.000107186,0.0001119656,0.00004996001,0.0001061112,0.0002017476,0.0003453178,0.00003641021,0.00001890195],"category_scores_gemma":[0.001053193,0.00008749143,0.0000180336,0.0001491391,0.00008765717,0.0004345166,0.0001188914,0.00009175893,0.00001064217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002735372,"about_ca_system_score_gemma":0.00006611848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001511581,"about_ca_topic_score_gemma":0.000007633444,"domain_scores_codex":[0.9989615,0.00007981952,0.0001956845,0.0003348925,0.0002351482,0.0001929529],"domain_scores_gemma":[0.998962,0.000238851,0.00007407318,0.0005165861,0.0001163121,0.00009213567],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[7.996591e-7,0.00002569004,0.0006596186,0.00001159423,0.00000494973,0.000005060334,0.0002528834,1.902156e-7,0.001684417,0.9612743,0.001842613,0.03423789],"study_design_scores_gemma":[0.003468968,0.000782962,0.2189988,0.0004853475,0.0001182492,0.0009130063,0.003636598,0.1369373,0.2073388,0.3396357,0.08374012,0.003944131],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008328625,0.00003760022,0.9858076,0.001559389,0.00004452363,0.0001606508,0.000009169629,0.0003187675,0.01122942],"genre_scores_gemma":[0.5545719,0.000007813897,0.4448607,0.0003435717,0.000003680566,0.0000189136,0.000003426057,0.000004470317,0.0001855006],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6216386,"threshold_uncertainty_score":0.3567797,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W129457532","doi":"","title":"Learning from Imbalanced Data Sets: A Comparison of Various Strategies *","year":2000,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":453,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Class (philosophy); Connectionism; Computer science; Artificial intelligence; Machine learning; Training set; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.05633284169889121,"gpt":0.3302678964709482,"spread":0.273935054772057,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001848305,0.0001165188,0.0002319889,0.00005113482,0.00006861367,0.0001791565,0.002560164,0.00006273164,0.0003784327],"category_scores_gemma":[0.00003291288,0.0001069933,0.00002040572,0.0002741575,0.00005946849,0.001347209,0.000361094,0.0001792573,0.0001009441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001798847,"about_ca_system_score_gemma":0.00008492103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004603986,"about_ca_topic_score_gemma":0.00003846967,"domain_scores_codex":[0.9986498,0.00008080947,0.0003551337,0.0004780139,0.0002531769,0.000183015],"domain_scores_gemma":[0.9977657,0.0001178414,0.0001415574,0.001880575,0.00005070756,0.00004362021],"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":[0.000033918,0.0004276672,0.009843105,0.00002814619,0.00007680065,0.000007012093,0.003181478,0.001267138,0.02227564,0.07252619,0.02724778,0.8630851],"study_design_scores_gemma":[0.0004678614,0.0001948163,0.01916838,0.00004684742,0.00001226286,0.000003859884,0.0006132602,0.9021525,0.02396422,0.01235382,0.04060017,0.0004220111],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02017044,0.00009526299,0.9584292,0.0003001398,0.0000517991,0.000131782,0.00005144874,0.000878237,0.01989168],"genre_scores_gemma":[0.7756978,0.00003659354,0.223646,0.00006225349,0.00001279431,0.000005584129,0.0002726402,0.000005935143,0.0002604592],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9008853,"threshold_uncertainty_score":0.4757464,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4316469706","doi":"10.3390/info14010054","title":"A Comparison of Undersampling, Oversampling, and SMOTE Methods for Dealing with Imbalanced Classification in Educational Data Mining","year":2023,"lang":"en","type":"article","venue":"Information","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":340,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Undersampling; Oversampling; Resampling; Random forest; Computer science; Machine learning; Class (philosophy); Data mining; Sampling (signal processing); Artificial intelligence; Bandwidth (computing)","retraction":null,"screen_n_in":null,"score":{"opus":0.1915929103132564,"gpt":0.4664089199150849,"spread":0.2748160096018285,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009683475,0.0000886963,0.0001551233,0.0002932725,0.00007535575,0.0001030364,0.0005421008,0.00005746223,0.000001336778],"category_scores_gemma":[0.000332891,0.00008768291,0.00001101586,0.0004468172,0.0000412298,0.002283878,0.0001594059,0.00006780628,0.000002547192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005303537,"about_ca_system_score_gemma":0.0001038215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002968286,"about_ca_topic_score_gemma":0.00001403879,"domain_scores_codex":[0.9989897,0.00003045496,0.0004736742,0.0002044497,0.0001530755,0.0001486641],"domain_scores_gemma":[0.9983493,0.0004581049,0.0004136715,0.000604413,0.0001439146,0.00003059866],"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":[0.00006531984,0.00006155464,0.02665085,0.0003214801,0.00003109942,6.180012e-8,0.009385664,0.001103155,0.006587048,0.287988,0.001561066,0.6662447],"study_design_scores_gemma":[0.0003550835,0.00004511188,0.0471288,0.00007044253,0.000005008169,0.000001509578,0.0005735024,0.9419191,0.002192307,0.003243722,0.004345863,0.0001195354],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007340113,0.00002388627,0.9909887,0.0008116769,0.00006457167,0.0003468254,0.00003685788,0.0001430677,0.0002442492],"genre_scores_gemma":[0.2953897,0.00002009535,0.7036268,0.00004480202,0.000009318019,0.00004715758,0.0008535706,0.000004113036,0.000004403564],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.940816,"threshold_uncertainty_score":0.3575605,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2115650093","doi":"10.1007/s10994-006-8199-5","title":"Cost curves: An improved method for visualizing classifier performance","year":2006,"lang":"en","type":"article","venue":"Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":324,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta; National Research Council Canada","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Classifier (UML); Computer science; Artificial intelligence; Pattern recognition (psychology); Software; Learning curve; Visualization; Machine learning; Receiver operating characteristic; Range (aeronautics); Data mining; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.03939313177323189,"gpt":0.3477566611305509,"spread":0.308363529357319,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001156954,0.0001824243,0.0002042607,0.0001290799,0.0003365926,0.0001930566,0.0008199487,0.00007379762,0.00001374196],"category_scores_gemma":[0.0001374872,0.0001757817,0.00005827227,0.000328283,0.00002694325,0.001016457,0.000159643,0.0002764205,0.00001094283],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006660791,"about_ca_system_score_gemma":0.00004253285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000136842,"about_ca_topic_score_gemma":0.00002458299,"domain_scores_codex":[0.9984053,0.0001855618,0.000325201,0.0005226203,0.0001910572,0.0003702868],"domain_scores_gemma":[0.9988351,0.0001616723,0.0002255595,0.0005919001,0.0001209683,0.00006475226],"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":[0.00004469805,0.0002639799,0.01620242,0.0005075472,0.00002777197,0.000003424069,0.000450094,0.001654077,0.1019359,0.05387899,0.007365544,0.8176655],"study_design_scores_gemma":[0.0002663679,0.0001453083,0.002960971,0.0000510549,0.000005766939,0.000008255183,0.000008751314,0.8894117,0.01298412,0.0003785345,0.09354976,0.0002293644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000841417,0.0001646084,0.9955739,0.0006238515,0.000102734,0.0004667922,0.00000952183,0.0009886813,0.001228451],"genre_scores_gemma":[0.1313073,0.00005171987,0.8654658,0.0009059614,0.0001494958,0.0002723079,0.0002855865,0.00003941304,0.001522481],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8877577,"threshold_uncertainty_score":0.716817,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W752888290","doi":"10.1007/s10844-015-0368-1","title":"Types of minority class examples and their influence on learning classifiers from imbalanced data","year":2015,"lang":"en","type":"article","venue":"Journal of Intelligent Information Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":287,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"University of Ottawa","keywords":"Computer science; Outlier; Machine learning; Artificial intelligence; Identification (biology); Class (philosophy); Classifier (UML); Neighbourhood (mathematics); Data mining; Data type; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.07618345526224594,"gpt":0.2870352410138041,"spread":0.2108517857515581,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001351233,0.0001291436,0.0002995665,0.0002598105,0.00004487832,0.0002301155,0.001255998,0.00008366749,0.000001302124],"category_scores_gemma":[0.0006941609,0.00009461749,0.00003215619,0.0002278364,0.00005922015,0.003588855,0.0002339597,0.0002581027,0.00001696548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009659,"about_ca_system_score_gemma":0.0001547429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009760422,"about_ca_topic_score_gemma":0.00000171681,"domain_scores_codex":[0.9981136,0.0001425164,0.00103537,0.0001235224,0.0004604348,0.0001245828],"domain_scores_gemma":[0.9966052,0.0002604786,0.00156875,0.0006564761,0.0007864097,0.0001227136],"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":[0.0009484206,0.0005076478,0.0608161,0.000979377,0.0009387216,0.00001553881,0.05630567,0.05740239,0.01703307,0.2590288,0.06235243,0.4836718],"study_design_scores_gemma":[0.001272526,0.001233669,0.01091954,0.00127429,0.00003453498,0.0001692794,0.01319884,0.417071,0.04823048,0.001887337,0.5040334,0.0006750891],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07507265,0.0004770244,0.9212421,0.0001960548,0.0006396295,0.0002208979,0.00009033801,0.00007705297,0.001984222],"genre_scores_gemma":[0.9931608,0.0002162975,0.006401529,0.00008771746,0.00006216612,0.00000274592,0.00004832526,0.0000030457,0.00001732794],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9180882,"threshold_uncertainty_score":0.3858389,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2126734246","doi":"10.1007/s10115-009-0198-y","title":"Boosting support vector machines for imbalanced data sets","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":279,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"National Institutes of Health","keywords":"Support vector machine; Boosting (machine learning); Classifier (UML); Machine learning; Artificial intelligence; Computer science; Margin classifier; Data mining; Structured support vector machine; Relevance vector machine; Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.03635550629993588,"gpt":0.3092264469905259,"spread":0.27287094069059,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005966123,0.0001187576,0.0001665566,0.00012892,0.0001536226,0.0004052713,0.0008417442,0.00006325058,0.000001474214],"category_scores_gemma":[0.0001389793,0.0001043766,0.00001824412,0.0002018749,0.00001457913,0.006741441,0.0001657871,0.00005913844,0.00006596997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002859385,"about_ca_system_score_gemma":0.00006388925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004030068,"about_ca_topic_score_gemma":8.231892e-7,"domain_scores_codex":[0.9990044,0.00002704536,0.0004564001,0.0001999501,0.0001263576,0.0001858298],"domain_scores_gemma":[0.9985817,0.00006994687,0.000227254,0.0008392452,0.0002161107,0.00006570998],"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":[0.00001407183,0.00004768093,0.0004486191,0.0003374548,0.00001696981,4.414367e-7,0.002476966,0.000004635871,0.001087167,0.3098598,0.1801419,0.5055643],"study_design_scores_gemma":[0.0004115945,0.0001109259,0.004568014,0.00005826338,0.000004503831,0.0000294131,0.00004517331,0.3933702,0.0006587317,0.0003552405,0.6001729,0.000215015],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003040078,0.0002586794,0.9745212,0.0005168449,0.0005639926,0.0007288966,0.0002305308,0.0005936896,0.02228214],"genre_scores_gemma":[0.968823,0.00005544183,0.02850256,0.0005063423,0.0001770562,0.00009187179,0.001496064,0.000006733002,0.0003409789],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.968519,"threshold_uncertainty_score":0.4887382,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4313421210","doi":"10.1007/s10994-022-06268-8","title":"The class imbalance problem in deep learning","year":2022,"lang":"en","type":"article","venue":"Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":270,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; National Research Council Canada; University of Alberta","funders":"","keywords":"Artificial intelligence; Deep learning; Computer science; Machine learning; Class (philosophy); Context (archaeology)","retraction":null,"screen_n_in":null,"score":{"opus":0.007893058798280584,"gpt":0.2351205030355744,"spread":0.2272274442372938,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001594122,0.0001366829,0.000138481,0.00013024,0.001227841,0.0002133822,0.001556248,0.00002933665,0.0000339925],"category_scores_gemma":[0.0002161822,0.000117784,0.00004187259,0.0008189601,0.00004274244,0.000287173,0.001078749,0.001330353,0.00002558936],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001804565,"about_ca_system_score_gemma":0.00003920694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007687417,"about_ca_topic_score_gemma":0.00004413929,"domain_scores_codex":[0.9977947,0.000683082,0.0002989678,0.000421414,0.0003990731,0.0004028009],"domain_scores_gemma":[0.9989344,0.000276936,0.0002117651,0.000503498,0.00003239681,0.00004094506],"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":[0.00003796087,0.0001318572,0.2537819,0.00002802194,0.00002185796,0.00006463336,0.003214826,0.1116962,0.005872093,0.157999,0.001389754,0.4657619],"study_design_scores_gemma":[0.0001943378,0.00009053003,0.008757674,0.00000590597,9.981333e-7,0.00002240645,0.0001248601,0.60501,0.0001643542,0.001644659,0.3838211,0.0001631786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01687898,0.002367247,0.9346989,0.0142694,0.0005359176,0.0009831137,0.000005267758,0.003266586,0.02699455],"genre_scores_gemma":[0.9791753,0.00007677604,0.01763399,0.0002723296,0.00002787327,0.0002595936,0.00002543767,0.000021608,0.002507115],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9622963,"threshold_uncertainty_score":0.9443681,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4378417908","doi":"10.1016/j.asoc.2023.110415","title":"A broad review on class imbalance learning techniques","year":2023,"lang":"en","type":"review","venue":"Applied Soft Computing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":258,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Class (philosophy); Support vector machine; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.05958989506665886,"gpt":0.3534783318788895,"spread":0.2938884368122306,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001982061,0.0009204366,0.002565868,0.0004995829,0.0004089971,0.0003312755,0.00400414,0.0004801251,0.000005453289],"category_scores_gemma":[0.0003797013,0.0008456056,0.0004788668,0.002346359,0.00009316116,0.0001760077,0.001635634,0.001950201,0.001342878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003504432,"about_ca_system_score_gemma":0.0003085405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004151225,"about_ca_topic_score_gemma":3.394045e-7,"domain_scores_codex":[0.9946837,0.0003519537,0.001556454,0.001801302,0.0007499433,0.0008565895],"domain_scores_gemma":[0.9944912,0.001239717,0.001643485,0.002345433,0.0001249541,0.0001552606],"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":[4.337615e-7,0.00002370887,1.894353e-7,0.02131077,0.00004102675,0.00001179603,0.00001705521,0.000001697626,0.000003351183,0.02505629,0.007811601,0.9457221],"study_design_scores_gemma":[0.00004410763,0.00004059418,5.350673e-7,0.07730808,0.00007920319,0.00002874291,0.000002098467,0.0006641617,0.00003052401,0.0004470755,0.9205841,0.0007707304],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.715452e-8,0.7219288,0.2639842,0.0001056191,0.0001777563,0.0017277,0.000008947967,0.007196222,0.004870714],"genre_scores_gemma":[0.000003103972,0.9328093,0.06471898,0.001010427,0.0002393488,0.0005255278,0.000205148,0.0001579387,0.0003302523],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9449514,"threshold_uncertainty_score":0.9994347,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2012290523","doi":"10.1016/j.eswa.2011.09.058","title":"Gradient boosting trees for auto insurance loss cost modeling and prediction","year":2011,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":251,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Royal Bank of Canada","funders":"","keywords":"Computer science; Gradient boosting; Softmax function; Support vector machine; Feature selection; Data mining; Parameterized complexity; Generalized linear model; Hinge loss; Artificial neural network; Data pre-processing; Machine learning; Artificial intelligence; Algorithm; Mathematical optimization; Random forest; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04805340199553818,"gpt":0.2653546485366028,"spread":0.2173012465410646,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001941751,0.0001296046,0.0001400126,0.00008476454,0.000297069,0.00009790441,0.0004205127,0.00005361875,4.319757e-7],"category_scores_gemma":[0.00001367283,0.0001115143,0.00001864309,0.0002295883,0.00005131555,0.0004830592,0.00005668572,0.00005938521,0.000004021967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006031568,"about_ca_system_score_gemma":0.00003491734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001267412,"about_ca_topic_score_gemma":0.00001046104,"domain_scores_codex":[0.9988924,0.00002355613,0.0002885644,0.0004554775,0.0001422358,0.0001977914],"domain_scores_gemma":[0.9988533,0.00004678042,0.0001465597,0.0006961369,0.0001718796,0.00008537834],"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":[0.00005777618,0.0004018756,0.01099592,0.0002154321,0.00008569095,0.000002156251,0.01088579,0.001202825,0.008124596,0.9083772,0.003009928,0.05664087],"study_design_scores_gemma":[0.0004033414,0.00009909021,0.002444819,0.0001197985,0.000005733598,0.00006008975,0.000275215,0.9672219,0.002000777,0.001107597,0.02598058,0.0002811279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008836997,0.0003800306,0.9954076,0.0001334235,0.00006810381,0.001907405,0.00006784334,0.0006355011,0.0005164376],"genre_scores_gemma":[0.8300952,0.00004416025,0.1597288,0.00004650876,0.00007125638,0.009916168,0.00003059384,0.00001482598,0.00005254758],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.966019,"threshold_uncertainty_score":0.454742,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2137539029","doi":"10.1109/icdm.2003.1250975","title":"Comparing naive Bayes, decision trees, and SVM with AUC and accuracy","year":2004,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":235,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Support vector machine; Naive Bayes classifier; Computer science; Machine learning; Decision tree; Artificial intelligence; Receiver operating characteristic; Measure (data warehouse); Data mining; Bayes' theorem; Statistical classification; Bayesian probability","retraction":null,"screen_n_in":null,"score":{"opus":0.0216262061828978,"gpt":0.2627378892251433,"spread":0.2411116830422455,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001216823,0.0000980916,0.0001163749,0.0000746104,0.0001005007,0.0002139312,0.0003338693,0.00003245587,0.000003062905],"category_scores_gemma":[0.00004320432,0.00007226935,0.000007159459,0.0001796029,0.00006701989,0.0008340417,0.0002499028,0.00007504496,0.000006599925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003208216,"about_ca_system_score_gemma":0.00003519023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009121053,"about_ca_topic_score_gemma":0.0001007419,"domain_scores_codex":[0.9992243,0.00001193521,0.0001296673,0.0003427536,0.000153951,0.0001374112],"domain_scores_gemma":[0.9992791,0.0001093248,0.00005756942,0.0004348558,0.00004407367,0.00007508155],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00004281009,0.0001084183,0.02603385,0.00001920893,0.00001973868,0.00002476329,0.0008394358,0.00004816058,0.003610101,0.6153198,0.002693424,0.3512402],"study_design_scores_gemma":[0.004955229,0.0007770135,0.7198321,0.0004617418,0.00002281913,0.0005234833,0.0002283538,0.05175205,0.07923075,0.1134746,0.02740342,0.001338347],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06235385,0.00009062247,0.9350342,0.0005762143,0.00001896248,0.0001270434,0.000001251377,0.0003008349,0.001497088],"genre_scores_gemma":[0.6306667,0.0000531858,0.3690935,0.0001397254,0.000005938151,0.000006087796,0.000002151246,0.000003406055,0.00002929126],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6937983,"threshold_uncertainty_score":0.2947059,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2147834490","doi":"","title":"Exploiting the Cost (In)sensitivity of Decision Tree Splitting Criteria","year":2000,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":202,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Pruning; Decision tree; Sensitivity (control systems); Computer science; Tree (set theory); Class (philosophy); Incremental decision tree; Total cost; Mathematical optimization; Decision tree learning; ID3 algorithm; Artificial intelligence; Machine learning; Mathematics; Statistics; Engineering; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.03196853507049728,"gpt":0.3018882251731047,"spread":0.2699196901026074,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00126585,0.00007315241,0.0001128739,0.00005863887,0.00006253148,0.00007222511,0.0005180934,0.00003192,0.00008586165],"category_scores_gemma":[0.0001801994,0.00005197141,0.00002968846,0.0003486704,0.00004434093,0.0004980162,0.0001268471,0.00008482084,0.00002883811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000270682,"about_ca_system_score_gemma":0.00001801989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008983292,"about_ca_topic_score_gemma":0.0000541023,"domain_scores_codex":[0.9989862,0.0001356181,0.0002886063,0.0002407308,0.0001855927,0.0001631871],"domain_scores_gemma":[0.9985744,0.0005694333,0.00007114342,0.000713744,0.00004826942,0.00002298311],"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":[0.000003986138,0.00002498072,0.0004606505,0.000002559589,8.468371e-7,0.000004558347,0.0002270436,0.000009922086,0.01196393,0.01200309,0.0005786431,0.9747198],"study_design_scores_gemma":[0.0004935345,0.00005449278,0.1215522,0.0002180721,0.000003379106,0.00006256448,0.0002452388,0.5172234,0.3387774,0.013339,0.007660895,0.0003697747],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0947536,0.000007566935,0.8929836,0.0006417736,0.00003907899,0.0001727703,0.000002718208,0.0001665916,0.01123233],"genre_scores_gemma":[0.8528109,0.00001399317,0.1468044,0.0002217502,0.00001583927,0.00001236622,0.000001662242,0.000003810296,0.0001152157],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.97435,"threshold_uncertainty_score":0.2119333,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4382196087","doi":"10.1016/j.neuroimage.2023.120253","title":"Class imbalance should not throw you off balance: Choosing the right classifiers and performance metrics for brain decoding with imbalanced data","year":2023,"lang":"en","type":"article","venue":"NeuroImage","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":196,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; Montreal Neurological Institute and Hospital; Concordia University; University of Alberta; Université de Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Courtois Foundation; Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Canada Research Chairs; Canada First Research Excellence Fund; Canadian Institutes of Health Research; Mitacs; McGill University","keywords":"Magnetoencephalography; Computer science; Robustness (evolution); Metric (unit); Artificial intelligence; Binary classification; Decoding methods; Machine learning; Class (philosophy); Random forest; Performance metric; Receiver operating characteristic; Electroencephalography; Brain activity and meditation; Binary number; Sensitivity (control systems); Pattern recognition (psychology); Support vector machine; Mathematics; Psychology; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.08644324549238729,"gpt":0.317593803694679,"spread":0.2311505582022917,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001550674,0.0003723094,0.0003808747,0.0002938758,0.0007095723,0.000685703,0.003499136,0.0001225506,0.000003608162],"category_scores_gemma":[0.0006447655,0.0002692043,0.0000503652,0.002118497,0.0003198743,0.002099719,0.001107667,0.0005030368,0.00002184526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007565531,"about_ca_system_score_gemma":0.0001300209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004473407,"about_ca_topic_score_gemma":0.000007029324,"domain_scores_codex":[0.9965854,0.0001370146,0.0004492671,0.001373037,0.0006698498,0.0007854052],"domain_scores_gemma":[0.9951777,0.001064541,0.0003341761,0.003122221,0.0001641197,0.0001372522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004621868,0.0002310687,0.04775582,0.0007479059,0.0001784906,0.0001496991,0.001154275,0.00019235,0.1625078,0.04832892,0.4328455,0.305446],"study_design_scores_gemma":[0.001012602,0.0002466268,0.06768133,0.00008609117,0.00002651467,0.00006648264,0.00004991933,0.806309,0.01674672,0.0003689828,0.1068365,0.0005691343],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07152924,0.0002912875,0.8764067,0.04234805,0.001037635,0.002300039,0.000695324,0.00306615,0.002325607],"genre_scores_gemma":[0.9208063,0.001063328,0.07042202,0.005891896,0.000238012,0.000249962,0.0003261941,0.00009890658,0.0009033168],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8492771,"threshold_uncertainty_score":0.999976,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4321380810","doi":"10.1109/tim.2023.3246470","title":"A Systematic Review on Imbalanced Learning Methods in Intelligent Fault Diagnosis","year":2023,"lang":"en","type":"review","venue":"IEEE Transactions on Instrumentation and Measurement","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":191,"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, Okanagan Campus; University of British Columbia","funders":"National Key Research and Development Program of China","keywords":"Fault (geology); Computer science; Process (computing); Field (mathematics); Set (abstract data type); Artificial intelligence; Machine learning; Data processing; Data mining; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1601030557112119,"gpt":0.4134479746721709,"spread":0.253344918960959,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002671075,0.0004746275,0.001526548,0.0007720346,0.0001634937,0.000154857,0.0005847948,0.0001674935,0.00001451226],"category_scores_gemma":[0.0001501401,0.0003994233,0.0002815984,0.001182093,0.00003277932,0.0002456566,0.000007764257,0.000651011,0.0001295362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009376443,"about_ca_system_score_gemma":0.0001582035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000157901,"about_ca_topic_score_gemma":0.00001843356,"domain_scores_codex":[0.995208,0.001407611,0.0014789,0.0007755241,0.0008372163,0.0002927818],"domain_scores_gemma":[0.9979416,0.0003872066,0.0006789878,0.0007484735,0.0001297386,0.0001140411],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.000001519532,0.0001000744,9.749202e-8,0.2506253,0.0001047653,0.000002028866,0.00008858191,0.00002030255,0.000002796268,0.0002206566,0.00005952031,0.7487743],"study_design_scores_gemma":[0.0003128413,0.0002826882,0.000001413663,0.9510655,0.0007414902,0.00001739346,0.00007495935,0.0007833231,0.001198507,0.00007869612,0.04474948,0.0006937158],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[7.098007e-8,0.4414683,0.5552712,0.00009718761,0.0003143429,0.00250699,0.00001237726,0.0002828204,0.00004674129],"genre_scores_gemma":[0.00002455806,0.979463,0.01225217,0.0003092865,0.000009157578,0.007776627,0.00001946442,0.00004158191,0.0001041594],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.7480806,"threshold_uncertainty_score":0.9998457,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2167793421","doi":"10.1145/347090.347126","title":"Explicitly representing expected cost","year":2000,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":186,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Citation; Library science; Computer science; Information technology; Operations research; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02325582657334252,"gpt":0.2720641851169671,"spread":0.2488083585436245,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000113129,0.00006918934,0.00007137437,0.00005166473,0.00007433169,0.0001360334,0.0008284387,0.00003190763,0.0008507746],"category_scores_gemma":[0.00002931779,0.00006349706,0.00002393624,0.0003498264,0.00001894818,0.0006096108,0.00009783802,0.00006325873,0.0005674009],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002053449,"about_ca_system_score_gemma":0.00001488595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002888185,"about_ca_topic_score_gemma":0.000001707657,"domain_scores_codex":[0.9991474,0.00002982331,0.0001637648,0.0003203917,0.0001571051,0.0001815725],"domain_scores_gemma":[0.9988577,0.00003708561,0.00003442834,0.0009825589,0.00004035409,0.00004788566],"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":[0.000002753146,0.00006590931,0.0006927777,0.000002809133,0.000005981613,0.000008891496,0.0003008614,0.000006260064,0.013659,0.1477595,0.06681031,0.770685],"study_design_scores_gemma":[0.0004833428,0.00004557001,0.01608516,0.00002619644,0.000003076347,0.00004998236,0.00007546761,0.07032817,0.3880524,0.009410069,0.514791,0.0006496168],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003558415,0.00001124784,0.826584,0.000896981,0.00003842811,0.0001546518,0.000001195306,0.001623465,0.1671316],"genre_scores_gemma":[0.5682425,0.00003434155,0.4111982,0.001156505,0.000065817,0.0001273102,0.00001545406,0.00001201218,0.01914791],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7700354,"threshold_uncertainty_score":0.9315385,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3186924568","doi":"10.1109/access.2021.3096799","title":"Intelligent Fraud Detection in Financial Statements Using Machine Learning and Data Mining: A Systematic Literature Review","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":186,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Audit; Cluster analysis; Anomaly detection; Unsupervised learning; Focus (optics); Key (lock); Machine learning; Heuristic; Finance; Artificial intelligence; Data mining; Data science; Accounting; Computer security; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.09531188645907628,"gpt":0.4084828426708726,"spread":0.3131709562117964,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006991263,0.0001167392,0.0002547683,0.0001208938,0.00007718636,0.0004644769,0.0009857827,0.00005098416,0.000003371126],"category_scores_gemma":[0.0005553522,0.0001090578,0.00001511764,0.0008796505,0.00001297686,0.001985278,0.0006972809,0.0002027644,0.000001962293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000600216,"about_ca_system_score_gemma":0.00006274406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001869101,"about_ca_topic_score_gemma":0.0000700424,"domain_scores_codex":[0.998485,0.0002548321,0.000421356,0.0004830255,0.0002019676,0.0001538717],"domain_scores_gemma":[0.9987595,0.00006807246,0.0002264226,0.000800473,0.0001078948,0.00003762935],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005027125,0.000809279,0.02566748,0.4508148,0.0001880035,0.001644726,0.00533436,0.0001841157,0.06130847,0.001890161,0.003154974,0.4489534],"study_design_scores_gemma":[0.0005590389,0.00007974231,0.001373262,0.1734722,0.00008383441,0.0003872548,0.00005276944,0.7068633,0.1099217,0.0007680224,0.00556264,0.0008761898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007610324,0.03903184,0.9522516,0.0001601017,0.0002938123,0.0004857101,0.00002404213,0.000121203,0.0000214312],"genre_scores_gemma":[0.7857246,0.08723909,0.1241367,0.001971164,0.000142161,0.0001884745,0.0003780052,0.00004572705,0.0001740722],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8281148,"threshold_uncertainty_score":0.4478962,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1982672081","doi":"10.5539/gjhs.v7n1p194","title":"Using Data Mining to Detect Health Care Fraud and Abuse: A Review of Literature","year":2014,"lang":"en","type":"review","venue":"Global Journal of Health Science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":154,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Tehran University of Medical Sciences and Health Services","keywords":"Context (archaeology); Health care; Payment; Knowledge extraction; Data science; Data mining; Computer science; Service (business); Business; Political science; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.1291464525878868,"gpt":0.4738601705266665,"spread":0.3447137179387796,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.008310511,0.0003381918,0.002338921,0.0004785378,0.0003107454,0.0002845715,0.006874873,0.0001036402,8.075295e-7],"category_scores_gemma":[0.0006154468,0.0002563953,0.0001310301,0.00401802,0.0002169024,0.001252391,0.001212672,0.0004438455,0.00000153979],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008981131,"about_ca_system_score_gemma":0.008274484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002348474,"about_ca_topic_score_gemma":0.000003641087,"domain_scores_codex":[0.994385,0.0004544207,0.002409564,0.0008421469,0.001286922,0.0006219603],"domain_scores_gemma":[0.9914605,0.00008800187,0.004752984,0.002217228,0.0008868713,0.00059441],"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":[6.754503e-7,0.00000543281,0.000003926767,0.05591032,0.000004997055,0.000003762299,0.0001153975,2.010031e-7,2.717926e-7,0.0002005232,0.002963474,0.940791],"study_design_scores_gemma":[0.00005577786,0.0002538266,0.00002132214,0.3060915,0.00002490397,0.001622611,0.00001300876,0.0000687283,8.321339e-7,0.00002746449,0.6916303,0.0001897112],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[9.630439e-7,0.8124669,0.1857978,0.0005479375,0.0003850441,0.0005712204,0.0001892631,0.00002436996,0.00001658004],"genre_scores_gemma":[0.000004420544,0.6358826,0.3624532,0.001583565,0.00005645338,0.000002008006,0.00001110811,0.000006145915,4.568382e-7],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9406013,"threshold_uncertainty_score":0.9999889,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2166045895","doi":"10.1007/11731139_15","title":"Boosting Prediction Accuracy on Imbalanced Datasets with SVM Ensembles","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":149,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Boosting (machine learning); Computer science; Support vector machine; Artificial intelligence; Machine learning; Data mining; Sampling (signal processing); Context (archaeology); Ensemble learning; Oversampling; Pattern recognition (psychology); Data sampling; Bandwidth (computing)","retraction":null,"screen_n_in":null,"score":{"opus":0.0174732329986504,"gpt":0.253741026703638,"spread":0.2362677937049876,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007230949,0.0006447018,0.0005011036,0.0008650728,0.0003649913,0.0007445363,0.003766307,0.0003132116,0.00000799809],"category_scores_gemma":[0.0001882783,0.0005441923,0.00006782109,0.0007072255,0.0005769355,0.001316939,0.0009130203,0.0009192692,0.00004255215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004387645,"about_ca_system_score_gemma":0.0004641849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003183942,"about_ca_topic_score_gemma":0.00003899021,"domain_scores_codex":[0.9952155,0.00004497025,0.0006274629,0.002081851,0.001325152,0.0007050276],"domain_scores_gemma":[0.9955117,0.0007370113,0.0006054222,0.002778856,0.0002278914,0.0001391768],"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":[0.00004253322,0.0001219458,0.0003271952,0.00009605936,0.00002328889,0.0002062745,0.0002499663,0.02834466,0.002069205,0.03474829,0.003946203,0.9298244],"study_design_scores_gemma":[0.001354552,0.00150662,0.003971905,0.003471405,0.0000353489,0.0004081308,3.639459e-7,0.8018651,0.05131619,0.09681084,0.03626275,0.002996763],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005150056,0.00008517252,0.9925771,0.0005582008,0.0005911415,0.0006001991,0.0002437742,0.0007448418,0.004548123],"genre_scores_gemma":[0.1408366,0.00006580652,0.854803,0.002290781,0.0007294677,0.0000626413,0.0007817819,0.00008992726,0.0003400038],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9268276,"threshold_uncertainty_score":0.999701,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2157751754","doi":"10.1109/tkde.2006.131","title":"Test strategies for cost-sensitive decision trees","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":145,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Hong Kong University of Science and Technology","keywords":"Computer science; Medical diagnosis; Decision tree; Machine learning; Test (biology); Artificial intelligence; Test case; Process (computing); Medical costs; Data mining; Health care; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.02750885075641095,"gpt":0.2859938931044155,"spread":0.2584850423480046,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000150702,0.0001414718,0.0001266255,0.0001656278,0.0001238907,0.0001864817,0.0005170818,0.00005941732,0.000001495578],"category_scores_gemma":[0.00001378495,0.0001397748,0.00002550986,0.0002248815,0.00002306067,0.001118471,0.0000104551,0.0001033851,0.00001196586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003096646,"about_ca_system_score_gemma":0.00004309484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000127861,"about_ca_topic_score_gemma":0.00007561653,"domain_scores_codex":[0.9991253,0.000007476686,0.0001887185,0.0004169702,0.00008169304,0.000179832],"domain_scores_gemma":[0.9985084,0.0005348213,0.0000298615,0.000809367,0.00007151535,0.00004601159],"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":[0.00004069004,0.0007419148,0.00001592206,0.0001374785,0.00004983195,0.000009757272,0.0003729459,0.01906031,0.07036135,0.0450838,0.0155964,0.8485296],"study_design_scores_gemma":[0.0004426764,0.000104,0.0005472545,0.0000828764,0.00001694826,0.0000169346,0.00003084982,0.8973285,0.07337502,0.0008244778,0.02692505,0.0003054193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000287398,0.000094606,0.9978827,0.00005465498,0.0002334535,0.0002648158,0.0005355648,0.0004254546,0.000221413],"genre_scores_gemma":[0.8282907,0.00005557546,0.1713178,0.00001474395,0.00006024666,0.00008239884,0.0000799073,0.00001518114,0.00008349338],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8782682,"threshold_uncertainty_score":0.5699851,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388099759","doi":"10.1016/j.eswa.2023.122156","title":"Financial fraud detection using graph neural networks: A systematic review","year":2023,"lang":"en","type":"review","venue":"Expert Systems with Applications","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":144,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Wilfrid Laurier University; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Graph; Artificial neural network; Artificial intelligence; Machine learning; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.06262470066207466,"gpt":0.3396527258724665,"spread":0.2770280252103919,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007831998,0.0006717124,0.002669726,0.0004741597,0.0004413367,0.0003643677,0.002342365,0.0003651552,0.000001130312],"category_scores_gemma":[0.0001136664,0.0005011428,0.000375233,0.003837416,0.00007418582,0.0004495739,0.0002602875,0.0004767544,0.0001268267],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003643878,"about_ca_system_score_gemma":0.0002764757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000797837,"about_ca_topic_score_gemma":0.000009468493,"domain_scores_codex":[0.9954456,0.0005521597,0.001784171,0.001156432,0.0005650977,0.0004965472],"domain_scores_gemma":[0.9940347,0.0003031784,0.00188336,0.003366194,0.0002739551,0.0001386315],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[5.547178e-7,0.00004474529,7.554577e-8,0.948245,0.0001287282,0.000007366762,0.00003178677,0.00004613054,7.564748e-7,0.00852731,0.001606444,0.0413611],"study_design_scores_gemma":[0.00006883207,0.00003847877,1.114232e-7,0.5887665,0.0006227036,0.0004669471,0.00001057362,0.03622296,8.263453e-7,0.00005684238,0.3728431,0.0009021881],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[2.785482e-9,0.5021304,0.4901414,0.00001225242,0.0001715709,0.006587726,0.00002187829,0.0009206858,0.00001405537],"genre_scores_gemma":[0.000004407521,0.9468744,0.005666037,0.0001313708,0.0003573309,0.04661574,0.0001468211,0.0001072012,0.00009673688],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4844754,"threshold_uncertainty_score":0.999744,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W83133245","doi":"","title":"Thresholding for making classifiers cost-sensitive","year":2006,"lang":"en","type":"article","venue":"National Conference on Artificial Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":143,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Thresholding; Computer science; Artificial intelligence; Balanced histogram thresholding; Pattern recognition (psychology); Machine learning; Sensitivity (control systems); Histogram; Image (mathematics); Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1945087779740975,"gpt":0.3871194660419463,"spread":0.1926106880678488,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006410741,0.000198229,0.0001764227,0.0002810632,0.0003037255,0.0004031119,0.0008458019,0.0001194509,0.0000315303],"category_scores_gemma":[0.0004026912,0.0002068172,0.00008104472,0.0004576385,0.0001434378,0.0005680525,0.00009416509,0.0002022475,0.0001396801],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002429974,"about_ca_system_score_gemma":0.000267366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001487132,"about_ca_topic_score_gemma":0.00003227656,"domain_scores_codex":[0.9978239,0.00005808276,0.0004826392,0.0006250776,0.0006569392,0.0003533873],"domain_scores_gemma":[0.9977926,0.0004408709,0.0002291568,0.0003612912,0.001124047,0.00005205492],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002153006,0.00006001296,0.000009546999,0.000003918525,0.000004168054,0.000001523458,0.00004353057,0.00042839,0.006044582,0.9192563,0.001435378,0.07269118],"study_design_scores_gemma":[0.00002502334,0.00005540259,0.0002910609,0.00003777448,0.000002217589,0.000003280962,0.00005667808,0.2909472,0.1518375,0.5535893,0.002930142,0.0002244495],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002139609,0.000006200183,0.9706386,0.003659766,0.0002974159,0.0005790643,0.00007109621,0.0003419329,0.0241919],"genre_scores_gemma":[0.9190659,0.000004639559,0.07944835,0.0008642934,0.0001798584,0.0002007986,0.00005654,0.00001242043,0.0001672281],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9188519,"threshold_uncertainty_score":0.8433762,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2152325113","doi":"10.1007/3-540-45153-6_7","title":"Concept-Learning in the Presence of Between-Class and Within-Class Imbalances","year":2001,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":136,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Class (philosophy); Focus (optics); Sampling (signal processing); Artificial intelligence; Mechanism (biology); Order (exchange); Machine learning; Theoretical computer science; Epistemology; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.02099275441995642,"gpt":0.2643135857297962,"spread":0.2433208313098398,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001952817,0.0004492037,0.000622823,0.0006589307,0.0001945907,0.0004104078,0.004842696,0.0003061476,0.000005668793],"category_scores_gemma":[0.0002767608,0.0003453357,0.0000655842,0.001031202,0.001783786,0.0008218718,0.0011517,0.001292854,0.000004653632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001313866,"about_ca_system_score_gemma":0.0003587101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004355633,"about_ca_topic_score_gemma":0.00005906149,"domain_scores_codex":[0.996034,0.0001594613,0.0007832258,0.001344407,0.001134026,0.0005449147],"domain_scores_gemma":[0.9959664,0.001578771,0.0006653437,0.001491181,0.0002084182,0.00008988541],"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":[0.00001218481,0.00006357348,0.008930239,0.0001352172,0.00002185485,0.0001117991,0.008680022,0.01025467,0.0007009912,0.1925872,0.0001403043,0.778362],"study_design_scores_gemma":[0.0009465923,0.0008693442,0.0113456,0.002126172,0.0000269066,0.0002369398,0.00001252689,0.5598142,0.01293109,0.3967091,0.01297337,0.002008199],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005639021,0.0004972621,0.9928874,0.001523388,0.0003444943,0.0005126465,0.00001068191,0.0001533206,0.003506934],"genre_scores_gemma":[0.8523154,0.000201601,0.1463007,0.0007219031,0.0002208292,0.00002321296,0.00001253304,0.00002560524,0.0001782272],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8517515,"threshold_uncertainty_score":0.9998999,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1541033774","doi":"10.1007/978-3-642-13059-5_22","title":"Overlap versus Imbalance","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":134,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Classifier (UML); Interdependence; Training set; Isolation (microbiology); Artificial intelligence; Machine learning; Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.02038288687829102,"gpt":0.2655751414727915,"spread":0.2451922545945005,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008133386,0.0005901762,0.0005237971,0.0007929769,0.0002724124,0.0006825423,0.006708858,0.0005854804,0.00003842799],"category_scores_gemma":[0.0002082877,0.0005737853,0.0001293304,0.0006729316,0.001027458,0.001055323,0.001844122,0.001650321,0.000183831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003585737,"about_ca_system_score_gemma":0.0006720114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001280514,"about_ca_topic_score_gemma":0.0000577765,"domain_scores_codex":[0.9955101,0.00002534443,0.0005599478,0.001956109,0.00119109,0.0007574345],"domain_scores_gemma":[0.9951813,0.0005110152,0.0004168516,0.003375823,0.0003123017,0.0002027569],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002036248,0.0000434146,0.0000693534,0.00003448911,0.00001318234,0.00008283603,0.0002555963,0.0003718208,0.004258779,0.214584,0.0001486802,0.7801175],"study_design_scores_gemma":[0.001514722,0.0006212053,0.0008835513,0.000607508,0.0000201543,0.0001594172,1.865293e-7,0.2312115,0.06869977,0.6021608,0.0908526,0.003268608],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001843576,0.0001592007,0.9824937,0.0009625262,0.004121608,0.0003757837,0.00001678271,0.0006451822,0.0112068],"genre_scores_gemma":[0.04117057,0.00008994727,0.9560795,0.001295606,0.0006460221,0.00002530397,0.00002102235,0.0000527158,0.000619303],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7768489,"threshold_uncertainty_score":0.9996713,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2912895282","doi":"10.1016/j.neucom.2018.11.100","title":"Pre-processing approaches for imbalanced distributions in regression","year":2019,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":130,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"European Regional Development Fund; Fundação para a Ciência e a Tecnologia","keywords":"Computer science; Regression; Machine learning; Variable (mathematics); Relevance (law); Regression analysis; Artificial intelligence; Context (archaeology); Feature selection; Set (abstract data type); Data mining; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.03953302892903467,"gpt":0.2872695688861338,"spread":0.2477365399570991,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000312835,0.0001402926,0.0001774154,0.0001172571,0.0001272482,0.0001554194,0.0008109495,0.00006631316,0.000001054713],"category_scores_gemma":[0.00007960042,0.0001304592,0.0000467855,0.0004846297,0.00002076808,0.0005119629,0.0002736837,0.0001796605,0.000009805332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006065127,"about_ca_system_score_gemma":0.00006292711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002921887,"about_ca_topic_score_gemma":5.916257e-7,"domain_scores_codex":[0.998585,0.00005318557,0.0003052262,0.0005663274,0.0001561135,0.0003341509],"domain_scores_gemma":[0.9990228,0.0001428015,0.0001853403,0.0005532581,0.0000529815,0.00004283051],"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":[0.00002316316,0.0001811023,0.02264263,0.000229981,0.000003974572,0.000003379657,0.0006091256,0.001242776,0.0233996,0.06456565,0.000891034,0.8862076],"study_design_scores_gemma":[0.0004681148,0.00005405276,0.05397982,0.0001581389,0.000001538142,0.000008830089,0.0000178775,0.9235759,0.01495003,0.003125796,0.00343443,0.00022548],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06668311,0.00003273218,0.9309683,0.0004790309,0.0001454183,0.0006062023,0.000006269956,0.000467029,0.0006118909],"genre_scores_gemma":[0.8459752,0.000001784115,0.1537273,0.00008961211,0.00004032136,0.00006200092,0.00002922761,0.00001144336,0.00006307198],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9223331,"threshold_uncertainty_score":0.5319971,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3207601856","doi":"10.1038/s41592-021-01302-4","title":"The class imbalance problem","year":2021,"lang":"en","type":"article","venue":"Nature Methods","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":126,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Class (philosophy); Computational biology; Computer science; Biology; Chemistry; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01395549485720575,"gpt":0.3723376864885252,"spread":0.3583821916313195,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001738654,0.0001194176,0.0001344084,0.00003275551,0.000250799,0.0002973654,0.001522467,0.000229702,0.000006345722],"category_scores_gemma":[0.0007548993,0.00008193837,0.00006269118,0.0007841483,0.0000633254,0.000286927,0.0003730097,0.0007781714,0.00001952159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005383385,"about_ca_system_score_gemma":0.0001476587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.88418e-7,"about_ca_topic_score_gemma":0.000003003493,"domain_scores_codex":[0.9981462,0.0006577484,0.0002111118,0.0004404762,0.0002693913,0.0002750118],"domain_scores_gemma":[0.9972653,0.0006997266,0.0001121418,0.001580024,0.000287617,0.00005522381],"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":[0.000001363655,0.00001528213,0.00005776086,0.000006036728,0.000008963164,0.000007091937,0.00003624993,8.133895e-7,0.02597216,0.6475908,0.02922209,0.2970814],"study_design_scores_gemma":[0.0000611337,0.000008867461,0.0011023,0.000008772625,0.000002229005,0.00003021585,0.000007857522,0.002753034,0.2015782,0.05741728,0.7369229,0.0001072941],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001296697,0.003268911,0.9652421,0.0121222,0.0006448529,0.0001203807,0.000003536215,0.0004481941,0.01813688],"genre_scores_gemma":[0.003855226,0.0001628044,0.9912066,0.001877128,0.00008562802,0.00005215305,0.000006954685,0.000009647805,0.002743846],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7077008,"threshold_uncertainty_score":0.3380811,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3139397034","doi":"10.1109/access.2021.3068614","title":"The Benefits of the Matthews Correlation Coefficient (MCC) Over the Diagnostic Odds Ratio (DOR) in Binary Classification Assessment","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Imbalanced Data Classification Techniques","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 Toronto","funders":"Magyar Tudományos Akadémia; University of Southampton; Belarusian Republican Foundation for Fundamental Research","keywords":"Contingency table; False positive paradox; Computer science; Confusion; Kappa; Confusion matrix; Artificial intelligence; Correlation coefficient; Statistics; Correlation; Data mining; Mathematics; Machine learning; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.03775231095962638,"gpt":0.3249331132441325,"spread":0.2871808022845061,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008150054,0.0001338964,0.0001321764,0.00006267447,0.0003585224,0.0004395362,0.002355178,0.00007324928,0.00001056938],"category_scores_gemma":[0.0003795396,0.00007425178,0.00005997319,0.001183884,0.0001375651,0.000642177,0.0004476005,0.000258565,0.00000834302],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001550722,"about_ca_system_score_gemma":0.0002427933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004670306,"about_ca_topic_score_gemma":0.0001378978,"domain_scores_codex":[0.9979961,0.0003964017,0.0004911302,0.0003596259,0.0005452432,0.0002115166],"domain_scores_gemma":[0.9961813,0.001458182,0.0004168305,0.001677325,0.0002401651,0.00002620617],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00001606298,0.0007093283,0.11631,0.00005366749,0.0000401649,0.000005871512,0.00124661,0.03784282,0.01651992,0.7345913,0.01807968,0.07458457],"study_design_scores_gemma":[0.0001397703,0.0000136038,0.7935044,0.00005504698,0.000007135714,0.000003412184,0.00004363647,0.1887884,0.01483087,0.001273684,0.001249684,0.00009045138],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.217321,0.0002958566,0.7693207,0.009341759,0.00161703,0.0009808454,0.00002694538,0.0001156477,0.0009802441],"genre_scores_gemma":[0.9983118,0.000217456,0.0005933002,0.0004715201,0.00004133883,0.0002092883,0.00001705494,0.0000101037,0.0001281988],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7809908,"threshold_uncertainty_score":0.4376547,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1608531804","doi":"10.1007/978-3-642-01818-3_25","title":"Evaluation Methods for Ordinal Classification","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":106,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Metric (unit); Class (philosophy); Mean absolute error; Ordinal regression; Mean squared error; Ordinal data; Data mining; Statistics; Artificial intelligence; Machine learning; Pattern recognition (psychology); Algorithm; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.08103451214580921,"gpt":0.3884510258369434,"spread":0.3074165136911342,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007141163,0.0004526123,0.0004541589,0.0009977365,0.0002734358,0.000566624,0.003649726,0.0003941795,0.00001469318],"category_scores_gemma":[0.0006903196,0.0004413008,0.000134117,0.0006702518,0.0003726865,0.0009747361,0.0004322839,0.0005108109,0.00001954877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009274303,"about_ca_system_score_gemma":0.001115722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003462427,"about_ca_topic_score_gemma":0.000007997183,"domain_scores_codex":[0.9955674,0.0001488834,0.0006688288,0.001820971,0.001262577,0.0005313387],"domain_scores_gemma":[0.9951306,0.0007046128,0.0005513258,0.002168807,0.001322831,0.0001218415],"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":[0.000003030673,0.00001744367,0.000001531268,0.00001112725,0.000004799239,7.411383e-7,0.00008048201,0.0005734661,0.001240707,0.0763548,0.00007402147,0.9216378],"study_design_scores_gemma":[0.000149563,0.0001194247,0.0001235153,0.00008453647,0.00001466566,0.00001205625,4.491187e-8,0.575092,0.004314783,0.4114662,0.008297127,0.0003260833],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[9.103429e-7,0.0003221935,0.9907253,0.001779776,0.0009454649,0.001400309,0.000008700486,0.000369073,0.004448213],"genre_scores_gemma":[0.00432066,0.00003862557,0.9939638,0.0009200748,0.0003101646,0.0001221277,0.00004810735,0.0000266315,0.0002498483],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9213118,"threshold_uncertainty_score":0.9998039,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4402194596","doi":"10.1057/s41599-024-03606-0","title":"Financial fraud detection through the application of machine learning techniques: a literature review","year":2024,"lang":"en","type":"review","venue":"Humanities and Social Sciences Communications","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":103,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science; Finance; Artificial intelligence; Machine learning; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.1239832197598417,"gpt":0.3835576234455726,"spread":0.2595744036857309,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0009431925,0.0002381537,0.0005858264,0.0001488767,0.001875864,0.0004234981,0.003375298,0.0001788468,0.000001952568],"category_scores_gemma":[0.0000866442,0.0001581394,0.0002093187,0.001410726,0.001086302,0.0005139635,0.001190996,0.0008019228,0.000006223591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006945217,"about_ca_system_score_gemma":0.0001787537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008243975,"about_ca_topic_score_gemma":0.0001129918,"domain_scores_codex":[0.9980894,0.0004936006,0.0005880588,0.0003735088,0.0002822053,0.0001732121],"domain_scores_gemma":[0.9978803,0.0002585334,0.0006048627,0.001100002,0.0001477034,0.000008548915],"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":[7.424869e-8,0.00001063285,5.724144e-8,0.004277659,0.000007312949,9.278716e-8,0.0009886494,6.152537e-9,7.065495e-7,0.4129029,0.0005824445,0.5812295],"study_design_scores_gemma":[0.000008746456,0.00003244254,3.923366e-7,0.008192733,0.0001295533,0.00001350736,0.00005570366,0.000191784,0.000002699364,0.007892928,0.9833202,0.000159327],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.672882e-8,0.9502547,0.0450657,0.001075495,0.00005041686,0.0008021038,0.00005989171,0.0002805948,0.002411028],"genre_scores_gemma":[0.00002762844,0.9893951,0.009021038,0.0004520432,0.00007181805,0.0007586604,0.0001213557,0.00001263389,0.0001397167],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9827377,"threshold_uncertainty_score":0.9994236,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1851653583","doi":"10.1007/s10994-015-5535-7","title":"Learning to identify relevant studies for systematic reviews using random forest and external information","year":2015,"lang":"en","type":"article","venue":"Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Random forest; Computer science; Heuristics; Machine learning; Classifier (UML); Artificial intelligence; Cluster analysis; Systematic review; Class (philosophy); Recall; USable; Task (project management); Data mining; Information retrieval; Natural language processing; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.09096737967275106,"gpt":0.3815705795832492,"spread":0.2906031999104981,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002732664,0.0001553762,0.0004358626,0.0001994585,0.0002498922,0.0003484708,0.0003543269,0.00003739154,4.799728e-7],"category_scores_gemma":[0.006535427,0.0001238257,0.00004760855,0.0002327659,0.00002059163,0.001346337,0.0003040576,0.0001844383,0.00002349649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001006142,"about_ca_system_score_gemma":0.00002124252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002384685,"about_ca_topic_score_gemma":0.000005902542,"domain_scores_codex":[0.9984247,0.0002987865,0.0006055691,0.000221158,0.0002426863,0.0002071118],"domain_scores_gemma":[0.9985757,0.0003375062,0.000471889,0.0002833073,0.0002336652,0.00009787907],"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":[0.0007638857,0.0001882387,0.07189763,0.1094768,0.0005691663,0.00003425526,0.1742913,0.2071294,0.03541701,0.05300159,0.007588075,0.3396426],"study_design_scores_gemma":[0.001008604,0.0002105279,0.0004560792,0.003750595,0.00003047487,0.00004902403,0.0005741933,0.978644,0.0002433031,0.001650502,0.0131114,0.0002712948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01411717,0.001569202,0.9822214,0.0002332765,0.0001261577,0.001437122,0.000001187271,0.000261049,0.00003346516],"genre_scores_gemma":[0.5247203,0.0003068684,0.4735105,0.0003923212,0.00009509682,0.0005639467,0.00002505232,0.00002426578,0.0003616664],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7715146,"threshold_uncertainty_score":0.7823988,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2108197782","doi":"10.1016/j.jbi.2004.07.008","title":"Classification and knowledge discovery in protein databases","year":2004,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Imbalanced Data Classification Techniques","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":"Canadian Imperial Bank of Commerce (Canada)","funders":"U.S. National Library of Medicine; National Institutes of Health; National Science Foundation","keywords":"Artificial intelligence; Computer science; Machine learning; Feature selection; Cluster analysis; Robustness (evolution); Pattern recognition (psychology); Data mining; Ensemble learning","retraction":null,"screen_n_in":null,"score":{"opus":0.03453498297277332,"gpt":0.3070496474201495,"spread":0.2725146644473762,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007526706,0.00007805599,0.0001584463,0.0003590948,0.00003080397,0.0001180769,0.0005107183,0.00005232669,0.000001204187],"category_scores_gemma":[0.0002623183,0.0000588455,0.00002491617,0.000451362,0.0001352687,0.003005581,0.0001609707,0.0001976496,0.000005580811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001081285,"about_ca_system_score_gemma":0.0003022451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003447254,"about_ca_topic_score_gemma":0.000002944394,"domain_scores_codex":[0.9986639,0.00002721415,0.0008086095,0.00005910071,0.0003083615,0.000132805],"domain_scores_gemma":[0.9990307,0.00005382214,0.0004556017,0.0002630346,0.00009216738,0.0001046517],"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":[0.00004950589,0.001470409,0.001354372,0.0005766972,0.00004552357,0.00005198799,0.008407217,0.00001458902,0.02685905,0.7016554,0.00758636,0.2519289],"study_design_scores_gemma":[0.01683379,0.003627005,0.138703,0.007408,0.00007283501,0.002835118,0.006617858,0.131759,0.0963078,0.124847,0.4685071,0.002481443],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05665304,0.00008467102,0.9411774,0.001574064,0.0000997439,0.0001167829,0.000007710745,0.00002797523,0.0002586295],"genre_scores_gemma":[0.6584296,0.0001364349,0.3411868,0.0001598305,0.00005027951,0.000005651224,0.00001062316,0.000003529322,0.00001725477],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6017765,"threshold_uncertainty_score":0.239965,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2294246171","doi":"10.5220/0005595502260234","title":"SCUT: Multi-Class Imbalanced Data Classification using SMOTE and Cluster-based Undersampling","year":2015,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":90,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"","keywords":"Undersampling; Computer science; Class (philosophy); Cluster (spacecraft); Support vector machine; Artificial intelligence; Data mining; Multi-label classification; Pattern recognition (psychology); Computer network","retraction":null,"screen_n_in":null,"score":{"opus":0.3499846869511297,"gpt":0.3807716212091559,"spread":0.03078693425802626,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009505644,0.0001972975,0.0001959623,0.0001791593,0.0001452855,0.0003888421,0.001804237,0.0001172319,0.000002630415],"category_scores_gemma":[0.00025937,0.0001870535,0.00002050643,0.0004426782,0.0001185026,0.001610931,0.0008110963,0.0001589242,0.00002036392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001634851,"about_ca_system_score_gemma":0.0002678889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008583171,"about_ca_topic_score_gemma":0.00002077636,"domain_scores_codex":[0.9979743,0.0001215595,0.0003620202,0.0008750313,0.00035332,0.0003137296],"domain_scores_gemma":[0.9967672,0.0001218813,0.0002097763,0.002534943,0.0002006068,0.0001656176],"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":[0.0002509043,0.002081727,0.02269973,0.0004681924,0.0002519831,0.00003998082,0.002707403,0.00761491,0.2535246,0.3533604,0.03720111,0.319799],"study_design_scores_gemma":[0.0007929019,0.00002549523,0.001346138,0.00002526327,0.00000803959,0.000009247081,0.00008997217,0.9894975,0.003392991,0.00080888,0.003755402,0.0002481984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002313468,0.00006806561,0.9940267,0.001850133,0.0001782108,0.0003188658,0.00003130844,0.0007664552,0.0004467814],"genre_scores_gemma":[0.4378453,0.000005487748,0.5613011,0.0006023021,0.00002211457,0.000007751349,0.0001519746,0.0000135164,0.00005042551],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9818826,"threshold_uncertainty_score":0.7627822,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1967158716","doi":"10.1109/icmla.2012.212","title":"One-Class versus Binary Classification: Which and When?","year":2012,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Binary number; Binary classification; Artificial intelligence; Class (philosophy); Computer science; Machine learning; Pattern recognition (psychology); Multiclass classification; One-class classification; Classifier (UML); Support vector machine; Data mining; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0767719356677637,"gpt":0.2971836471206444,"spread":0.2204117114528807,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003392959,0.0001133906,0.0001117315,0.0001026402,0.0001160179,0.0001367377,0.0006494764,0.00008525066,0.00006418915],"category_scores_gemma":[0.00007628709,0.0001130049,0.00001748682,0.0003488557,0.00005517853,0.001660512,0.0002971289,0.0001194881,0.0002207362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005538691,"about_ca_system_score_gemma":0.00004028225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008319528,"about_ca_topic_score_gemma":0.000004708335,"domain_scores_codex":[0.9988894,0.0000586417,0.0001945442,0.0003225224,0.0002364072,0.0002984751],"domain_scores_gemma":[0.9985859,0.000117883,0.00008144223,0.0009482938,0.0001137753,0.0001527118],"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":[0.00001112515,0.0001201696,0.001720507,0.000009827606,0.00001539295,2.264577e-7,0.0002821259,1.003038e-7,0.006934289,0.9346278,0.02032308,0.03595539],"study_design_scores_gemma":[0.002228829,0.0004698217,0.3607,0.00004903093,0.00004996968,0.00003309413,0.0003506673,0.04717626,0.04763182,0.01357633,0.5262372,0.001496935],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005396909,0.0003289171,0.872351,0.0140802,0.0008303781,0.0003366329,0.000006947449,0.001640148,0.1050289],"genre_scores_gemma":[0.8033148,0.00006636115,0.1954453,0.0003662591,0.0001000182,0.00004879141,0.00001500958,0.000009086375,0.0006343224],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9210514,"threshold_uncertainty_score":0.4608207,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3113150236","doi":"10.5267/j.ac.2020.12.003","title":"The effect of artificial intelligence technologies on audit evidence","year":2020,"lang":"en","type":"article","venue":"Accounting","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Audit; Certification; Information technology audit; Internal audit; Knowledge management; Information technology; Business; Information security audit; Accounting; Computer science; Joint audit; Management; Computer security; Information security","retraction":null,"screen_n_in":null,"score":{"opus":0.04680938038711206,"gpt":0.3019430930530131,"spread":0.2551337126659011,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000671675,0.0000954257,0.0001169833,0.0000416177,0.0001637808,0.0001623795,0.001923496,0.00004944524,0.000001513142],"category_scores_gemma":[0.003839357,0.00006313554,0.00003638932,0.0005775635,0.0001183557,0.000495592,0.0004273735,0.0001826095,0.00007367228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002033656,"about_ca_system_score_gemma":0.00002244311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005464708,"about_ca_topic_score_gemma":9.631527e-7,"domain_scores_codex":[0.9989658,0.0000517532,0.0002600584,0.0002833016,0.0002638928,0.0001752178],"domain_scores_gemma":[0.997802,0.001261265,0.0002174839,0.0006407357,0.00006422056,0.00001424926],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001520515,0.000003971155,0.0006946893,0.00002580131,0.000004822694,0.000001509223,0.00009473559,0.00002204065,0.0168257,0.08473836,0.0009814852,0.8965917],"study_design_scores_gemma":[0.00001290967,0.0002866307,0.0003130418,0.0001019791,0.000003152163,0.0000011353,0.00006133816,0.0340235,0.9584293,0.004511046,0.002151772,0.0001042375],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01457711,0.0002562141,0.9667985,0.01616907,0.0001742381,0.0003192215,0.000001662669,0.001328243,0.0003757013],"genre_scores_gemma":[0.9899046,0.0000548764,0.009809122,0.0001554124,0.00003771556,0.00002948253,3.895348e-7,0.000005010435,0.000003366291],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9753275,"threshold_uncertainty_score":0.4596346,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3013276295","doi":"10.1109/access.2020.2983003","title":"SMOTEFUNA: Synthetic Minority Over-Sampling Technique Based on Furthest Neighbour Algorithm","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"European Social Fund; Magyarország Kormánya","keywords":"Computer science; Algorithm; Sampling (signal processing); Detector; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.06019594001374554,"gpt":0.3177182528903892,"spread":0.2575223128766436,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003137445,0.000265536,0.0002636491,0.0001569697,0.0001571888,0.0005280967,0.003162108,0.0001479568,0.00003950806],"category_scores_gemma":[0.0001617541,0.00026058,0.00009196206,0.0008004647,0.00006684001,0.001017146,0.000290461,0.0003637558,0.00007178071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000955764,"about_ca_system_score_gemma":0.0001101327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005735739,"about_ca_topic_score_gemma":0.000001799727,"domain_scores_codex":[0.9978701,0.0001086554,0.0003465611,0.0008246935,0.0004727915,0.0003771235],"domain_scores_gemma":[0.9979583,0.0002428773,0.000206771,0.001284817,0.0001103594,0.0001968588],"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":[0.00009089964,0.001012247,0.00378968,0.0004164056,0.00006680464,0.0001636704,0.0004569188,0.001456587,0.1149178,0.03135382,0.01835788,0.8279173],"study_design_scores_gemma":[0.0003924738,0.0002191874,0.004447513,0.0001060276,0.0000140408,0.00000884635,0.000004925857,0.4872396,0.4866076,0.003939664,0.01630081,0.0007192672],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005661537,0.00001378261,0.9927079,0.003116421,0.0002592558,0.0005055277,0.00005595794,0.001309923,0.001465084],"genre_scores_gemma":[0.6680821,0.00001019776,0.3266169,0.004803022,0.0002311005,0.0001959913,0.00001607025,0.0000269373,0.00001773866],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.827198,"threshold_uncertainty_score":0.9999846,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2473695717","doi":"10.48550/arxiv.1606.07558","title":"Satisfying Real-world Goals with Dataset Constraints","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":80,"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; Benchmark (surveying); Real world data; Classifier (UML); Machine learning; Set (abstract data type); Training set; Data mining; Artificial intelligence; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.09058333476013208,"gpt":0.224372604028407,"spread":0.1337892692682749,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003139722,0.0003546569,0.0003584028,0.0003996334,0.0001504302,0.0001833322,0.002963998,0.0001869665,0.0000894831],"category_scores_gemma":[0.00002924514,0.000322939,0.00006889068,0.0005378716,0.0004215691,0.0007898626,0.002206897,0.0004349783,0.0001743654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003101067,"about_ca_system_score_gemma":0.0003470775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001494656,"about_ca_topic_score_gemma":0.0001416245,"domain_scores_codex":[0.9976174,0.0001557334,0.000248954,0.001430793,0.0001427847,0.0004043446],"domain_scores_gemma":[0.9960371,0.0001632834,0.0004566447,0.00300655,0.0001549063,0.0001815006],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002938858,0.00006481112,0.009007031,0.00008337478,0.0001148107,0.0004457074,0.00005806876,0.0003999686,0.0003265562,0.9665933,0.01767862,0.005198325],"study_design_scores_gemma":[0.00639653,0.0005410234,0.05359517,0.004622585,0.0005214132,0.0001387291,0.0002040065,0.1291391,0.02477965,0.6747217,0.09587377,0.009466373],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002290467,0.000008279808,0.9821938,0.0002617225,0.0001843174,0.000411711,0.002611024,0.0007589016,0.01127976],"genre_scores_gemma":[0.9738288,0.000209062,0.02358109,0.0001821784,0.00005304672,0.000004109997,0.0007944846,0.00002454052,0.001322708],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9715383,"threshold_uncertainty_score":0.9999223,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2481773658","doi":"10.1016/j.compmedimag.2016.07.011","title":"Ensemble based adaptive over-sampling method for imbalanced data learning in computer aided detection of microaneurysm","year":2016,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Ensemble learning; Adaptive sampling; Sampling (signal processing); Machine learning; Pattern recognition (psychology); Training set; Computer vision; Mathematics; Monte Carlo method; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.03898227865516279,"gpt":0.3250309721664764,"spread":0.2860486935113136,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001651438,0.0001960795,0.0003830316,0.0003309848,0.0001020549,0.00006985525,0.001103638,0.0001122498,0.000001364621],"category_scores_gemma":[0.0004191616,0.0001583933,0.00005829513,0.0004323779,0.0001748742,0.0004869759,0.0006238259,0.000260615,4.152498e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003083218,"about_ca_system_score_gemma":0.0001181182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003219222,"about_ca_topic_score_gemma":0.000007863538,"domain_scores_codex":[0.9977788,0.0002594124,0.0005077849,0.0007739202,0.0003458075,0.0003342504],"domain_scores_gemma":[0.9970336,0.001604313,0.000259529,0.0008165236,0.0001422703,0.0001437669],"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":[0.00006408686,0.00007111306,0.001086102,0.00007298789,0.00001536947,0.000008148858,0.00006677475,0.00001589183,0.1393361,0.003080877,0.0001480735,0.8560345],"study_design_scores_gemma":[0.002006874,0.00009103019,0.003484388,0.0003221096,0.000007784509,0.00002500983,0.000003554711,0.9745825,0.01469704,0.002873424,0.001697533,0.0002087545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002722848,0.00009302872,0.9947021,0.001609693,0.0002705203,0.0002865194,0.00002501467,0.0002867025,0.000003589224],"genre_scores_gemma":[0.334913,0.00007184496,0.6643053,0.0005739781,0.00006626686,0.00002483327,0.00002809088,0.00001433948,0.000002406077],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9745666,"threshold_uncertainty_score":0.6459092,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2125722086","doi":"10.1007/978-3-540-78671-9_23","title":"GP Classification under Imbalanced Data sets: Active Sub-sampling and AUC Approximation","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Universities Space Research Association","keywords":"Computer science; Artificial intelligence; Machine learning; Statistic; Classifier (UML); Binary classification; Estimator; Naive Bayes classifier; Boosting (machine learning); Support vector machine; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.07612656226787208,"gpt":0.3049186266414283,"spread":0.2287920643735562,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008621073,0.0005398377,0.0005020737,0.000785378,0.00040696,0.0005863931,0.004754582,0.0004166956,0.000003892559],"category_scores_gemma":[0.0001838173,0.0005330083,0.00004832722,0.0006792275,0.0009076613,0.002467187,0.002416795,0.0008302116,0.00002212876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004732983,"about_ca_system_score_gemma":0.0005580834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001424137,"about_ca_topic_score_gemma":0.00002708635,"domain_scores_codex":[0.9952855,0.00005922993,0.0006440048,0.002480478,0.0009756855,0.000555154],"domain_scores_gemma":[0.9947,0.0005121903,0.0006214739,0.003688469,0.0003233424,0.0001545677],"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":[0.00001020173,0.00003992588,0.00004449216,0.00004948821,0.00001571656,0.00000953705,0.0005400014,0.001000192,0.003224983,0.02615987,0.0001636752,0.9687419],"study_design_scores_gemma":[0.0003056068,0.00008081693,0.003589903,0.0003205515,0.00001143223,0.0001225103,9.063448e-7,0.8934623,0.00651915,0.09240349,0.002272509,0.0009108405],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001196426,0.0002837178,0.9957755,0.001323415,0.0005220751,0.000668312,0.00007855699,0.0004664354,0.0007622953],"genre_scores_gemma":[0.1282294,0.0008906479,0.868889,0.001125953,0.0002536461,0.00003668603,0.0004591471,0.00005401011,0.00006152307],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9678311,"threshold_uncertainty_score":0.9997122,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2724383523","doi":"10.1016/j.patcog.2017.06.030","title":"Online pruning of base classifiers for Dynamic Ensemble Selection","year":2017,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal; École de Technologie Supérieure","funders":"Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Artificial intelligence; Random subspace method; Computer science; Classifier (UML); Machine learning; Pattern recognition (psychology); Competence (human resources); Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.06849559556228693,"gpt":0.3224757485655906,"spread":0.2539801530033037,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002444604,0.0000925575,0.0001206404,0.0001118054,0.0002282805,0.0001170918,0.0005120019,0.00006861791,0.000008444973],"category_scores_gemma":[0.0001705134,0.00009910791,0.00005078238,0.00006415392,0.00003912331,0.0007479149,0.00007859513,0.00008397039,0.0000122342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005613433,"about_ca_system_score_gemma":0.00003408653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003585597,"about_ca_topic_score_gemma":0.0000771436,"domain_scores_codex":[0.9991676,0.00003382026,0.0002249212,0.0002881253,0.0001272669,0.000158286],"domain_scores_gemma":[0.9987437,0.00006114312,0.0004099753,0.0005258881,0.0002233051,0.00003606362],"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":[0.000007416858,0.00009294334,0.001381174,0.00005665781,0.000009658493,4.84078e-7,0.00005830206,0.000001318519,0.04987086,0.0001294439,0.0003469387,0.9480448],"study_design_scores_gemma":[0.0009926662,0.0002972315,0.05854539,0.0002687014,0.00002943622,0.00001705631,0.00005052416,0.5324459,0.3903771,0.0157773,0.0007921467,0.0004065179],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05889997,0.000004710364,0.9395413,0.0005655764,0.0001860654,0.0002906917,0.000126005,0.0001668871,0.0002187387],"genre_scores_gemma":[0.8620529,0.00001841547,0.1373794,0.0001097672,0.00003690229,0.00007445426,0.0002648188,0.00001052578,0.00005289525],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9476383,"threshold_uncertainty_score":0.4041504,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3186353005","doi":"10.1016/j.engappai.2023.106248","title":"Uncertainty-aware credit card fraud detection using deep learning","year":2023,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"Australian Research Council","keywords":"Computer science; Credit card fraud; Process (computing); Dropout (neural networks); Confusion matrix; Machine learning; Monte Carlo method; Artificial intelligence; Deep learning; Ensemble learning; Database transaction; Credit card; Data mining; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.03142392293625725,"gpt":0.2878609277436617,"spread":0.2564370048074044,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003646916,0.0001432083,0.0001580355,0.000413943,0.0001726978,0.00007839646,0.0008180671,0.00009099548,0.000006030982],"category_scores_gemma":[0.0001595256,0.0001702198,0.00006245099,0.002148592,0.00005139423,0.0002935819,0.0001723888,0.0002353582,0.0001125608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009366658,"about_ca_system_score_gemma":0.00003306873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008136858,"about_ca_topic_score_gemma":0.000007622503,"domain_scores_codex":[0.998636,0.00002571815,0.0004302181,0.0003845434,0.0002579623,0.0002655275],"domain_scores_gemma":[0.9987063,0.0001712861,0.0001510867,0.0006967733,0.0002074596,0.00006706232],"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":[0.000001815666,0.00002166653,0.00002016502,0.00003205146,0.00001087399,7.905501e-7,0.0002500756,0.6297704,0.07600216,0.03474709,0.00001253575,0.2591304],"study_design_scores_gemma":[0.000005685256,0.00001828826,0.00007608997,0.000015084,0.00000408057,0.000002534964,0.00009694992,0.7943521,0.200779,0.00229102,0.0022271,0.0001320038],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005576069,0.00003195713,0.9924652,0.00007465015,0.0001535222,0.0002791654,0.00000767339,0.001375669,0.00003607921],"genre_scores_gemma":[0.928438,0.00003555997,0.07114591,0.000006831714,0.0001068877,0.0002032356,0.00002470895,0.00001970454,0.00001913752],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9228619,"threshold_uncertainty_score":0.6941361,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}