{"meta":{"query_hash":"7313441f4fd3","filters":{"topic":"Imbalanced Data Classification Techniques"},"cohort_total":529,"direct_labels_cover":1,"predictions_cover":529,"exported":529,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/7313441f4fd3","api":"https://metacan.xera.ac/api/v1/cohort?topic=Imbalanced+Data+Classification+Techniques"},"results":[{"id":"W111607860","doi":"10.1007/11564126_51","title":"Rank Measures for Ordering","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Rank (graph theory); Ranking (information retrieval); Computer science; Data mining; Preference; Information retrieval; Measure (data warehouse); Order (exchange); The Internet; Learning to rank; Data science; Operations research; Statistics; World Wide Web; Mathematics","score_opus":0.030336124075654808,"score_gpt":0.27242332548377635,"score_spread":0.24208720140812154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W111607860","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000021539852,0.00037438556,0.9932083,0.0015817115,0.00093064486,0.00070461864,0.000015072291,0.00054402853,0.0026391114],"genre_scores_gemma":[0.015203368,0.0000863996,0.9819584,0.0015116535,0.0006047662,0.000060986218,0.000012655988,0.00004321572,0.00051854487],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99638975,0.000019467323,0.0005396931,0.0015650303,0.00084452116,0.0006415582],"domain_scores_gemma":[0.9968392,0.00042493406,0.00030364105,0.0019206017,0.00038253833,0.0001290357],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00107844,0.00047299758,0.00047159547,0.0007887623,0.0002608373,0.0005492827,0.004597425,0.00031330285,0.000011748081],"category_scores_gemma":[0.00019813035,0.0004542821,0.00013241073,0.0004467046,0.0004509575,0.0008541067,0.0009259521,0.0005240895,0.000030778127],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037546067,0.000012881159,0.0000058707114,0.000023386428,0.0000056082504,0.0000050263798,0.00014504613,0.0022571431,0.00048078145,0.057762645,0.00013566678,0.9391622],"study_design_scores_gemma":[0.0005119159,0.00019684753,0.00007182831,0.00044243963,0.000011003302,0.00006213591,8.3734356e-8,0.5302159,0.021047322,0.33215696,0.113943934,0.0013396036],"about_ca_topic_score_codex":0.000006701635,"about_ca_topic_score_gemma":0.00003904326,"teacher_disagreement_score":0.9378226,"about_ca_system_score_codex":0.0003515526,"about_ca_system_score_gemma":0.0004810423,"threshold_uncertainty_score":0.9997909},"labels":[],"label_agreement":null},{"id":"W115533587","doi":"10.1007/978-3-642-30353-1_30","title":"Mining the Hidden Structure of Inductive Learning Data Sets","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Artificial intelligence; Cluster analysis; Curse of dimensionality; Visualization; Machine learning; Domain (mathematical analysis); Variety (cybernetics); Process (computing); Class (philosophy); Data mining; Pattern recognition (psychology); Mathematics","score_opus":0.04681161006848464,"score_gpt":0.2897300678363297,"score_spread":0.24291845776784507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W115533587","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023121327,0.00050021015,0.9965992,0.0006075052,0.00079351605,0.00035322882,0.000045412155,0.00017339872,0.0006963319],"genre_scores_gemma":[0.37195593,0.000045861838,0.6271897,0.00035692798,0.00029851173,0.0000032075075,0.00005924834,0.00002891049,0.00006168365],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964565,0.000090627655,0.00054276205,0.0013506705,0.0010213038,0.00053810625],"domain_scores_gemma":[0.99431735,0.00066905137,0.00071713736,0.003927879,0.00027282606,0.00009577163],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0010801163,0.0004210261,0.00045621445,0.0004982699,0.00027664684,0.00029565036,0.010398291,0.00032307848,0.000023115004],"category_scores_gemma":[0.00029582458,0.00031050795,0.000055139855,0.0006639596,0.001004966,0.0014648115,0.0053436775,0.0012418735,0.000009016763],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022958677,0.000010184462,0.00020719768,0.000023735409,0.000014236922,0.0000048789625,0.0016073969,0.00044900298,0.0013147274,0.012461767,0.00008155927,0.983823],"study_design_scores_gemma":[0.0005507007,0.00038364972,0.0035819488,0.0013714322,0.00007384687,0.0002991593,0.0000076049128,0.650172,0.04598125,0.270817,0.024132667,0.0026287474],"about_ca_topic_score_codex":0.000022663075,"about_ca_topic_score_gemma":0.00003126063,"teacher_disagreement_score":0.98119426,"about_ca_system_score_codex":0.00016176875,"about_ca_system_score_gemma":0.00044854157,"threshold_uncertainty_score":0.9999347},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Class (philosophy); Connectionism; Computer science; Artificial intelligence; Machine learning; Training set; Artificial neural network","score_opus":0.05633284169889121,"score_gpt":0.33026789647094823,"score_spread":0.27393505477205704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W129457532","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020170443,0.00009526299,0.9584292,0.00030013983,0.0000517991,0.000131782,0.000051448744,0.00087823696,0.019891685],"genre_scores_gemma":[0.77569777,0.00003659354,0.22364596,0.00006225349,0.000012794308,0.000005584129,0.0002726402,0.000005935143,0.0002604592],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864984,0.00008080947,0.00035513367,0.00047801394,0.0002531769,0.000183015],"domain_scores_gemma":[0.9977657,0.00011784137,0.00014155738,0.0018805752,0.000050707557,0.000043620206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018483045,0.000116518844,0.00023198892,0.000051134815,0.00006861367,0.00017915654,0.002560164,0.00006273164,0.00037843265],"category_scores_gemma":[0.00003291288,0.00010699327,0.000020405723,0.00027415747,0.00005946849,0.0013472089,0.000361094,0.00017925732,0.00010094406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033918,0.0004276672,0.009843105,0.000028146187,0.00007680065,0.0000070120927,0.0031814785,0.0012671384,0.022275643,0.072526194,0.027247785,0.8630851],"study_design_scores_gemma":[0.00046786142,0.00019481633,0.01916838,0.00004684742,0.0000122628635,0.000003859884,0.0006132602,0.9021525,0.02396422,0.012353822,0.04060017,0.00042201107],"about_ca_topic_score_codex":0.00046039856,"about_ca_topic_score_gemma":0.000038469665,"teacher_disagreement_score":0.90088534,"about_ca_system_score_codex":0.000017988466,"about_ca_system_score_gemma":0.000084921034,"threshold_uncertainty_score":0.47574642},"labels":[],"label_agreement":null},{"id":"W1482063780","doi":"10.2139/ssrn.445122","title":"A Fuzzy-based Algorithm for Auditors to Detect Element of Fraud in Settled Insurance Claims","year":2003,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Windsor","funders":"","keywords":"Audit; Insurance fraud; Element (criminal law); Fuzzy logic; Business; Algorithm; Computer science; Actuarial science; Artificial intelligence; Accounting; Political science; Law","score_opus":0.008849797137484013,"score_gpt":0.2591207920752367,"score_spread":0.2502709949377527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1482063780","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046655857,0.00028462635,0.99366754,0.0005500726,0.00023357884,0.0004379023,0.00001757084,0.000062324085,0.00008080976],"genre_scores_gemma":[0.5868783,0.00019454781,0.4124008,0.00024697874,0.00007826919,0.0001239614,0.0000043689024,0.00001891279,0.00005386344],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99732786,0.00013702916,0.00049939065,0.00031813845,0.0003310852,0.0013865128],"domain_scores_gemma":[0.99891925,0.00010155183,0.0002736386,0.00045278974,0.0001698983,0.0000828711],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023197248,0.00016370535,0.00024169014,0.00033481218,0.00008919784,0.000045827648,0.00085938076,0.000073839874,0.0000031979055],"category_scores_gemma":[0.0001249376,0.0001526616,0.00009500577,0.0006683369,0.000024903953,0.00025983716,0.000034783352,0.00063340954,0.000006202703],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041154985,0.00017603558,0.001094732,0.000019181609,0.0000455185,0.0000029075766,0.00014084353,0.00019246257,0.00871841,0.19547898,0.00091594824,0.79317385],"study_design_scores_gemma":[0.003453958,0.0021461102,0.00252192,0.00012395809,0.000013491564,0.00009241718,0.00016798706,0.011451553,0.20134331,0.75807756,0.019904858,0.0007028907],"about_ca_topic_score_codex":0.000009492901,"about_ca_topic_score_gemma":0.00010782002,"teacher_disagreement_score":0.79247093,"about_ca_system_score_codex":0.000913129,"about_ca_system_score_gemma":0.001821197,"threshold_uncertainty_score":0.6225359},"labels":[],"label_agreement":null},{"id":"W1487177647","doi":"10.1007/978-3-642-13529-3_23","title":"Experienced Physicians and Automatic Generation of Decision Rules from Clinical Data","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's Hospital of Eastern Ontario; University of Ottawa","funders":"","keywords":"Computer science; Certainty; Clinical decision support system; Data quality; Decision support system; Data mining; Quality (philosophy); Artificial intelligence; Clinical decision making; Decision rule; Machine learning; Data science; Family medicine; Medicine; Operations management","score_opus":0.07289657544182045,"score_gpt":0.3425378673874523,"score_spread":0.26964129194563186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1487177647","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040608044,0.00018550587,0.9936024,0.00022460902,0.0012484669,0.00031540875,0.00008651035,0.00016483697,0.00011144778],"genre_scores_gemma":[0.075486526,0.00012144116,0.923456,0.00043010394,0.0003652475,0.0000066432003,0.00010561541,0.000016970154,0.000011455469],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99628353,0.00004907202,0.00086124404,0.0017362981,0.0007945304,0.0002753133],"domain_scores_gemma":[0.9943322,0.00092101167,0.00059708377,0.0038563984,0.00020175887,0.000091571936],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011132916,0.00032403207,0.00054512394,0.00035753733,0.00015290438,0.00035440017,0.005307278,0.00037761143,0.000012631987],"category_scores_gemma":[0.00040034673,0.0002936024,0.000053233234,0.00026091587,0.0012196169,0.0011987798,0.0028564588,0.0006414617,0.000010503837],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015204267,0.00002559747,0.000046718214,0.000006854323,0.000004236156,0.0000055902024,0.00030348258,0.000033649576,0.005000302,0.003506187,0.000041204767,0.9910247],"study_design_scores_gemma":[0.00017383098,0.00008809537,0.00090952014,0.00029174986,0.0000076240826,0.000009409545,2.2251585e-7,0.89236987,0.014159936,0.09082032,0.0007987795,0.00037066962],"about_ca_topic_score_codex":0.000025370076,"about_ca_topic_score_gemma":0.00007975558,"teacher_disagreement_score":0.990654,"about_ca_system_score_codex":0.000051017785,"about_ca_system_score_gemma":0.00031052102,"threshold_uncertainty_score":0.9999516},"labels":[],"label_agreement":null},{"id":"W1498792559","doi":"10.20381/ruor-3739","title":"Applying Supervised Learning Algorithms and a New Feature Selection Method to Predict Coronary Artery Disease","year":2014,"lang":"en","type":"preprint","venue":"uO Research (University of Ottawa)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Random forest; Feature selection; Artificial intelligence; Pattern recognition (psychology); Classifier (UML); Feature vector; Dimensionality reduction; Receiver operating characteristic; Computer science; Algorithm; Mathematics; Machine learning","score_opus":0.06233182192597868,"score_gpt":0.3261054983147381,"score_spread":0.2637736763887594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1498792559","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020332127,0.000037831855,0.99177384,0.003777386,0.00006394266,0.0011951984,0.00004049767,0.00038491705,0.0006931607],"genre_scores_gemma":[0.047045544,0.00012872671,0.9472765,0.000074270596,0.00012047515,0.000024201927,0.00016036662,0.000026245252,0.005143681],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965127,0.0009057826,0.00014575399,0.0010399447,0.00094659417,0.00044923023],"domain_scores_gemma":[0.99761754,0.00031236463,0.00014142325,0.000876043,0.00045599852,0.0005966124],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001996108,0.00021437001,0.0003405189,0.0009012826,0.0004710769,0.00019163218,0.0018874318,0.00026694124,0.00002564854],"category_scores_gemma":[0.00023585423,0.00027106088,0.000091677866,0.0007297296,0.00013210792,0.0005014537,0.0032705981,0.0015041493,0.000018905224],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006284463,0.00015848245,0.03084148,0.00076467084,0.00017568997,0.00013895151,0.0016865938,0.0011757663,0.005531341,0.01370004,0.070988685,0.87477547],"study_design_scores_gemma":[0.0007999625,0.00043654014,0.17445782,0.00044394244,0.00004371758,0.000030572894,0.00035303918,0.6493215,0.00077310385,0.005424454,0.16726083,0.000654526],"about_ca_topic_score_codex":0.00014908239,"about_ca_topic_score_gemma":0.000032436154,"teacher_disagreement_score":0.87412095,"about_ca_system_score_codex":0.00022112345,"about_ca_system_score_gemma":0.0005227962,"threshold_uncertainty_score":0.99997413},"labels":[],"label_agreement":null},{"id":"W1514644537","doi":"10.1007/978-1-4899-7687-1_110","title":"Class Imbalance Problem","year":2017,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Machine Learning and Data Mining","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Class (philosophy); Computer science; Artificial intelligence","score_opus":0.027497299382150876,"score_gpt":0.28974571712309577,"score_spread":0.2622484177409449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1514644537","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000100837115,0.0025968968,0.049498435,0.0005236958,0.00023123405,0.00024857343,0.00043151368,0.0004503248,0.9460092],"genre_scores_gemma":[0.0019988422,0.01599406,0.3646237,0.00009164776,0.00034547682,0.000018625757,0.0027550366,0.00010670471,0.6140659],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99751645,0.000055559503,0.0005630724,0.0011536744,0.00041575194,0.00029546168],"domain_scores_gemma":[0.9952721,0.00026053062,0.0012046929,0.0030488253,0.00009833567,0.00011548578],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009109237,0.000401844,0.00058766984,0.00020745731,0.00030991677,0.00021110679,0.003590258,0.00028498675,0.000039058166],"category_scores_gemma":[0.0004463099,0.00039484492,0.00005123049,0.00002892673,0.00020287347,0.000940281,0.003168046,0.0008697801,0.000029523972],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018605846,0.00003353641,0.004179643,0.00038810872,0.00011772516,0.00005952732,0.0005467354,0.00000457018,0.00007841258,0.14506464,0.03144285,0.81806564],"study_design_scores_gemma":[0.00019588924,0.00009242779,0.00020470012,0.00043703298,0.000030902043,0.000030400319,0.000005175981,0.010931129,0.00001201515,0.002763945,0.98485523,0.0004411481],"about_ca_topic_score_codex":0.00004046325,"about_ca_topic_score_gemma":0.000018129233,"teacher_disagreement_score":0.9534124,"about_ca_system_score_codex":0.000023131564,"about_ca_system_score_gemma":0.00014400801,"threshold_uncertainty_score":0.99985033},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.030474266314674505,"score_gpt":0.2873676294616058,"score_spread":0.25689336314693134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1514907448","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00083286245,0.000037600224,0.9858076,0.0015593893,0.000044523626,0.0001606508,0.000009169629,0.0003187675,0.011229425],"genre_scores_gemma":[0.5545719,0.000007813897,0.4448607,0.0003435717,0.0000036805664,0.000018913597,0.0000034260565,0.0000044703165,0.00018550064],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989615,0.00007981952,0.00019568446,0.00033489254,0.00023514815,0.00019295291],"domain_scores_gemma":[0.99896204,0.00023885102,0.00007407318,0.0005165861,0.00011631212,0.00009213567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031899736,0.00010718597,0.00011196557,0.000049960014,0.00010611117,0.00020174762,0.0003453178,0.00003641021,0.000018901947],"category_scores_gemma":[0.0010531932,0.00008749143,0.0000180336,0.00014913906,0.00008765717,0.0004345166,0.00011889145,0.00009175893,0.000010642172],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.996591e-7,0.000025690042,0.0006596186,0.0000115942275,0.0000049497303,0.0000050603344,0.0002528834,1.902156e-7,0.0016844174,0.96127427,0.0018426134,0.034237888],"study_design_scores_gemma":[0.0034689675,0.00078296196,0.21899879,0.00048534747,0.00011824925,0.00091300625,0.0036365981,0.13693732,0.2073388,0.33963573,0.083740115,0.003944131],"about_ca_topic_score_codex":0.000015115811,"about_ca_topic_score_gemma":0.000007633444,"teacher_disagreement_score":0.6216386,"about_ca_system_score_codex":0.000027353715,"about_ca_system_score_gemma":0.00006611848,"threshold_uncertainty_score":0.3567797},"labels":[],"label_agreement":null},{"id":"W1515231270","doi":"10.1007/11564126_29","title":"Hybrid Cost-Sensitive Decision Tree","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Decision tree; Computer science; Tree (set theory); Forestry; Mathematics; Artificial intelligence; Geography; Combinatorics","score_opus":0.019700516008589512,"score_gpt":0.26717104973799405,"score_spread":0.24747053372940453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1515231270","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000017060485,0.00015994675,0.9884405,0.0010396348,0.0011112826,0.0006693145,0.000027934773,0.00055055926,0.0079837525],"genre_scores_gemma":[0.049616892,0.00012813024,0.9463703,0.0026879543,0.0005514525,0.000023808481,0.00002638,0.000046825124,0.000548274],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950554,0.000040024865,0.00068648346,0.0021192636,0.0013584534,0.0007404094],"domain_scores_gemma":[0.99539447,0.0007909778,0.00041450927,0.002735733,0.0004440642,0.00022022244],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009959636,0.00062000524,0.00058875664,0.0011651885,0.00025960663,0.00066479575,0.0048588486,0.00029801458,0.000024850378],"category_scores_gemma":[0.00021160595,0.00058444316,0.00014565037,0.0005380995,0.000774265,0.0011964283,0.0019105693,0.0009477524,0.00023289247],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005260043,0.00001984848,0.000004485404,0.00000538245,0.0000041560534,0.00007798311,0.00011442279,0.0013230533,0.00019321154,0.023414657,0.00027738465,0.97456014],"study_design_scores_gemma":[0.00046514452,0.00021779892,0.00036985954,0.0006698765,0.000010669794,0.0003531674,1.135491e-7,0.6281945,0.03691353,0.29516473,0.036129188,0.0015113855],"about_ca_topic_score_codex":0.0000096736385,"about_ca_topic_score_gemma":0.000053785134,"teacher_disagreement_score":0.97304875,"about_ca_system_score_codex":0.0006945168,"about_ca_system_score_gemma":0.0005730438,"threshold_uncertainty_score":0.9996607},"labels":[],"label_agreement":null},{"id":"W151594930","doi":"10.1007/978-3-642-30217-6_19","title":"Foundation of Mining Class-Imbalanced Data","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Class (philosophy); Bounded function; Upper and lower bounds; Machine learning; Artificial intelligence; Data mining; Order (exchange); Word error rate; Sample complexity; Empirical research; Sample (material); Statistics; Mathematics","score_opus":0.05203166455733296,"score_gpt":0.2970614443172095,"score_spread":0.24502977975987653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W151594930","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028275837,0.00031656222,0.99388236,0.00046322437,0.0010598002,0.00034164308,0.000031697786,0.0002581009,0.0036183612],"genre_scores_gemma":[0.12828219,0.00010012937,0.8704468,0.00047554434,0.00033759957,0.000008801089,0.00014763822,0.00003217415,0.00016910593],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99609643,0.000041235257,0.0007427422,0.0015233035,0.0010317854,0.00056452345],"domain_scores_gemma":[0.9935108,0.00047161788,0.0007456632,0.0048307804,0.00031403813,0.00012708914],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0015411075,0.00041527516,0.00053433474,0.00077495707,0.00013916477,0.0002893063,0.008414654,0.00030012906,0.00003006548],"category_scores_gemma":[0.00024019157,0.00040569258,0.00006129062,0.0006511619,0.00070863566,0.0021694629,0.00357589,0.0005083051,0.00004447047],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034478855,0.000029642004,0.00014107964,0.000046623012,0.000008934023,0.0000048448715,0.00032772534,0.00030257634,0.0012155697,0.043443818,0.00013484531,0.9543409],"study_design_scores_gemma":[0.0004971052,0.00021901545,0.001270183,0.00096147595,0.000028436707,0.00008078309,5.467727e-7,0.85192454,0.01969038,0.09605468,0.02772472,0.0015481212],"about_ca_topic_score_codex":0.000011530906,"about_ca_topic_score_gemma":0.000026943388,"teacher_disagreement_score":0.95279276,"about_ca_system_score_codex":0.0002664575,"about_ca_system_score_gemma":0.000622479,"threshold_uncertainty_score":0.9998395},"labels":[],"label_agreement":null},{"id":"W1516042217","doi":"10.1007/3-540-45153-6_1","title":"A Case Study for Learning from Imbalanced Data Sets","year":2001,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Skew; Machine learning; Artificial intelligence; Rule induction; Quality (philosophy); Focus (optics); Data mining; Set (abstract data type); Variety (cybernetics); Training set","score_opus":0.07340706613005715,"score_gpt":0.31967708466063144,"score_spread":0.2462700185305743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1516042217","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027639332,0.00014459924,0.99564075,0.00030018136,0.0008974869,0.0014558992,0.00010571037,0.00061797124,0.0005610019],"genre_scores_gemma":[0.20878473,0.00003472341,0.78964,0.00058205525,0.0004152734,0.000070932125,0.00022693304,0.00005900059,0.00018635728],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99459267,0.0000756158,0.00070648297,0.0030518493,0.0008786819,0.0006946958],"domain_scores_gemma":[0.9928198,0.0010668831,0.0005162214,0.00510736,0.000321121,0.0001686072],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0014640773,0.00059717934,0.00066035334,0.00065288343,0.00045847252,0.00088410656,0.008369105,0.00030147523,0.00001542154],"category_scores_gemma":[0.00033720565,0.0005785472,0.00007939698,0.00062818587,0.00036640442,0.0013466481,0.0041665933,0.0009725435,0.000023877434],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010142081,0.00011463123,0.00034143665,0.000019269577,0.000028698907,0.0020378316,0.001218469,0.0022633786,0.00009610532,0.0013899959,0.00018780612,0.9922922],"study_design_scores_gemma":[0.00065187353,0.00041223352,0.000084133666,0.00017519311,0.000023262068,0.00094758027,0.0000031412933,0.9391872,0.00029397928,0.0509522,0.006326633,0.00094254577],"about_ca_topic_score_codex":0.00020352768,"about_ca_topic_score_gemma":0.00032221977,"teacher_disagreement_score":0.9913497,"about_ca_system_score_codex":0.0002844726,"about_ca_system_score_gemma":0.0004889936,"threshold_uncertainty_score":0.9996666},"labels":[],"label_agreement":null},{"id":"W1520065212","doi":"10.1007/11871842_16","title":"Evaluating Misclassifications in Imbalanced Data","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Receiver operating characteristic; Classifier (UML); Artificial intelligence; Confidence interval; Pattern recognition (psychology); Class (philosophy); Computer science; Machine learning; Statistics; Mathematics","score_opus":0.0892702449882283,"score_gpt":0.3475017225279319,"score_spread":0.25823147753970355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1520065212","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000021968945,0.00027346183,0.9899546,0.0015474038,0.000667181,0.00064296136,0.00006627142,0.00040087823,0.0064252974],"genre_scores_gemma":[0.044835463,0.00005005103,0.9531062,0.0007101952,0.00028751203,0.000043888293,0.00028403217,0.000046040037,0.0006366135],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99411565,0.00007921199,0.0009879121,0.0027737615,0.0012934422,0.00075004745],"domain_scores_gemma":[0.9921114,0.0006030814,0.0005519406,0.0063340333,0.00028349302,0.000116068404],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0023552545,0.00053915026,0.0005632251,0.001301996,0.00022162922,0.00064997416,0.011176203,0.00036552592,0.000016072852],"category_scores_gemma":[0.00037220665,0.0005453579,0.00006304822,0.0012735759,0.00064946397,0.0014864189,0.0033209764,0.001030739,0.000060847473],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042362917,0.000088686196,0.00024097704,0.000046387686,0.0000067600836,0.000045107936,0.00020059443,0.013121937,0.0021679096,0.039931513,0.00082867726,0.94331723],"study_design_scores_gemma":[0.00026397165,0.000060781957,0.00139664,0.0003527728,0.0000050202,0.00002493938,9.859999e-8,0.896128,0.00118863,0.09670936,0.0032060528,0.0006637413],"about_ca_topic_score_codex":0.000069564936,"about_ca_topic_score_gemma":0.00023145115,"teacher_disagreement_score":0.9426535,"about_ca_system_score_codex":0.0006046802,"about_ca_system_score_gemma":0.001027331,"threshold_uncertainty_score":0.9996998},"labels":[],"label_agreement":null},{"id":"W1534746498","doi":"","title":"Adaptive selection of ensembles for imbalanced class distributions","year":2012,"lang":"en","type":"article","venue":"Espace ÉTS (ETS)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Skew; Computer science; Artificial intelligence; Boolean function; Class (philosophy); Reliability (semiconductor); Selection (genetic algorithm); Machine learning; Receiver operating characteristic; Pattern recognition (psychology); Data mining; Algorithm","score_opus":0.024218949121449812,"score_gpt":0.28139932090020137,"score_spread":0.2571803717787515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1534746498","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005021468,0.00006134908,0.99212325,0.0010007938,0.00023440932,0.00039111634,0.000125214,0.0003415414,0.0007008702],"genre_scores_gemma":[0.8469905,0.000014217066,0.15231071,0.000054504853,0.00008599976,0.00014461295,0.000047785914,0.0000100098205,0.000341612],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99889004,0.000062970845,0.00022289265,0.0002688467,0.00019142184,0.00036383866],"domain_scores_gemma":[0.9987804,0.00016883403,0.00022134122,0.00049750134,0.00023942454,0.00009249241],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003378514,0.00013565323,0.00018266417,0.00010444667,0.0001344822,0.000039299688,0.00047106465,0.00009396594,0.000009678002],"category_scores_gemma":[0.00016876527,0.00013327312,0.00007367754,0.00047690183,0.00006124897,0.0007742472,0.000104752224,0.00010142465,0.000023074701],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056107157,0.00029209963,0.0055159247,0.000036665555,0.000044380526,2.3684518e-7,0.00068688317,0.000024237244,0.098332174,0.84466153,0.036980137,0.013369637],"study_design_scores_gemma":[0.0006603259,0.0002995799,0.0477152,0.000057509147,0.000029101899,0.000016331296,0.00014698863,0.031457193,0.8102864,0.0052338974,0.10360267,0.00049477164],"about_ca_topic_score_codex":0.000011741138,"about_ca_topic_score_gemma":0.000012126128,"teacher_disagreement_score":0.8419691,"about_ca_system_score_codex":0.00012303964,"about_ca_system_score_gemma":0.00006863748,"threshold_uncertainty_score":0.54347205},"labels":[],"label_agreement":null},{"id":"W1539524058","doi":"10.1007/11551188_36","title":"Empirical Study on Weighted Voting Multiple Classifiers","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Voting; Computer science; Classifier (UML); Weighted voting; Artificial intelligence; Random subspace method; Machine learning; AdaBoost; Majority rule; Pattern recognition (psychology)","score_opus":0.043365052029538886,"score_gpt":0.3060205666199402,"score_spread":0.2626555145904013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1539524058","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032063326,0.00004986058,0.9921518,0.0015027332,0.0010080485,0.00093470246,0.000010186669,0.0007697825,0.003252256],"genre_scores_gemma":[0.5753803,0.000009684007,0.4209734,0.0025759465,0.0005610874,0.000038598315,0.00001263196,0.000055812194,0.0003925272],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99422014,0.00009759505,0.00080734614,0.0024744908,0.0015829703,0.00081743224],"domain_scores_gemma":[0.99556035,0.0009333468,0.0004609198,0.0025413546,0.0002733034,0.00023071776],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012257106,0.00070440106,0.0006443857,0.0012957378,0.00037710814,0.00066949415,0.005336206,0.00041072565,0.000018428627],"category_scores_gemma":[0.00023841497,0.0006344436,0.00013495825,0.0009374499,0.00058367354,0.0007711776,0.00154838,0.0014477968,0.00014463105],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019062,0.00041895502,0.0037911907,0.000019601479,0.00002784347,0.00014912679,0.0017048183,0.0023936639,0.00023950965,0.014247158,0.00045429904,0.9765348],"study_design_scores_gemma":[0.0009804931,0.0010467931,0.007305071,0.00043790197,0.000015997408,0.000054065204,0.0000015255324,0.9483105,0.003960999,0.024342066,0.0117073255,0.0018372592],"about_ca_topic_score_codex":0.000008736178,"about_ca_topic_score_gemma":0.000056731104,"teacher_disagreement_score":0.97469753,"about_ca_system_score_codex":0.0007377238,"about_ca_system_score_gemma":0.000475565,"threshold_uncertainty_score":0.99961066},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.020382886878291023,"score_gpt":0.2655751414727915,"score_spread":0.24519225459450047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1541033774","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001843576,0.00015920066,0.9824937,0.0009625262,0.004121608,0.00037578365,0.000016782706,0.0006451822,0.011206805],"genre_scores_gemma":[0.041170575,0.00008994727,0.9560795,0.0012956059,0.0006460221,0.000025303974,0.000021022352,0.000052715804,0.000619303],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955101,0.000025344427,0.0005599478,0.001956109,0.0011910903,0.0007574345],"domain_scores_gemma":[0.99518126,0.0005110152,0.00041685163,0.003375823,0.00031230165,0.00020275691],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008133386,0.0005901762,0.00052379706,0.00079297693,0.00027241244,0.0006825423,0.006708858,0.00058548036,0.00003842799],"category_scores_gemma":[0.00020828772,0.00057378534,0.00012933036,0.0006729316,0.001027458,0.0010553229,0.0018441224,0.0016503206,0.00018383103],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020362477,0.000043414602,0.0000693534,0.000034489105,0.000013182336,0.00008283603,0.00025559627,0.00037182082,0.0042587793,0.21458398,0.00014868018,0.7801175],"study_design_scores_gemma":[0.001514722,0.00062120525,0.0008835513,0.000607508,0.0000201543,0.00015941724,1.8652935e-7,0.23121154,0.06869977,0.60216075,0.0908526,0.0032686077],"about_ca_topic_score_codex":0.000012805141,"about_ca_topic_score_gemma":0.000057776502,"teacher_disagreement_score":0.7768489,"about_ca_system_score_codex":0.00035857366,"about_ca_system_score_gemma":0.0006720114,"threshold_uncertainty_score":0.99967134},"labels":[],"label_agreement":null},{"id":"W1541236345","doi":"10.1007/11871842_44","title":"Improving the Ranking Performance of Decision Trees","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Ranking (information retrieval); Computer science; Decision tree; Shrinkage; Artificial intelligence; Node (physics); Tree (set theory); Machine learning; Class (philosophy); Algorithm; Sample (material); Interpolation (computer graphics); Pattern recognition (psychology); Mathematics; Image (mathematics)","score_opus":0.013703560184896576,"score_gpt":0.23664064039214722,"score_spread":0.22293708020725064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1541236345","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004894726,0.0002613051,0.99649906,0.00019961502,0.00063730543,0.00034070187,0.000005352496,0.00017264124,0.0013945487],"genre_scores_gemma":[0.45224202,0.000045500074,0.54708433,0.00030134668,0.00016954051,0.00000988171,0.0000049039472,0.000021144475,0.00012133372],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967852,0.000026695672,0.0006499336,0.0010281845,0.0010802064,0.00042976916],"domain_scores_gemma":[0.99624753,0.00068548904,0.00057764584,0.0021693038,0.000272133,0.000047904454],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00130386,0.0003614673,0.0003908175,0.0006174214,0.0002721838,0.00032550126,0.0053173103,0.00021287226,0.0000054486645],"category_scores_gemma":[0.0001083635,0.00025839914,0.00010061484,0.000660976,0.00077133166,0.0007726,0.0014476854,0.0005942964,0.000009507916],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000043256555,0.000011097819,0.00009433254,0.000023148212,0.0000024153692,0.000005485848,0.000112763686,0.0072553405,0.0012451345,0.0075228517,0.00005254783,0.98367053],"study_design_scores_gemma":[0.0001777338,0.0001426867,0.0010894585,0.0005394498,0.000006282611,0.000043370645,7.050412e-8,0.9288601,0.030148594,0.03737944,0.00115398,0.00045877992],"about_ca_topic_score_codex":0.000036292928,"about_ca_topic_score_gemma":0.00003479492,"teacher_disagreement_score":0.98321176,"about_ca_system_score_codex":0.00019452978,"about_ca_system_score_gemma":0.0003355901,"threshold_uncertainty_score":0.9999868},"labels":[],"label_agreement":null},{"id":"W1542204591","doi":"10.1007/978-3-540-27868-9_107","title":"Multiple Classifier Prediction Improvements against Imbalanced Datasets through Added Synthetic Examples","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Boosting (machine learning); Computer science; Machine learning; Benchmarking; Classifier (UML); Artificial intelligence; Training set; Ensemble learning; Data mining; Pattern recognition (psychology)","score_opus":0.02694847425055517,"score_gpt":0.2593697036325736,"score_spread":0.23242122938201845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1542204591","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000061015227,0.00016313481,0.9932405,0.0004597111,0.0016772223,0.0010601665,0.00067436823,0.0008078178,0.0018561136],"genre_scores_gemma":[0.2000492,0.00027924185,0.7951925,0.002623434,0.0004575226,0.00012472815,0.0010199199,0.00009279137,0.00016071036],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9938119,0.000060253507,0.0009810047,0.0027303924,0.0014518807,0.00096457487],"domain_scores_gemma":[0.99471253,0.0004108134,0.0006721653,0.003745121,0.000260282,0.00019911352],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008107168,0.000817468,0.0006835973,0.00068214035,0.00041731828,0.00071901095,0.0052583204,0.000529221,0.000028139355],"category_scores_gemma":[0.00026495205,0.00077893084,0.00014645352,0.00072909007,0.0009574887,0.0020323023,0.001961756,0.0010183137,0.000076120894],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028409637,0.0002358783,0.00022811003,0.00017550304,0.000058881444,0.000115181894,0.00094686716,0.007817335,0.014800626,0.052973993,0.0007645225,0.9218547],"study_design_scores_gemma":[0.0023536682,0.00062892673,0.0015322044,0.0024356376,0.00004264304,0.00008747961,0.0000013515839,0.4934064,0.07943959,0.3897254,0.027318005,0.0030287253],"about_ca_topic_score_codex":0.00004938497,"about_ca_topic_score_gemma":0.00005841507,"teacher_disagreement_score":0.918826,"about_ca_system_score_codex":0.0011087959,"about_ca_system_score_gemma":0.0008137048,"threshold_uncertainty_score":0.9994662},"labels":[],"label_agreement":null},{"id":"W1555474281","doi":"","title":"Electronic Fraud Detection in the U.S. Medicaid Healthcare Program: Lessons Learned from other Industries","year":2011,"lang":"en","type":"article","venue":"University of Twente Research Information","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicaid; Health care; Business; Government (linguistics); Quarter (Canadian coin); Actuarial science; Finance; Economics; Economic growth","score_opus":0.20648329850608618,"score_gpt":0.3585661105535196,"score_spread":0.15208281204743343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1555474281","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07956315,0.00010625681,0.860407,0.04304782,0.0001359591,0.0024974404,0.00010397352,0.00067662075,0.013461783],"genre_scores_gemma":[0.99565196,0.00020074844,0.0039794613,0.0000857887,0.0000074890686,0.0000051210372,0.000039673487,0.0000020084744,0.00002774645],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998617,0.00030007164,0.0001491581,0.00011989771,0.0005403198,0.00027354347],"domain_scores_gemma":[0.99904716,0.000077945595,0.00012765625,0.00045549165,0.000250784,0.000040939834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013863376,0.000055267235,0.00007500228,0.0003710691,0.00018552045,0.000050113573,0.0011593457,0.00009989429,0.000022893879],"category_scores_gemma":[0.00013411482,0.00005021241,0.000021353086,0.0008783827,0.00015379857,0.0019678127,0.00018185985,0.0005171115,0.00003733649],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053270196,0.00008966916,0.00083683914,0.000020953556,0.000010986875,0.0000012859891,0.016229086,9.143349e-7,0.000117237156,0.059531793,0.001455097,0.92165285],"study_design_scores_gemma":[0.0019352133,0.0014873195,0.08814293,0.00023009558,0.000010719185,0.000006666551,0.033395503,0.023586472,0.034610886,0.05172798,0.7644161,0.00045012723],"about_ca_topic_score_codex":0.0060543576,"about_ca_topic_score_gemma":0.00093509303,"teacher_disagreement_score":0.9212027,"about_ca_system_score_codex":0.00019524782,"about_ca_system_score_gemma":0.00023246916,"threshold_uncertainty_score":0.91524184},"labels":[],"label_agreement":null},{"id":"W1566313113","doi":"10.3233/ida-140686","title":"Hybrid probabilistic sampling with random subspace for imbalanced data learning","year":2014,"lang":"en","type":"article","venue":"Intelligent Data Analysis","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Alberta Innovates; China Scholarship Council","keywords":"Subspace topology; Probabilistic logic; Sampling (signal processing); Artificial intelligence; Computer science; Pattern recognition (psychology); Machine learning; Mathematics","score_opus":0.08624709222993643,"score_gpt":0.33377634411083296,"score_spread":0.24752925188089653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1566313113","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034622845,0.00007415733,0.9974277,0.0004374546,0.00007589365,0.0004671803,0.00061172526,0.00046505255,0.00009462376],"genre_scores_gemma":[0.32110912,0.00013922446,0.65625864,0.00018058428,0.00014766159,0.00010608279,0.021847367,0.000032377346,0.00017891682],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99683994,0.00018196207,0.0005054117,0.0016190417,0.0004367183,0.00041690946],"domain_scores_gemma":[0.9901934,0.00092762645,0.00037593633,0.007991597,0.00038815947,0.00012327729],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0021861873,0.00025414562,0.00052806153,0.00034986646,0.00023774743,0.0004890584,0.0071844324,0.00004802144,0.000013945567],"category_scores_gemma":[0.0028945487,0.00020979335,0.00008381191,0.0011557065,0.00009121896,0.0013171,0.0017476453,0.00020922233,0.000032877462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008452552,0.0010242772,0.034484267,0.000565801,0.008448068,0.000018115159,0.0007685627,0.08135494,0.002722771,0.09839477,0.047933057,0.7234401],"study_design_scores_gemma":[0.00028678126,0.00006727901,0.00024358834,0.000024041225,0.0005120763,0.0000021277017,0.000019808,0.8882022,0.0018825253,0.0013096003,0.107152775,0.0002972297],"about_ca_topic_score_codex":0.000072589326,"about_ca_topic_score_gemma":0.0001229576,"teacher_disagreement_score":0.8068472,"about_ca_system_score_codex":0.00006322006,"about_ca_system_score_gemma":0.00007070463,"threshold_uncertainty_score":0.9981872},"labels":[],"label_agreement":null},{"id":"W1574815653","doi":"10.5555/1497096.1497101","title":"Learning from Skewed Class Multi-relational Databases","year":2009,"lang":"en","type":"article","venue":"Fundamenta Informaticae","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Relation (database); Computer science; Class (philosophy); Relational database; Tuple; Data mining; Benchmarking; Feature (linguistics); Database; Machine learning; Artificial intelligence; Mathematics","score_opus":0.06297568131224934,"score_gpt":0.2940272656755052,"score_spread":0.23105158436325585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1574815653","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004103047,0.000020695088,0.9880195,0.0012032067,0.00013211287,0.0002174641,0.00005497897,0.00076906255,0.0054799155],"genre_scores_gemma":[0.36790988,0.00001936909,0.62827426,0.0024890355,0.000047653153,0.000024607252,0.00083956344,0.0000064178703,0.00038924228],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998546,0.000050706596,0.0004897123,0.00023666416,0.00040200053,0.00027490128],"domain_scores_gemma":[0.99869394,0.0001538878,0.00023550933,0.00074359844,0.00006864288,0.00010441702],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002382674,0.0001625923,0.0001608457,0.00013561902,0.00021589108,0.00024465896,0.00081607007,0.000052327752,0.00014087952],"category_scores_gemma":[0.00016575785,0.00015624454,0.000047166093,0.00027604116,0.000048058297,0.0030468248,0.00022474807,0.00026092076,0.000837977],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028631795,0.00047491223,0.008075081,0.00002962369,0.00007904951,0.000009298775,0.004922016,0.0004591991,0.0058870283,0.68504846,0.04554539,0.24944133],"study_design_scores_gemma":[0.0012195433,0.00020606643,0.09642136,0.00009613608,0.000013591072,0.000011424345,0.00028513887,0.5409125,0.007944359,0.0034128823,0.34885344,0.0006235428],"about_ca_topic_score_codex":0.000023721337,"about_ca_topic_score_gemma":0.000002414229,"teacher_disagreement_score":0.68163556,"about_ca_system_score_codex":0.00010683467,"about_ca_system_score_gemma":0.000064384934,"threshold_uncertainty_score":0.99994},"labels":[],"label_agreement":null},{"id":"W1602311394","doi":"10.1007/11564126_52","title":"Dynamic Ensemble Re-Construction for Better Ranking","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Ranking (information retrieval); Ensemble learning; Construct (python library); Machine learning; AdaBoost; Artificial intelligence; Task (project management); Learning to rank; Data mining; Ensemble forecasting; Support vector machine","score_opus":0.016400313872440946,"score_gpt":0.26007662780684343,"score_spread":0.24367631393440248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1602311394","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018450337,0.00016160191,0.9929718,0.0024002986,0.0013582483,0.0007044588,0.00001596195,0.00047008132,0.0018990918],"genre_scores_gemma":[0.01771362,0.00004334854,0.9795344,0.0019464359,0.00035145154,0.00004595603,0.000028612321,0.000039141978,0.00029707514],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963906,0.000024311785,0.0005963006,0.0016496764,0.00070530124,0.0006338099],"domain_scores_gemma":[0.9969907,0.00039367887,0.00041975948,0.0018130179,0.0002825348,0.00010032301],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00084493577,0.00047250264,0.00045578636,0.00090117875,0.00029416152,0.00056321715,0.003204187,0.00038064245,0.00001653465],"category_scores_gemma":[0.000084943546,0.00047201876,0.00014027022,0.00044323513,0.00055042084,0.001035952,0.00071731623,0.0006000606,0.000030958356],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040641507,0.000009360334,0.000010075347,0.000024919198,0.000005712478,0.0000048740058,0.0001417373,0.0010700143,0.0008387211,0.027908286,0.000082587765,0.96989965],"study_design_scores_gemma":[0.0003048145,0.00010517334,0.000059218422,0.00029477567,0.000009185385,0.0000753167,1.084802e-7,0.6170965,0.007823526,0.3583886,0.015099795,0.000743011],"about_ca_topic_score_codex":0.000004387571,"about_ca_topic_score_gemma":0.00004983678,"teacher_disagreement_score":0.9691566,"about_ca_system_score_codex":0.00053891476,"about_ca_system_score_gemma":0.00033534938,"threshold_uncertainty_score":0.99977314},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.08103451214580921,"score_gpt":0.38845102583694335,"score_spread":0.30741651369113415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1608531804","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.1034286e-7,0.0003221935,0.99072534,0.001779776,0.00094546494,0.0014003093,0.000008700486,0.000369073,0.0044482127],"genre_scores_gemma":[0.0043206597,0.000038625574,0.9939638,0.0009200748,0.00031016464,0.00012212772,0.000048107355,0.000026631504,0.00024984826],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955674,0.00014888341,0.00066882884,0.0018209714,0.0012625775,0.00053133874],"domain_scores_gemma":[0.9951306,0.00070461276,0.0005513258,0.0021688074,0.0013228314,0.00012184147],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0071411626,0.00045261232,0.00045415887,0.0009977365,0.0002734358,0.000566624,0.0036497256,0.0003941795,0.000014693175],"category_scores_gemma":[0.0006903196,0.0004413008,0.00013411703,0.0006702518,0.00037268654,0.0009747361,0.00043228394,0.0005108109,0.000019548768],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030306733,0.000017443672,0.000001531268,0.000011127253,0.000004799239,7.411383e-7,0.00008048201,0.00057346607,0.0012407074,0.0763548,0.000074021475,0.92163783],"study_design_scores_gemma":[0.00014956297,0.00011942466,0.00012351529,0.00008453647,0.0000146656585,0.000012056245,4.4911868e-8,0.57509196,0.0043147826,0.4114662,0.008297127,0.00032608333],"about_ca_topic_score_codex":0.000003462427,"about_ca_topic_score_gemma":0.000007997183,"teacher_disagreement_score":0.9213118,"about_ca_system_score_codex":0.00092743034,"about_ca_system_score_gemma":0.0011157223,"threshold_uncertainty_score":0.9998039},"labels":[],"label_agreement":null},{"id":"W163887238","doi":"","title":"Cost-sensitive test strategies","year":2006,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Decision tree; Test (biology); Machine learning; Medical costs; Artificial intelligence; Process (computing); Total cost; Test case; Health care","score_opus":0.024298555964320057,"score_gpt":0.2748367644207455,"score_spread":0.25053820845642544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W163887238","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019072353,0.000004598706,0.8684631,0.0008326169,0.000035889032,0.00010587886,0.0000058953747,0.000824554,0.12953675],"genre_scores_gemma":[0.76695526,0.0000024746785,0.23118602,0.00026937295,0.000034263583,0.000019042498,0.000013725534,0.0000036242177,0.0015162466],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993998,0.000014567988,0.00011551197,0.0002100908,0.000119962424,0.00014009477],"domain_scores_gemma":[0.9993209,0.00009373211,0.000040703926,0.00044018737,0.00008320295,0.000021266967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008331667,0.00006793735,0.000060948678,0.000049925166,0.000050705723,0.00022523965,0.00040016999,0.0000299633,0.000012421717],"category_scores_gemma":[0.000019685667,0.000059158643,0.000016533979,0.00020300478,0.00004053714,0.00076170673,0.00008721537,0.000050525832,0.00016024604],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.7092614e-7,0.00003422659,0.00020910986,0.0000011779375,7.862001e-7,0.00000479492,0.00002024965,0.0000045449306,0.011267893,0.95670134,0.02414003,0.0076155826],"study_design_scores_gemma":[0.0002940996,0.00010065341,0.08639687,0.000013964691,0.0000031115273,0.000045700755,0.00021919447,0.03150115,0.67879814,0.11980957,0.08228592,0.00053160137],"about_ca_topic_score_codex":0.00010152015,"about_ca_topic_score_gemma":0.000028805996,"teacher_disagreement_score":0.8368918,"about_ca_system_score_codex":0.000025580615,"about_ca_system_score_gemma":0.0000480419,"threshold_uncertainty_score":0.24124195},"labels":[],"label_agreement":null},{"id":"W1651734266","doi":"10.48550/arxiv.1109.3532","title":"A Characterization of the Combined Effects of Overlap and Imbalance on the SVM Classifier","year":2011,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Overfitting; Support vector machine; Covert; Artificial intelligence; Computer science; Machine learning; Regularization (linguistics); Classifier (UML); Parametric statistics; Pattern recognition (psychology); Artificial neural network; Mathematics; Statistics","score_opus":0.047118728097839006,"score_gpt":0.16944999757876614,"score_spread":0.12233126948092712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1651734266","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7813469,0.000008715454,0.2161014,0.00022280902,0.00033096934,0.0006866139,0.000031341096,0.00009495353,0.0011762745],"genre_scores_gemma":[0.9990939,0.0001305258,0.00024305742,0.000119858385,0.000010405778,0.0000034993373,0.00000904827,0.000008768808,0.0003809678],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9988762,0.00021244682,0.00018857761,0.00048619477,0.00010204262,0.00013454963],"domain_scores_gemma":[0.99729556,0.00019037256,0.00062062254,0.0017196059,0.00013966384,0.000034188473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001928373,0.00017893371,0.00024439022,0.00009672427,0.00007793811,0.000026975846,0.0017850576,0.00016322474,0.0000038679905],"category_scores_gemma":[0.000080276935,0.00012769375,0.00009346255,0.0003750117,0.00025413127,0.00017941868,0.0012711894,0.0003106907,0.0000033391211],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037962174,0.00012518204,0.0061255563,0.00020452212,0.00004951107,0.000004114789,0.00028664529,0.00003246656,0.04304877,0.9496654,0.00011727158,0.00030254328],"study_design_scores_gemma":[0.0007583672,0.00024955673,0.44890863,0.0008912052,0.000096263895,0.0000020443238,0.000027534845,0.049076103,0.4211354,0.07801391,0.00033333828,0.0005076477],"about_ca_topic_score_codex":0.000025775556,"about_ca_topic_score_gemma":0.0000024024966,"teacher_disagreement_score":0.87165153,"about_ca_system_score_codex":0.000047965437,"about_ca_system_score_gemma":0.00007882551,"threshold_uncertainty_score":0.52072},"labels":[],"label_agreement":null},{"id":"W1657318125","doi":"10.1007/978-3-642-30353-1_26","title":"Improvements to AdaBoost Dynamic","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Boosting (machine learning); Computer science; Overfitting; AdaBoost; Resampling; Artificial intelligence; Machine learning; Classifier (UML); Exponential function; Ensemble learning; Pattern recognition (psychology); Algorithm; Artificial neural network; Mathematics","score_opus":0.015532097009351742,"score_gpt":0.26489558991906426,"score_spread":0.24936349290971252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1657318125","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014852185,0.00024970213,0.99340534,0.0011328935,0.0014745499,0.00068556523,0.000023506602,0.00044981833,0.002563781],"genre_scores_gemma":[0.07227615,0.000055147782,0.9219136,0.004429975,0.000271738,0.000047603637,0.000022580673,0.000053449214,0.00092974363],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99587476,0.000023519955,0.00055013306,0.0016107344,0.0010691347,0.0008716941],"domain_scores_gemma":[0.99629736,0.00016906425,0.00028993405,0.002676933,0.00025300993,0.0003136899],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.000849531,0.00053166534,0.0004426701,0.0010533787,0.00020104034,0.0004915485,0.0056036725,0.00029146,0.00003268947],"category_scores_gemma":[0.000085093394,0.0005091975,0.00008767386,0.00073081505,0.0003322843,0.0010321626,0.0025922684,0.0006499615,0.00032337572],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021263504,0.000023787932,0.000020135752,0.000016749165,0.000004925895,0.000009970009,0.00022628112,0.00023642478,0.0018830524,0.019350875,0.00009413004,0.97813153],"study_design_scores_gemma":[0.0008023399,0.0008777628,0.0024689683,0.0013014999,0.000030191022,0.00014709841,3.61901e-7,0.43960547,0.04728381,0.40098846,0.10170865,0.0047854027],"about_ca_topic_score_codex":0.000015256314,"about_ca_topic_score_gemma":0.000041150237,"teacher_disagreement_score":0.9733461,"about_ca_system_score_codex":0.00066857063,"about_ca_system_score_gemma":0.0003851094,"threshold_uncertainty_score":0.9997765},"labels":[],"label_agreement":null},{"id":"W1747560310","doi":"10.5430/air.v4n2p93","title":"Augmenting cost-SVM with gaussian mixture models for imbalanced classification","year":2015,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Discriminative model; Artificial intelligence; Support vector machine; Machine learning; Computer science; Classifier (UML); Pattern recognition (psychology); Benchmark (surveying); Generative grammar; Mixture model; Generative model; Data mining","score_opus":0.3768862626796906,"score_gpt":0.4441573306332618,"score_spread":0.06727106795357118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1747560310","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008559834,0.0000556672,0.98844045,0.0049013863,0.00014273192,0.0015047124,0.000018931863,0.00038618752,0.0036939296],"genre_scores_gemma":[0.82640404,0.00002961,0.17195445,0.00009766153,0.00015100787,0.00093565683,0.000056525558,0.00002832163,0.0003427013],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963743,0.00026139454,0.00050049,0.00086346635,0.0011246962,0.0008756339],"domain_scores_gemma":[0.9961563,0.00039740617,0.00016121003,0.0013012731,0.0016644867,0.00031933247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003492604,0.00020103659,0.00021989837,0.00038849586,0.00040740328,0.0006290794,0.0018620727,0.00015194886,0.000007842324],"category_scores_gemma":[0.00054892007,0.000172033,0.00005290402,0.0015099733,0.00029713433,0.0013760609,0.00027340717,0.0004495767,0.00015354973],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009585849,0.00013582307,0.0000573492,0.000020348942,0.000012359352,0.0000040989084,0.0009294998,0.00051243784,0.010013626,0.78900576,0.0030800055,0.19613282],"study_design_scores_gemma":[0.000062774605,0.0002644099,0.00003833412,0.000045177487,0.0000031527682,0.00000677119,0.0009837906,0.5791242,0.15470363,0.2600284,0.0045070974,0.00023223118],"about_ca_topic_score_codex":0.00006652645,"about_ca_topic_score_gemma":0.00006442007,"teacher_disagreement_score":0.82554805,"about_ca_system_score_codex":0.00030733706,"about_ca_system_score_gemma":0.0005141593,"threshold_uncertainty_score":0.7015302},"labels":[],"label_agreement":null},{"id":"W1841999836","doi":"10.1007/11564096_36","title":"Simple Test Strategies for Cost-Sensitive Decision Trees","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Decision tree; Test (biology); Computer science; Simple (philosophy); Machine learning; Artificial intelligence; Decision tree learning; Total cost","score_opus":0.02663294647029125,"score_gpt":0.2935392305685823,"score_spread":0.26690628409829104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1841999836","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009116018,0.000113889524,0.9947665,0.00071914867,0.0005418458,0.0011010697,0.0000996868,0.0004601702,0.002188616],"genre_scores_gemma":[0.096449636,0.000060232407,0.9011416,0.0014556631,0.00051053683,0.000069682304,0.000049683535,0.000044178378,0.0002187722],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99600166,0.000020972191,0.0006329744,0.0017818586,0.0008634334,0.0006991283],"domain_scores_gemma":[0.9945609,0.0024219695,0.00039539777,0.0019006444,0.0005652913,0.00015579766],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008339095,0.0005673156,0.00055187877,0.0008234441,0.00032088882,0.0010893275,0.0036486764,0.00037125996,0.000011671884],"category_scores_gemma":[0.00035520643,0.00052318437,0.00014458301,0.0005254352,0.0006876861,0.0015225247,0.0010032556,0.00054160366,0.000038969556],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007240351,0.000031858544,0.000011508716,0.000012709123,0.000004563434,0.00001405687,0.00021313166,0.0040389765,0.00061812974,0.07600817,0.0003230508,0.9187166],"study_design_scores_gemma":[0.0003426129,0.00030361334,0.00028172147,0.00027326302,0.00000793338,0.000045484914,7.092405e-7,0.48508096,0.0098471055,0.4739092,0.029061696,0.0008456893],"about_ca_topic_score_codex":0.000014407163,"about_ca_topic_score_gemma":0.0002773586,"teacher_disagreement_score":0.91787094,"about_ca_system_score_codex":0.00043640262,"about_ca_system_score_gemma":0.0008623176,"threshold_uncertainty_score":0.99994767},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09096737967275106,"score_gpt":0.3815705795832492,"score_spread":0.2906031999104981,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1851653583","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014117168,0.0015692016,0.98222136,0.00023327649,0.00012615771,0.0014371225,0.0000011872712,0.00026104896,0.00003346516],"genre_scores_gemma":[0.5247203,0.00030686843,0.47351047,0.0003923212,0.00009509682,0.00056394667,0.000025052323,0.000024265779,0.00036166643],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984247,0.0002987865,0.0006055691,0.000221158,0.00024268626,0.00020711178],"domain_scores_gemma":[0.99857575,0.0003375062,0.00047188895,0.00028330734,0.00023366518,0.00009787907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002732664,0.00015537621,0.0004358626,0.00019945853,0.00024989218,0.00034847078,0.00035432688,0.00003739154,4.7997275e-7],"category_scores_gemma":[0.0065354267,0.00012382567,0.00004760855,0.0002327659,0.000020591633,0.0013463374,0.00030405758,0.0001844383,0.000023496486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007638857,0.00018823867,0.071897626,0.10947682,0.0005691663,0.00003425526,0.17429128,0.2071294,0.035417013,0.053001586,0.007588075,0.33964264],"study_design_scores_gemma":[0.0010086042,0.00021052791,0.0004560792,0.003750595,0.000030474872,0.00004902403,0.0005741933,0.978644,0.00024330315,0.0016505023,0.013111398,0.0002712948],"about_ca_topic_score_codex":0.000023846855,"about_ca_topic_score_gemma":0.000005902542,"teacher_disagreement_score":0.7715146,"about_ca_system_score_codex":0.00010061424,"about_ca_system_score_gemma":0.000021242522,"threshold_uncertainty_score":0.7823988},"labels":[],"label_agreement":null},{"id":"W1858246752","doi":"10.5430/air.v4n2p126","title":"K Nearest Gaussian-A model fusion based framework for imbalanced classification with noisy dataset","year":2015,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Noise (video); Computer science; Artificial intelligence; Pattern recognition (psychology); Gaussian noise; Benchmark (surveying); Gaussian; Data mining; Noisy data; Machine learning; Geography","score_opus":0.4051996626847235,"score_gpt":0.47102421377542,"score_spread":0.06582455109069646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1858246752","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005578236,0.000024253846,0.9905378,0.0066687707,0.00010999164,0.0010853964,0.00035300755,0.00032649375,0.00033641313],"genre_scores_gemma":[0.5118448,0.000015087563,0.48657507,0.00021568866,0.00009969786,0.0004908766,0.00068804517,0.00002620904,0.00004453773],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960594,0.00027062648,0.0005191281,0.001001558,0.0013196297,0.0008296258],"domain_scores_gemma":[0.99527454,0.00077771314,0.00016615159,0.0021741465,0.0012283429,0.00037908845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032623091,0.00022840792,0.00023638472,0.00041959365,0.00043879088,0.0006255674,0.0023563346,0.00021228788,0.0000150047135],"category_scores_gemma":[0.001511262,0.0001960353,0.000046581525,0.0016294265,0.0003968753,0.00093955704,0.00032317475,0.0005879561,0.00027239925],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002808086,0.00030179974,0.00010779331,0.000031272146,0.000008070843,0.0000062628806,0.00037109698,0.0034162372,0.009387814,0.9079275,0.012966637,0.06519469],"study_design_scores_gemma":[0.00004890443,0.0002896176,0.00004429349,0.000053218395,0.0000026796151,0.0000019210092,0.00023210618,0.7222465,0.071863905,0.20174992,0.0032614637,0.00020544896],"about_ca_topic_score_codex":0.00007119286,"about_ca_topic_score_gemma":0.000055476907,"teacher_disagreement_score":0.7188303,"about_ca_system_score_codex":0.0002673113,"about_ca_system_score_gemma":0.0009170518,"threshold_uncertainty_score":0.79940873},"labels":[],"label_agreement":null},{"id":"W1919031954","doi":"10.1109/icdm.2001.989495","title":"Comparisons of classification methods for screening potential compounds","year":2002,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pruning; Computer science; Machine learning; Data mining; Sampling (signal processing); Training set; Artificial intelligence; Set (abstract data type); Data set; Class (philosophy)","score_opus":0.12646528031024432,"score_gpt":0.38075029705572905,"score_spread":0.25428501674548476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1919031954","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000023325945,0.00006249973,0.99274206,0.0016249401,0.00010442552,0.0002613301,0.000008572213,0.00037903117,0.004793801],"genre_scores_gemma":[0.24392217,0.0000089507885,0.7555695,0.00012240486,0.000018676552,0.000044227338,0.00001607453,0.000005825768,0.0002921484],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893373,0.00009890434,0.00035476216,0.00029687953,0.00014269011,0.00017305503],"domain_scores_gemma":[0.9986339,0.00019348018,0.00021240112,0.00072682876,0.00018467565,0.000048672988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000490444,0.00009491274,0.00018818896,0.00013501683,0.00010108013,0.00007174497,0.0008812246,0.00006185081,0.00003089737],"category_scores_gemma":[0.00006454629,0.0000914205,0.00007365838,0.000313263,0.000065752225,0.00042815023,0.00011373005,0.000069960406,0.000008645485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047832723,0.00014627175,0.00017140237,0.000020197136,0.0000230888,1.2043165e-7,0.000098055876,0.00001831743,0.11699054,0.4817803,0.07581368,0.32493326],"study_design_scores_gemma":[0.00020488285,0.00004944863,0.0020432465,0.000006867869,0.000007955177,0.0000037256973,0.000024729212,0.8941121,0.059459053,0.0018667459,0.04210497,0.000116291245],"about_ca_topic_score_codex":0.00000773308,"about_ca_topic_score_gemma":6.689856e-7,"teacher_disagreement_score":0.89409375,"about_ca_system_score_codex":0.00001786176,"about_ca_system_score_gemma":0.000009586172,"threshold_uncertainty_score":0.372802},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Class (philosophy); Psychology; Computer science; Artificial intelligence","score_opus":0.0727591430494873,"score_gpt":0.29908448274792526,"score_spread":0.22632533969843796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1941659294","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000038165814,0.0018614584,0.99336046,0.002267629,0.00009480232,0.0005708612,0.00008440602,0.00041895293,0.001303235],"genre_scores_gemma":[0.9004814,0.0050071874,0.08777721,0.0008701822,0.00010777533,0.00055696955,0.00047889815,0.000037423077,0.0046829563],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969931,0.00029840658,0.00079620065,0.00085335324,0.0006736997,0.00038519845],"domain_scores_gemma":[0.99128896,0.00046762795,0.00040673465,0.0075620716,0.0001786955,0.00009590537],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.001486605,0.00021158844,0.0004382351,0.0002785766,0.00034701373,0.00080039445,0.008392807,0.000057878206,0.000041961364],"category_scores_gemma":[0.00035096056,0.00013826191,0.00014740883,0.0028713308,0.00009846099,0.00087499677,0.0013898268,0.00018483345,0.000589896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001669915,0.0017829809,0.011730554,0.003572595,0.014822947,0.000104795414,0.0032013794,0.0008829115,0.0008303174,0.4994125,0.36236778,0.101274535],"study_design_scores_gemma":[0.00005485141,0.000031416144,0.0002023973,0.0001510988,0.00063346454,0.0000059701333,0.00013314564,0.9621427,0.0006532918,0.0015770923,0.034106832,0.00030773427],"about_ca_topic_score_codex":0.000046863795,"about_ca_topic_score_gemma":0.00012243057,"teacher_disagreement_score":0.9612598,"about_ca_system_score_codex":0.00009282968,"about_ca_system_score_gemma":0.000018305449,"threshold_uncertainty_score":0.99697226},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0767719356677637,"score_gpt":0.29718364712064443,"score_spread":0.22041171145288074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967158716","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053969086,0.00032891706,0.872351,0.014080196,0.0008303781,0.00033663295,0.000006947449,0.0016401483,0.10502889],"genre_scores_gemma":[0.8033148,0.00006636115,0.19544534,0.0003662591,0.000100018224,0.000048791415,0.000015009578,0.000009086375,0.0006343224],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988894,0.000058641697,0.00019454416,0.0003225224,0.00023640724,0.00029847512],"domain_scores_gemma":[0.9985859,0.000117882984,0.00008144223,0.0009482938,0.0001137753,0.0001527118],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003392959,0.00011339061,0.000111731475,0.000102640195,0.00011601793,0.00013673774,0.0006494764,0.00008525066,0.00006418915],"category_scores_gemma":[0.00007628709,0.00011300492,0.000017486824,0.00034885568,0.000055178527,0.0016605121,0.0002971289,0.000119488126,0.00022073617],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011125148,0.00012016964,0.0017205072,0.000009827606,0.000015392952,2.2645771e-7,0.00028212593,1.003038e-7,0.0069342894,0.9346278,0.020323081,0.035955388],"study_design_scores_gemma":[0.0022288286,0.00046982174,0.36069998,0.00004903093,0.000049969683,0.00003309413,0.00035066728,0.04717626,0.047631815,0.013576325,0.52623725,0.0014969347],"about_ca_topic_score_codex":0.000008319528,"about_ca_topic_score_gemma":0.0000047083354,"teacher_disagreement_score":0.92105144,"about_ca_system_score_codex":0.00005538691,"about_ca_system_score_gemma":0.000040282248,"threshold_uncertainty_score":0.4608207},"labels":[],"label_agreement":null},{"id":"W1969114837","doi":"10.1109/icmla.2012.154","title":"A Sequential Ensemble Classification (SEC) System for Tackling the Problem of Unbalance Learning: A Case Study","year":2012,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Homogeneous; Class (philosophy); Range (aeronautics); Set (abstract data type); Artificial intelligence; Ensemble learning; Sequence (biology); Binary number; Implementation; Binary classification; Data set; Machine learning; Data mining; Pattern recognition (psychology); Mathematics; Support vector machine","score_opus":0.057397448898514995,"score_gpt":0.31601277418475215,"score_spread":0.25861532528623715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969114837","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06245716,0.000035768535,0.93403345,0.00018734719,0.00011225535,0.0014981002,0.0000040923896,0.0004900887,0.0011817598],"genre_scores_gemma":[0.9070366,0.0000017879016,0.09212253,0.000021224458,0.00006978039,0.00048441612,0.0000061692626,0.0000118268545,0.0002456423],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848837,0.00021123876,0.00043422464,0.00030870255,0.00025492732,0.00030253446],"domain_scores_gemma":[0.9983333,0.00019797517,0.0003707306,0.00078517833,0.00025344692,0.000059415393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001519296,0.00013159613,0.00017933222,0.00008218908,0.0002543384,0.00010478695,0.0007039741,0.000056491597,0.000001952407],"category_scores_gemma":[0.00004409989,0.00009291308,0.000056425863,0.0003851649,0.000042898457,0.0006522603,0.00016135957,0.00013474232,0.000009289778],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045075358,0.0012634549,0.029493738,0.00050573837,0.00013868927,0.000030543833,0.015208058,0.00017936547,0.0897576,0.8016,0.002512013,0.05926574],"study_design_scores_gemma":[0.0038197068,0.0018991551,0.008431322,0.00028838986,0.00024548554,0.003948851,0.050289255,0.5736647,0.31756946,0.0015327752,0.03657888,0.0017319754],"about_ca_topic_score_codex":0.000101552694,"about_ca_topic_score_gemma":0.00001353933,"teacher_disagreement_score":0.84457946,"about_ca_system_score_codex":0.00009261533,"about_ca_system_score_gemma":0.00006244691,"threshold_uncertainty_score":0.37888852},"labels":[],"label_agreement":null},{"id":"W1973798076","doi":"10.1109/ijcnn.2013.6706979","title":"Measure optimized wrapper framework for multi-class imbalanced data learning: An empirical study","year":2013,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Alberta Innovates; China Scholarship Council","keywords":"Computer science; Machine learning; Benchmark (surveying); Measure (data warehouse); Artificial intelligence; Class (philosophy); Binary classification; Focus (optics); Data mining; Sampling (signal processing); Scheme (mathematics); Function (biology); Support vector machine; Mathematics","score_opus":0.15466144151449066,"score_gpt":0.39794993179313215,"score_spread":0.2432884902786415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973798076","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024621496,0.000017046648,0.9912688,0.0019625751,0.00017823915,0.0020780386,0.00001787649,0.0017269113,0.000288368],"genre_scores_gemma":[0.2116634,0.000004716148,0.78642213,0.00069981656,0.00006647634,0.0005559566,0.00012831377,0.000028002103,0.0004311721],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969891,0.0003104221,0.00046515872,0.0012797458,0.00046569656,0.00048987946],"domain_scores_gemma":[0.9949887,0.00030077598,0.00018755425,0.003915359,0.00038971927,0.00021788596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009779253,0.0002775056,0.0003668471,0.00012402689,0.0002570976,0.00061352033,0.004582045,0.00019902487,0.00010103564],"category_scores_gemma":[0.00088601816,0.00022758375,0.000056758356,0.0004457728,0.000066536,0.0024151595,0.0010221427,0.00043913716,0.00016051128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039224478,0.01981111,0.11724293,0.00014001876,0.00080017006,0.000024942674,0.011326772,0.0010163728,0.019717483,0.10694123,0.36577395,0.35681278],"study_design_scores_gemma":[0.0016680238,0.00048600763,0.015843125,0.0000158091,0.000015169083,0.0000036394772,0.0005486239,0.9692617,0.0009385903,0.002451378,0.008261324,0.0005065961],"about_ca_topic_score_codex":0.0000439309,"about_ca_topic_score_gemma":0.000008745556,"teacher_disagreement_score":0.9682453,"about_ca_system_score_codex":0.000058627553,"about_ca_system_score_gemma":0.00010296428,"threshold_uncertainty_score":0.9280596},"labels":[],"label_agreement":null},{"id":"W1982069553","doi":"10.5539/cis.v8n1p151","title":"An Empirical Analysis of Imbalanced Data Classification","year":2015,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Naive Bayes classifier; Support vector machine; Artificial intelligence; Machine learning; Classifier (UML); Decision tree; Empirical research; Data mining; Pattern recognition (psychology); Statistics; Mathematics","score_opus":0.11201920652878578,"score_gpt":0.3778644614599534,"score_spread":0.2658452549311676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982069553","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015856655,0.000007242279,0.9825162,0.00028709084,0.00012471572,0.000093407165,0.000030000398,0.00015931849,0.0009253287],"genre_scores_gemma":[0.76478404,0.000010242466,0.23450802,0.00047895667,0.000013613824,0.0000036170877,0.00019923979,0.0000010493375,0.0000012073406],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984975,0.00003998246,0.0004081222,0.00032574643,0.0005734852,0.00015517995],"domain_scores_gemma":[0.99710244,0.000035975907,0.0002521249,0.0018406479,0.00058396504,0.00018481925],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0015923214,0.000082316954,0.00016334892,0.0008119964,0.00009880779,0.00041052428,0.0027008257,0.000035940546,0.0000014446738],"category_scores_gemma":[0.000099778284,0.00007185402,0.000016370841,0.0034756688,0.00028493785,0.02341259,0.0006613145,0.000059545444,0.000009267014],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017392218,0.00017270085,0.044245142,0.000025634978,0.00007061092,5.707203e-7,0.0069729197,0.0011917095,0.0022509224,0.19360057,0.007837658,0.7436142],"study_design_scores_gemma":[0.000091328686,0.000048499267,0.18897635,0.0000023088735,0.000010742733,0.000002025088,0.00004317251,0.8072237,0.0005689144,0.00019425093,0.0027629202,0.00007584034],"about_ca_topic_score_codex":0.00000736522,"about_ca_topic_score_gemma":7.5589753e-7,"teacher_disagreement_score":0.80603194,"about_ca_system_score_codex":0.000040188435,"about_ca_system_score_gemma":0.00023948717,"threshold_uncertainty_score":0.9902464},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.12914645258788685,"score_gpt":0.47386017052666646,"score_spread":0.3447137179387796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982672081","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.630439e-7,0.81246686,0.18579778,0.0005479375,0.00038504408,0.00057122036,0.00018926307,0.000024369963,0.00001658004],"genre_scores_gemma":[0.000004420544,0.6358826,0.3624532,0.0015835655,0.00005645338,0.0000020080063,0.0000111081135,0.000006145915,4.5683822e-7],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.994385,0.0004544207,0.0024095636,0.0008421469,0.0012869218,0.00062196027],"domain_scores_gemma":[0.9914605,0.00008800187,0.004752984,0.002217228,0.0008868713,0.00059441],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.008310511,0.00033819184,0.0023389214,0.00047853784,0.00031074535,0.0002845715,0.0068748733,0.00010364024,8.075295e-7],"category_scores_gemma":[0.00061544677,0.00025639535,0.00013103012,0.0040180204,0.00021690244,0.0012523914,0.0012126723,0.00044384546,0.0000015397904],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[6.7545034e-7,0.00000543281,0.000003926767,0.055910323,0.000004997055,0.0000037622992,0.000115397524,2.010031e-7,2.717926e-7,0.00020052317,0.0029634743,0.940791],"study_design_scores_gemma":[0.00005577786,0.00025382655,0.000021322141,0.3060915,0.000024903971,0.001622611,0.000013008761,0.0000687283,8.3213394e-7,0.000027464488,0.6916303,0.00018971118],"about_ca_topic_score_codex":0.000023484736,"about_ca_topic_score_gemma":0.0000036410866,"teacher_disagreement_score":0.9406013,"about_ca_system_score_codex":0.00089811307,"about_ca_system_score_gemma":0.008274484,"threshold_uncertainty_score":0.99998885},"labels":[],"label_agreement":null},{"id":"W1985074645","doi":"10.1016/j.inffus.2013.11.001","title":"Skew-sensitive boolean combination for adaptive ensembles – An application to face recognition in video surveillance","year":2013,"lang":"en","type":"article","venue":"Information Fusion","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; École de Technologie Supérieure","funders":"","keywords":"Computer science; Skew; Pattern recognition (psychology); Artificial intelligence; A priori and a posteriori; Set (abstract data type); Machine learning; Data mining","score_opus":0.017570094332057536,"score_gpt":0.25140054334348605,"score_spread":0.23383044901142852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985074645","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045277584,0.000002028724,0.94978774,0.0014625387,0.000094312796,0.002227747,0.000056220182,0.00036330623,0.0007285157],"genre_scores_gemma":[0.8940004,0.000009161119,0.10314456,0.00092211773,0.000020401529,0.000947764,0.00093169865,0.0000074254326,0.000016447744],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866456,0.00009013589,0.00048806253,0.00027351186,0.0002664695,0.0002172787],"domain_scores_gemma":[0.99830693,0.00012712128,0.00029325834,0.00046882132,0.0007163415,0.00008750062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005465396,0.0001455323,0.00014400392,0.0003991451,0.00013525489,0.00022641706,0.0003872281,0.00010896395,0.0000059837807],"category_scores_gemma":[0.00017516951,0.00015464738,0.000028055103,0.00054496026,0.000018732064,0.0059302533,0.00010126263,0.00009144362,0.000431263],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004338161,0.00009104586,0.00018254238,0.000023761198,0.000003150379,1.0773884e-7,0.003669869,0.00018385923,0.014140131,0.022225412,0.0033627788,0.95607394],"study_design_scores_gemma":[0.0012229304,0.0005820463,0.10952798,0.00009075444,0.0000028443367,0.0000062459603,0.001079654,0.77795553,0.07110154,0.027254269,0.010515737,0.00066045165],"about_ca_topic_score_codex":0.00020953701,"about_ca_topic_score_gemma":0.00007436125,"teacher_disagreement_score":0.9554135,"about_ca_system_score_codex":0.00018199666,"about_ca_system_score_gemma":0.000038697464,"threshold_uncertainty_score":0.6306337},"labels":[],"label_agreement":null},{"id":"W1985930887","doi":"10.1109/bigdata.2014.7004364","title":"Applying instance-weighted support vector machines to class imbalanced datasets","year":2014,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Dalhousie University","funders":"","keywords":"Support vector machine; Machine learning; Computer science; Artificial intelligence; Boosting (machine learning); Benchmark (surveying); Class (philosophy); Data mining","score_opus":0.01496149228429589,"score_gpt":0.27001987252476717,"score_spread":0.2550583802404713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985930887","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007424665,0.000005178218,0.9813834,0.0022824788,0.00028670742,0.00061983353,0.00014227573,0.0014350037,0.0131026935],"genre_scores_gemma":[0.41714376,0.000008989674,0.5711142,0.009393884,0.0001382924,0.00068621495,0.0006744873,0.000030170857,0.000810031],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979915,0.00008071355,0.00037349146,0.00073127856,0.00039462018,0.000428384],"domain_scores_gemma":[0.997581,0.000097824784,0.00012353958,0.0019002517,0.000087312335,0.00021008024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043436137,0.00022888549,0.00025571047,0.00018992096,0.00014339792,0.0002366324,0.0020068905,0.000078548306,0.0000922264],"category_scores_gemma":[0.00011556517,0.00019963423,0.000042496078,0.00068753073,0.000037768947,0.0008478509,0.0005363801,0.00015160488,0.000560301],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001704478,0.00010959674,0.0016066693,0.000031627365,0.000017096914,0.0000073838733,0.00012928959,0.0000062371823,0.03821909,0.42273635,0.33420178,0.20291784],"study_design_scores_gemma":[0.00036516308,0.00012843598,0.0063004307,0.00002202106,0.000004117251,0.000014037812,0.000006087773,0.047780797,0.04636091,0.002984145,0.89552724,0.00050660304],"about_ca_topic_score_codex":0.000026090896,"about_ca_topic_score_gemma":0.000029660687,"teacher_disagreement_score":0.5613255,"about_ca_system_score_codex":0.00007422158,"about_ca_system_score_gemma":0.000054795044,"threshold_uncertainty_score":0.81408477},"labels":[],"label_agreement":null},{"id":"W2001536048","doi":"10.1109/icmla.2012.144","title":"A Dynamic Sampling Framework for Multi-class Imbalanced Data","year":2012,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Sampling (signal processing); Computer science; Classifier (UML); Data mining; Machine learning; Oversampling; Artificial intelligence; Class (philosophy); Set (abstract data type); Sampling distribution; Training set; Pattern recognition (psychology); Bandwidth (computing); Mathematics; Statistics","score_opus":0.1637551525145151,"score_gpt":0.401709392639956,"score_spread":0.23795424012544086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001536048","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001279527,0.00010835104,0.9966996,0.0008764361,0.00043475878,0.00040920195,0.00011033746,0.0010005829,0.00023277772],"genre_scores_gemma":[0.11734068,0.000019338106,0.8814121,0.00067013915,0.0000579332,0.000096980664,0.00019067746,0.000015798327,0.00019634725],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854034,0.000028631439,0.00025788936,0.00050651736,0.00017460537,0.00049200567],"domain_scores_gemma":[0.99654615,0.0002791991,0.00012406791,0.0028552588,0.00007478534,0.000120522614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005893592,0.00014818202,0.00016264628,0.0000787353,0.00012583977,0.0001465301,0.0028966768,0.00011573139,0.000013790216],"category_scores_gemma":[0.00044623076,0.00013399222,0.000036155172,0.00027578403,0.000036399782,0.0017009334,0.00086992234,0.00014902421,0.00007428631],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000059259037,0.00020394888,0.0008508606,0.000031442272,0.000020852915,2.0859699e-7,0.00019305617,0.000003848513,0.0047963643,0.9327622,0.004870106,0.056261174],"study_design_scores_gemma":[0.0003449099,0.000028532431,0.0050494694,0.00003792123,0.000008368096,0.000007786636,0.000037509028,0.9092165,0.0043741665,0.014917468,0.06556634,0.00041100167],"about_ca_topic_score_codex":0.0000058607247,"about_ca_topic_score_gemma":0.000004438057,"teacher_disagreement_score":0.9178447,"about_ca_system_score_codex":0.00006505416,"about_ca_system_score_gemma":0.000041532367,"threshold_uncertainty_score":0.54640436},"labels":[],"label_agreement":null},{"id":"W2001652071","doi":"10.1016/j.compmedimag.2013.12.003","title":"Ensemble-based hybrid probabilistic sampling for imbalanced data learning in lung nodule CAD","year":2013,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Alberta Innovates; China Scholarship Council; National Natural Science Foundation of China; Simon Fraser University; University of Alberta","keywords":"Probabilistic logic; Artificial intelligence; Pattern recognition (psychology); Subspace topology; CAD; Computer science; Dimensionality reduction; Sampling (signal processing); Nodule (geology); Computer-aided diagnosis; Probabilistic classification; Statistics; Mathematics; Machine learning; Support vector machine; Computer vision; Naive Bayes classifier; Biology","score_opus":0.03378149451165669,"score_gpt":0.3051422654233574,"score_spread":0.2713607709117007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001652071","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0070806895,0.00020337442,0.98527646,0.0059445244,0.0002533281,0.0006397925,0.0000188783,0.0005615841,0.000021376269],"genre_scores_gemma":[0.5593461,0.000100131285,0.43757862,0.0021866858,0.00010819462,0.00021923087,0.00042463967,0.00002673649,0.000009689917],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99766624,0.00013213584,0.00047689892,0.0008535998,0.00039621998,0.00047489352],"domain_scores_gemma":[0.9976183,0.00077899155,0.000154882,0.0010455357,0.00015940012,0.00024289956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011001329,0.00021737954,0.0003356268,0.00024704463,0.00018431258,0.00035190812,0.0016266811,0.00007562842,0.0000038805983],"category_scores_gemma":[0.0009865693,0.00020703697,0.000042645843,0.00040083603,0.00021159313,0.0006619929,0.000697949,0.00045684687,0.0000029599069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051176627,0.0004780125,0.022567753,0.0011498155,0.00005156411,0.000065478176,0.00035925675,0.00021678061,0.007911149,0.040321562,0.01777372,0.90905374],"study_design_scores_gemma":[0.0011080527,0.000024129045,0.0037314831,0.00022431058,0.0000059224853,0.000022627917,0.0000056492254,0.98376113,0.00022956294,0.005922999,0.004714395,0.0002497405],"about_ca_topic_score_codex":0.000052636304,"about_ca_topic_score_gemma":0.0000045496827,"teacher_disagreement_score":0.98354435,"about_ca_system_score_codex":0.00003653234,"about_ca_system_score_gemma":0.00017756775,"threshold_uncertainty_score":0.84427226},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Class (philosophy); Focus (optics); Classifier (UML); Artificial intelligence; Machine learning","score_opus":0.068174256664078,"score_gpt":0.27984716191671505,"score_spread":0.21167290525263704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011376672","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008144988,0.00005157474,0.90442705,0.08279607,0.000939207,0.00034627883,0.000014351824,0.001199726,0.0020807404],"genre_scores_gemma":[0.5063142,0.00007157026,0.4810038,0.011148973,0.00044987816,0.0004912788,0.00016999706,0.000039314473,0.0003109741],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99811745,0.00006877974,0.0003845946,0.0006315607,0.00036870706,0.00042892195],"domain_scores_gemma":[0.9968916,0.0001860733,0.00015573841,0.002498135,0.00014358852,0.00012482172],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00020526625,0.00024690153,0.00019711319,0.00020124507,0.00027290804,0.00044784517,0.0026103356,0.000115136405,0.000025576723],"category_scores_gemma":[0.0003292368,0.00023413372,0.00008341561,0.0007420649,0.00011352304,0.0020114526,0.0005548025,0.00024680153,0.0010543634],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007889464,0.0005443797,0.00082105276,0.00003678228,0.00012090244,0.00008160621,0.003674977,0.00087153894,0.047750205,0.6932518,0.21748663,0.03528124],"study_design_scores_gemma":[0.0061004064,0.0007120852,0.0054148105,0.00012843915,0.000060494243,0.000042071944,0.00048954674,0.0022682433,0.22972727,0.15012863,0.60260624,0.0023217543],"about_ca_topic_score_codex":0.00003110094,"about_ca_topic_score_gemma":0.00007739377,"teacher_disagreement_score":0.5431231,"about_ca_system_score_codex":0.00016506619,"about_ca_system_score_gemma":0.00013704643,"threshold_uncertainty_score":0.99972343},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04805340199553818,"score_gpt":0.2653546485366028,"score_spread":0.2173012465410646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012290523","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00088369974,0.0003800306,0.9954076,0.00013342347,0.000068103815,0.0019074053,0.000067843335,0.00063550106,0.00051643763],"genre_scores_gemma":[0.8300952,0.000044160246,0.15972875,0.00004650876,0.00007125638,0.009916168,0.00003059384,0.000014825982,0.000052547584],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889237,0.000023556133,0.00028856436,0.00045547754,0.00014223582,0.00019779138],"domain_scores_gemma":[0.99885327,0.000046780417,0.0001465597,0.0006961369,0.00017187957,0.00008537834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019417511,0.00012960462,0.00014001263,0.00008476454,0.000297069,0.000097904405,0.00042051266,0.000053618754,4.3197568e-7],"category_scores_gemma":[0.0000136728295,0.000111514266,0.000018643088,0.00022958829,0.000051315554,0.0004830592,0.00005668572,0.00005938521,0.000004021967],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005777618,0.00040187564,0.01099592,0.00021543208,0.00008569095,0.0000021562512,0.010885787,0.0012028249,0.0081245955,0.9083772,0.0030099282,0.056640867],"study_design_scores_gemma":[0.00040334143,0.00009909021,0.0024448186,0.00011979846,0.000005733598,0.00006008975,0.00027521496,0.96722186,0.0020007773,0.0011075966,0.025980582,0.0002811279],"about_ca_topic_score_codex":0.00012674124,"about_ca_topic_score_gemma":0.000010461036,"teacher_disagreement_score":0.966019,"about_ca_system_score_codex":0.000060315684,"about_ca_system_score_gemma":0.000034917335,"threshold_uncertainty_score":0.45474195},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.3034801403945102,"score_gpt":0.4311119133602611,"score_spread":0.1276317729657509,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015452969","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.2152004e-7,0.5795948,0.4188398,0.000550981,0.00048512846,0.00021416329,0.00022559601,0.000024505163,0.00006406708],"genre_scores_gemma":[0.00017779824,0.988915,0.009767003,0.0003534641,0.00029336757,0.000011199519,0.00046146373,0.000013657892,0.0000070452165],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962633,0.00024811935,0.0022075295,0.00044571472,0.0006840434,0.00015126007],"domain_scores_gemma":[0.9945721,0.00026495522,0.0031806363,0.00072960544,0.0011592444,0.00009347257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011928887,0.00027260344,0.0009984187,0.00049760006,0.00003282489,0.0001657512,0.0032668568,0.0001541481,0.000049753853],"category_scores_gemma":[0.0004765134,0.00023042434,0.00023622764,0.00035584116,0.00009824874,0.0010048264,0.0003238042,0.00041920887,0.00005614442],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003409935,0.00009957133,9.194896e-7,0.0013928384,0.000075372285,0.000015657977,0.000020371464,5.6149887e-8,0.000014604619,0.0006830986,0.00060559885,0.9970885],"study_design_scores_gemma":[0.00008955945,0.00030935186,0.000034944067,0.1256484,0.0005432328,0.0011847059,0.00003884575,0.0016338582,0.0005859846,0.02335053,0.8457787,0.000801872],"about_ca_topic_score_codex":0.000005076367,"about_ca_topic_score_gemma":0.00000289537,"teacher_disagreement_score":0.99628663,"about_ca_system_score_codex":0.00007842808,"about_ca_system_score_gemma":0.00024516508,"threshold_uncertainty_score":0.93964314},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.14856716375644577,"score_gpt":0.39605426265136146,"score_spread":0.24748709889491569,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023639956","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025671194,0.00010155171,0.99733526,0.0009668512,0.00020356632,0.0003522985,0.00016190506,0.0005615682,0.000060263777],"genre_scores_gemma":[0.24950235,0.00001107783,0.7489188,0.00030851352,0.000055892968,0.000053073585,0.0011233544,0.0000128791025,0.000014112193],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803066,0.00007360439,0.00042029854,0.0008785095,0.0003250194,0.0002719278],"domain_scores_gemma":[0.996691,0.0016987117,0.00021720964,0.001003679,0.0003043317,0.00008505763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059120444,0.00017055498,0.0001904352,0.00011144474,0.0002466361,0.00022403889,0.0025103549,0.00007432677,0.0000075878206],"category_scores_gemma":[0.0010421113,0.00018208487,0.000048334947,0.00037159145,0.000052356103,0.0008704952,0.0006677986,0.00021274455,0.00006528133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002143019,0.00007855353,0.00023874808,0.00001541981,0.000030857882,0.0000034365405,0.00049936405,0.7082524,0.0017508254,0.13805598,0.00050560577,0.15054743],"study_design_scores_gemma":[0.00013551103,0.000031505206,0.00060933,0.000035261954,0.0000035300488,0.0000050799463,0.000027513472,0.72900766,0.008515215,0.2593768,0.0020854357,0.00016719059],"about_ca_topic_score_codex":0.000115624476,"about_ca_topic_score_gemma":0.000013102049,"teacher_disagreement_score":0.24924563,"about_ca_system_score_codex":0.00010460465,"about_ca_system_score_gemma":0.00018849065,"threshold_uncertainty_score":0.7425206},"labels":[],"label_agreement":null},{"id":"W2036783159","doi":"10.1145/1938606.1938607","title":"Two-stage approach for unbalanced classification with time-varying decision boundary","year":2010,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"Mitacs","keywords":"Agency (philosophy); Container (type theory); Boundary (topology); Computer science; Stage (stratigraphy); Operations research; Focus (optics); Simple (philosophy); Engineering; Mathematics; Geology","score_opus":0.023888311389192125,"score_gpt":0.28684113468606975,"score_spread":0.26295282329687764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036783159","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002301903,0.0000059191475,0.9750551,0.00031643253,0.00011164467,0.0006875911,0.00001819851,0.00097039365,0.0205328],"genre_scores_gemma":[0.19737291,0.0000022873583,0.80072206,0.00024972236,0.00005274075,0.00023321128,0.00012359112,0.00001859731,0.0012248805],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836487,0.000026284102,0.00028898355,0.0006833958,0.000330475,0.0003060051],"domain_scores_gemma":[0.9978491,0.00018617902,0.00018055955,0.0014559778,0.00022945506,0.000098732846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053073285,0.00018299898,0.00018006112,0.00015075736,0.0002638777,0.00039570854,0.0012435832,0.00010070304,0.00003236903],"category_scores_gemma":[0.000091655704,0.00014331535,0.000045662408,0.00044038496,0.00010369843,0.0011027489,0.00014171605,0.00022982039,0.000049011385],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009027031,0.00021635123,0.000602844,0.000031089687,0.000017778026,0.0000012976584,0.00011694897,0.00005361633,0.41504827,0.44411856,0.0066528716,0.13305008],"study_design_scores_gemma":[0.001235517,0.00013851991,0.0023588543,0.000016254626,0.000007752852,0.000022658609,0.000024507144,0.8809165,0.07543977,0.0050353208,0.03431864,0.00048571738],"about_ca_topic_score_codex":0.0000073802903,"about_ca_topic_score_gemma":0.0000051418565,"teacher_disagreement_score":0.8808629,"about_ca_system_score_codex":0.000045180903,"about_ca_system_score_gemma":0.0001401288,"threshold_uncertainty_score":0.58442307},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.14587677944015098,"score_gpt":0.31587666002732545,"score_spread":0.16999988058717447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040010062","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022824487,0.00006450046,0.9509304,0.025077892,0.0000963905,0.0002634567,0.00012269046,0.00054543914,0.00007473868],"genre_scores_gemma":[0.37854064,0.0000515419,0.6110542,0.0026441817,0.00023267814,0.00004877903,0.0073798634,0.000022367261,0.000025803334],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99789584,0.00009588418,0.00031387233,0.0011359652,0.00030559453,0.000252875],"domain_scores_gemma":[0.99358374,0.00014698908,0.00019090337,0.0059089293,0.000091913906,0.0000775059],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032223857,0.00019806148,0.00016735587,0.000105695064,0.00038364236,0.0006368018,0.0034325176,0.000072862706,0.000008761832],"category_scores_gemma":[0.00049666595,0.00018070023,0.000008969001,0.00036909958,0.00007639533,0.006221595,0.002521853,0.00027318398,0.00006503921],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049953393,0.00041404448,0.013119821,0.000047403955,0.0002928872,0.00014221165,0.009118505,0.0060617793,0.5167028,0.019365951,0.2208476,0.21383706],"study_design_scores_gemma":[0.0046656895,0.0005391771,0.014499639,0.00033866105,0.00015847365,0.00013027729,0.00071808946,0.7545464,0.085383154,0.017434167,0.11876088,0.0028253945],"about_ca_topic_score_codex":0.00012762267,"about_ca_topic_score_gemma":0.00014094487,"teacher_disagreement_score":0.7484846,"about_ca_system_score_codex":0.0000469216,"about_ca_system_score_gemma":0.00010443835,"threshold_uncertainty_score":0.7368741},"labels":[],"label_agreement":null},{"id":"W2045391158","doi":"10.1006/jmva.2001.1990","title":"An Almost Surely Optimal Combined Classification Rule","year":2002,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Mathematics; Classification rule; Classifier (UML); Artificial intelligence; Pattern recognition (psychology); Statistics; Machine learning; Computer science","score_opus":0.03741786258397855,"score_gpt":0.298022027308619,"score_spread":0.26060416472464043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045391158","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03282674,0.00005886067,0.96491426,0.0015109781,0.00011201286,0.000071923605,0.000008101893,0.000112691414,0.0003844173],"genre_scores_gemma":[0.78251064,0.00006549764,0.21710047,0.00011280693,0.00006057698,0.0000033556842,0.0000137268835,0.000008641714,0.00012426435],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978123,0.00027424333,0.0008151937,0.0003116769,0.00055893755,0.00022767975],"domain_scores_gemma":[0.9970432,0.00011538207,0.0010638778,0.00095534284,0.00063865073,0.00018356796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009660617,0.00016473551,0.00043103675,0.0008104487,0.00013263209,0.00027057272,0.0015497641,0.0001063751,0.00011939101],"category_scores_gemma":[0.00014923954,0.00014105749,0.00028997683,0.0019105702,0.000044951976,0.0017726833,0.00006954671,0.00026364744,0.00003829386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002955306,0.008141986,0.056797624,0.000048471848,0.0088632535,0.00030829848,0.007678405,0.017000828,0.49235913,0.110459164,0.019914465,0.27813283],"study_design_scores_gemma":[0.0005380226,0.00020671546,0.10210962,0.000009112539,0.00035079799,0.000019247704,0.00005243587,0.8896448,0.005000908,0.00034360564,0.0015212792,0.00020342869],"about_ca_topic_score_codex":0.00003066203,"about_ca_topic_score_gemma":0.0000033566744,"teacher_disagreement_score":0.872644,"about_ca_system_score_codex":0.00010652304,"about_ca_system_score_gemma":0.000034807304,"threshold_uncertainty_score":0.57521576},"labels":[],"label_agreement":null},{"id":"W2051778481","doi":"10.1007/s10044-014-0374-x","title":"Combining local and global learners in the pairwise multiclass classification","year":2014,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Pairwise comparison; Pattern recognition (psychology); Artificial intelligence; Benchmark (surveying); Multiclass classification; Margin (machine learning); Computer science; k-nearest neighbors algorithm; Class (philosophy); Binary classification; Machine learning; Binary number; Mathematics; Support vector machine","score_opus":0.019829353799847137,"score_gpt":0.2793350011628899,"score_spread":0.25950564736304277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051778481","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007274337,0.00003113118,0.9889192,0.002992606,0.000004390379,0.00017531954,0.0000073713236,0.000073693285,0.0005219711],"genre_scores_gemma":[0.99440265,0.000045406763,0.0046104486,0.0006519158,0.000011645193,0.00022906423,0.00003807384,0.0000026962298,0.000008103394],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900615,0.00013146554,0.00021495066,0.0003678149,0.00014894159,0.00013065748],"domain_scores_gemma":[0.9990707,0.00012563306,0.00010154647,0.0006212188,0.00003363961,0.000047268546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050913164,0.00009014181,0.00013394967,0.00010838951,0.00013888309,0.00018194134,0.00045442875,0.000041388786,0.0000017618559],"category_scores_gemma":[0.000015803975,0.00007023349,0.000034967987,0.0010354816,0.00011248465,0.00015566449,0.00008912387,0.00009058878,0.000008378316],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.36007e-7,0.000069795904,0.15959902,0.0000075172698,0.000031722022,1.9582157e-7,0.000287925,0.00003979593,0.00020051563,0.13024205,0.00007874761,0.7094421],"study_design_scores_gemma":[0.00013862876,0.0000116209985,0.460923,0.0000035617027,0.0000554484,0.0000022477175,0.00029911037,0.5313051,0.000075101125,0.0029616342,0.004114705,0.000109849854],"about_ca_topic_score_codex":0.0001599816,"about_ca_topic_score_gemma":0.00022405613,"teacher_disagreement_score":0.9871283,"about_ca_system_score_codex":0.000027294302,"about_ca_system_score_gemma":0.000007981476,"threshold_uncertainty_score":0.28640383},"labels":[],"label_agreement":null},{"id":"W2055498865","doi":"10.1109/his.2013.6920500","title":"Measure optimized cost-sensitive neural network ensemble for multiclass imbalance data learning","year":2013,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Ensemble learning; Machine learning; Subspace topology; Artificial neural network; Multiclass classification; Evolutionary algorithm; Focus (optics); Data mining; Support vector machine","score_opus":0.05602744217747754,"score_gpt":0.29273971145458605,"score_spread":0.2367122692771085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055498865","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026810434,0.000039856142,0.99260074,0.002463596,0.00024993203,0.001440038,0.000020194839,0.001095393,0.0018221681],"genre_scores_gemma":[0.29778033,0.00001556814,0.6996882,0.0008501408,0.00012612331,0.00028263315,0.00019218899,0.0000208456,0.0010439992],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978184,0.0001694655,0.00033919973,0.00082045235,0.00028236437,0.0005700982],"domain_scores_gemma":[0.9968694,0.000512561,0.00019873469,0.0018505115,0.00043901606,0.00012979668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070391555,0.00021491727,0.0002799093,0.00005300027,0.00025945264,0.00040301724,0.0020559067,0.00010148261,0.000012665979],"category_scores_gemma":[0.0004679399,0.00019143255,0.00005276561,0.00032101854,0.00006447159,0.0019032609,0.00081852195,0.00025021227,0.00009507974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010520025,0.00019334002,0.0013735415,0.00005106272,0.00012897975,0.000010950898,0.00045020002,0.016668143,0.03576498,0.050542198,0.45651668,0.43819472],"study_design_scores_gemma":[0.0006227596,0.0000487447,0.0011907172,0.000017509952,0.000006611783,0.000010037508,0.000034057477,0.9796913,0.005667827,0.00062667567,0.011816788,0.00026693832],"about_ca_topic_score_codex":0.00006629387,"about_ca_topic_score_gemma":0.000013166471,"teacher_disagreement_score":0.9630232,"about_ca_system_score_codex":0.000059483056,"about_ca_system_score_gemma":0.0000603088,"threshold_uncertainty_score":0.7806393},"labels":[],"label_agreement":null},{"id":"W2056960254","doi":"10.1145/1390334.1390354","title":"A boosting algorithm for learning bipartite ranking functions with partially labeled data","year":2008,"lang":"en","type":"preprint","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Boosting (machine learning); Computer science; Ranking (information retrieval); Machine learning; Artificial intelligence; Learning to rank; Bipartite graph; Labeled data; Algorithm; Training set; Semi-supervised learning; Ranking SVM; Data mining; Theoretical computer science; Graph","score_opus":0.08191461973988243,"score_gpt":0.304749296064842,"score_spread":0.2228346763249596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056960254","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006522394,0.000078656296,0.99445045,0.00062643306,0.0002909936,0.00091042125,0.00016190785,0.002293192,0.001122719],"genre_scores_gemma":[0.004756547,0.00012220794,0.9905991,0.00020531441,0.00022207337,0.0005011755,0.0019216524,0.00004427042,0.0016276662],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99704885,0.0001116779,0.00050206826,0.0014512197,0.00041398962,0.00047216576],"domain_scores_gemma":[0.9956051,0.0002862072,0.0004861765,0.0031622236,0.0003609806,0.00009928658],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007765089,0.00033549895,0.00038521326,0.00020736405,0.00049703784,0.0005201616,0.0030910661,0.0002028842,0.000010564264],"category_scores_gemma":[0.00026445804,0.00029818102,0.00006343524,0.00036913887,0.000079939826,0.0008792066,0.0035310998,0.00071290776,0.000026473068],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025501748,0.00017259021,0.00065278675,0.00015238416,0.0002540964,0.000025925545,0.00048136222,0.0034874643,0.00089934934,0.0051035145,0.029020395,0.9597246],"study_design_scores_gemma":[0.00036801898,0.00008083178,0.00010665189,0.00015849886,0.000032452634,0.000031074327,0.000016361942,0.92424405,0.0015820351,0.00044010626,0.07248819,0.00045171956],"about_ca_topic_score_codex":0.00007019047,"about_ca_topic_score_gemma":0.000039712064,"teacher_disagreement_score":0.9592729,"about_ca_system_score_codex":0.00007852957,"about_ca_system_score_gemma":0.00047640497,"threshold_uncertainty_score":0.999947},"labels":[],"label_agreement":null},{"id":"W2061538022","doi":"10.1109/icdm.2014.75","title":"Classification by CUT: Clearance under Threshold","year":2014,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Hydro (Canada); Simon Fraser University","funders":"","keywords":"Clearance; Computer science; Partition (number theory); Artificial intelligence; Machine learning; Clearing; Data mining; Mathematics","score_opus":0.023515623309686675,"score_gpt":0.2643902895113973,"score_spread":0.24087466620171064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061538022","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006903923,0.000019185507,0.95029867,0.0052831364,0.0001001401,0.00010800672,0.0000023870266,0.00094527623,0.04255282],"genre_scores_gemma":[0.9290691,0.000024361303,0.06576866,0.0027650201,0.00003412219,0.000034131142,0.000019248786,0.000010154552,0.0022751775],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99890983,0.0000427994,0.00019615579,0.0004140426,0.00023635545,0.00020080137],"domain_scores_gemma":[0.998604,0.000045862344,0.000088028544,0.0011301321,0.00006736925,0.00006461703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002875795,0.0001051961,0.00009774616,0.000056245648,0.00009075411,0.0001569707,0.0010777669,0.000071287206,0.000031299827],"category_scores_gemma":[0.000026585278,0.0000950578,0.000027957105,0.00028177924,0.000053623146,0.0006780754,0.00011187527,0.00010725838,0.00037262868],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001142352,0.000028044276,0.00017124119,0.0000024701912,0.0000018831631,4.8982887e-8,0.000014657483,0.0000026182206,0.015658202,0.8757911,0.09155695,0.016771665],"study_design_scores_gemma":[0.00038232442,0.00009624478,0.028897423,0.000018185714,0.0000039047636,0.0000071851136,0.000025175788,0.3562697,0.12648539,0.085134424,0.40211576,0.00056429615],"about_ca_topic_score_codex":0.0000073088213,"about_ca_topic_score_gemma":0.0000030079434,"teacher_disagreement_score":0.92837876,"about_ca_system_score_codex":0.0000404209,"about_ca_system_score_gemma":0.000018242885,"threshold_uncertainty_score":0.47895122},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.22461924927234064,"score_gpt":0.3280352919055073,"score_spread":0.10341604263316664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068258779","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003120379,0.000015738464,0.9938718,0.0047070533,0.00012721577,0.00052848354,0.00007924305,0.00018357909,0.0001748128],"genre_scores_gemma":[0.21990101,0.000112890244,0.7786322,0.00054930436,0.000015402618,0.00015549464,0.00011411368,0.000005796559,0.0005137876],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915266,0.000021319984,0.00026821118,0.00025285786,0.00014559386,0.0001593778],"domain_scores_gemma":[0.9969796,0.00074634654,0.00014932088,0.0018672734,0.00022953516,0.000027940368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029013553,0.00007763216,0.00010029543,0.00010057378,0.00013830542,0.00019012256,0.0019670895,0.000029504394,0.00003795454],"category_scores_gemma":[0.00027187113,0.000050891696,0.00002313783,0.000527281,0.00003948212,0.002675552,0.0004935092,0.00006449789,0.00002755129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001555352,0.00005195119,0.0010864945,0.000024062756,0.00002630595,2.162765e-8,0.00010474259,0.00007257378,0.0026352366,0.07418336,0.26566768,0.656146],"study_design_scores_gemma":[0.00008765133,0.000019848674,0.0030954268,0.0000062475256,0.0000043316954,8.8350447e-7,0.0000160127,0.72341305,0.014819841,0.0002564355,0.25819984,0.0000803974],"about_ca_topic_score_codex":0.00007035575,"about_ca_topic_score_gemma":0.0000031296304,"teacher_disagreement_score":0.7233405,"about_ca_system_score_codex":0.000019138808,"about_ca_system_score_gemma":0.000033091474,"threshold_uncertainty_score":0.36553743},"labels":[],"label_agreement":null},{"id":"W2079999948","doi":"10.1145/1871437.1871749","title":"Adapting cost-sensitive learning for reject option","year":2010,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Binary number; Binary classification; Mathematics","score_opus":0.025668560369527898,"score_gpt":0.2922093554751682,"score_spread":0.26654079510564027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079999948","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024015638,0.000001016288,0.9906572,0.0006537118,0.00017333918,0.0003071186,0.0000014727725,0.000786875,0.0050176703],"genre_scores_gemma":[0.5084999,0.0000016509823,0.49066395,0.00012780153,0.000045715173,0.000051984,0.000010881888,0.0000048706083,0.00059323246],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993125,0.000027400858,0.00012705149,0.00026597086,0.00010282262,0.00016423488],"domain_scores_gemma":[0.99921274,0.00017169595,0.0000832239,0.0003378104,0.00015788156,0.00003664726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044912493,0.00006849963,0.000074091746,0.000065204535,0.00014450766,0.00011538393,0.00032544913,0.000056944147,0.0000057627135],"category_scores_gemma":[0.0003275364,0.000064558015,0.000029925555,0.00013828772,0.000023224376,0.0005019367,0.000092901035,0.00019799429,0.00003111231],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004069165,0.000013359147,0.0000980556,0.000004043188,0.0000032766377,6.938692e-7,0.00016421084,0.000015396763,0.26508126,0.53827846,0.0012891579,0.195048],"study_design_scores_gemma":[0.0002005592,0.00008055893,0.0016919248,0.000009719667,0.000002440388,0.000015822985,0.000076261094,0.4874162,0.444247,0.003106079,0.062948585,0.00020483484],"about_ca_topic_score_codex":0.000011324259,"about_ca_topic_score_gemma":0.000012196719,"teacher_disagreement_score":0.5351724,"about_ca_system_score_codex":0.000019060015,"about_ca_system_score_gemma":0.00002977535,"threshold_uncertainty_score":0.26325995},"labels":[],"label_agreement":null},{"id":"W2083279581","doi":"10.1081/sac-120003337","title":"A COMPARISON STUDY OF SOME COMBINED CLASSIFIERS","year":2002,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Random subspace method; Computer science; Construct (python library); Artificial intelligence; Machine learning; Pattern recognition (psychology); Data mining; Classifier (UML)","score_opus":0.2367078500754393,"score_gpt":0.4541656929958778,"score_spread":0.2174578429204385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083279581","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01853547,0.00011447071,0.97986937,0.0003080114,0.00005927218,0.00054303487,0.000021067424,0.0001442015,0.00040512686],"genre_scores_gemma":[0.83029884,0.000055592125,0.16945799,0.000050607716,0.0000038587423,0.000038940223,0.000068248024,0.000007559055,0.000018380044],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983217,0.00031834954,0.00072479935,0.00026171122,0.00024616436,0.00012727635],"domain_scores_gemma":[0.9974004,0.0008785592,0.00036942787,0.0010835022,0.00022127878,0.000046820544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028955424,0.00012448142,0.0002415439,0.00034128738,0.00016481361,0.0000943295,0.0007700891,0.00005662709,0.000006612718],"category_scores_gemma":[0.00015045964,0.00014363977,0.000014180743,0.0005928711,0.000120890196,0.00050851336,0.00031803394,0.00017855625,0.000007221129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019193403,0.003404329,0.025098007,0.00004678486,0.00003439381,0.0000016462564,0.011314078,0.10378043,0.000116520256,0.65171105,0.0009660954,0.20350745],"study_design_scores_gemma":[0.00082566834,0.00020485281,0.033916123,0.000015670206,0.000007732987,5.0650186e-7,0.00039631172,0.9503301,0.000016832233,0.013894148,0.0002647207,0.00012735676],"about_ca_topic_score_codex":0.000031628777,"about_ca_topic_score_gemma":0.000024790197,"teacher_disagreement_score":0.84654963,"about_ca_system_score_codex":0.000061965984,"about_ca_system_score_gemma":0.00001532609,"threshold_uncertainty_score":0.585746},"labels":[],"label_agreement":null},{"id":"W2087805359","doi":"10.1109/eisic.2012.51","title":"Data Mining Applications for Fraud Detection in Securities Market","year":2012,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Alberta Innovates","keywords":"Computer science; Security market; Data science; Securities fraud; Business; Finance","score_opus":0.06259008482857968,"score_gpt":0.31885863526993596,"score_spread":0.25626855044135627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087805359","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017020435,0.00007498848,0.99335015,0.00024097649,0.00007282367,0.00038585733,0.000060118207,0.00030360254,0.0053412714],"genre_scores_gemma":[0.40763542,0.000018191733,0.5909601,0.00019521953,0.00008601504,0.0006467036,0.00007838364,0.0000062690606,0.00037368308],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99930775,0.000023570541,0.00015987623,0.00023365719,0.0000830299,0.00019213445],"domain_scores_gemma":[0.99865365,0.00013996422,0.000052315125,0.0010867569,0.000031506377,0.000035786445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005347076,0.00005972635,0.00006444309,0.00010451717,0.00006332822,0.000064053966,0.0009864435,0.000042513693,0.00001611155],"category_scores_gemma":[0.000058113616,0.000060228198,0.000010615736,0.0002450772,0.00001870386,0.0014853699,0.00029051845,0.000045795467,0.000009796694],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000068973427,0.00017337892,0.002938422,0.00006518465,0.00000847553,1.15118105e-7,0.0005194423,4.9871863e-7,0.003318268,0.1738341,0.06844682,0.7506884],"study_design_scores_gemma":[0.00023951985,0.000023898061,0.015840301,0.000015635183,0.00000407213,0.000007676148,0.00022467681,0.12008298,0.03170358,0.0049590343,0.82661086,0.00028776197],"about_ca_topic_score_codex":0.0000095083715,"about_ca_topic_score_gemma":0.00004263383,"teacher_disagreement_score":0.75816405,"about_ca_system_score_codex":0.000032148208,"about_ca_system_score_gemma":0.000016319862,"threshold_uncertainty_score":0.24560347},"labels":[],"label_agreement":null},{"id":"W2088609660","doi":"10.6000/1929-6029.2015.04.01.11","title":"The Hybrid ROC (HROC) Curve and its Divergence Measures for Binary Classification","year":2015,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Receiver operating characteristic; Divergence (linguistics); Mathematics; Measure (data warehouse); Binary classification; Statistics; Binary number; Pattern recognition (psychology); Kullback–Leibler divergence; Function (biology); Artificial intelligence; Computer science; Biology; Data mining","score_opus":0.19146622763271332,"score_gpt":0.4669100906900752,"score_spread":0.2754438630573619,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088609660","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021422065,0.0006723349,0.9830665,0.013035847,0.00069446047,0.0001657126,0.00006421679,0.000011739443,0.00014700765],"genre_scores_gemma":[0.93739444,0.003949134,0.05803182,0.00016117477,0.0002762053,0.0000413483,0.000014869975,0.00000884472,0.00012217477],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954275,0.00033155462,0.00053911796,0.00018051552,0.003293077,0.00022821646],"domain_scores_gemma":[0.99239814,0.0028904984,0.00021850098,0.0001879608,0.0040588393,0.00024603432],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00931679,0.00006918416,0.000114275375,0.00028753647,0.000112230955,0.00021464608,0.002342463,0.00005148026,0.0000072197877],"category_scores_gemma":[0.024973853,0.000049430477,0.000020560157,0.00021313854,0.00023416356,0.0003746492,0.00038140672,0.00053086155,0.000006962458],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015952255,0.0001227555,0.0011487954,0.000011827137,0.000034847373,0.00015010263,0.0002877806,0.000009884129,0.0004891116,0.58897936,0.07403767,0.33456835],"study_design_scores_gemma":[0.001641033,0.0006421516,0.01474783,0.00026038245,0.0000048675433,0.0002877972,0.00035408454,0.46681672,0.0026144683,0.37185407,0.14057624,0.00020036155],"about_ca_topic_score_codex":0.000011716877,"about_ca_topic_score_gemma":0.000017315258,"teacher_disagreement_score":0.93525225,"about_ca_system_score_codex":0.00024897643,"about_ca_system_score_gemma":0.0008542001,"threshold_uncertainty_score":0.98323923},"labels":[],"label_agreement":null},{"id":"W2094656673","doi":"10.5430/air.v4n1p22","title":"Diagnostic with incomplete nominal/discrete data","year":2015,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Missing data; Computer science; Imputation (statistics); Data mining; Decision tree; Cartesian product; Machine learning; Bayesian probability; Naive Bayes classifier; Outcome (game theory); Artificial intelligence; Mathematics; Support vector machine","score_opus":0.5670274782417085,"score_gpt":0.48427376241003667,"score_spread":0.08275371583167185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094656673","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002608278,0.00009440047,0.98936033,0.004620686,0.000121119745,0.0004774461,0.00003571852,0.00032080177,0.002361219],"genre_scores_gemma":[0.88408893,0.000040188894,0.115308434,0.00009601397,0.00016075098,0.00009633878,0.00008101486,0.000020334632,0.00010799237],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962105,0.00040644288,0.00040457142,0.00094179047,0.001317092,0.00071958825],"domain_scores_gemma":[0.9937494,0.0013323767,0.00008517733,0.0036359017,0.00084143155,0.00035570946],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0043168645,0.00016293068,0.00018691932,0.00034593942,0.00025680097,0.0006022323,0.0057982816,0.00007374032,0.000027791375],"category_scores_gemma":[0.0033510888,0.00013504842,0.000019283949,0.001701476,0.00052271027,0.0015433123,0.0023804114,0.0005044767,0.0014824332],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007401031,0.00020903694,0.0008668441,0.000020905585,0.000022203338,0.00014197765,0.0010676028,0.00010284426,0.001963144,0.6338836,0.01565101,0.3459968],"study_design_scores_gemma":[0.00010780252,0.0013515363,0.00097517617,0.00018719153,0.000011286424,0.00010546796,0.002094513,0.38446936,0.14801697,0.3900749,0.07167052,0.0009352731],"about_ca_topic_score_codex":0.00064150215,"about_ca_topic_score_gemma":0.000418679,"teacher_disagreement_score":0.88148063,"about_ca_system_score_codex":0.00014594242,"about_ca_system_score_gemma":0.00058206596,"threshold_uncertainty_score":0.9995808},"labels":[],"label_agreement":null},{"id":"W2094794062","doi":"10.6000/1929-6029.2012.01.01.08","title":"Performance Measures in Binary Classification","year":2012,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Predictive value; Receiver operating characteristic; Binary classification; Statistics; Sensitivity (control systems); Mathematics; Binary number; Value (mathematics); Likelihood ratios in diagnostic testing; Artificial intelligence; Pattern recognition (psychology); Computer science; Medicine; Support vector machine; Internal medicine; Engineering; Arithmetic","score_opus":0.14221368785995453,"score_gpt":0.46019623576992613,"score_spread":0.3179825479099716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094794062","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049190633,0.00024805762,0.94099516,0.005993308,0.0010759339,0.00012698171,0.00001569633,0.000018943667,0.0023353146],"genre_scores_gemma":[0.9311994,0.0014083654,0.06701578,0.000114076065,0.00020646429,0.000011025262,0.000006890494,0.000005644508,0.00003238114],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9947486,0.00038408156,0.0006937137,0.00013366572,0.0037034594,0.0003364803],"domain_scores_gemma":[0.99725455,0.0010414245,0.00017893211,0.00022300021,0.0011067882,0.00019531164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00944539,0.0000695578,0.00013780656,0.0010520611,0.000030358178,0.00007280858,0.0022436106,0.00009469407,0.00007922769],"category_scores_gemma":[0.0059483508,0.000061144645,0.000019152805,0.00055544946,0.0001734488,0.00085909414,0.00026671728,0.0009859571,0.00003276426],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063030406,0.0005189126,0.09317636,0.000016251992,0.000014261898,0.0001858231,0.0006214233,0.000013678141,0.0011758928,0.19172156,0.00822936,0.70426345],"study_design_scores_gemma":[0.0010966127,0.00022224712,0.83130884,0.0005111743,0.0000015277333,0.00022923661,0.00018803557,0.11926416,0.0017505004,0.014212989,0.031026686,0.00018797038],"about_ca_topic_score_codex":0.000022754046,"about_ca_topic_score_gemma":0.00001273976,"teacher_disagreement_score":0.88200873,"about_ca_system_score_codex":0.00046021523,"about_ca_system_score_gemma":0.00049568387,"threshold_uncertainty_score":0.7121161},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09066818198011457,"score_gpt":0.36427771998820674,"score_spread":0.2736095380080922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096451472","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00894332,0.00035339608,0.99011266,0.000068032634,0.000105427396,0.000108614746,0.000016149323,0.00024273459,0.00004968545],"genre_scores_gemma":[0.68607575,0.000179386,0.31363192,0.000013854731,0.00004045405,0.00001263597,0.0000078499515,0.000012049299,0.000026105074],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999059,0.000033897497,0.00020603418,0.0004149186,0.00009663967,0.0001895097],"domain_scores_gemma":[0.99914235,0.00019877493,0.000036044283,0.00053367537,0.000028324797,0.000060829843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004324713,0.00012765932,0.00012357759,0.00024086074,0.000115293966,0.00011566273,0.00040132855,0.00005380643,0.0000035803712],"category_scores_gemma":[0.000038647686,0.00013922688,0.000010970224,0.00030868992,0.000016768903,0.0014475895,0.000025576199,0.00028808718,0.00000661875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028092593,0.00006130484,0.00002767492,0.000040366176,0.000010287849,0.0000019830834,0.0006082497,0.031069074,0.015809016,0.00030831047,0.000025598727,0.9520353],"study_design_scores_gemma":[0.00020956731,0.000025590862,0.00018452054,0.000074669726,0.0000060417347,0.00001956216,0.000015250223,0.9869223,0.010098672,0.000011923785,0.0022801047,0.00015179551],"about_ca_topic_score_codex":0.000013082415,"about_ca_topic_score_gemma":0.00001194664,"teacher_disagreement_score":0.9558532,"about_ca_system_score_codex":0.000054579756,"about_ca_system_score_gemma":0.000032820048,"threshold_uncertainty_score":0.5677507},"labels":[],"label_agreement":null},{"id":"W2101303134","doi":"10.1108/17465661011026158","title":"Classification and prediction in customer scoring","year":2010,"lang":"en","type":"article","venue":"Journal of Modelling in Management","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"CHAID; Interpretability; Computer science; Artificial intelligence; Logistic regression; Machine learning; Decision tree; Sample (material); Data mining; Logit; Univariate; Linear discriminant analysis; Multivariate statistics","score_opus":0.027957862147005907,"score_gpt":0.26014286681542365,"score_spread":0.23218500466841774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101303134","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08620908,0.000020437119,0.91204846,0.0003739739,0.00021637819,0.000094336865,2.7345e-7,0.00002173196,0.0010153225],"genre_scores_gemma":[0.7933533,0.00021610939,0.20633717,0.000021184507,0.00002265718,0.000005409499,4.1427595e-7,0.000003160423,0.000040610063],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915034,0.000018945777,0.00039009695,0.0001403138,0.00020135485,0.0000989255],"domain_scores_gemma":[0.99947506,0.00002045564,0.00020079708,0.00022909073,0.000046770736,0.000027845652],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010268525,0.00005598253,0.00008729008,0.00049270544,0.000020420875,0.00006951832,0.0003389477,0.00003727781,0.000001725382],"category_scores_gemma":[0.0000095271735,0.000053988722,0.000014600146,0.00025799428,0.00001594309,0.000653348,0.00006891038,0.0002757138,0.0000030249093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050697978,0.00046479955,0.06778868,0.0002027425,0.000034005367,0.00008871108,0.001572561,0.1544123,0.017643733,0.5658545,0.0011816646,0.19070563],"study_design_scores_gemma":[0.00027155207,0.000018051585,0.045574155,0.00008533132,0.0000030501983,0.000010572775,0.000041368854,0.94461393,0.00039887076,0.0071515855,0.0017713628,0.000060167415],"about_ca_topic_score_codex":0.0000048348443,"about_ca_topic_score_gemma":0.0000035957737,"teacher_disagreement_score":0.7902016,"about_ca_system_score_codex":0.000055383614,"about_ca_system_score_gemma":0.000010865256,"threshold_uncertainty_score":0.22015962},"labels":[],"label_agreement":null},{"id":"W2101499181","doi":"","title":"Decision tree with better ranking","year":2003,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Ranking (information retrieval); Decision tree; Computer science; Tree (set theory); Artificial intelligence; Statistics; Receiver operating characteristic; Machine learning; Data mining; Mathematics; Pattern recognition (psychology)","score_opus":0.012543709907052752,"score_gpt":0.23634609739987744,"score_spread":0.2238023874928247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101499181","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018899118,0.000007459267,0.9564383,0.00038989924,0.000045887304,0.000069678645,2.4469418e-7,0.00035719905,0.040801425],"genre_scores_gemma":[0.24944368,0.0000021253989,0.74939615,0.00083238713,0.0000057379502,0.000009749076,8.418931e-7,0.0000038865824,0.0003054552],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993203,0.00002537158,0.000101302605,0.00023429841,0.00018927857,0.0001294429],"domain_scores_gemma":[0.9991854,0.00006110718,0.000034012774,0.0006477871,0.000040589923,0.00003112728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017948376,0.000065881984,0.00006292501,0.000064019936,0.000052317173,0.000102717306,0.00046244284,0.000025702222,0.000045296674],"category_scores_gemma":[0.000029931378,0.000045352048,0.00001362672,0.00025663996,0.000018221523,0.00046203367,0.000043302327,0.000052923155,0.000075425865],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037590921,0.00003215028,0.0032279345,0.000001865034,0.0000046633436,0.000007270183,0.000062485116,0.0000029723471,0.002102533,0.6111544,0.012969476,0.3704305],"study_design_scores_gemma":[0.001385193,0.00022631741,0.01934246,0.00007355812,0.000007107624,0.00012835482,0.000023937342,0.010916582,0.41147336,0.10782681,0.44782642,0.0007698839],"about_ca_topic_score_codex":0.000002054166,"about_ca_topic_score_gemma":0.0000062886393,"teacher_disagreement_score":0.50332755,"about_ca_system_score_codex":0.00001849544,"about_ca_system_score_gemma":0.000021537726,"threshold_uncertainty_score":0.18494028},"labels":[],"label_agreement":null},{"id":"W2102563871","doi":"10.71781/15328","title":"Statistical methods for insurance fraud detection","year":2008,"lang":"en","type":"dissertation","venue":"Open MIND","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Actuarial science; Insurance fraud; Business; Data science; Statistics; Computer science; Mathematics","score_opus":0.06904321972103122,"score_gpt":0.43499041162189506,"score_spread":0.36594719190086383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102563871","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00049422367,0.000076629316,0.98905826,0.0000363827,0.00067532505,0.0010577037,0.00019539527,0.00002329404,0.008382818],"genre_scores_gemma":[0.0070189945,0.00006362829,0.9857857,0.000032072046,0.00005344643,0.00049600645,0.0012630796,0.000024500236,0.00526253],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99832696,0.00014293537,0.00038866024,0.0007398013,0.00017490909,0.00022673851],"domain_scores_gemma":[0.99820364,0.00033361185,0.00032934194,0.00083965855,0.00022499783,0.000068783236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005342773,0.00021222894,0.00031560755,0.00013164763,0.00020000241,0.00037757392,0.0019752686,0.00026772227,0.00009813629],"category_scores_gemma":[0.00036465132,0.00022047048,0.00005380506,0.00026250505,0.000030006786,0.0006443618,0.0001237816,0.00023455125,0.000122013545],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028798837,0.00003098638,0.0000048908114,0.000016901264,0.000011258046,0.0000015351822,0.0002730014,3.58732e-7,0.0055878744,0.0009519113,0.0012514609,0.991841],"study_design_scores_gemma":[0.00038143076,0.00017252336,0.005365065,0.0000768432,0.000017672017,0.000016819378,0.000054727894,0.0064073936,0.5112687,0.0051956507,0.4704679,0.00057533965],"about_ca_topic_score_codex":0.00002381256,"about_ca_topic_score_gemma":0.000057951514,"teacher_disagreement_score":0.99126565,"about_ca_system_score_codex":0.000080371894,"about_ca_system_score_gemma":0.00022582828,"threshold_uncertainty_score":0.8990525},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.1947451742491384,"score_gpt":0.3649999840489949,"score_spread":0.17025480979985652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103614420","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067552733,0.000009098921,0.99064285,0.00031156428,0.00018268012,0.0006857865,0.0005032206,0.00024338688,0.0006661333],"genre_scores_gemma":[0.8282302,0.000012766548,0.16907437,0.00022804104,0.00008892014,0.000056876816,0.002286038,0.000012060456,0.000010738863],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986179,0.00004446543,0.00042180112,0.00047968968,0.00020132161,0.0002348498],"domain_scores_gemma":[0.99780196,0.00039190368,0.00040261852,0.0009583221,0.0003959065,0.000049298957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011821769,0.00011068377,0.00014733268,0.0001436759,0.0000743432,0.000047610083,0.0007465906,0.00007781807,0.000004385553],"category_scores_gemma":[0.000332711,0.000118998636,0.00003289246,0.00024023846,0.00004238904,0.0007889438,0.00017794794,0.00008715973,0.000027267828],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014147063,0.000047804107,0.00083177985,0.00003416217,0.0000085687825,8.5795364e-7,0.00011706773,1.3420005e-7,0.059163667,0.000297136,0.000664739,0.93881994],"study_design_scores_gemma":[0.0010324381,0.00016069406,0.13279733,0.00023148138,0.000032159693,0.0000243138,0.00024726446,0.14326379,0.7136181,0.0052341777,0.0028559659,0.0005023165],"about_ca_topic_score_codex":0.000017023054,"about_ca_topic_score_gemma":0.000022519554,"teacher_disagreement_score":0.9383176,"about_ca_system_score_codex":0.00005377892,"about_ca_system_score_gemma":0.00003232591,"threshold_uncertainty_score":0.48526236},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03453498297277332,"score_gpt":0.30704964742014945,"score_spread":0.27251466444737615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108197782","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05665304,0.00008467102,0.94117737,0.0015740643,0.0000997439,0.00011678285,0.000007710745,0.000027975233,0.0002586295],"genre_scores_gemma":[0.65842956,0.00013643486,0.34118682,0.00015983045,0.00005027951,0.0000056512245,0.000010623161,0.0000035293222,0.00001725477],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986639,0.000027214148,0.00080860953,0.00005910071,0.0003083615,0.00013280504],"domain_scores_gemma":[0.9990307,0.00005382214,0.00045560172,0.0002630346,0.00009216738,0.00010465169],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075267063,0.000078055986,0.00015844626,0.00035909485,0.00003080397,0.000118076925,0.00051071827,0.000052326694,0.0000012041874],"category_scores_gemma":[0.00026231832,0.000058845504,0.00002491617,0.00045136196,0.00013526874,0.003005581,0.00016097065,0.00019764956,0.0000055808114],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004950589,0.001470409,0.0013543718,0.00057669723,0.00004552357,0.000051987987,0.008407217,0.000014589016,0.026859052,0.70165545,0.00758636,0.25192887],"study_design_scores_gemma":[0.016833792,0.0036270053,0.13870305,0.007408,0.00007283501,0.0028351177,0.0066178576,0.13175899,0.0963078,0.12484704,0.46850708,0.0024814433],"about_ca_topic_score_codex":0.0000034472537,"about_ca_topic_score_gemma":0.000002944394,"teacher_disagreement_score":0.60177654,"about_ca_system_score_codex":0.00010812848,"about_ca_system_score_gemma":0.0003022451,"threshold_uncertainty_score":0.239965},"labels":[],"label_agreement":null},{"id":"W2108323282","doi":"10.1007/978-3-642-40319-4_13","title":"On the Application of Multi-class Classification in Physical Therapy Recommendation","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Class (philosophy); Machine learning; Artificial intelligence; Intervention (counseling); Rehabilitation; Decision support system; Referral; Clinical decision support system; Medicine; Physical therapy; Nursing","score_opus":0.04274484403340551,"score_gpt":0.2946739266865733,"score_spread":0.25192908265316777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108323282","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00031677997,0.000022862923,0.99344116,0.003360741,0.00022902274,0.001073072,0.0000080137315,0.000124562,0.0014237524],"genre_scores_gemma":[0.8476213,0.00009149456,0.15036309,0.0014089303,0.00013085174,0.00022466113,0.000046001147,0.000032867774,0.00008080095],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99734277,0.000092510294,0.0005513294,0.0010967727,0.0006031476,0.00031345876],"domain_scores_gemma":[0.9963943,0.0008827365,0.0005940455,0.001816139,0.00026161212,0.000051171883],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009369107,0.00034921992,0.00036137886,0.0006383021,0.0001134103,0.0001890728,0.002868907,0.00022057483,0.000014881773],"category_scores_gemma":[0.00012096771,0.00025455712,0.00007751383,0.0007587006,0.00048166647,0.00056218886,0.00034960068,0.0006648194,0.000067264176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003851856,0.00010067792,0.000020018439,0.0000076233728,0.0000027579574,3.275512e-7,0.00028401974,0.00078896125,0.0031075187,0.21561696,0.000047543523,0.78001976],"study_design_scores_gemma":[0.0001894988,0.00009742373,0.0010750043,0.00008738788,0.0000011524392,0.0000017809929,2.8451691e-7,0.8501178,0.010377266,0.13656293,0.0012354578,0.00025401957],"about_ca_topic_score_codex":0.0000315768,"about_ca_topic_score_gemma":0.000024429426,"teacher_disagreement_score":0.8493288,"about_ca_system_score_codex":0.00033756407,"about_ca_system_score_gemma":0.00019608715,"threshold_uncertainty_score":0.99999064},"labels":[],"label_agreement":null},{"id":"W2113747757","doi":"10.1109/icdm.2005.119","title":"Partial Ensemble Classifiers Selection for Better Ranking","year":2006,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Ranking (information retrieval); Computer science; AdaBoost; Machine learning; Artificial intelligence; Ensemble learning; Task (project management); Selection (genetic algorithm); Data mining; Ranking SVM; Learning to rank; Pattern recognition (psychology); Support vector machine; Engineering","score_opus":0.01879128591362798,"score_gpt":0.2566670148366264,"score_spread":0.23787572892299844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113747757","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015587627,0.0000045455563,0.9897304,0.0018451565,0.00015451506,0.00022551384,0.0000019297734,0.00075267884,0.0057264897],"genre_scores_gemma":[0.52044266,8.1750346e-7,0.47756684,0.0006444236,0.00017266248,0.00011454522,0.000018081219,0.000007783582,0.0010321839],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991256,0.000023258533,0.00018498776,0.00030048608,0.00013608811,0.00022958602],"domain_scores_gemma":[0.9994794,0.00005704757,0.00006798244,0.00029527757,0.00007615372,0.000024137984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002001033,0.000084461106,0.000083597,0.00008039112,0.00013048785,0.00015022494,0.00035450835,0.000060510298,0.000013333378],"category_scores_gemma":[0.000016246631,0.00007918497,0.000044898377,0.00022042566,0.000020237267,0.00051556755,0.000044389875,0.000057340196,0.000024786415],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000910434,0.000051153445,0.0019285778,0.000009874165,0.0000069568664,4.1802406e-7,0.000030368952,0.000026846581,0.111994825,0.66626686,0.1543458,0.065329246],"study_design_scores_gemma":[0.00036514213,0.000055064505,0.0017926216,0.000005636416,0.000004699377,0.000006701341,0.0000038903454,0.16524592,0.62770575,0.041419055,0.16317216,0.00022333582],"about_ca_topic_score_codex":0.0000428982,"about_ca_topic_score_gemma":0.00002103938,"teacher_disagreement_score":0.62484777,"about_ca_system_score_codex":0.000053247575,"about_ca_system_score_gemma":0.000029779796,"threshold_uncertainty_score":0.32290694},"labels":[],"label_agreement":null},{"id":"W2114249012","doi":"10.1109/icdm.2006.42","title":"Constructing Ensembles for Better Ranking","year":2006,"lang":"en","type":"article","venue":"Proceedings","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Ottawa","funders":"","keywords":"AdaBoost; Ranking (information retrieval); Computer science; Machine learning; Artificial intelligence; Learning to rank; Training set; Ensemble learning; Data mining; Pattern recognition (psychology); Support vector machine","score_opus":0.013496029009498364,"score_gpt":0.2378559596851372,"score_spread":0.22435993067563884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114249012","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016481893,0.000022238468,0.9662621,0.0020369894,0.00009991822,0.00025112927,0.000004793289,0.00077911967,0.014061787],"genre_scores_gemma":[0.4985409,8.318713e-7,0.5009002,0.00025342708,0.00012497288,0.00007018337,0.000005517174,0.000007662664,0.00009629351],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991811,0.0000019431284,0.00018315272,0.00028818133,0.00012817708,0.00021743577],"domain_scores_gemma":[0.9995245,0.00004592727,0.000119958546,0.000120446275,0.000168919,0.000020255618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021665436,0.0000882703,0.000097043645,0.000083450126,0.00011671767,0.0002471132,0.0004835151,0.000044072214,0.0000023201512],"category_scores_gemma":[0.000056792633,0.000087436994,0.00003372214,0.000185591,0.000035354515,0.0006733825,0.00009037368,0.00005982347,0.000007040109],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021488122,0.000010588834,0.0064978516,0.000037026497,0.0000030261285,2.8620633e-7,0.000082386694,8.716983e-8,0.034829527,0.8745007,0.015174607,0.06886175],"study_design_scores_gemma":[0.0005033502,0.00004164627,0.0018221965,0.000067256224,0.000008286419,0.00005044636,0.00008923462,0.016442573,0.70091563,0.2079662,0.0716823,0.00041090196],"about_ca_topic_score_codex":0.000007341822,"about_ca_topic_score_gemma":7.3857865e-7,"teacher_disagreement_score":0.66653454,"about_ca_system_score_codex":0.000042324547,"about_ca_system_score_gemma":0.000013730732,"threshold_uncertainty_score":0.35655773},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.03939313177323189,"score_gpt":0.3477566611305509,"score_spread":0.30836352935731903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115650093","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000841417,0.00016460837,0.99557394,0.00062385155,0.000102734004,0.00046679217,0.00000952183,0.0009886813,0.0012284508],"genre_scores_gemma":[0.13130726,0.000051719868,0.86546576,0.0009059614,0.0001494958,0.00027230792,0.0002855865,0.000039413044,0.0015224809],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984053,0.00018556179,0.00032520102,0.00052262034,0.00019105722,0.00037028678],"domain_scores_gemma":[0.99883515,0.00016167232,0.0002255595,0.00059190014,0.000120968274,0.00006475226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011569539,0.00018242428,0.00020426074,0.00012907994,0.0003365926,0.00019305662,0.00081994873,0.00007379762,0.00001374196],"category_scores_gemma":[0.00013748716,0.00017578172,0.00005827227,0.000328283,0.000026943255,0.0010164574,0.00015964304,0.00027642047,0.000010942827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044698052,0.0002639799,0.016202424,0.0005075472,0.000027771974,0.0000034240686,0.00045009397,0.0016540772,0.101935945,0.053878985,0.0073655443,0.8176655],"study_design_scores_gemma":[0.0002663679,0.00014530831,0.002960971,0.0000510549,0.0000057669386,0.000008255183,0.0000087513135,0.88941175,0.0129841175,0.00037853452,0.09354976,0.00022936439],"about_ca_topic_score_codex":0.00013684198,"about_ca_topic_score_gemma":0.000024582992,"teacher_disagreement_score":0.88775766,"about_ca_system_score_codex":0.000066607914,"about_ca_system_score_gemma":0.000042532854,"threshold_uncertainty_score":0.716817},"labels":[],"label_agreement":null},{"id":"W2116129845","doi":"10.1007/3-540-45357-1_46","title":"Hierarchical Classification of Documents with Error Control","year":2001,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Classifier (UML); Artificial intelligence; Data mining; One-class classification; Machine learning; Pattern recognition (psychology); Software","score_opus":0.020458997378542176,"score_gpt":0.2710244702270422,"score_spread":0.2505654728485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116129845","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000042062657,0.00007371259,0.9906207,0.0015182367,0.00029906657,0.0005738582,0.000016705935,0.00022721193,0.0066284933],"genre_scores_gemma":[0.48942715,0.000036897814,0.5093106,0.00070378324,0.00013514743,0.000032286473,0.000019409721,0.00003273162,0.0003019625],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99620503,0.000051431536,0.00065331033,0.0013778323,0.0012170564,0.0004953092],"domain_scores_gemma":[0.99640673,0.00034921017,0.00060328795,0.0021011266,0.00039488738,0.00014473803],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00073200447,0.0004330386,0.0005535995,0.0008527032,0.00013165842,0.00023963337,0.0037190553,0.00029085923,0.000021418236],"category_scores_gemma":[0.00007416086,0.0003575171,0.00008007512,0.0007376735,0.0011235952,0.00078715076,0.0004808494,0.00069011265,0.000021227595],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044136174,0.00010579155,0.0005294267,0.000058388046,0.000028820343,0.000051401115,0.00029814965,0.0020067822,0.002047241,0.28820157,0.00009810101,0.70653015],"study_design_scores_gemma":[0.0016416904,0.0009920038,0.006706903,0.0010468177,0.000033884426,0.00020489792,3.2963672e-7,0.6562989,0.0077845724,0.31382895,0.009864169,0.0015969194],"about_ca_topic_score_codex":0.0000127325875,"about_ca_topic_score_gemma":0.000025276377,"teacher_disagreement_score":0.7049333,"about_ca_system_score_codex":0.000294689,"about_ca_system_score_gemma":0.0005776441,"threshold_uncertainty_score":0.9998877},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.07612656226787208,"score_gpt":0.30491862664142827,"score_spread":0.2287920643735562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125722086","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011964263,0.00028371785,0.9957755,0.001323415,0.0005220751,0.000668312,0.00007855699,0.00046643542,0.00076229527],"genre_scores_gemma":[0.12822944,0.0008906479,0.868889,0.001125953,0.00025364614,0.000036686026,0.0004591471,0.000054010114,0.000061523075],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99528545,0.000059229926,0.0006440048,0.0024804776,0.0009756855,0.000555154],"domain_scores_gemma":[0.99469995,0.00051219034,0.00062147394,0.0036884693,0.00032334242,0.0001545677],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00086210726,0.0005398377,0.00050207373,0.00078537804,0.00040695997,0.00058639306,0.004754582,0.00041669564,0.0000038925587],"category_scores_gemma":[0.00018381728,0.0005330083,0.00004832722,0.0006792275,0.00090766134,0.0024671871,0.0024167947,0.0008302116,0.000022128756],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010201729,0.000039925882,0.000044492157,0.00004948821,0.000015716561,0.00000953705,0.0005400014,0.0010001922,0.0032249826,0.026159868,0.00016367523,0.9687419],"study_design_scores_gemma":[0.00030560675,0.00008081693,0.003589903,0.0003205515,0.000011432227,0.00012251032,9.0634484e-7,0.8934623,0.00651915,0.092403494,0.0022725086,0.0009108405],"about_ca_topic_score_codex":0.0000142413655,"about_ca_topic_score_gemma":0.000027086351,"teacher_disagreement_score":0.9678311,"about_ca_system_score_codex":0.0004732983,"about_ca_system_score_gemma":0.00055808335,"threshold_uncertainty_score":0.99971217},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.03635550629993588,"score_gpt":0.3092264469905259,"score_spread":0.27287094069059004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126734246","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00030400776,0.0002586794,0.9745212,0.0005168449,0.0005639926,0.0007288966,0.00023053076,0.00059368956,0.022282144],"genre_scores_gemma":[0.96882296,0.000055441826,0.028502557,0.0005063423,0.00017705618,0.00009187179,0.0014960638,0.000006733002,0.0003409789],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990044,0.000027045357,0.0004564001,0.00019995008,0.00012635757,0.00018582982],"domain_scores_gemma":[0.9985817,0.000069946866,0.00022725403,0.0008392452,0.00021611065,0.00006570998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059661234,0.00011875759,0.00016655664,0.00012891996,0.00015362256,0.0004052713,0.0008417442,0.000063250576,0.0000014742138],"category_scores_gemma":[0.00013897926,0.00010437658,0.000018244116,0.00020187491,0.000014579133,0.0067414413,0.00016578712,0.000059138438,0.00006596997],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014071827,0.000047680925,0.00044861907,0.00033745478,0.000016969805,4.4143673e-7,0.002476966,0.000004635871,0.0010871666,0.3098598,0.18014185,0.50556433],"study_design_scores_gemma":[0.00041159446,0.00011092589,0.004568014,0.00005826338,0.0000045038314,0.000029413097,0.00004517331,0.39337018,0.00065873173,0.00035524054,0.60017294,0.00021501498],"about_ca_topic_score_codex":0.000004030068,"about_ca_topic_score_gemma":8.2318917e-7,"teacher_disagreement_score":0.968519,"about_ca_system_score_codex":0.000028593848,"about_ca_system_score_gemma":0.00006388925,"threshold_uncertainty_score":0.4887382},"labels":[],"label_agreement":null},{"id":"W2127242195","doi":"10.5120/8930-3007","title":"Improving Credit Card Fraud Detection using a Meta-Classification Strategy","year":2012,"lang":"en","type":"article","venue":"International Journal of Computer Applications","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Credit card fraud; Credit card; Computer security; Data mining; Artificial intelligence; World Wide Web; Payment","score_opus":0.0763044949014617,"score_gpt":0.3300077224562295,"score_spread":0.2537032275547678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127242195","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019380753,0.00025376352,0.9958027,0.00046323962,0.00095490506,0.00022847239,0.000017749402,0.00013349867,0.00020761679],"genre_scores_gemma":[0.6742506,0.000022360682,0.3241609,0.00015216257,0.0013241795,0.000055366057,0.000010627203,0.000012102835,0.000011685426],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979669,0.00009962919,0.0007597557,0.0002404891,0.00069346814,0.00023976227],"domain_scores_gemma":[0.9969482,0.0001229467,0.0010468394,0.0005313653,0.0011927156,0.00015796711],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007043602,0.00017815281,0.00025791174,0.000456715,0.00012199186,0.00031289304,0.0017656689,0.000093031544,0.000014664783],"category_scores_gemma":[0.000029090908,0.00016366257,0.00023253521,0.00038177983,0.000051275587,0.0023286939,0.00020888148,0.00027623173,0.000024763285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024864206,0.0006663227,0.0008351294,0.0000222348,0.0015957421,0.000006172401,0.00044588497,0.0018686316,0.13338853,0.119526334,0.001310355,0.7403098],"study_design_scores_gemma":[0.0010069645,0.00021801505,0.017866489,0.000043839686,0.0006954965,0.0015847567,0.000090799105,0.78820366,0.077309184,0.0103267785,0.10179675,0.00085724524],"about_ca_topic_score_codex":0.000025623398,"about_ca_topic_score_gemma":0.0000015907555,"teacher_disagreement_score":0.78633505,"about_ca_system_score_codex":0.00028644264,"about_ca_system_score_gemma":0.00013629376,"threshold_uncertainty_score":0.6673966},"labels":[],"label_agreement":null},{"id":"W2127761070","doi":"10.1109/icpr.2010.139","title":"Rare Class Classification by Support Vector Machine","year":2010,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Support vector machine; Margin (machine learning); Computer science; Artificial intelligence; Machine learning; Pattern recognition (psychology); Class (philosophy); Structured support vector machine; Data mining","score_opus":0.014943024287552792,"score_gpt":0.2618360558466719,"score_spread":0.24689303155911912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127761070","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019162764,0.000009031178,0.95155495,0.008957354,0.0005267783,0.0002604965,0.00006594652,0.0017157657,0.03499341],"genre_scores_gemma":[0.86936975,0.000011021988,0.12463262,0.0012050435,0.00005638019,0.00007278336,0.00025958024,0.000015368732,0.00437745],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99867123,0.000034605233,0.0002729732,0.00048581237,0.00028561824,0.0002497337],"domain_scores_gemma":[0.9981656,0.000054013748,0.00012471019,0.0014175118,0.00011665888,0.0001215078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002872592,0.00014572426,0.00012463453,0.00009159325,0.00010469075,0.00019328784,0.0014363182,0.00012809758,0.00043798712],"category_scores_gemma":[0.00007713123,0.00012915299,0.000041334468,0.000329641,0.000067093795,0.0008183056,0.00017391767,0.00030891484,0.00047749563],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016056644,0.00006341127,0.0010345472,0.0000039654133,0.0000031463749,0.0000011952557,0.000030072986,3.175345e-8,0.3997345,0.3325208,0.24340944,0.023197275],"study_design_scores_gemma":[0.00024136118,0.000064873915,0.014811634,0.000002652561,0.0000034655534,0.000025958774,0.000007783681,0.024143325,0.24257211,0.0021926295,0.7155799,0.00035430354],"about_ca_topic_score_codex":0.000018811761,"about_ca_topic_score_gemma":0.000023575974,"teacher_disagreement_score":0.86745346,"about_ca_system_score_codex":0.000033035412,"about_ca_system_score_gemma":0.000072377734,"threshold_uncertainty_score":0.61373997},"labels":[],"label_agreement":null},{"id":"W2130387956","doi":"10.1136/bmjopen-2015-009518","title":"Prediction of individual combined benefit and harm for patients with atrial fibrillation considering warfarin therapy: a study protocol","year":2015,"lang":"en","type":"article","venue":"BMJ Open","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph’s Healthcare Hamilton; St. Joseph's Hospital; McMaster University","funders":"China Scholarship Council","keywords":"Medicine; Warfarin; Atrial fibrillation; Stroke (engine); Logistic regression; Emergency medicine; Population; Proportional hazards model; Emergency department; Medical record; Ambulatory; Intensive care medicine; Medical emergency; Internal medicine","score_opus":0.1816235207828419,"score_gpt":0.39067174150524714,"score_spread":0.20904822072240523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130387956","genre_codex":"protocol","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17962375,0.0000014996566,0.06584068,0.0001943693,0.000096190284,0.7537605,0.00012813175,0.00018256281,0.00017229239],"genre_scores_gemma":[0.7171737,3.289826e-7,0.12445378,0.000046711742,0.00007997041,0.1580796,0.00010605971,0.0000216938,0.00003816711],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99903494,0.00005266176,0.0002684337,0.000248909,0.00030495174,0.0000900931],"domain_scores_gemma":[0.99898815,0.00005412591,0.0002671106,0.00040086295,0.00024709952,0.000042657794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073993596,0.00008439865,0.0001583411,0.00005843361,0.000057078792,0.0002163267,0.00046515834,0.00003135099,0.0000011228117],"category_scores_gemma":[0.00008155856,0.000067235305,0.000013325748,0.00013002787,0.000023494229,0.00077753176,0.00042401525,0.000026934089,3.7240343e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037365493,0.00034954058,0.9041725,0.00005807327,0.00012694036,5.069373e-7,0.004291093,0.00008695168,0.00006454581,0.0037896237,0.0016780715,0.0816456],"study_design_scores_gemma":[0.043004338,0.014562339,0.9135126,0.00013852098,0.000028023318,0.0000033586243,0.00028839873,0.013430554,0.0030507653,0.0055896062,0.005988405,0.0004031191],"about_ca_topic_score_codex":0.00002901063,"about_ca_topic_score_gemma":0.000007498712,"teacher_disagreement_score":0.59568095,"about_ca_system_score_codex":0.000023494038,"about_ca_system_score_gemma":0.00011157336,"threshold_uncertainty_score":0.2741776},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0216262061828978,"score_gpt":0.2627378892251433,"score_spread":0.2411116830422455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137539029","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062353853,0.00009062247,0.93503416,0.0005762143,0.00001896248,0.00012704339,0.000001251377,0.00030083492,0.0014970883],"genre_scores_gemma":[0.63066673,0.0000531858,0.36909348,0.00013972538,0.000005938151,0.000006087796,0.0000021512462,0.0000034060554,0.000029291265],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9992243,0.000011935211,0.00012966729,0.00034275363,0.00015395104,0.0001374112],"domain_scores_gemma":[0.9992791,0.00010932482,0.000057569425,0.00043485584,0.000044073666,0.000075081545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012168232,0.0000980916,0.0001163749,0.0000746104,0.00010050074,0.00021393115,0.0003338693,0.00003245587,0.0000030629046],"category_scores_gemma":[0.000043204323,0.00007226935,0.000007159459,0.00017960288,0.00006701989,0.00083404174,0.00024990278,0.00007504496,0.000006599925],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042810094,0.00010841833,0.026033849,0.000019208934,0.000019738676,0.000024763294,0.0008394358,0.000048160582,0.0036101006,0.61531985,0.0026934242,0.35124025],"study_design_scores_gemma":[0.004955229,0.00077701354,0.7198321,0.00046174176,0.000022819127,0.00052348326,0.00022835378,0.05175205,0.07923075,0.113474645,0.027403422,0.0013383474],"about_ca_topic_score_codex":0.00009121053,"about_ca_topic_score_gemma":0.000100741876,"teacher_disagreement_score":0.6937983,"about_ca_system_score_codex":0.000032082164,"about_ca_system_score_gemma":0.000035190227,"threshold_uncertainty_score":0.29470587},"labels":[],"label_agreement":null},{"id":"W2141921295","doi":"10.1007/978-3-540-68123-6_4","title":"Boosting Support Vector Machines for Imbalanced Data Sets","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Boosting (machine learning); Support vector machine; Artificial intelligence; Computer science; Machine learning; Pattern recognition (psychology); Data mining","score_opus":0.04956617104562905,"score_gpt":0.3038860867448879,"score_spread":0.2543199156992588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141921295","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000075214557,0.00021681174,0.9933576,0.0011982297,0.0014804645,0.00090327585,0.00029883164,0.00066274364,0.0018744998],"genre_scores_gemma":[0.012108197,0.0001192025,0.984511,0.0017877397,0.00053011393,0.00004616808,0.0004677377,0.000065822394,0.0003640285],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946633,0.00003125759,0.00077994773,0.0026886151,0.0009837692,0.0008531412],"domain_scores_gemma":[0.99311715,0.00077774463,0.0005737692,0.004973676,0.00037311335,0.00018457169],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0011595737,0.0006466889,0.00067940593,0.00069251185,0.00042862212,0.0005214452,0.010825471,0.000357547,0.000016183774],"category_scores_gemma":[0.0004703542,0.0006144181,0.00011120238,0.0005488169,0.00066127547,0.0015416088,0.0037272007,0.00069072936,0.00003848597],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000106732,0.000038835013,0.000091556925,0.00008752358,0.000016439537,0.00006636656,0.0003504335,0.00045862593,0.00063753675,0.00819221,0.003867403,0.9861824],"study_design_scores_gemma":[0.00043955093,0.00023916975,0.00040287455,0.0003179424,0.000011833277,0.00025267893,6.7942366e-8,0.9120041,0.0035987687,0.046236873,0.03527132,0.0012248221],"about_ca_topic_score_codex":0.000014969144,"about_ca_topic_score_gemma":0.000033613076,"teacher_disagreement_score":0.9849576,"about_ca_system_score_codex":0.00028417745,"about_ca_system_score_gemma":0.0009403375,"threshold_uncertainty_score":0.9996307},"labels":[],"label_agreement":null},{"id":"W2144252306","doi":"10.6000/1929-6029.2013.02.02.06","title":"A Comparison of Error Correcting Output Coding Methods for Multiclass Classification by Using Support Vector Machine: The Prediction of Self-Monitoring of Blood Sugar","year":2013,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Multiclass classification; Support vector machine; Artificial intelligence; Binary number; Computer science; Machine learning; Structured support vector machine; Binary classification; Pattern recognition (psychology); Coding (social sciences); Class (philosophy); AdaBoost; Data mining; Mathematics; Statistics","score_opus":0.21699383592999893,"score_gpt":0.5356901599460219,"score_spread":0.31869632401602294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144252306","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033193946,0.00007858758,0.9651388,0.00052164204,0.0006185229,0.00028265614,0.00012993152,0.000010000836,0.000025915364],"genre_scores_gemma":[0.5950664,0.00006286067,0.40477443,0.0000045484394,0.000057685003,0.000012646812,0.000009770755,0.0000061964224,0.000005427424],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99555516,0.0005677101,0.001428287,0.00017193497,0.0020699655,0.00020694292],"domain_scores_gemma":[0.98943955,0.005594002,0.0011157157,0.00023844023,0.003515463,0.0000968334],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0067226575,0.00008874193,0.00031012736,0.00043047208,0.00005885765,0.000053564963,0.0016073359,0.00010089305,0.000016398364],"category_scores_gemma":[0.011243044,0.00007017583,0.000054328513,0.00034642048,0.00023711953,0.00029789266,0.0002106615,0.00062296115,3.4524882e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016024079,0.0017642032,0.13021696,0.0003646901,0.00043116216,0.0000095520645,0.004710168,0.0001298813,0.34852225,0.025065662,0.0041637514,0.4844615],"study_design_scores_gemma":[0.00077074615,0.00035723433,0.0164099,0.0003804548,0.00002246369,0.000032473476,0.0007183308,0.8360245,0.14328647,0.0016926753,0.00024113458,0.000063622545],"about_ca_topic_score_codex":0.00013232604,"about_ca_topic_score_gemma":0.0000031998738,"teacher_disagreement_score":0.8358946,"about_ca_system_score_codex":0.00018966074,"about_ca_system_score_gemma":0.00045249722,"threshold_uncertainty_score":0.9970857},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03196853507049728,"score_gpt":0.3018882251731047,"score_spread":0.2699196901026074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147834490","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0947536,0.0000075669345,0.89298356,0.0006417736,0.00003907899,0.00017277026,0.0000027182084,0.00016659164,0.0112323295],"genre_scores_gemma":[0.8528109,0.000013993172,0.14680442,0.00022175025,0.000015839272,0.000012366218,0.0000016622424,0.0000038102962,0.00011521566],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898624,0.00013561807,0.0002886063,0.0002407308,0.00018559265,0.00016318713],"domain_scores_gemma":[0.99857444,0.0005694333,0.00007114342,0.00071374397,0.000048269416,0.000022983106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012658502,0.00007315241,0.00011287391,0.00005863887,0.00006253148,0.000072225106,0.00051809335,0.00003192,0.000085861655],"category_scores_gemma":[0.00018019941,0.00005197141,0.000029688465,0.0003486704,0.000044340926,0.00049801625,0.00012684711,0.000084820844,0.000028838114],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000039861384,0.000024980716,0.00046065054,0.0000025595893,8.4683705e-7,0.0000045583465,0.00022704355,0.000009922086,0.01196393,0.012003087,0.00057864306,0.97471976],"study_design_scores_gemma":[0.0004935345,0.000054492775,0.12155224,0.00021807215,0.0000033791064,0.00006256448,0.00024523877,0.5172234,0.3387774,0.013338996,0.007660895,0.0003697747],"about_ca_topic_score_codex":0.000089832916,"about_ca_topic_score_gemma":0.0000541023,"teacher_disagreement_score":0.97435004,"about_ca_system_score_codex":0.000027068203,"about_ca_system_score_gemma":0.000018019895,"threshold_uncertainty_score":0.21193326},"labels":[],"label_agreement":null},{"id":"W2150038176","doi":"","title":"VipBoost: A More Accurate Boosting Algorithm","year":2009,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Boosting (machine learning); AdaBoost; Machine learning; Computer science; Artificial intelligence; Ensemble learning; Voting; Gradient boosting; Statistical classification; Majority rule; Algorithm; Pattern recognition (psychology); Classifier (UML); Random forest","score_opus":0.019612028796072975,"score_gpt":0.2904801912128576,"score_spread":0.27086816241678463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150038176","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009959291,0.000023365325,0.97786736,0.0049863025,0.000062273946,0.00011405469,0.0000032275516,0.0013781511,0.015465682],"genre_scores_gemma":[0.076947175,0.00001086322,0.9176941,0.0041890196,0.00004859069,0.000010526686,0.00000981588,0.0000048510783,0.0010850397],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903446,0.000021275284,0.00019095092,0.00032566747,0.0001944493,0.00023317784],"domain_scores_gemma":[0.99900705,0.000035897905,0.000078225734,0.0007347362,0.00007746142,0.0000666241],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017531669,0.0001053294,0.00009759096,0.00008084785,0.00009229529,0.00018142429,0.000956317,0.000045764635,0.000019635057],"category_scores_gemma":[0.000053353087,0.00009200647,0.000030244204,0.00034969175,0.000020499441,0.00087595644,0.00012068139,0.00010059713,0.000112524576],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.164237e-7,0.000029567065,0.000017058639,0.0000011428441,0.0000020399757,0.000009644444,0.00011800413,0.0000016228526,0.004356705,0.07611561,0.0117637785,0.9075843],"study_design_scores_gemma":[0.00045586115,0.00021468499,0.018629523,0.0000476635,0.0000052355863,0.00010578465,0.00006371863,0.6900205,0.18334298,0.038240664,0.068076655,0.0007967201],"about_ca_topic_score_codex":0.0000061240207,"about_ca_topic_score_gemma":2.991163e-7,"teacher_disagreement_score":0.9067876,"about_ca_system_score_codex":0.000032538803,"about_ca_system_score_gemma":0.00003425918,"threshold_uncertainty_score":0.37519148},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.02099275441995642,"score_gpt":0.2643135857297962,"score_spread":0.24332083130983978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152325113","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005639021,0.00049726205,0.9928874,0.0015233881,0.00034449427,0.00051264645,0.000010681914,0.00015332057,0.003506934],"genre_scores_gemma":[0.8523154,0.00020160095,0.14630067,0.00072190305,0.00022082916,0.000023212955,0.000012533039,0.000025605237,0.00017822719],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99603397,0.00015946131,0.0007832258,0.0013444066,0.0011340261,0.0005449147],"domain_scores_gemma":[0.9959664,0.0015787712,0.0006653437,0.0014911811,0.00020841816,0.00008988541],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019528174,0.00044920368,0.00062282296,0.00065893074,0.0001945907,0.00041040784,0.004842696,0.00030614756,0.000005668793],"category_scores_gemma":[0.0002767608,0.00034533575,0.0000655842,0.0010312021,0.0017837859,0.0008218718,0.0011517002,0.0012928537,0.0000046536325],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012184805,0.00006357348,0.008930239,0.0001352172,0.000021854848,0.00011179909,0.008680022,0.010254674,0.0007009912,0.1925872,0.00014030433,0.778362],"study_design_scores_gemma":[0.0009465923,0.0008693442,0.0113456,0.0021261722,0.000026906599,0.0002369398,0.000012526892,0.5598142,0.012931085,0.39670905,0.012973373,0.0020081995],"about_ca_topic_score_codex":0.000043556327,"about_ca_topic_score_gemma":0.000059061495,"teacher_disagreement_score":0.8517515,"about_ca_system_score_codex":0.00013138664,"about_ca_system_score_gemma":0.0003587101,"threshold_uncertainty_score":0.99989986},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.02750885075641095,"score_gpt":0.28599389310441553,"score_spread":0.25848504234800457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157751754","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028739797,0.000094605995,0.99788266,0.00005465498,0.0002334535,0.00026481578,0.0005355648,0.00042545458,0.00022141302],"genre_scores_gemma":[0.8282907,0.00005557546,0.17131777,0.000014743953,0.000060246664,0.000082398845,0.0000799073,0.00001518114,0.00008349338],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991253,0.0000074766863,0.00018871849,0.00041697023,0.00008169304,0.00017983203],"domain_scores_gemma":[0.9985084,0.0005348213,0.000029861496,0.00080936705,0.00007151535,0.000046011588],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015070196,0.00014147181,0.00012662551,0.00016562785,0.00012389073,0.00018648166,0.00051708176,0.00005941732,0.0000014955782],"category_scores_gemma":[0.000013784951,0.0001397748,0.000025509857,0.00022488147,0.000023060671,0.0011184709,0.000010455095,0.00010338512,0.000011965863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040690036,0.0007419148,0.000015922058,0.00013747849,0.000049831953,0.000009757272,0.0003729459,0.019060306,0.07036135,0.0450838,0.015596396,0.84852964],"study_design_scores_gemma":[0.00044267642,0.00010399996,0.00054725446,0.000082876395,0.000016948257,0.000016934597,0.00003084982,0.8973285,0.073375024,0.00082447776,0.026925048,0.0003054193],"about_ca_topic_score_codex":0.000012786102,"about_ca_topic_score_gemma":0.00007561653,"teacher_disagreement_score":0.8782682,"about_ca_system_score_codex":0.000030966457,"about_ca_system_score_gemma":0.00004309484,"threshold_uncertainty_score":0.5699851},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.017473232998650397,"score_gpt":0.25374102670363796,"score_spread":0.23626779370498757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166045895","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000051500556,0.00008517252,0.9925771,0.0005582008,0.0005911415,0.0006001991,0.00024377424,0.00074484176,0.004548123],"genre_scores_gemma":[0.14083657,0.00006580652,0.854803,0.0022907807,0.00072946766,0.0000626413,0.00078178186,0.000089927256,0.00034000378],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99521554,0.000044970246,0.00062746287,0.0020818515,0.0013251518,0.0007050276],"domain_scores_gemma":[0.99551165,0.0007370113,0.00060542225,0.0027788559,0.00022789142,0.00013917676],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00072309485,0.0006447018,0.0005011036,0.0008650728,0.0003649913,0.00074453634,0.0037663074,0.00031321158,0.00000799809],"category_scores_gemma":[0.00018827833,0.00054419227,0.00006782109,0.00070722547,0.00057693553,0.0013169388,0.0009130203,0.0009192692,0.000042552154],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042533222,0.00012194579,0.00032719522,0.00009605936,0.000023288889,0.00020627455,0.00024996628,0.028344663,0.0020692046,0.034748293,0.003946203,0.92982435],"study_design_scores_gemma":[0.001354552,0.0015066202,0.003971905,0.0034714052,0.000035348898,0.00040813076,3.6394593e-7,0.8018651,0.05131619,0.09681084,0.036262754,0.0029967634],"about_ca_topic_score_codex":0.00003183942,"about_ca_topic_score_gemma":0.000038990205,"teacher_disagreement_score":0.9268276,"about_ca_system_score_codex":0.0004387645,"about_ca_system_score_gemma":0.00046418488,"threshold_uncertainty_score":0.99970096},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.023255826573342523,"score_gpt":0.27206418511696706,"score_spread":0.24880835854362454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167793421","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035584148,0.000011247842,0.826584,0.000896981,0.00003842811,0.00015465176,0.0000011953064,0.0016234649,0.16713163],"genre_scores_gemma":[0.5682425,0.00003434155,0.41119817,0.0011565048,0.000065816996,0.00012731017,0.000015454056,0.000012012182,0.019147906],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99914736,0.000029823308,0.00016376477,0.00032039173,0.0001571051,0.00018157248],"domain_scores_gemma":[0.9988577,0.00003708561,0.00003442834,0.0009825589,0.000040354094,0.000047885664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000113128975,0.00006918934,0.00007137437,0.00005166473,0.00007433169,0.0001360334,0.00082843873,0.000031907628,0.0008507746],"category_scores_gemma":[0.000029317793,0.000063497064,0.000023936238,0.00034982644,0.00001894818,0.0006096108,0.00009783802,0.00006325873,0.00056740094],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027531455,0.000065909306,0.0006927777,0.0000028091333,0.000005981613,0.000008891496,0.00030086137,0.000006260064,0.013658998,0.14775945,0.06681031,0.770685],"study_design_scores_gemma":[0.0004833428,0.000045570006,0.016085159,0.000026196443,0.0000030763467,0.00004998236,0.000075467615,0.07032817,0.3880524,0.009410069,0.51479095,0.0006496168],"about_ca_topic_score_codex":0.000028881846,"about_ca_topic_score_gemma":0.000001707657,"teacher_disagreement_score":0.7700354,"about_ca_system_score_codex":0.000020534491,"about_ca_system_score_gemma":0.000014885951,"threshold_uncertainty_score":0.93153846},"labels":[],"label_agreement":null},{"id":"W2169074127","doi":"10.1109/icsmc.1998.727521","title":"Using misclassified training samples to improve classification","year":2002,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Classifier (UML); Computer science; Training set; Artificial intelligence; Pattern recognition (psychology); Machine learning; Test set; Data mining","score_opus":0.28211252646704227,"score_gpt":0.32972813739316165,"score_spread":0.04761561092611938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169074127","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016569508,0.000013639535,0.9773179,0.0028535752,0.00019987892,0.0002852245,0.0000130678745,0.0009523213,0.016707439],"genre_scores_gemma":[0.44918656,0.000004665214,0.54910123,0.00083315,0.000053659318,0.00003895105,0.0000053421923,0.000011246593,0.00076517963],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839056,0.000053477048,0.00033209275,0.00059507205,0.00028121093,0.00034761956],"domain_scores_gemma":[0.99844176,0.00008072444,0.00011740264,0.0010957438,0.00010836881,0.00015598597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002586055,0.0001589147,0.00016137416,0.00021029155,0.0001590283,0.0002615342,0.0010546716,0.000081715676,0.00011497831],"category_scores_gemma":[0.00014298725,0.00015203943,0.000047206748,0.00061048614,0.000037005557,0.00073717244,0.0001683874,0.00011370907,0.0002118287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016108387,0.000053922617,0.000094705785,0.0000065069944,0.000007991301,0.0000015365055,0.001016837,0.0000111070985,0.48058382,0.28166407,0.008182579,0.2283753],"study_design_scores_gemma":[0.000321581,0.000100365876,0.0041949,0.00003093802,0.000008186731,0.000022083317,0.00035324236,0.81440157,0.115105756,0.0047202646,0.060081262,0.00065987377],"about_ca_topic_score_codex":0.000017479393,"about_ca_topic_score_gemma":0.0000042054817,"teacher_disagreement_score":0.8143904,"about_ca_system_score_codex":0.00011956621,"about_ca_system_score_gemma":0.000031138858,"threshold_uncertainty_score":0.6199988},"labels":[],"label_agreement":null},{"id":"W2171171642","doi":"10.1142/s0218213008003819","title":"LAZY LEARNER ON DECISION TREE FOR RANKING","year":2008,"lang":"en","type":"article","venue":"International Journal of Artificial Intelligence Tools","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Ranking (information retrieval); Tree (set theory); sort; Machine learning; Decision tree; Class (philosophy); Metric (unit); Artificial intelligence; Sample (material); Set (abstract data type); Path (computing); Data mining; Information retrieval; Mathematics","score_opus":0.14075467666543623,"score_gpt":0.3696724673995253,"score_spread":0.22891779073408908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171171642","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011157766,0.00002759031,0.9834958,0.0028795572,0.0015604154,0.00014453869,0.000011565044,0.000060635073,0.00066215027],"genre_scores_gemma":[0.7433574,0.00011400148,0.25525683,0.0005999953,0.0005533172,0.0000114454515,0.0000053957856,0.000011939906,0.000089651134],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978685,0.00004426966,0.0008278792,0.00024031512,0.00083197374,0.00018707397],"domain_scores_gemma":[0.9970958,0.0007898645,0.00051874766,0.00042322406,0.0010957435,0.00007658955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071160577,0.00013274656,0.00019513676,0.00039726522,0.000119140605,0.00025145404,0.0028151053,0.000071395385,0.00004023895],"category_scores_gemma":[0.001796203,0.000114570714,0.00018756546,0.00020861665,0.000082502534,0.0011877769,0.00015540149,0.00022166948,0.00008363072],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022864426,0.00018809318,0.000040929637,0.0000012385195,0.0000325585,0.000051442534,0.00027566182,0.0009125841,0.004452216,0.16893218,0.0035566532,0.8213278],"study_design_scores_gemma":[0.00031375446,0.00123339,0.001231746,0.00025819134,0.000012189458,0.00061730086,0.00012164925,0.052939907,0.54906964,0.3513573,0.04238233,0.00046261356],"about_ca_topic_score_codex":0.000003282988,"about_ca_topic_score_gemma":0.000003325982,"teacher_disagreement_score":0.82086515,"about_ca_system_score_codex":0.00013521695,"about_ca_system_score_gemma":0.00013502188,"threshold_uncertainty_score":0.5231213},"labels":[],"label_agreement":null},{"id":"W2189812566","doi":"10.1016/j.patcog.2015.10.010","title":"The Multiclass ROC Front method for cost-sensitive classification","year":2015,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Agence Nationale de la Recherche","keywords":"Multiclass classification; Classifier (UML); Computer science; Artificial intelligence; Machine learning; Pattern recognition (psychology); Data mining; Support vector machine","score_opus":0.13044419202681293,"score_gpt":0.35259691295814527,"score_spread":0.22215272093133234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2189812566","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026768085,0.000020079524,0.99352217,0.0033962256,0.00042346393,0.0010088044,0.000100332116,0.00034137096,0.00091987],"genre_scores_gemma":[0.34774324,0.00003804523,0.64798343,0.0012161926,0.00025580992,0.001849299,0.0005862096,0.00003273769,0.00029505094],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985113,0.00024837465,0.00029788903,0.00041850886,0.00026112644,0.00026277127],"domain_scores_gemma":[0.9978584,0.0005505646,0.0002403161,0.00057936285,0.00066752324,0.00010382446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001227022,0.0001369722,0.00012393246,0.00006951954,0.00021303217,0.0002475897,0.0005126048,0.00008493897,0.0000026973846],"category_scores_gemma":[0.00043136443,0.00010882507,0.000057723315,0.0001289559,0.00004201924,0.0005423101,0.00008981924,0.000119965414,0.00025842455],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016292162,0.000034816007,0.0000694545,0.0000057775246,0.000010915667,8.989326e-7,0.00031905549,0.0000015915739,0.001972642,0.0007055062,0.0067591853,0.99010384],"study_design_scores_gemma":[0.0010745269,0.00015876093,0.004357952,0.000043873195,0.000025351235,0.0000391964,0.0005076279,0.8302603,0.09758063,0.022540512,0.043003667,0.00040762045],"about_ca_topic_score_codex":0.000030741365,"about_ca_topic_score_gemma":0.000033638906,"teacher_disagreement_score":0.98969626,"about_ca_system_score_codex":0.00017391327,"about_ca_system_score_gemma":0.00006439175,"threshold_uncertainty_score":0.44377577},"labels":[],"label_agreement":null},{"id":"W2206560168","doi":"10.1145/1390156.1390192","title":"Pointwise exact bootstrap distributions of cost curves","year":2008,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Confidence interval; Resampling; Pointwise; Receiver operating characteristic; Classifier (UML); Mathematics; Computation; Statistics; Binary number; Complement (music); Coverage probability; Binary classification; Computer science; Confidence distribution; Algorithm; Artificial intelligence; Support vector machine","score_opus":0.06289615371710643,"score_gpt":0.3000983568561167,"score_spread":0.23720220313901025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2206560168","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010276806,0.000087809,0.9889927,0.001574287,0.00004324599,0.00016884065,0.000066274726,0.0003886761,0.0076504834],"genre_scores_gemma":[0.9155785,0.0004602303,0.082921244,0.0003219075,0.000011163178,0.000034718287,0.000071582326,0.000004138415,0.00059651636],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992528,0.00002830673,0.00021373946,0.00019256734,0.00017560797,0.00013698413],"domain_scores_gemma":[0.9989672,0.000052166386,0.00008707684,0.0007284343,0.000110728455,0.000054393786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011426383,0.0000708954,0.00010823326,0.000052930725,0.00007040259,0.000012368415,0.0006932056,0.00002911882,0.00006876637],"category_scores_gemma":[0.000072526826,0.00006293434,0.000041642837,0.00032878015,0.0001129079,0.00045295173,0.000114919196,0.00006303769,0.00004097814],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033380225,0.00033490095,0.0058835335,0.00005698316,0.000017151762,0.000012987348,0.00011962633,0.0000016119612,0.012893032,0.6538229,0.3152683,0.01158563],"study_design_scores_gemma":[0.00048820747,0.00015787776,0.24682558,0.00016615276,0.000009855562,0.00019230861,0.000017483919,0.0047902963,0.6356581,0.0074574547,0.103679895,0.0005568069],"about_ca_topic_score_codex":0.000026266656,"about_ca_topic_score_gemma":0.0000027776305,"teacher_disagreement_score":0.91455084,"about_ca_system_score_codex":0.00002494662,"about_ca_system_score_gemma":0.00006803231,"threshold_uncertainty_score":0.2566388},"labels":[],"label_agreement":null},{"id":"W2223602837","doi":"","title":"A new method for learning decision trees from rules and its illustration for online identity application fraud detection","year":2010,"lang":"en","type":"dissertation","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Decision tree; ID3 algorithm; Incremental decision tree; Decision tree learning; Computer science; Machine learning; Decision rule; Data mining; Artificial intelligence; Alternating decision tree; Decision stump; Tree (set theory); Set (abstract data type); Influence diagram; Decision engineering; Decision analysis; Mathematics; Business decision mapping; Decision support system; Statistics","score_opus":0.02604447998424599,"score_gpt":0.36190969226525777,"score_spread":0.3358652122810118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2223602837","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0074551026,0.00013486548,0.9893951,0.00011341635,0.00045011358,0.001714832,0.00015148171,0.00054394896,0.00004113324],"genre_scores_gemma":[0.011458044,0.00011139495,0.9781396,0.000040816976,0.00032277624,0.0006305514,0.0077991113,0.000037012043,0.0014607228],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99802524,0.000052084302,0.0005160528,0.00090788834,0.00030247847,0.00019624335],"domain_scores_gemma":[0.99766743,0.0006658796,0.0005998882,0.0005054637,0.00046851576,0.00009280442],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00051184604,0.0002785503,0.00031448426,0.00027535367,0.00029966855,0.00041554426,0.0006620663,0.00061492005,0.0000093990675],"category_scores_gemma":[0.00062238576,0.00028142,0.00010395368,0.00022246756,0.0000075499124,0.0014662817,0.000056709032,0.00035337493,0.000006928492],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005909003,0.00003167746,0.0000039482543,0.000037467584,0.000013277479,3.57946e-8,0.0001238664,0.0000065469085,0.1428749,0.016493278,0.00019883325,0.8401571],"study_design_scores_gemma":[0.0006894574,0.00022455279,0.0058989017,0.000082262035,0.00007972395,0.000001989399,0.000115018185,0.5923009,0.25039497,0.13185093,0.017852874,0.0005084223],"about_ca_topic_score_codex":0.00034512815,"about_ca_topic_score_gemma":0.010051378,"teacher_disagreement_score":0.83964866,"about_ca_system_score_codex":0.000063813655,"about_ca_system_score_gemma":0.00011915921,"threshold_uncertainty_score":0.9999638},"labels":[],"label_agreement":null},{"id":"W2228056711","doi":"","title":"Financial Fraud Detection and Data Mining of Imbalanced Databases using State Space Machine Learning","year":2016,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Finance; Computer science; State (computer science); Database; Space (punctuation); Data mining; Data science; Artificial intelligence; Machine learning; Business","score_opus":0.026573973773539046,"score_gpt":0.24874003938140432,"score_spread":0.22216606560786528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2228056711","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8346917,0.00018471811,0.1637664,0.00012540132,0.00021462537,0.00022998934,0.0005747399,0.00016620671,0.000046193596],"genre_scores_gemma":[0.5359864,0.0017136594,0.4078358,0.000016119242,0.0000779854,0.0000011761097,0.0034027311,0.00007259554,0.05089352],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99844265,0.00011025079,0.00020256729,0.0006972169,0.0003067025,0.00024060548],"domain_scores_gemma":[0.9977789,0.000083831736,0.0007769174,0.0011088976,0.0001947811,0.000056662728],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032954878,0.000230233,0.00041290736,0.0003759151,0.00023832728,0.00003108717,0.0012341863,0.0001412926,0.000012956597],"category_scores_gemma":[0.00012458827,0.00025031282,0.00004552704,0.00028936897,0.00012180807,0.0013448711,0.0006532296,0.00022925281,0.000002835032],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046660018,0.00012650757,0.0046657217,0.0011480328,0.0001577079,0.00004986022,0.042381678,0.00004028202,0.7625695,0.00092405116,0.00054658117,0.18692347],"study_design_scores_gemma":[0.0043007196,0.00088861067,0.052104607,0.0045624794,0.0005100648,0.000049933573,0.027413676,0.23445684,0.6643219,0.0011027491,0.007161509,0.0031269104],"about_ca_topic_score_codex":0.011007783,"about_ca_topic_score_gemma":0.011006509,"teacher_disagreement_score":0.2987053,"about_ca_system_score_codex":0.00005779823,"about_ca_system_score_gemma":0.000138572,"threshold_uncertainty_score":0.99999493},"labels":[],"label_agreement":null},{"id":"W2232470570","doi":"10.5539/mas.v9n13p188","title":"Providing a Combination Classification (Honeybee Clooney and Decision Tree) Based on Developmental Learning","year":2015,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Decision tree; Classifier (UML); Ensemble learning; MATLAB; Machine learning; Artificial intelligence; Decision tree learning; Data mining; Pattern recognition (psychology)","score_opus":0.04718113927339433,"score_gpt":0.2728182754613657,"score_spread":0.22563713618797138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2232470570","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02898333,0.0000058843166,0.9618472,0.00031747084,0.00007615695,0.00036234266,8.6943345e-7,0.0004490942,0.007957639],"genre_scores_gemma":[0.73260736,0.000001780506,0.26708177,0.00019281874,0.000007980979,0.00007167421,0.00000699544,0.0000076504675,0.000021985268],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99753577,0.000034673423,0.00026318122,0.00083514047,0.0010186877,0.00031253413],"domain_scores_gemma":[0.99885637,0.00011653351,0.000171297,0.00047278812,0.00017701008,0.00020600115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017444592,0.0001616237,0.00013166571,0.00040195463,0.00046600762,0.0004942512,0.0010365773,0.00006401772,0.0000010538474],"category_scores_gemma":[0.0002727215,0.0001553842,0.000013974138,0.0009969032,0.00025351736,0.00092184934,0.00028840575,0.00019384564,0.00004126696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030446841,0.000110844085,0.00079334475,0.000005829724,0.0000010746495,0.0000010823769,0.0009909122,0.00033648865,0.30129436,0.08265649,0.00018759466,0.61359155],"study_design_scores_gemma":[0.00049846846,0.0000706937,0.0071959747,0.000021004425,0.0000013480507,0.000003200864,0.00008972376,0.9439935,0.03181485,0.01573535,0.000377207,0.00019864118],"about_ca_topic_score_codex":0.000004021562,"about_ca_topic_score_gemma":0.0000020603652,"teacher_disagreement_score":0.94365704,"about_ca_system_score_codex":0.00043181732,"about_ca_system_score_gemma":0.00045272236,"threshold_uncertainty_score":0.6336384},"labels":[],"label_agreement":null},{"id":"W2241877823","doi":"10.1007/s11227-015-1541-6","title":"Improving the classification performance of biological imbalanced datasets by swarm optimization algorithms","year":2015,"lang":"en","type":"article","venue":"The Journal of Supercomputing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"Universidade de Macau","keywords":"Computer science; Machine learning; Artificial intelligence; Class (philosophy); Data mining; Swarm behaviour; Particle swarm optimization; Population; Algorithm","score_opus":0.054495153893035705,"score_gpt":0.2758229984584579,"score_spread":0.2213278445654222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2241877823","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15533131,0.00022864329,0.8432104,0.0008124494,0.00019320394,0.000126517,0.000016172042,0.000047229114,0.000034107194],"genre_scores_gemma":[0.8659882,0.00013306724,0.13359386,0.0001361442,0.00010297321,0.0000016419564,0.000034020344,0.000006866027,0.000003259123],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982619,0.00029501115,0.00066340505,0.00015282458,0.00042696795,0.00019988579],"domain_scores_gemma":[0.9979271,0.0002748324,0.0007399307,0.0006177272,0.0003734821,0.00006687917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033990599,0.00012406416,0.00019844121,0.000073846895,0.00017445977,0.0000792083,0.0019904564,0.00006271142,0.0000014956792],"category_scores_gemma":[0.00028633233,0.00006636471,0.000044327182,0.00040840215,0.00014542657,0.00082918967,0.00030312018,0.00029978235,0.000002554921],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027434435,0.00063524634,0.01013491,0.00010367418,0.00016422017,0.0000071184395,0.007931906,0.10980196,0.39214554,0.004684436,0.04302894,0.4310877],"study_design_scores_gemma":[0.0003063572,0.00024069445,0.001987632,0.000041997122,0.000012291209,0.00011884981,0.00037279708,0.9635275,0.032724403,0.000081848266,0.00047751854,0.00010809074],"about_ca_topic_score_codex":0.000017508793,"about_ca_topic_score_gemma":1.711429e-7,"teacher_disagreement_score":0.85372555,"about_ca_system_score_codex":0.00007914764,"about_ca_system_score_gemma":0.00010979741,"threshold_uncertainty_score":0.36987963},"labels":[],"label_agreement":null},{"id":"W2260365916","doi":"10.3982/te2914","title":"Optimal adaptive testing: Informativeness and incentives","year":2018,"lang":"en","type":"article","venue":"Theoretical Economics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Incentive; Computer science; Microeconomics; Economics","score_opus":0.020752272242018498,"score_gpt":0.24199401634335213,"score_spread":0.22124174410133363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2260365916","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08580267,0.000005341148,0.892579,0.00031919405,0.00006334393,0.00010552947,0.000009880865,0.00020116287,0.020913854],"genre_scores_gemma":[0.7200979,0.000009294849,0.27962497,0.00020962513,0.000034743724,0.000008041058,0.0000017436182,0.0000042559777,0.000009426698],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993502,0.00003522315,0.00018261209,0.00022044343,0.00003620063,0.0001753151],"domain_scores_gemma":[0.99921423,0.00019977866,0.00007643856,0.0003477116,0.0000858153,0.000076033895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028171294,0.000094236166,0.00011672221,0.000049524297,0.00009373741,0.00012420763,0.000498463,0.000047867987,0.000019676349],"category_scores_gemma":[0.00011268849,0.00008833723,0.00001327114,0.00009884232,0.0011872697,0.0006838383,0.00040889022,0.00007885592,0.000068572874],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009996497,0.000009264864,0.000058445614,0.0000017015708,0.0000037962195,1.9967405e-7,0.00025555535,0.0000025138197,0.000062180916,0.96903825,0.000029972009,0.0305281],"study_design_scores_gemma":[0.0002523609,0.00034241338,0.0024982274,0.000019386762,0.0000039439915,0.000019766694,0.00010073451,0.4788425,0.020503053,0.49431312,0.0028240667,0.00028043147],"about_ca_topic_score_codex":0.0000011380548,"about_ca_topic_score_gemma":2.1447921e-7,"teacher_disagreement_score":0.6342952,"about_ca_system_score_codex":0.000036910318,"about_ca_system_score_gemma":0.000044758024,"threshold_uncertainty_score":0.43745446},"labels":[],"label_agreement":null},{"id":"W2261923652","doi":"10.1007/978-3-319-06483-3_23","title":"Using Ensemble of Bayesian Classifying Algorithms for Medical Systematic Reviews","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Machine learning; Computer science; Artificial intelligence; Support vector machine; Naive Bayes classifier; Bayesian probability; Bayes' theorem; Discriminative model; Data mining","score_opus":0.08168163749375508,"score_gpt":0.3357261139570094,"score_spread":0.25404447646325434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2261923652","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.2867604e-7,0.00079993537,0.9955713,0.00029025445,0.0009223964,0.0018311552,0.000006890246,0.00015925601,0.00041795033],"genre_scores_gemma":[0.0055966363,0.00011922037,0.99300873,0.00077412935,0.00027934895,0.000074035655,0.000007643325,0.000036457146,0.0001038078],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950552,0.00013827826,0.0015446111,0.0013348093,0.0013704111,0.0005566835],"domain_scores_gemma":[0.99450547,0.0014546595,0.001244047,0.0022095873,0.00039049375,0.00019577716],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0049134484,0.0004948419,0.0014075667,0.00078963576,0.00018500049,0.0002486306,0.0047045196,0.00047098487,0.000008225079],"category_scores_gemma":[0.001438741,0.00041065016,0.00023058183,0.0005391744,0.0005645607,0.00040209512,0.00092482247,0.0005267442,0.000008520288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047246926,0.000043296437,0.000011590936,0.015987976,0.0000265622,0.000018426746,0.00045765837,0.00090606103,0.0013312631,0.12548773,0.00013861893,0.8555861],"study_design_scores_gemma":[0.00015883632,0.00009599465,0.0000016185583,0.012289434,0.000017686745,0.00007214101,9.1484665e-8,0.9301642,0.0034308124,0.052130144,0.0011938682,0.0004451361],"about_ca_topic_score_codex":0.000008312943,"about_ca_topic_score_gemma":0.000013761941,"teacher_disagreement_score":0.92925817,"about_ca_system_score_codex":0.00031244697,"about_ca_system_score_gemma":0.0006700558,"threshold_uncertainty_score":0.99983454},"labels":[],"label_agreement":null},{"id":"W2270983878","doi":"10.5430/air.v5n1p135","title":"Cost-sensitive performance metric for comparing multiple ordinal classifiers","year":2016,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"U.S. Food and Drug Administration; National Institutes of Health","keywords":"Pairwise comparison; Classifier (UML); Computer science; Metric (unit); Ordinal data; Data mining; Machine learning; Artificial intelligence; Ordinal optimization; Performance metric","score_opus":0.4412564894946245,"score_gpt":0.45241214398568325,"score_spread":0.011155654491058764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2270983878","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013379114,0.000020357505,0.9816271,0.0024859186,0.0002325076,0.0009996715,0.000017981441,0.00029202545,0.00094532466],"genre_scores_gemma":[0.9513673,0.00008404741,0.047676705,0.000046053887,0.00012434802,0.0003871778,0.0000067411934,0.000018262515,0.0002893686],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99673253,0.00024366843,0.00049528346,0.00077155826,0.0007948175,0.00096214394],"domain_scores_gemma":[0.995475,0.0020884126,0.00011083078,0.00096825,0.001153195,0.00020432664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003127733,0.00017526593,0.00024052458,0.00076044,0.0005544286,0.00028015906,0.0016740292,0.00011247701,0.000017832042],"category_scores_gemma":[0.002261718,0.00013345822,0.00008127392,0.0019068719,0.00046366928,0.0010548725,0.00047567484,0.0003065764,0.00053525757],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008387272,0.00008421453,0.0012854631,0.000016745118,0.000012362812,0.0000032889777,0.00023100231,0.000021284852,0.0318733,0.15739691,0.0011744008,0.80781716],"study_design_scores_gemma":[0.00006902255,0.00024818353,0.0011107564,0.00006926871,0.0000023230546,0.0000063890325,0.0002931334,0.2217363,0.75431126,0.015497126,0.0064110695,0.00024515513],"about_ca_topic_score_codex":0.000047829537,"about_ca_topic_score_gemma":0.000043728414,"teacher_disagreement_score":0.93798816,"about_ca_system_score_codex":0.00036219857,"about_ca_system_score_gemma":0.00021196468,"threshold_uncertainty_score":0.68798316},"labels":[],"label_agreement":null},{"id":"W2273045451","doi":"10.1007/978-3-642-20862-1_17","title":"Intelligent Monitoring System for Online Listing and Auctioning","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in business information processing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Listing (finance); Common value auction; Process (computing); Computer science; Database; Operations research; World Wide Web; Computer security; Business; Engineering; Finance; Operating system","score_opus":0.03990115982261253,"score_gpt":0.26723212133203966,"score_spread":0.22733096150942714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2273045451","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020355124,0.00059738156,0.99411577,0.0001493518,0.0005021215,0.000457269,0.00002200374,0.0005645112,0.003571227],"genre_scores_gemma":[0.17371956,0.00030810005,0.82417995,0.00018796697,0.0005552962,0.00015980037,0.000447414,0.000073831696,0.00036810682],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835634,0.000008801789,0.0008102873,0.00033236257,0.0002479613,0.0002442336],"domain_scores_gemma":[0.9978036,0.00011585628,0.00087276474,0.00039027844,0.00077315734,0.000044341657],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003154758,0.0003329033,0.00033392955,0.0006057994,0.00024936546,0.00052634784,0.00051537924,0.0003580749,0.0000018840116],"category_scores_gemma":[0.00033488337,0.0003313232,0.000035553596,0.00025160253,0.0000586954,0.0028034349,0.00021459705,0.00035463445,0.0000038702315],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008602048,0.0000052856017,0.000041612468,0.0016423838,0.000006653913,8.144212e-7,0.0010452856,0.0003878719,0.000022253509,0.023447905,0.0000044236767,0.9733869],"study_design_scores_gemma":[0.002417849,0.00022260421,0.0033747803,0.05142009,0.00023413243,0.00053401245,0.00038959502,0.5199451,0.04027168,0.15780944,0.21707475,0.006306002],"about_ca_topic_score_codex":0.000026874404,"about_ca_topic_score_gemma":0.000008822594,"teacher_disagreement_score":0.9670809,"about_ca_system_score_codex":0.00029516654,"about_ca_system_score_gemma":0.00018427063,"threshold_uncertainty_score":0.9999139},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.34998468695112966,"score_gpt":0.3807716212091559,"score_spread":0.030786934258026255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2294246171","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023134677,0.00006806561,0.9940267,0.0018501328,0.00017821077,0.0003188658,0.00003130844,0.0007664552,0.00044678137],"genre_scores_gemma":[0.4378453,0.0000054877482,0.5613011,0.00060230214,0.000022114571,0.000007751349,0.00015197456,0.000013516403,0.000050425508],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99797434,0.00012155946,0.00036202022,0.0008750313,0.00035331998,0.00031372963],"domain_scores_gemma":[0.99676716,0.00012188135,0.00020977635,0.0025349432,0.00020060678,0.0001656176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009505644,0.00019729747,0.0001959623,0.00017915928,0.00014528549,0.0003888421,0.0018042374,0.00011723193,0.0000026304147],"category_scores_gemma":[0.00025937005,0.00018705352,0.000020506426,0.00044267817,0.000118502634,0.001610931,0.00081109634,0.00015892425,0.000020363921],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025090433,0.0020817274,0.022699729,0.00046819242,0.00025198312,0.000039980816,0.0027074032,0.0076149097,0.2535246,0.3533604,0.037201114,0.31979904],"study_design_scores_gemma":[0.0007929019,0.000025495232,0.0013461378,0.000025263265,0.00000803959,0.000009247081,0.00008997217,0.9894975,0.0033929914,0.00080888,0.003755402,0.0002481984],"about_ca_topic_score_codex":0.000085831714,"about_ca_topic_score_gemma":0.000020776355,"teacher_disagreement_score":0.9818826,"about_ca_system_score_codex":0.00016348512,"about_ca_system_score_gemma":0.00026788894,"threshold_uncertainty_score":0.76278216},"labels":[],"label_agreement":null},{"id":"W2296166010","doi":"10.1109/icmla.2015.112","title":"Multi-label Classification of Anemia Patients","year":2015,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; University of Ottawa","funders":"","keywords":"Machine learning; Artificial intelligence; Computer science; Task (project management); Anemia; Class (philosophy); Domain (mathematical analysis); Iron deficiency; Medicine; Mathematics","score_opus":0.09390380367586909,"score_gpt":0.31397772988821937,"score_spread":0.22007392621235028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2296166010","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0113279885,0.000008281775,0.9833019,0.00026799826,0.00011459473,0.00015382865,0.000006370048,0.00032611762,0.004492928],"genre_scores_gemma":[0.47582567,0.0000020132472,0.5237716,0.00008219512,0.000005340992,0.000012240292,0.000021178403,0.0000034598415,0.000276304],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991519,0.00003622019,0.00023189704,0.00022211857,0.00024846193,0.000109442546],"domain_scores_gemma":[0.9986787,0.000020882437,0.00014486148,0.0006997366,0.0003805571,0.00007530091],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020768409,0.00006862364,0.00008655518,0.000082937295,0.00001908718,0.000029067869,0.0007357433,0.000050107366,0.0000042821207],"category_scores_gemma":[0.00013279743,0.000060488546,0.000013590888,0.00028629968,0.00003793763,0.00053701,0.00013403158,0.000049174527,0.000070290735],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001706711,0.0017737627,0.086243704,0.000041129697,0.000012928229,9.649763e-7,0.0010141153,0.0000026786197,0.070748575,0.38401115,0.09635057,0.35978338],"study_design_scores_gemma":[0.0029772932,0.0003554594,0.4154376,0.000025666195,0.0000072085436,0.0000023375987,0.00009730761,0.42541423,0.13962258,0.0043459493,0.011203681,0.0005106593],"about_ca_topic_score_codex":0.000015321919,"about_ca_topic_score_gemma":0.000002362771,"teacher_disagreement_score":0.4644977,"about_ca_system_score_codex":0.00005234208,"about_ca_system_score_gemma":0.000062243176,"threshold_uncertainty_score":0.24666514},"labels":[],"label_agreement":null},{"id":"W234147271","doi":"10.2307/3316066","title":"Empirical likelihood confidence regions for comparison distributions and roc curves","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Statistics; Receiver operating characteristic; Confidence interval; Econometrics; Empirical likelihood; Mathematics","score_opus":0.05741963420146927,"score_gpt":0.31669896982056445,"score_spread":0.25927933561909516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W234147271","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000051584702,0.00082475226,0.9952234,0.0027487332,0.00015629039,0.00010852731,0.0007844719,0.000011781027,0.000090472306],"genre_scores_gemma":[0.33522785,0.00023562986,0.66377515,0.0006413653,0.000026987911,0.0000080549735,0.000037780814,0.0000071328095,0.000040078325],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991415,0.000056577734,0.00034439785,0.000119603574,0.00011377334,0.00022410616],"domain_scores_gemma":[0.9983311,0.00028948294,0.00023237432,0.00021869718,0.00046618542,0.00046213114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032162052,0.000077751014,0.00016616718,0.00010655076,0.00018608347,0.000120951016,0.00035928332,0.000038958002,0.000007739835],"category_scores_gemma":[0.0012804461,0.00007716443,0.000023499268,0.00016959355,0.00012611519,0.00023219398,0.000009638495,0.00014459036,0.0000016976105],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.1959935e-7,0.000008955113,0.001776407,0.000018846355,0.000006998284,0.000010318773,0.000092654904,7.8960056e-7,0.0000141121145,0.73960555,0.25725916,0.0012055795],"study_design_scores_gemma":[0.000519664,0.0004038617,0.017424107,0.0003172193,0.00006007889,0.000524745,0.00015793122,0.00408095,0.0013917054,0.5518075,0.42293978,0.00037242795],"about_ca_topic_score_codex":0.00009719059,"about_ca_topic_score_gemma":0.0017474743,"teacher_disagreement_score":0.33517626,"about_ca_system_score_codex":0.00009372057,"about_ca_system_score_gemma":0.0013071364,"threshold_uncertainty_score":0.31466743},"labels":[],"label_agreement":null},{"id":"W2354260511","doi":"","title":"Anticipation Capability and Signal Mode That Analysts Use to Communicate Financial Fraud: Empirical Evidences from Punishment Bulletins by CSRC","year":2013,"lang":"en","type":"article","venue":"Cai-mao yanjiu","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Business; Quarter (Canadian coin); Financial fraud; Accounting; Finance; Securities fraud; Law","score_opus":0.06611742238091056,"score_gpt":0.3183867243237853,"score_spread":0.2522693019428747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2354260511","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67722577,0.00013533907,0.31120673,0.01031724,0.000081609585,0.0005786801,0.00011688833,0.00026947833,0.00006827813],"genre_scores_gemma":[0.942479,0.00007297744,0.05515488,0.0019283113,0.000031411808,0.00015178912,0.00010134704,0.0000110427145,0.000069246555],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9977117,0.0003274585,0.00042758108,0.000712241,0.0004557545,0.00036524484],"domain_scores_gemma":[0.997353,0.0004671497,0.0001917906,0.0015241242,0.00021220422,0.0002516873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041966216,0.00023652865,0.00032348206,0.00011273014,0.0002348983,0.0006189886,0.001373981,0.0001520571,0.00011738571],"category_scores_gemma":[0.00034496043,0.00021747698,0.000058527137,0.0003441127,0.00017187042,0.0014050346,0.00069605117,0.00020901299,0.00015189966],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056104236,0.00071671954,0.38810042,0.00005016521,0.000064702486,0.000010084583,0.00580859,0.000101329606,0.035006642,0.0023055882,0.51954466,0.048235018],"study_design_scores_gemma":[0.00074509106,0.0004254442,0.6913403,0.00021618343,0.000063226835,0.0000068036506,0.00018440615,0.123698816,0.10177015,0.014795663,0.06532371,0.0014302009],"about_ca_topic_score_codex":0.0030849879,"about_ca_topic_score_gemma":0.00016590758,"teacher_disagreement_score":0.45422092,"about_ca_system_score_codex":0.00014140125,"about_ca_system_score_gemma":0.00008754686,"threshold_uncertainty_score":0.88684535},"labels":[],"label_agreement":null},{"id":"W2424157389","doi":"10.1109/pic.2015.7489903","title":"Using discretization to improve E-commerce anomaly detection process","year":2015,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Discretization; Anomaly detection; Naive Bayes classifier; Computer science; Data mining; Database transaction; Anomaly (physics); Preprocessor; Transaction data; Logistic regression; Data pre-processing; Set (abstract data type); Process (computing); Data set; Data modeling; Discretization of continuous features; Machine learning; Artificial intelligence; Database; Discretization error; Mathematics; Support vector machine","score_opus":0.06093315320387,"score_gpt":0.33215980251317445,"score_spread":0.27122664930930446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2424157389","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011295354,0.0000029652554,0.9843618,0.00057793123,0.00016369224,0.00024333385,0.0000019117206,0.00058799796,0.0027649938],"genre_scores_gemma":[0.78208643,3.0348627e-7,0.2173044,0.00036922185,0.000034281606,0.000026812322,0.0000035475857,0.000006723273,0.00016826665],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991404,0.000031927288,0.00015861893,0.00031018365,0.00020823878,0.00015065708],"domain_scores_gemma":[0.9990731,0.000010420779,0.00006774003,0.00050178875,0.00022893182,0.000118029995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023014008,0.00008467634,0.00007473387,0.000115332245,0.000061421684,0.00015598076,0.00051562197,0.00004367621,0.0000027874041],"category_scores_gemma":[0.00010864158,0.00007749925,0.000013651133,0.0005909774,0.000013170588,0.0010456803,0.00013609465,0.00005317027,0.00004157019],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004704027,0.00024912934,0.0041694567,0.00005403346,0.000018497527,0.0000037144703,0.0030615872,0.0013005935,0.54740864,0.09421058,0.002930315,0.3465464],"study_design_scores_gemma":[0.00016158854,0.00011654304,0.0014965285,0.000009596985,0.000003069798,0.0000093310155,0.000099120065,0.4154081,0.576356,0.003860391,0.0022476818,0.0002320599],"about_ca_topic_score_codex":0.00006554991,"about_ca_topic_score_gemma":0.00001632562,"teacher_disagreement_score":0.7707911,"about_ca_system_score_codex":0.00010911695,"about_ca_system_score_gemma":0.000065001674,"threshold_uncertainty_score":0.3160328},"labels":[],"label_agreement":null},{"id":"W2462867792","doi":"10.1007/s13748-016-0096-y","title":"Applying multi-label and multi-class classification to enhance K-anonymity in sequential releases","year":2016,"lang":"en","type":"article","venue":"Progress in Artificial Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; k-anonymity; Naive Bayes classifier; Class (philosophy); Anonymity; Data publishing; Data mining; Identification (biology); Identifier; Publication; Data anonymization; Multi-label classification; Machine learning; Information privacy; Artificial intelligence; Publishing; Computer security","score_opus":0.12554164646011629,"score_gpt":0.39892442074057793,"score_spread":0.27338277428046165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2462867792","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032569077,0.00022256967,0.9635801,0.0018431705,0.00021012404,0.0012323675,0.000013511267,0.000298472,0.00003064254],"genre_scores_gemma":[0.7113325,0.00010668317,0.28723902,0.000115969815,0.00002815645,0.0011286068,0.0000028023437,0.000013803533,0.000032494754],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99717206,0.00019563765,0.0007731255,0.0010264906,0.00031880222,0.00051390415],"domain_scores_gemma":[0.99845314,0.00022145473,0.00021132844,0.0008188919,0.00015265492,0.00014254233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082742336,0.00024166882,0.00025633042,0.00041448977,0.00010448785,0.00021028412,0.001101389,0.00014112687,0.000008432558],"category_scores_gemma":[0.00053949794,0.00021008335,0.000028070639,0.00096549693,0.00028464824,0.0009181425,0.0004366334,0.0002138846,0.0001175758],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027697759,0.0003487563,0.008490146,0.000017035762,0.000002453841,0.000011360857,0.00028024486,0.000003698181,0.03602243,0.03042846,0.000016434711,0.9243513],"study_design_scores_gemma":[0.00015660143,0.000106486106,0.011490273,0.0004075013,0.0000033765316,0.0000072034563,0.000121143574,0.36232227,0.61683536,0.0072524673,0.0006833154,0.00061400665],"about_ca_topic_score_codex":0.00005122383,"about_ca_topic_score_gemma":0.0004258467,"teacher_disagreement_score":0.9237373,"about_ca_system_score_codex":0.00023001806,"about_ca_system_score_gemma":0.00008160556,"threshold_uncertainty_score":0.85669506},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09058333476013208,"score_gpt":0.22437260402840697,"score_spread":0.1337892692682749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2473695717","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022904675,0.000008279808,0.9821938,0.00026172245,0.00018431741,0.00041171096,0.002611024,0.0007589016,0.011279764],"genre_scores_gemma":[0.9738288,0.00020906203,0.023581088,0.0001821784,0.000053046715,0.0000041099975,0.00079448463,0.000024540517,0.0013227075],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99761736,0.00015573345,0.00024895396,0.0014307927,0.00014278467,0.0004043446],"domain_scores_gemma":[0.9960371,0.00016328342,0.00045664475,0.0030065505,0.00015490629,0.00018150064],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003139722,0.00035465686,0.00035840282,0.00039963343,0.00015043023,0.00018333222,0.002963998,0.00018696646,0.000089483096],"category_scores_gemma":[0.000029245135,0.00032293904,0.00006889068,0.0005378716,0.00042156907,0.00078986265,0.0022068974,0.00043497825,0.00017436538],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002938858,0.000064811116,0.009007031,0.00008337478,0.00011481066,0.00044570735,0.00005806876,0.00039996865,0.00032655624,0.9665933,0.017678622,0.005198325],"study_design_scores_gemma":[0.0063965297,0.0005410234,0.053595174,0.004622585,0.0005214132,0.00013872914,0.00020400652,0.12913908,0.024779648,0.67472166,0.09587377,0.009466373],"about_ca_topic_score_codex":0.00014946563,"about_ca_topic_score_gemma":0.00014162449,"teacher_disagreement_score":0.9715383,"about_ca_system_score_codex":0.00031010673,"about_ca_system_score_gemma":0.0003470775,"threshold_uncertainty_score":0.9999223},"labels":[],"label_agreement":null},{"id":"W2477917200","doi":"10.1109/cisti.2016.7521522","title":"The use of predictive analytics technology to detect credit card fraud in Canada","year":2016,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Concordia University of Edmonton","funders":"","keywords":"Vendor; Credit card; Balanced scorecard; Credit card fraud; Predictive analytics; Analytics; Business; Chargeback; Card security code; Computer security; Computer science; Finance; Data science; Marketing; Payment","score_opus":0.025410230623641835,"score_gpt":0.24771915634985658,"score_spread":0.22230892572621475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2477917200","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064913486,0.000009399684,0.9866296,0.0062212003,0.00009947645,0.00018215486,0.00003929844,0.00011954801,0.00020794872],"genre_scores_gemma":[0.91914046,0.000029872519,0.08035974,0.0002042884,0.000008722693,0.00003940582,4.760664e-7,0.000004403167,0.00021261959],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991285,0.000030387724,0.00022526742,0.0002188552,0.00020235783,0.00019463514],"domain_scores_gemma":[0.9984962,0.00030909892,0.000074209594,0.0009406419,0.0001388626,0.000041018913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001301319,0.000068859415,0.0001085395,0.00015051854,0.000032873777,0.000020814576,0.0010397315,0.000043373693,0.0000026942155],"category_scores_gemma":[0.0004349065,0.000038076687,0.000012962557,0.0007042155,0.00005965527,0.00020775294,0.0002890606,0.00006383428,0.0000036934068],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033233842,0.00002621049,0.04995483,0.000007537387,0.000053172276,0.000018786983,0.00011021693,0.00020912684,0.020629711,0.122573696,0.14660652,0.6597769],"study_design_scores_gemma":[0.00040614395,0.00031829916,0.086267754,0.00009395741,0.000007717651,0.000009482084,0.00011354687,0.028688207,0.5934281,0.012009215,0.27823842,0.00041916347],"about_ca_topic_score_codex":0.18055904,"about_ca_topic_score_gemma":0.6736188,"teacher_disagreement_score":0.9126491,"about_ca_system_score_codex":0.00035342562,"about_ca_system_score_gemma":0.00052665104,"threshold_uncertainty_score":0.8248977},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.038982278655162794,"score_gpt":0.3250309721664764,"score_spread":0.2860486935113136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2481773658","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002722848,0.00009302872,0.9947021,0.0016096933,0.00027052028,0.00028651944,0.000025014673,0.00028670247,0.0000035892235],"genre_scores_gemma":[0.33491296,0.00007184496,0.66430527,0.0005739781,0.00006626686,0.000024833273,0.00002809088,0.000014339484,0.000002406077],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777883,0.00025941237,0.0005077849,0.00077392015,0.00034580752,0.00033425036],"domain_scores_gemma":[0.9970336,0.0016043127,0.00025952898,0.00081652356,0.00014227034,0.00014376687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016514382,0.00019607949,0.00038303164,0.00033098483,0.000102054895,0.00006985525,0.001103638,0.00011224979,0.0000013646206],"category_scores_gemma":[0.00041916157,0.00015839332,0.00005829513,0.00043237788,0.00017487424,0.00048697586,0.0006238259,0.000260615,4.1524976e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006408686,0.000071113056,0.0010861022,0.00007298789,0.000015369465,0.000008148858,0.00006677475,0.000015891834,0.1393361,0.0030808765,0.00014807351,0.85603446],"study_design_scores_gemma":[0.0020068737,0.00009103019,0.0034843879,0.00032210964,0.000007784509,0.000025009835,0.0000035547114,0.9745825,0.014697041,0.0028734242,0.0016975331,0.00020875449],"about_ca_topic_score_codex":0.000032192216,"about_ca_topic_score_gemma":0.000007863538,"teacher_disagreement_score":0.9745666,"about_ca_system_score_codex":0.000030832176,"about_ca_system_score_gemma":0.00011811822,"threshold_uncertainty_score":0.64590925},"labels":[],"label_agreement":null},{"id":"W2504431993","doi":"10.1145/2948068","title":"The Convergence Behavior of Naive Bayes on Large Sparse Datasets","year":2016,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Naive Bayes classifier; Computer science; Machine learning; Missing data; Bayes' theorem; Artificial intelligence; Convergence (economics); Data mining; Bayesian probability; Support vector machine","score_opus":0.05267241250637728,"score_gpt":0.3180910509676954,"score_spread":0.26541863846131813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2504431993","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024778892,0.00012111405,0.925047,0.0008988146,0.0007544235,0.00033049317,0.07009839,0.00016450968,0.000107356784],"genre_scores_gemma":[0.9836447,0.0008412626,0.012249186,0.000121869954,0.000054365162,0.00016141894,0.0023418511,0.000025372743,0.00055994577],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99791545,0.000157279,0.00041405216,0.00086044107,0.00033082106,0.000321951],"domain_scores_gemma":[0.9897711,0.0012239489,0.00018627678,0.00865044,0.0000859293,0.00008229438],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00039857035,0.00022520123,0.00020829738,0.0001054803,0.00032572672,0.00014977409,0.00716618,0.00008459675,0.00008766792],"category_scores_gemma":[0.00021198651,0.00013870203,0.00006730847,0.0003405692,0.00021525106,0.0026634822,0.00033874833,0.0001821051,0.0003999763],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002863266,0.0044664163,0.0014160891,0.00003639912,0.0002943533,0.000023102883,0.00056974543,0.0000034966556,0.039795004,0.061819907,0.12564114,0.765648],"study_design_scores_gemma":[0.0022989998,0.0005847816,0.020563984,0.00063083845,0.00021107323,0.00001063036,0.00021404884,0.002315516,0.6187772,0.009784552,0.34336403,0.001244325],"about_ca_topic_score_codex":0.000052194628,"about_ca_topic_score_gemma":0.0002123773,"teacher_disagreement_score":0.98116684,"about_ca_system_score_codex":0.00006625922,"about_ca_system_score_gemma":0.00014602898,"threshold_uncertainty_score":0.99820554},"labels":[],"label_agreement":null},{"id":"W2519490316","doi":"10.1016/j.neucom.2016.09.016","title":"Risk upper bounds for general ensemble methods with an application to multiclass classification","year":2016,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Agence Nationale de la Recherche","keywords":"Upper and lower bounds; Classifier (UML); Margin (machine learning); Binary number; Binary classification; Multiclass classification; Artificial intelligence; Computer science; Bayesian probability; Pattern recognition (psychology); Mathematics; Naive Bayes classifier; Machine learning; Support vector machine","score_opus":0.030887292671378654,"score_gpt":0.3463149787642599,"score_spread":0.31542768609288124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2519490316","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0336162,0.0000033930646,0.962874,0.0014776482,0.0001092719,0.00091614004,0.000010745849,0.0008323303,0.00016028609],"genre_scores_gemma":[0.3067045,0.000002145282,0.6923431,0.00044483965,0.00012521874,0.00027881796,0.000008450174,0.000025009238,0.000067927984],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978452,0.00025480386,0.00034841752,0.0009331593,0.00022475205,0.00039368938],"domain_scores_gemma":[0.9975999,0.0004241894,0.00029169026,0.0012485719,0.00027265074,0.00016300792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086204294,0.0001980349,0.00018044104,0.00016909772,0.00031251585,0.0002047886,0.0010194575,0.00007610493,9.657032e-7],"category_scores_gemma":[0.00018455913,0.00014420044,0.000045247118,0.00043835232,0.000040798008,0.0006830123,0.00016883426,0.00010135589,0.000024147874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016872855,0.0000408779,0.0009648074,0.000005267085,0.0000043252785,2.0411429e-7,0.00010626413,0.00005605395,0.29342073,0.031715024,0.0002112643,0.6734583],"study_design_scores_gemma":[0.0006228311,0.00043855747,0.03765257,0.000025857851,0.000012407969,0.000014255614,0.000013381592,0.732358,0.18403535,0.004529035,0.03989144,0.00040634285],"about_ca_topic_score_codex":0.000015179476,"about_ca_topic_score_gemma":0.000005523468,"teacher_disagreement_score":0.73230195,"about_ca_system_score_codex":0.000102339785,"about_ca_system_score_gemma":0.000057424037,"threshold_uncertainty_score":0.58803236},"labels":[],"label_agreement":null},{"id":"W2522324495","doi":"10.1109/ecticon.2016.7561287","title":"A survey - data mining frameworks in credit card processing","year":2016,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Credit card; ATM card; Computer science; Process (computing); Credit card interest; Quarter (Canadian coin); Chargeback; Business; Work (physics); Finance; Computer security; Payment; Engineering","score_opus":0.09289083720699215,"score_gpt":0.33185126308560103,"score_spread":0.23896042587860888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2522324495","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011717881,0.000042491203,0.995103,0.0012422372,0.000094590854,0.00008452725,0.000041158448,0.0003957666,0.0018244314],"genre_scores_gemma":[0.6592144,0.000013343454,0.34012115,0.00027864953,0.000033766242,0.0000126544355,0.00003928982,0.000006857955,0.00027990137],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99872243,0.0000948797,0.00022767075,0.0005270854,0.00020164455,0.0002263129],"domain_scores_gemma":[0.9977474,0.0002747261,0.00007968173,0.0017771559,0.00007484842,0.000046147572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010734928,0.00008825243,0.00011813406,0.00010976073,0.000037781214,0.00015155145,0.002502225,0.00012787523,0.000014611358],"category_scores_gemma":[0.0006863672,0.000060004604,0.000007955217,0.00046219115,0.000041376683,0.0017177262,0.0008823689,0.0001330246,0.000028115084],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033623826,0.000036134257,0.04849844,0.000008042807,0.000002851336,0.000005826433,0.00018195361,3.8700722e-7,0.00092296576,0.0025566956,0.032867026,0.91491634],"study_design_scores_gemma":[0.0009409814,0.000088910165,0.7069301,0.000788742,0.0000045440024,0.000018929222,0.00008774942,0.23907277,0.010476417,0.0052666524,0.03516222,0.0011619696],"about_ca_topic_score_codex":0.000119424905,"about_ca_topic_score_gemma":0.00023167326,"teacher_disagreement_score":0.91375434,"about_ca_system_score_codex":0.00004403233,"about_ca_system_score_gemma":0.00010921805,"threshold_uncertainty_score":0.46497986},"labels":[],"label_agreement":null},{"id":"W2525985184","doi":"10.22360/springsim.2016.cns.009","title":"Credit Card Fraud Detection Using Fuzzy Logic and Neural Network","year":2016,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Credit card fraud; Credit card; Computer science; Fuzzy logic; Defuzzification; Data mining; Toolbox; Database transaction; Artificial intelligence; Neuro-fuzzy; Artificial neural network; Fuzzy electronics; Machine learning; Fuzzy set operations; Fuzzy set; Fuzzy control system; Fuzzy number; Database; Payment","score_opus":0.036077475495578784,"score_gpt":0.26516031452073363,"score_spread":0.22908283902515486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2525985184","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013405098,0.00004470161,0.98409265,0.0006599161,0.00029834913,0.000087385815,0.0000017861603,0.0005066465,0.00090344803],"genre_scores_gemma":[0.86508316,0.00001942576,0.13426708,0.0003184906,0.00017250095,0.0000069222465,5.9596005e-7,0.0000048861843,0.00012695519],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924946,0.00004110763,0.00012608069,0.000279755,0.00011467258,0.00018893862],"domain_scores_gemma":[0.99937254,0.000052574083,0.000059994327,0.00041764553,0.000047589794,0.000049658167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016112205,0.000080158985,0.00008143975,0.00004440824,0.000100982004,0.00008543513,0.00029595543,0.000054320524,0.0000070614446],"category_scores_gemma":[0.000031507545,0.00005261328,0.00001824824,0.00018361262,0.000046253175,0.0006057807,0.00018134013,0.000048203092,0.00001097292],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009952392,0.000020971278,0.0042847386,0.000009711824,0.000013227877,0.0000075167495,0.00005740149,0.00009530028,0.1383991,0.103298716,0.004969373,0.748834],"study_design_scores_gemma":[0.0010111077,0.0004493735,0.06444393,0.00009897612,0.00002437925,0.00027496266,0.000025098121,0.5290879,0.18614648,0.1865019,0.030686487,0.0012493804],"about_ca_topic_score_codex":0.000026324078,"about_ca_topic_score_gemma":0.000008588483,"teacher_disagreement_score":0.8516781,"about_ca_system_score_codex":0.000039124505,"about_ca_system_score_gemma":0.000012109409,"threshold_uncertainty_score":0.21455073},"labels":[],"label_agreement":null},{"id":"W2537424881","doi":"10.1109/embc.2016.7591262","title":"An empirical study on the effect of imbalanced data on bleeding detection in endoscopic video","year":2016,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Classifier (UML); Artificial intelligence; Computer science; Training set; Pattern recognition (psychology); Machine learning; Class (philosophy)","score_opus":0.048131937297862123,"score_gpt":0.35219395768591694,"score_spread":0.3040620203880548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2537424881","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6931363,0.0000013985359,0.3046518,0.000801623,0.00010648793,0.0005910696,0.000006827742,0.00023342812,0.00047106436],"genre_scores_gemma":[0.9985803,0.0000021278167,0.001177595,0.00011960053,0.000023781256,0.00006953525,0.0000021881024,0.000006404259,0.000018514485],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99838334,0.00039076712,0.00024247843,0.00052026205,0.00029698858,0.00016618849],"domain_scores_gemma":[0.9965943,0.0008969746,0.000098804536,0.0023539988,0.000023768218,0.000032169286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012687226,0.00011751141,0.00015970884,0.0001455286,0.000050799572,0.00004850319,0.0019494535,0.000042216772,0.000009311302],"category_scores_gemma":[0.00033870022,0.000055823886,0.000015155999,0.00037949614,0.000035784145,0.000569084,0.0002717616,0.00011250701,0.0000268247],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001575761,0.00069134193,0.25145772,0.000014635086,0.00002552281,0.0000062837726,0.00042619708,0.0000044336985,0.48577586,0.004588797,0.0013478826,0.25550377],"study_design_scores_gemma":[0.00074617896,0.0032415309,0.21579032,0.000060199873,0.0000032901492,7.95396e-7,0.000031391177,0.006381996,0.77327466,0.00025101,0.00011698323,0.00010162045],"about_ca_topic_score_codex":0.000025998004,"about_ca_topic_score_gemma":0.000033185894,"teacher_disagreement_score":0.30544394,"about_ca_system_score_codex":0.00006700799,"about_ca_system_score_gemma":0.000015446203,"threshold_uncertainty_score":0.36226022},"labels":[],"label_agreement":null},{"id":"W2551525315","doi":"10.5539/ijsp.v6n1p1","title":"Estimating the Area under the ROC Curve with Modified Profile Likelihoods","year":2016,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Parametric statistics; Receiver operating characteristic; Measure (data warehouse); Inference; Mathematics; Statistical inference; Statistics; Parametric model; Sample size determination; Boundary (topology); Computer science; Nonparametric statistics; Sensitivity (control systems); Statistical hypothesis testing; Confidence interval; Artificial intelligence; Data mining","score_opus":0.028157936569660647,"score_gpt":0.2862194103667396,"score_spread":0.25806147379707894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2551525315","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006943622,0.000021676793,0.98210293,0.010343536,0.00020121671,0.00012256237,0.00009622431,0.000016117672,0.0001521285],"genre_scores_gemma":[0.664499,0.000013519458,0.33521914,0.0001770829,0.000056083747,0.000008451831,0.0000017355358,0.0000030157196,0.000021963097],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998944,0.00009066322,0.0003105541,0.00013705109,0.00042548418,0.00009223777],"domain_scores_gemma":[0.9979302,0.0006103239,0.00038094548,0.00027636782,0.0007653086,0.0000368488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008787349,0.00007799728,0.00008874693,0.000030296305,0.00009361665,0.00018557416,0.0009111121,0.000020610702,0.000011860721],"category_scores_gemma":[0.00029957187,0.0000301018,0.000019641038,0.00006570651,0.00018316154,0.0003160671,0.00013498795,0.00012456412,0.0000013568142],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073082294,0.00009767244,0.0042042416,0.000011907709,0.000105892024,0.00000980586,0.00037724146,0.00031292802,0.000471919,0.7762611,0.003200747,0.21487351],"study_design_scores_gemma":[0.0005630903,0.00021817071,0.062513776,0.000132309,0.000016432625,0.00023704997,0.000032215103,0.073594525,0.0010216079,0.8602938,0.00122724,0.00014979375],"about_ca_topic_score_codex":0.000008103488,"about_ca_topic_score_gemma":0.000008150334,"teacher_disagreement_score":0.6575554,"about_ca_system_score_codex":0.00006004958,"about_ca_system_score_gemma":0.0001200202,"threshold_uncertainty_score":0.1789496},"labels":[],"label_agreement":null},{"id":"W2555801311","doi":"10.5220/0006033800210029","title":"Classification Confusion within Nefclass Caused by Feature Value Skewness in Multi-dimensional Datasets","year":2016,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Allison University; University of Guelph","funders":"","keywords":"Confusion; Skewness; Feature (linguistics); Computer science; Value (mathematics); Pattern recognition (psychology); Artificial intelligence; Data mining; Statistics; Machine learning; Mathematics; Psychology; Linguistics","score_opus":0.03241016102305022,"score_gpt":0.2910278246572896,"score_spread":0.2586176636342394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2555801311","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039257314,0.000032112297,0.9826102,0.011548812,0.00025749695,0.00043332757,0.00043373363,0.00058867753,0.00016985531],"genre_scores_gemma":[0.7483239,0.000039409744,0.24425034,0.0026057689,0.00003413896,0.0001631247,0.0013686582,0.000035439283,0.003179191],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99783707,0.00018563546,0.00039834608,0.000810441,0.0004461609,0.00032233525],"domain_scores_gemma":[0.9979815,0.00017487719,0.00022121692,0.0013862132,0.00011347251,0.00012274274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057145517,0.00022460638,0.00020505274,0.00019296956,0.000102936836,0.00011022203,0.0012160384,0.00020496709,0.000025441785],"category_scores_gemma":[0.00015378285,0.00015143795,0.00003178163,0.00048251674,0.000104216364,0.0012435456,0.00034079025,0.00018860915,0.00013926096],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013603968,0.00023834218,0.0012491525,0.000008978449,0.000006926431,0.000007910515,0.00008617986,0.000004458837,0.6601064,0.17599134,0.15544811,0.006838585],"study_design_scores_gemma":[0.004583468,0.00015151176,0.106166415,0.0003289335,0.0000118421285,0.000035381752,0.00005616022,0.2233805,0.56712663,0.008247298,0.088485986,0.0014258438],"about_ca_topic_score_codex":0.00005983928,"about_ca_topic_score_gemma":0.00006507274,"teacher_disagreement_score":0.7443982,"about_ca_system_score_codex":0.00018370917,"about_ca_system_score_gemma":0.00012813663,"threshold_uncertainty_score":0.617546},"labels":[],"label_agreement":null},{"id":"W2556317093","doi":"","title":"Identifying fraudulent online transactions using data mining and statistical techniques","year":2012,"lang":"en","type":"article","venue":"Computing and Convergence Technology (ICCCT), 2012 7th International Conference on","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Payment; Computer science; The Internet; Data science; Computer security; Online business; Business; Internet privacy; Data mining; World Wide Web","score_opus":0.16494283121172126,"score_gpt":0.3931878711863341,"score_spread":0.22824503997461282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2556317093","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031406887,0.0003004706,0.96435183,0.0018482917,0.000770683,0.00016717691,0.00012948233,0.0007473909,0.0002778012],"genre_scores_gemma":[0.69563156,0.00023851782,0.30376196,0.00015431782,0.0000757515,0.0000075364073,0.00006339873,0.000010787632,0.000056195408],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99807084,0.000067928464,0.00043397004,0.0006956738,0.00030929985,0.00042232],"domain_scores_gemma":[0.99848413,0.00012287365,0.00024249477,0.0008296759,0.00018815385,0.00013265341],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00051684905,0.00024428897,0.00024562248,0.0004454561,0.00028078523,0.00016848053,0.0015465582,0.00020853788,0.000086258195],"category_scores_gemma":[0.00009935901,0.0002512571,0.000019660192,0.00029387258,0.00033861023,0.0011711154,0.0007493009,0.00037694827,0.000009300005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012841697,0.0002388011,0.008941425,0.000037479072,0.000077254335,0.00000845299,0.0003494157,0.0000028189145,0.008306664,0.38711876,0.00059800205,0.5943081],"study_design_scores_gemma":[0.0004913755,0.00020573671,0.014379801,0.0005781934,0.000063013424,0.00032998342,0.0009250457,0.94488853,0.015273474,0.0148939835,0.0069291447,0.0010416878],"about_ca_topic_score_codex":0.00002801227,"about_ca_topic_score_gemma":0.000006180991,"teacher_disagreement_score":0.94488573,"about_ca_system_score_codex":0.00006762865,"about_ca_system_score_gemma":0.0000681764,"threshold_uncertainty_score":0.999994},"labels":[],"label_agreement":null},{"id":"W2587013329","doi":"10.1186/2047-2501-1-15","title":"On the application of multi-class classification in physical therapy recommendation","year":2013,"lang":"en","type":"article","venue":"Health Information Science and Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Machine learning; Random forest; Class (philosophy); Computer science; Intervention (counseling); Artificial intelligence; Rehabilitation; Referral; Decision support system; Data mining; Medicine; Physical therapy; Nursing","score_opus":0.08194860754192809,"score_gpt":0.3512711454446907,"score_spread":0.2693225379027626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587013329","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050669186,0.000016468202,0.93079305,0.0148752425,0.00016579546,0.0022619397,0.000007725762,0.00011878159,0.0010918292],"genre_scores_gemma":[0.99706256,0.00006085236,0.0011194112,0.0012690243,0.000009174239,0.00045926147,0.000012839037,0.0000017983157,0.000005093166],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985597,0.00011218622,0.00051934,0.00017703579,0.0004518549,0.00017987976],"domain_scores_gemma":[0.9983552,0.00015029592,0.0005215413,0.00048527136,0.00042773565,0.000059933776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002523781,0.00007859003,0.00012551907,0.00031574978,0.00021331503,0.00025357676,0.000543497,0.000030676485,0.0000013492992],"category_scores_gemma":[0.00017304778,0.000051797866,0.000011013337,0.0011573719,0.00013967049,0.003934261,0.000046299938,0.00009775607,0.00005727319],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021885212,0.000058600144,0.0003433255,0.000034059878,7.826702e-7,3.8524917e-9,0.0025635478,0.00004145066,0.0019915784,0.57917005,0.0011733568,0.41462108],"study_design_scores_gemma":[0.00016344093,0.00006224208,0.031139472,0.000019684303,1.11306996e-7,0.0000010786537,0.0004736205,0.96003616,0.000705879,0.00051019026,0.0068284287,0.00005966515],"about_ca_topic_score_codex":0.00027561054,"about_ca_topic_score_gemma":0.000002510115,"teacher_disagreement_score":0.95999473,"about_ca_system_score_codex":0.00015758703,"about_ca_system_score_gemma":0.00020839785,"threshold_uncertainty_score":0.28522444},"labels":[],"label_agreement":null},{"id":"W2588644130","doi":"10.1109/iconsip.2016.7857447","title":"GMR based pain intensity recognition using imbalanced data handling techniques","year":2016,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Council of Scientific and Industrial Research, India; University of Northern British Columbia","keywords":"Oversampling; Pattern recognition (psychology); Computer science; Artificial intelligence; Data set; Feature extraction; Facial expression; Gaussian; Support vector machine; Feature (linguistics); Machine learning; Data mining","score_opus":0.11616245588577394,"score_gpt":0.3072264104453996,"score_spread":0.19106395455962566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588644130","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00085391244,0.00000795399,0.99439245,0.0018626805,0.00009846355,0.00024069776,0.00006138847,0.0019938452,0.0004885978],"genre_scores_gemma":[0.20861667,0.000014051389,0.78977334,0.0013762924,0.00005687763,0.000017776933,0.00009044203,0.000012256446,0.000042275773],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982898,0.00017082384,0.00031476273,0.0007033323,0.00024138564,0.00027989768],"domain_scores_gemma":[0.9969671,0.00025114464,0.00016969396,0.0022684278,0.00027048538,0.00007318037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019175563,0.00015821513,0.00018251162,0.00016604758,0.0001215959,0.00014080315,0.0017751303,0.000097256765,0.000038078153],"category_scores_gemma":[0.00069102325,0.00011238649,0.000031927924,0.0003321533,0.000074267,0.0016871984,0.0006219843,0.000091921254,0.00003835467],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012496818,0.000051265833,0.00068710593,0.000012566815,0.00000710981,0.0000045492425,0.000011757533,1.8637682e-7,0.23848327,0.00089650304,0.0069848583,0.7528483],"study_design_scores_gemma":[0.0002448942,0.000060592603,0.0004037629,0.0002612738,0.00000646909,0.0000115381135,0.000007735579,0.21562582,0.7704104,0.00574525,0.006838589,0.00038364634],"about_ca_topic_score_codex":0.000045689336,"about_ca_topic_score_gemma":0.00000879676,"teacher_disagreement_score":0.7524647,"about_ca_system_score_codex":0.000112241425,"about_ca_system_score_gemma":0.00009875803,"threshold_uncertainty_score":0.4582988},"labels":[],"label_agreement":null},{"id":"W2589167313","doi":"10.1007/978-3-319-52941-7_26","title":"Sparse Learning and Hybrid Probabilistic Oversampling for Alzheimer’s Disease Diagnosis","year":2017,"lang":"en","type":"book-chapter","venue":"Advances in intelligent systems and computing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Oversampling; Hinge loss; Discriminative model; Artificial intelligence; Probabilistic logic; Machine learning; Computer science; Feature (linguistics); Pattern recognition (psychology); Support vector machine","score_opus":0.052797289323444574,"score_gpt":0.31927574662889796,"score_spread":0.2664784573054534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2589167313","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004958077,0.057815965,0.9332224,0.000072663905,0.00084921555,0.0014816402,0.000045972833,0.00024383026,0.0062187393],"genre_scores_gemma":[0.83218795,0.06276116,0.086283274,0.00016786798,0.0012804896,0.0010118535,0.00026412273,0.00026676463,0.015776535],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.997877,0.00003519995,0.00061697525,0.0009293415,0.00022043168,0.0003210754],"domain_scores_gemma":[0.9976626,0.0007125056,0.0007569661,0.00060582726,0.0001205124,0.00014159715],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005363407,0.00036455388,0.0005099746,0.00018109835,0.00038228312,0.00047330128,0.000608086,0.00009658003,0.0000016112207],"category_scores_gemma":[0.00026433205,0.0003699492,0.00007009148,0.000019560606,0.00014736177,0.00050816446,0.00049869425,0.0003132804,0.0000034295285],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014913388,0.000020206815,0.0019512158,0.00073849584,0.00004098903,0.000024609644,0.00015833412,0.0020304865,0.0000012976315,0.6185046,0.000103344166,0.37641153],"study_design_scores_gemma":[0.00022198247,0.00012892798,0.00010191984,0.004757279,0.00007436512,0.00003123249,0.000037294638,0.29826593,0.000057392488,0.060924552,0.6345008,0.0008983424],"about_ca_topic_score_codex":0.000020375961,"about_ca_topic_score_gemma":0.00000621843,"teacher_disagreement_score":0.84693915,"about_ca_system_score_codex":0.00007830731,"about_ca_system_score_gemma":0.000050406816,"threshold_uncertainty_score":0.99987525},"labels":[],"label_agreement":null},{"id":"W2607410741","doi":"10.1007/978-3-319-57351-9_11","title":"Classification of Imbalanced Auction Fraud Data","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Bidding; Class (philosophy); Binary classification; Sampling (signal processing); Set (abstract data type); Data mining; Domain (mathematical analysis); Artificial intelligence; Machine learning; Support vector machine","score_opus":0.055256731834891215,"score_gpt":0.30805407415858066,"score_spread":0.25279734232368944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607410741","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012173326,0.00017127836,0.99253154,0.0009330924,0.0013174207,0.0004288809,0.00007012223,0.000273279,0.004262214],"genre_scores_gemma":[0.2083889,0.00021278566,0.78975433,0.0002974651,0.00046076404,0.000018352493,0.00022415692,0.000044385844,0.0005988538],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957484,0.000038109127,0.0007224845,0.001990923,0.0010619336,0.00043814752],"domain_scores_gemma":[0.98918337,0.00023540464,0.0012215952,0.008818118,0.0004338252,0.00010767376],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0013894079,0.00042054433,0.0005514467,0.00077125494,0.00028553282,0.0004749522,0.012721712,0.0003958036,0.000013003782],"category_scores_gemma":[0.00034027154,0.0004097982,0.000072886716,0.0002886355,0.0010965703,0.0020795094,0.0030690953,0.0006644099,0.000035773304],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006463144,0.000040920706,0.00012293109,0.000061243954,0.000012020664,0.0000093476165,0.00016466095,0.00040422473,0.0034924215,0.05082641,0.00031952895,0.94453984],"study_design_scores_gemma":[0.00031367902,0.0001432935,0.0048445174,0.00062250166,0.000015369773,0.00004393276,1.6345669e-7,0.7607872,0.010992326,0.20975742,0.011606023,0.0008735761],"about_ca_topic_score_codex":0.000026008898,"about_ca_topic_score_gemma":0.000046335947,"teacher_disagreement_score":0.9436663,"about_ca_system_score_codex":0.000255182,"about_ca_system_score_gemma":0.00067474303,"threshold_uncertainty_score":0.9998354},"labels":[],"label_agreement":null},{"id":"W2611665460","doi":"10.1007/s10994-009-5134-6","title":"Pointwise exact bootstrap distributions of ROC curves","year":2009,"lang":"en","type":"article","venue":"Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Pointwise; Mathematics; Receiver operating characteristic; Confidence interval; Statistics; Mathematical analysis","score_opus":0.0197606494335381,"score_gpt":0.28621812602858154,"score_spread":0.26645747659504343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2611665460","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025973942,0.00052164186,0.989415,0.004129078,0.000035559176,0.00010635482,0.000020039994,0.0005758374,0.002599092],"genre_scores_gemma":[0.97252506,0.00013174118,0.026692059,0.00027597413,0.000017124337,0.000005245288,0.00010288421,0.0000046822493,0.00024524273],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990762,0.00008768715,0.00023571885,0.00023306442,0.00018951806,0.00017782516],"domain_scores_gemma":[0.9991902,0.00005476247,0.00016307874,0.00047523197,0.00006542274,0.000051270752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028628373,0.00010036303,0.00014525674,0.00008301488,0.00010407344,0.00004223949,0.00062462036,0.000035085952,0.00003520184],"category_scores_gemma":[0.00023277928,0.00009574633,0.000053559816,0.00036296397,0.000030828258,0.0003678806,0.0000873879,0.00022277037,0.000015997975],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021449248,0.00061572145,0.036593016,0.00018885049,0.000044910495,0.000027598195,0.00069908553,0.0004898657,0.08691147,0.40582833,0.019121744,0.44945797],"study_design_scores_gemma":[0.0010330477,0.0010871928,0.49844006,0.0007516033,0.000039990628,0.00009963142,0.00003139974,0.1986175,0.115267836,0.02552366,0.1579346,0.0011734683],"about_ca_topic_score_codex":0.000019769115,"about_ca_topic_score_gemma":0.0000021771987,"teacher_disagreement_score":0.96992767,"about_ca_system_score_codex":0.000026153359,"about_ca_system_score_gemma":0.000026992313,"threshold_uncertainty_score":0.3904422},"labels":[],"label_agreement":null},{"id":"W2614362749","doi":"","title":"Investigating the Process of Developing a KDD Model for the Classification of Cases with Cardiovascular Disease Based on a Canadian Database","year":2013,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Database; Data mining; Process (computing); Artificial intelligence; Information retrieval; Data science; Programming language","score_opus":0.03385744037593748,"score_gpt":0.23317690074233438,"score_spread":0.19931946036639692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2614362749","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4537257,0.00017087854,0.5379549,0.003850014,0.000081369755,0.0029795195,0.0010727642,0.00010626638,0.000058579866],"genre_scores_gemma":[0.9281798,0.00003526455,0.06808358,0.00006762076,0.000010373443,0.000039100294,0.0012501224,0.000025287238,0.0023088758],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872214,0.000070227405,0.00016746261,0.0003866915,0.00046198,0.00019149402],"domain_scores_gemma":[0.99721766,0.00018109527,0.00048026585,0.0013421478,0.00067982124,0.00009900211],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035880858,0.0001816464,0.00027762327,0.00024971372,0.00029858967,0.000030519124,0.0013941184,0.00008646653,0.000001970224],"category_scores_gemma":[0.00012125498,0.00013178385,0.00012894516,0.00039544053,0.00019710006,0.00037459363,0.00004067656,0.00013816835,7.520009e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013092189,0.0007070978,0.0035991936,0.020472202,0.0038418681,0.00007420935,0.4411882,0.23955624,0.018314926,0.18727045,0.011647341,0.07201907],"study_design_scores_gemma":[0.00031121928,0.000058013877,0.0055412524,0.0007459095,0.0002531392,9.040823e-7,0.014352771,0.9739052,0.004235588,0.00028702218,0.00006891565,0.00024007719],"about_ca_topic_score_codex":0.12994272,"about_ca_topic_score_gemma":0.13760054,"teacher_disagreement_score":0.73434895,"about_ca_system_score_codex":0.00010233309,"about_ca_system_score_gemma":0.001544109,"threshold_uncertainty_score":0.878136},"labels":[],"label_agreement":null},{"id":"W2619846146","doi":"10.1007/978-3-319-59876-5_1","title":"A Weight-Selection Strategy on Training Deep Neural Networks for Imbalanced Classification","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; MNIST database; Artificial intelligence; Artificial neural network; Selection (genetic algorithm); Machine learning; Set (abstract data type); Class (philosophy); Deep neural networks; Training (meteorology); Pattern recognition (psychology)","score_opus":0.050856760569540214,"score_gpt":0.2947353926549329,"score_spread":0.2438786320853927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2619846146","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012012246,0.00008765568,0.9935656,0.00081375515,0.0015138877,0.0009836827,0.000011872244,0.00050492695,0.0025065877],"genre_scores_gemma":[0.63129205,0.000051281437,0.36599463,0.0009727548,0.0010799934,0.0001659234,0.000074115334,0.0000663772,0.00030287],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957001,0.000046597288,0.0006437356,0.0020486163,0.0007398483,0.0008210698],"domain_scores_gemma":[0.9959105,0.0005103011,0.0008657832,0.0021413302,0.00040686585,0.00016516655],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010101048,0.000611368,0.00057989714,0.0007486211,0.0006574994,0.0011811506,0.0042998414,0.0005329258,0.0000068928657],"category_scores_gemma":[0.00018455638,0.00058657356,0.00016364951,0.00029852337,0.0005370836,0.0011195552,0.00037901505,0.00095308403,0.000010055468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017999484,0.000021652553,0.000020043753,0.000017315608,0.000008069293,0.0000049390655,0.00016037267,0.034075733,0.00030524214,0.07144529,0.000048234593,0.8938751],"study_design_scores_gemma":[0.00028512353,0.00034529538,0.0005076826,0.0001472305,0.000007239122,0.000026051157,1.8679728e-7,0.9177796,0.0008474314,0.0783672,0.0011141045,0.00057283853],"about_ca_topic_score_codex":0.0000067440865,"about_ca_topic_score_gemma":0.000064086504,"teacher_disagreement_score":0.89330226,"about_ca_system_score_codex":0.00049052614,"about_ca_system_score_gemma":0.0003643358,"threshold_uncertainty_score":0.9998557},"labels":[],"label_agreement":null},{"id":"W2626053049","doi":"10.1080/24751839.2017.1323476","title":"Information granulation construction and representation strategies for classification in imbalanced data based on granular computing","year":2017,"lang":"en","type":"article","venue":"Journal of Information and Telecommunication","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Categorical variable; Granular computing; Computer science; Granulation; Discretization; Class (philosophy); Data mining; Representation (politics); Product (mathematics); Machine learning; Artificial intelligence; Rough set; Mathematics; Engineering","score_opus":0.0520747727813069,"score_gpt":0.3332560773157003,"score_spread":0.2811813045343934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2626053049","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02087998,0.000022700846,0.97433954,0.0036463032,0.00012756788,0.0004166881,0.000019543446,0.000046517394,0.0005011607],"genre_scores_gemma":[0.80819136,0.00022053442,0.1910357,0.00019796262,0.000021406495,0.000010089887,0.00031969856,0.0000028714508,3.8387205e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985125,0.000101966056,0.0009107039,0.000104401486,0.000252423,0.00011798137],"domain_scores_gemma":[0.99579364,0.0002077976,0.0021618102,0.0013209552,0.00047021324,0.0000456083],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0016440512,0.000114499315,0.00019625173,0.00050278194,0.00042365983,0.0011919179,0.0010843868,0.00009585262,7.90785e-7],"category_scores_gemma":[0.000722183,0.00011173373,0.000025205802,0.0001526331,0.000095894255,0.018007066,0.00016643389,0.00019702713,0.000001198936],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013681245,0.000043762568,0.008427993,0.00009652516,0.000009146282,1.05831525e-7,0.001236176,0.0006900128,0.0005205295,0.119170934,0.00039903822,0.86926895],"study_design_scores_gemma":[0.0014232418,0.00009928496,0.21913397,0.00009631414,0.000007964015,0.000015526559,0.00065033167,0.76875174,0.0004103997,0.0061777243,0.0031164854,0.0001170196],"about_ca_topic_score_codex":0.000024618234,"about_ca_topic_score_gemma":0.0000102076065,"teacher_disagreement_score":0.86915195,"about_ca_system_score_codex":0.00007239079,"about_ca_system_score_gemma":0.00012212174,"threshold_uncertainty_score":0.99984497},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06849559556228693,"score_gpt":0.32247574856559064,"score_spread":0.2539801530033037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2724383523","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058899973,0.000004710364,0.93954134,0.00056557637,0.00018606539,0.0002906917,0.00012600499,0.00016688713,0.0002187387],"genre_scores_gemma":[0.86205286,0.000018415465,0.13737938,0.00010976719,0.000036902293,0.00007445426,0.00026481884,0.000010525784,0.000052895248],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916756,0.000033820255,0.00022492118,0.00028812527,0.00012726695,0.000158286],"domain_scores_gemma":[0.99874365,0.00006114312,0.00040997533,0.00052588806,0.00022330513,0.000036063622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024446042,0.0000925575,0.00012064042,0.000111805406,0.00022828049,0.00011709183,0.00051200186,0.00006861791,0.000008444973],"category_scores_gemma":[0.00017051342,0.000099107914,0.000050782375,0.00006415392,0.000039123308,0.00074791495,0.00007859513,0.000083970386,0.000012234198],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000074168584,0.000092943344,0.0013811737,0.000056657813,0.000009658493,4.84078e-7,0.000058302063,0.0000013185193,0.049870864,0.00012944391,0.00034693873,0.9480448],"study_design_scores_gemma":[0.0009926662,0.0002972315,0.058545392,0.00026870138,0.00002943622,0.000017056313,0.00005052416,0.5324459,0.39037713,0.015777303,0.0007921467,0.0004065179],"about_ca_topic_score_codex":0.000035855974,"about_ca_topic_score_gemma":0.0000771436,"teacher_disagreement_score":0.9476383,"about_ca_system_score_codex":0.00005613433,"about_ca_system_score_gemma":0.000034086534,"threshold_uncertainty_score":0.40415037},"labels":[],"label_agreement":null},{"id":"W2740749606","doi":"10.1371/journal.pone.0180830","title":"Adaptive Swarm Balancing Algorithms for rare-event prediction in imbalanced healthcare data","year":2017,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Scalability; Particle swarm optimization; Data mining; Swarm behaviour; Heuristic; Machine learning; Algorithm; Classifier (UML); Artificial intelligence","score_opus":0.1822312412829347,"score_gpt":0.33611206715412945,"score_spread":0.15388082587119475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2740749606","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040596146,0.00011015364,0.98748815,0.0052997135,0.0002015457,0.0012301614,0.0008983922,0.0004591728,0.00025307434],"genre_scores_gemma":[0.6299592,0.00007567907,0.3687591,0.0001935934,0.00016556923,0.00032136473,0.0003472783,0.000016961292,0.00016121338],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981014,0.000055520046,0.00035891228,0.00074529694,0.00038574205,0.00035309375],"domain_scores_gemma":[0.99597996,0.00008374653,0.0003397589,0.0033241522,0.0001821968,0.000090191286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006608077,0.00014898342,0.00027297172,0.00011026091,0.00031231702,0.00021002849,0.0029416103,0.00009780571,0.000002585847],"category_scores_gemma":[0.0003858211,0.00015798326,0.00002646061,0.000117919364,0.000050416194,0.0016581123,0.0008389694,0.000198649,0.000016491897],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006452868,0.011423799,0.1175279,0.0022701262,0.0009006984,0.00010579552,0.005157107,0.00009819826,0.084610425,0.1450339,0.039901663,0.5923251],"study_design_scores_gemma":[0.0012873723,0.00035601002,0.06754932,0.000732078,0.000023936564,0.0000034415928,0.000055328277,0.86999565,0.050117895,0.008768232,0.0007189539,0.0003917908],"about_ca_topic_score_codex":0.00014174217,"about_ca_topic_score_gemma":0.00009107493,"teacher_disagreement_score":0.8698974,"about_ca_system_score_codex":0.00018592196,"about_ca_system_score_gemma":0.00012932712,"threshold_uncertainty_score":0.64423704},"labels":[],"label_agreement":null},{"id":"W2743178907","doi":"10.1111/coin.12128","title":"Learning over subconcepts: Strategies for 1‐class classification","year":2017,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Health Canada","keywords":"Computer science; Property (philosophy); Class (philosophy); Machine learning; Artificial intelligence; Domain (mathematical analysis); Multiclass classification; One-class classification; Classifier (UML); Support vector machine; Mathematics","score_opus":0.0847742673357272,"score_gpt":0.374068715977271,"score_spread":0.2892944486415438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2743178907","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012524961,0.00003070449,0.9932513,0.0012947277,0.0002943131,0.0003087161,0.000012872359,0.00038157625,0.0031732984],"genre_scores_gemma":[0.8057242,0.0000150333135,0.1935593,0.00017453617,0.00007663004,0.00011780944,0.000059607304,0.0000111510135,0.00026172926],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985125,0.00004880902,0.00034988337,0.0005325604,0.00030829496,0.00024794458],"domain_scores_gemma":[0.9978055,0.00038012463,0.00044392524,0.0008484655,0.00045080238,0.000071203016],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00038032007,0.00016167543,0.00015049381,0.00010202246,0.0008566866,0.0012811534,0.0020666404,0.00008369211,0.000019990704],"category_scores_gemma":[0.00039099867,0.00016926943,0.00007490601,0.00011175054,0.00022779289,0.0021417039,0.00022882198,0.00017421736,0.00007719747],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005693292,0.000027194565,0.00047391624,0.000013504038,0.00000886521,8.005321e-7,0.00023999067,0.008761499,0.0004776136,0.9254338,0.0011421252,0.063415006],"study_design_scores_gemma":[0.00007426437,0.00006997061,0.015668146,0.000021742446,0.000002954283,0.0000039227966,0.00014238665,0.6979563,0.0018234783,0.2747761,0.009263449,0.00019725216],"about_ca_topic_score_codex":0.0000138837195,"about_ca_topic_score_gemma":0.000004032617,"teacher_disagreement_score":0.80447173,"about_ca_system_score_codex":0.000084881525,"about_ca_system_score_gemma":0.00021592852,"threshold_uncertainty_score":0.9997556},"labels":[],"label_agreement":null},{"id":"W2754505060","doi":"10.1109/compsac.2017.49","title":"An Adaptive Diversity-Based Ensemble Method for Binary Classification","year":2017,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Ensemble learning; Binary number; Artificial intelligence; Machine learning; Construct (python library); Ensemble forecasting; Data mining; Binary classification; Base (topology); Model selection; Pattern recognition (psychology); Support vector machine; Mathematics","score_opus":0.10649602094414655,"score_gpt":0.36680054144672153,"score_spread":0.26030452050257497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2754505060","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020458,0.000002617644,0.9922184,0.0025247245,0.000112255635,0.00036131823,0.000020691481,0.0005243111,0.0040311506],"genre_scores_gemma":[0.38843137,0.0000010992758,0.61096287,0.00034537827,0.000020162877,0.000052885607,0.000021302472,0.0000048172515,0.00016012763],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989432,0.00007505163,0.00013598881,0.000478528,0.00018094911,0.00018629865],"domain_scores_gemma":[0.9972255,0.00011804781,0.00022553788,0.002135684,0.00021389665,0.000081332655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005928918,0.00010670611,0.00011741635,0.000098624325,0.0011613901,0.0003052483,0.0024337915,0.0000774933,0.0000072749626],"category_scores_gemma":[0.00008127509,0.00010171152,0.000051085815,0.000070379894,0.000058626,0.0015594215,0.00038613408,0.00006250979,0.000021814705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043127773,0.00014974149,0.0005740364,0.000009475097,0.00000952738,0.0000015389612,0.00011440296,0.000015242503,0.07702784,0.8023204,0.011058947,0.108675726],"study_design_scores_gemma":[0.00032651945,0.00029105868,0.017096559,0.000006620654,0.0000068365925,7.947809e-7,0.000026249847,0.8685283,0.092209525,0.0154462345,0.005866831,0.0001944966],"about_ca_topic_score_codex":0.000053780856,"about_ca_topic_score_gemma":0.000015190091,"teacher_disagreement_score":0.86851305,"about_ca_system_score_codex":0.000060942028,"about_ca_system_score_gemma":0.00007300727,"threshold_uncertainty_score":0.8932591},"labels":[],"label_agreement":null},{"id":"W2774222091","doi":"","title":"Sampling a Longer Life: Binary versus One-class classification Revisited","year":2017,"lang":"en","type":"article","venue":"Learning with Imbalanced Domains: Theory and Applications","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of Alberta","funders":"","keywords":"Class (philosophy); Binary number; Sampling (signal processing); Computer science; Statistics; Mathematics; Artificial intelligence; Arithmetic; Computer vision","score_opus":0.03681048116922473,"score_gpt":0.3051340556227185,"score_spread":0.26832357445349375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2774222091","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010172376,0.00018237036,0.98026854,0.001407077,0.00005546697,0.000744921,0.000014943806,0.0009210367,0.00623328],"genre_scores_gemma":[0.9123906,0.00027886228,0.085396945,0.0002607724,0.00016311511,0.0009018151,0.00009863736,0.000036910278,0.00047236902],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9978232,0.00025130986,0.00035188044,0.0008831003,0.00029688125,0.0003936777],"domain_scores_gemma":[0.9961068,0.0005499206,0.0006708873,0.0022792292,0.00018337769,0.00020980374],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0010199996,0.0002753697,0.00030106452,0.00014475851,0.0021021222,0.0007461698,0.0014533005,0.00014944207,0.00001319775],"category_scores_gemma":[0.0005195977,0.00025614846,0.00004998103,0.00032940024,0.000437637,0.0010309552,0.00034512283,0.00049681286,0.0000661789],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020235071,0.00008836397,0.0016787056,0.000040043215,0.000054653163,0.0000015869016,0.00021494631,0.000041243176,0.012030044,0.95022076,0.0000931198,0.035334207],"study_design_scores_gemma":[0.010825902,0.0015594882,0.46320668,0.0010568753,0.00037300255,0.00008646198,0.00167606,0.033218976,0.0075704046,0.18268117,0.29374793,0.0039970516],"about_ca_topic_score_codex":0.0000033363506,"about_ca_topic_score_gemma":0.0000014347931,"teacher_disagreement_score":0.9022182,"about_ca_system_score_codex":0.00006970953,"about_ca_system_score_gemma":0.000089151676,"threshold_uncertainty_score":0.9999891},"labels":[],"label_agreement":null},{"id":"W2787390697","doi":"10.4018/978-1-4666-5202-6.ch165","title":"Performance Measures and RTB Optimization","year":2014,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science","score_opus":0.020568685957235825,"score_gpt":0.23115373210771598,"score_spread":0.21058504615048015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2787390697","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000019768825,0.000061177365,0.48120132,0.00005465269,0.0001065596,0.00014023793,0.000016775655,0.0003401073,0.5180772],"genre_scores_gemma":[0.23422399,0.00032369487,0.586256,0.0028216206,0.0006222782,0.00012216419,0.000058791164,0.00014075947,0.17543069],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985542,0.000018485805,0.0002907057,0.00055769895,0.00036988975,0.00020898659],"domain_scores_gemma":[0.99853647,0.000019471792,0.00023818958,0.0009467867,0.00015955274,0.00009955498],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018510381,0.00029145856,0.00027148498,0.00007503121,0.00011262162,0.00019745268,0.00082353107,0.00027996392,0.000005601793],"category_scores_gemma":[0.00001902039,0.00029050084,0.000049276518,0.000020538853,0.00010288625,0.00015598038,0.00031648504,0.00017254741,0.000054765587],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027774222,0.0000014641178,0.000010199061,0.000019787358,0.000010325927,0.0000015596792,0.00001130406,0.000041914227,0.000008745346,0.91740155,0.0019736232,0.08051675],"study_design_scores_gemma":[0.00075153424,0.00041221318,0.000290315,0.000751539,0.000088279565,0.00022719649,0.00000221041,0.14443064,0.0013047691,0.3264686,0.5229957,0.002277001],"about_ca_topic_score_codex":0.0000056063623,"about_ca_topic_score_gemma":0.000003153092,"teacher_disagreement_score":0.59093297,"about_ca_system_score_codex":0.00012185495,"about_ca_system_score_gemma":0.00009145486,"threshold_uncertainty_score":0.9999547},"labels":[],"label_agreement":null},{"id":"W2789598342","doi":"10.1002/mp.12757","title":"Guided undersampling classification for automated radiation therapy quality assurance of prostate cancer treatment","year":2018,"lang":"en","type":"article","venue":"Medical Physics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; University of Toronto","funders":"","keywords":"Undersampling; Quality assurance; Prostate cancer; Medicine; Radiation therapy; Image-guided radiation therapy; Medical physics; Prostate; Cancer; Medical imaging; Radiology; Artificial intelligence; Internal medicine; Computer science; Pathology","score_opus":0.11846706177157362,"score_gpt":0.4102754358627509,"score_spread":0.29180837409117727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789598342","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013017955,0.00007224864,0.9826521,0.0026518458,0.00022914058,0.00057533965,0.000049500155,0.0006248512,0.00012696229],"genre_scores_gemma":[0.974762,0.00039989353,0.023748819,0.00036283236,0.00023833034,0.0003401058,0.000095646916,0.000012586548,0.000039764127],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99859303,0.00007763276,0.00039768597,0.00033053124,0.0004156806,0.00018544352],"domain_scores_gemma":[0.99848163,0.00022758359,0.00033910593,0.0005555645,0.00032326434,0.00007285791],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046108468,0.000118682256,0.0002002798,0.000032168537,0.00009668862,0.000034054112,0.0004644665,0.000081227285,0.000007917096],"category_scores_gemma":[0.00018354128,0.00009805922,0.000055175864,0.00032237885,0.00015430068,0.00029202554,0.000028726436,0.000047709018,0.0000054252723],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035788173,0.0003281237,0.0031467082,0.000047130372,0.000054711472,1.4452549e-7,0.0010455722,0.000013982588,0.014141956,0.038183633,0.0065788524,0.9364234],"study_design_scores_gemma":[0.002239112,0.0004741381,0.049994618,0.0000927723,0.000012089832,6.9644375e-7,0.000021264534,0.39713877,0.5112607,0.02353323,0.014886039,0.00034659315],"about_ca_topic_score_codex":0.000101865706,"about_ca_topic_score_gemma":0.000011730192,"teacher_disagreement_score":0.96174407,"about_ca_system_score_codex":0.00017268707,"about_ca_system_score_gemma":0.0003548225,"threshold_uncertainty_score":0.3998739},"labels":[],"label_agreement":null},{"id":"W2791757685","doi":"10.1016/j.eswa.2018.01.023","title":"Progressive boosting for class imbalance and its application to face re-identification","year":2018,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Horizon 2020 Framework Programme; Mitacs; European Commission","keywords":"Boosting (machine learning); Computer science; Classifier (UML); Artificial intelligence; Uncorrelated; Pattern recognition (psychology); Facial recognition system; Class (philosophy); Machine learning; Oversampling; Face (sociological concept); Sampling (signal processing); Computer vision; Mathematics; Statistics","score_opus":0.020431693406293045,"score_gpt":0.3075387842174565,"score_spread":0.2871070908111635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791757685","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005005498,0.0005098794,0.9895592,0.002449919,0.000078979516,0.0056927367,0.000050434457,0.0007131126,0.00044520985],"genre_scores_gemma":[0.881767,0.000012177995,0.08454552,0.00028563334,0.00032734172,0.032580703,0.00007739076,0.000030097983,0.0003741373],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99803424,0.000043933527,0.00043820197,0.0009008479,0.00027154884,0.0003112372],"domain_scores_gemma":[0.99735147,0.00011810429,0.00038972875,0.0012642052,0.00071551173,0.00016099743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035995743,0.00020066879,0.00020152237,0.00014305426,0.00050953747,0.00029607848,0.0008984397,0.0000919059,9.891994e-7],"category_scores_gemma":[0.00006760955,0.00018345714,0.000021650607,0.0006992332,0.000081030994,0.0005509773,0.00013415632,0.00007296913,0.00009415199],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051994255,0.00020975142,0.00032762202,0.00021316436,0.000054675766,7.520554e-7,0.003754062,0.000073971474,0.28383306,0.6560072,0.017930025,0.03754374],"study_design_scores_gemma":[0.0007002644,0.00040398058,0.0017196264,0.0002285031,0.000018860239,0.0000813273,0.00083045906,0.29041138,0.16161452,0.0011991562,0.5417853,0.0010066495],"about_ca_topic_score_codex":0.000016222282,"about_ca_topic_score_gemma":0.000005892681,"teacher_disagreement_score":0.9050137,"about_ca_system_score_codex":0.0001103239,"about_ca_system_score_gemma":0.000065695625,"threshold_uncertainty_score":0.74811655},"labels":[],"label_agreement":null},{"id":"W2793726301","doi":"10.1142/s0218001419400093","title":"Dynamic Ensemble Selection and Data Preprocessing for Multi-Class Imbalance Learning","year":2018,"lang":"en","type":"preprint","venue":"International Journal of Pattern Recognition and Artificial Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Preprocessor; Ensemble learning; Computer science; Artificial intelligence; Machine learning; Class (philosophy); Selection (genetic algorithm); Data pre-processing; Data mining; Binary number; Binary classification; Pattern recognition (psychology); Mathematics; Support vector machine","score_opus":0.19280881496129756,"score_gpt":0.40317454379188167,"score_spread":0.2103657288305841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793726301","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028079186,0.00017996776,0.9691591,0.0009522326,0.001163728,0.00021930148,0.00015552455,0.00007575271,0.000015190923],"genre_scores_gemma":[0.82036954,0.00082928746,0.17791721,0.00020451655,0.00036790696,0.000020268339,0.00024922675,0.000018980598,0.000023063336],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978844,0.00010532281,0.0008186033,0.0006441856,0.00037012322,0.00017740118],"domain_scores_gemma":[0.9967505,0.00017337964,0.0011934984,0.00030032918,0.0014974029,0.000084892155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010401108,0.00021127153,0.0002598065,0.0003273357,0.00013489951,0.0008128277,0.0014241114,0.00016997177,0.000012405347],"category_scores_gemma":[0.0005751224,0.00021478841,0.000059185364,0.00009267489,0.0001058224,0.00094698777,0.0009797405,0.000528015,0.000009587596],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049824095,0.00010257739,0.00035350287,0.00008515192,0.000082548475,0.000006622325,0.00036228076,0.0000934638,0.0056625605,0.000120130535,0.000089634785,0.9929917],"study_design_scores_gemma":[0.00009600066,0.00013258729,0.0002794455,0.0007051532,0.000028520506,0.00017728058,0.00010202309,0.9368962,0.028077496,0.032712113,0.00052380445,0.00026935348],"about_ca_topic_score_codex":0.000017815952,"about_ca_topic_score_gemma":0.000052367293,"teacher_disagreement_score":0.99272233,"about_ca_system_score_codex":0.00008740428,"about_ca_system_score_gemma":0.0001353277,"threshold_uncertainty_score":0.87588173},"labels":[],"label_agreement":null},{"id":"W2797412169","doi":"10.1109/ijcnn.2018.8489737","title":"K-Nearest Oracles Borderline Dynamic Classifier Ensemble Selection","year":2018,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Artificial intelligence; Classifier (UML); k-nearest neighbors algorithm; Pattern recognition (psychology); Ensemble learning; Machine learning","score_opus":0.016811523175120725,"score_gpt":0.2898235127196939,"score_spread":0.2730119895445732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797412169","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027832328,0.000010878136,0.9780635,0.0017826622,0.0002019336,0.00013477773,0.0000025315696,0.0013798381,0.015640605],"genre_scores_gemma":[0.66638684,0.000013632648,0.32970434,0.00057959306,0.00007223924,0.000021106862,0.0000126564655,0.000010735934,0.0031988646],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988535,0.00004744981,0.00021135465,0.0004218866,0.00020934809,0.0002564716],"domain_scores_gemma":[0.99889225,0.000038770162,0.00008407489,0.00066341186,0.0002568488,0.00006467169],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002143363,0.000120926496,0.000105989086,0.00013567215,0.00018156871,0.00018501417,0.000708907,0.000083690495,0.00011589062],"category_scores_gemma":[0.000059273636,0.000108484885,0.000028787883,0.0006225945,0.00009313263,0.0007361335,0.0001648494,0.00011046614,0.0005763829],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015636717,0.00019959985,0.0012717113,0.000014840984,0.00002221158,0.000003551095,0.00021663686,0.0000032653888,0.17502958,0.36351722,0.08169079,0.37801495],"study_design_scores_gemma":[0.00030573033,0.00034916043,0.016177792,0.00001974746,0.0000058137334,0.000044569406,0.000029077062,0.50131655,0.23562576,0.015951345,0.22969744,0.0004770265],"about_ca_topic_score_codex":0.000037307444,"about_ca_topic_score_gemma":0.00024786798,"teacher_disagreement_score":0.6636036,"about_ca_system_score_codex":0.000076672186,"about_ca_system_score_gemma":0.0000754205,"threshold_uncertainty_score":0.7408429},"labels":[],"label_agreement":null},{"id":"W2804541737","doi":"10.2196/medinform.9960","title":"Predicting the Reasons of Customer Complaints: A First Step Toward Anticipating Quality Issues of In Vitro Diagnostics Assays with Machine Learning","year":2018,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Boosting (machine learning); Vendor; Machine learning; Data mining; Artificial intelligence; Training set; Quality (philosophy); Customer satisfaction; Data quality; Set (abstract data type); Operations management; Engineering","score_opus":0.034454761967715644,"score_gpt":0.33729159992895574,"score_spread":0.3028368379612401,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804541737","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19845977,0.000054442007,0.7959917,0.0018161534,0.00010574714,0.0006624107,0.000061163264,0.0002866167,0.0025619643],"genre_scores_gemma":[0.89971054,0.00006569194,0.09991995,0.00018773488,0.000036526988,0.000040934385,0.000024004497,0.0000075171765,0.000007079633],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99732137,0.00017668278,0.0010723381,0.00012354978,0.0010318743,0.0002742123],"domain_scores_gemma":[0.9969952,0.0012200796,0.0008144357,0.00058463955,0.00028905654,0.00009660612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021046726,0.00014254914,0.00035322455,0.00012558654,0.000121410434,0.000042950254,0.0011205436,0.000112537215,0.000017770055],"category_scores_gemma":[0.0027565546,0.00009303678,0.000034916153,0.000633388,0.0005378287,0.00046174187,0.00045299163,0.00043729186,0.000006424767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002860911,0.001313172,0.5956616,0.0035522757,0.00021621585,0.00002096105,0.19488825,0.00015012875,0.0008145168,0.05664609,0.0064904382,0.13996027],"study_design_scores_gemma":[0.00087251945,0.00039351417,0.029852612,0.0012165296,0.000015203752,0.00002325395,0.004095364,0.94756067,0.009854013,0.00012972686,0.0057047354,0.0002818615],"about_ca_topic_score_codex":0.00026551905,"about_ca_topic_score_gemma":0.00009403387,"teacher_disagreement_score":0.9474105,"about_ca_system_score_codex":0.00004262917,"about_ca_system_score_gemma":0.000114015056,"threshold_uncertainty_score":0.37939298},"labels":[],"label_agreement":null},{"id":"W2807512355","doi":"10.1007/978-3-319-92058-0_29","title":"Online Detection of Shill Bidding Fraud Based on Machine Learning Techniques","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Bidding; Computer science; Common value auction; Support vector machine; Classifier (UML); Artificial intelligence; Machine learning; Data mining; Business","score_opus":0.019769815373298513,"score_gpt":0.2634754865622676,"score_spread":0.24370567118896908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807512355","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000647797,0.00006807796,0.99703425,0.00028444343,0.00047028286,0.00038211085,0.000026089729,0.00071859476,0.00095134747],"genre_scores_gemma":[0.2074342,0.000037420057,0.7912069,0.0008261219,0.00029312735,0.000012986549,0.000034487184,0.000043952725,0.00011081759],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99647766,0.00006911786,0.0006346124,0.0013768624,0.0009961644,0.00044558744],"domain_scores_gemma":[0.9967146,0.00045957332,0.0006491773,0.0016790961,0.0003985874,0.00009898417],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011097935,0.00047894407,0.00050352747,0.0016758675,0.00022073879,0.00021112354,0.0029609771,0.00039111255,0.000029350611],"category_scores_gemma":[0.0002939943,0.00044527077,0.00011917968,0.00087367254,0.00067544065,0.0004911549,0.00076429476,0.0010611011,0.00001600188],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016677617,0.00009830187,0.00005465744,0.000065799184,0.0000070817136,0.000014165235,0.00019695374,0.0024970497,0.01747854,0.0028915163,0.000010704093,0.97666854],"study_design_scores_gemma":[0.00011129622,0.00060485135,0.00009084691,0.00058974535,0.0000046129644,0.000011012531,7.9270954e-8,0.6599035,0.3171592,0.018016463,0.0030702688,0.00043813017],"about_ca_topic_score_codex":0.0000250501,"about_ca_topic_score_gemma":0.00005216673,"teacher_disagreement_score":0.97623044,"about_ca_system_score_codex":0.00034740323,"about_ca_system_score_gemma":0.00025558483,"threshold_uncertainty_score":0.9997999},"labels":[],"label_agreement":null},{"id":"W2810188754","doi":"10.6000/1929-6029.2018.07.03.1","title":"A Note on the Area under the Gains Chart","year":2018,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Chart; Receiver operating characteristic; Computer science; Artificial intelligence; Classifier (UML); Statistics; Shewhart individuals control chart; EWMA chart; Control chart; Pattern recognition (psychology); Machine learning; Mathematics; Process (computing)","score_opus":0.17035335559078355,"score_gpt":0.49281998398945087,"score_spread":0.32246662839866735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810188754","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010803025,0.000013214124,0.8941574,0.10140287,0.00053338066,0.00007919018,0.00002262156,0.000008458762,0.0027025708],"genre_scores_gemma":[0.97038627,0.00030499342,0.023964873,0.0045512384,0.00061543676,0.000012055345,0.000003165586,0.0000070978213,0.00015487486],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9947073,0.00043546892,0.0004115724,0.00014083255,0.0040802127,0.00022461405],"domain_scores_gemma":[0.9925404,0.005076099,0.00015167856,0.00037857555,0.0017476171,0.0001056223],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0074590296,0.00006313436,0.000089985486,0.00027414155,0.00011962917,0.00019161394,0.004173414,0.00005596929,0.00034040108],"category_scores_gemma":[0.009311086,0.000032526168,0.000026414384,0.00034932856,0.0006996371,0.00013716849,0.0004013478,0.001114056,0.000086806715],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028165314,0.000079009034,0.000074054406,0.0000010019876,0.00001567894,0.000113089496,0.00030072607,0.0000025357522,0.00012030395,0.8586662,0.08301164,0.057587594],"study_design_scores_gemma":[0.0008217008,0.00072409457,0.020487614,0.0004957082,0.0000028588804,0.0002752279,0.00040521353,0.12823,0.0038508233,0.7048532,0.13968624,0.00016733242],"about_ca_topic_score_codex":0.000020783888,"about_ca_topic_score_gemma":0.000044128956,"teacher_disagreement_score":0.969306,"about_ca_system_score_codex":0.00021560669,"about_ca_system_score_gemma":0.00056760106,"threshold_uncertainty_score":0.9990339},"labels":[],"label_agreement":null},{"id":"W2860849205","doi":"10.1111/exsy.12311","title":"Resampling with neighbourhood bias on imbalanced domains","year":2018,"lang":"en","type":"article","venue":"Expert Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"European Regional Development Fund; Fundação para a Ciência e a Tecnologia","keywords":"Resampling; Computer science; Neighbourhood (mathematics); Machine learning; Artificial intelligence; Regression; Data mining; Variable (mathematics); Set (abstract data type); Statistics; Mathematics","score_opus":0.04663654710554879,"score_gpt":0.29313055383288333,"score_spread":0.24649400672733454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2860849205","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00483651,0.000111596586,0.9754444,0.00066573475,0.0008234798,0.00041243085,0.000010324525,0.0011152528,0.016580274],"genre_scores_gemma":[0.9529088,0.000012515373,0.045206238,0.0006039273,0.0005802325,0.00015317042,0.00000873511,0.00002392192,0.00050246506],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99822766,0.000105359875,0.00029335395,0.000576067,0.0004415864,0.00035596476],"domain_scores_gemma":[0.9978681,0.0001085583,0.00019173218,0.0015595345,0.00016552937,0.00010652805],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003420219,0.00019529845,0.00022447952,0.00014026092,0.00022833784,0.0003122027,0.0010923228,0.00008198532,0.0000116592755],"category_scores_gemma":[0.0000630409,0.00014459805,0.000032881402,0.00042767404,0.00009352358,0.00042353565,0.00011651724,0.0001161325,0.000267675],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013436697,0.00030534758,0.0022476984,0.00004963045,0.00009283822,0.000054785916,0.0058954614,0.00003994314,0.047919627,0.8364066,0.09250651,0.014347229],"study_design_scores_gemma":[0.0030292983,0.0036770187,0.011444054,0.0015610214,0.000009482368,0.00034185758,0.0009779263,0.08170175,0.25193828,0.0019143088,0.64100045,0.0024045515],"about_ca_topic_score_codex":0.00017181934,"about_ca_topic_score_gemma":0.0000116907395,"teacher_disagreement_score":0.9480723,"about_ca_system_score_codex":0.00011657275,"about_ca_system_score_gemma":0.000061814455,"threshold_uncertainty_score":0.58965373},"labels":[],"label_agreement":null},{"id":"W2883381152","doi":"10.4236/ijis.2018.83003","title":"Using Hybrid and Diversity-Based Adaptive Ensemble Method for Binary Classification","year":2018,"lang":"en","type":"article","venue":"International Journal of Intelligence Science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Ensemble learning; Computer science; Ensemble forecasting; Artificial intelligence; Machine learning; Binary number; Construct (python library); Predictive modelling; Data mining; Pattern recognition (psychology); Mathematics","score_opus":0.1306199949990329,"score_gpt":0.40139414616523944,"score_spread":0.2707741511662065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2883381152","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005584753,0.000025711503,0.992088,0.0011016965,0.0008374338,0.00012060871,0.0000121671865,0.00003196812,0.0001976563],"genre_scores_gemma":[0.50129724,0.000008373519,0.49835053,0.00025272428,0.00008103704,0.0000015441485,5.359213e-7,0.0000024683313,0.0000055255646],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820286,0.000051996896,0.00039328422,0.00033719023,0.0008199049,0.00019475631],"domain_scores_gemma":[0.9956499,0.00024382783,0.0005597769,0.00027353293,0.003163157,0.000109814246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020122577,0.00010511043,0.00012848848,0.0006219689,0.00035947384,0.00025089158,0.0027130859,0.000029667373,0.0000062535805],"category_scores_gemma":[0.0005268758,0.00009534131,0.000058078378,0.00047965467,0.0006140723,0.0018583798,0.00052624673,0.00010952572,0.000004303014],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018057381,0.00014774344,0.0005849487,0.0000075619187,0.000038931776,0.000026201633,0.0008322381,0.00028746508,0.42847574,0.30269763,0.0007634768,0.26595747],"study_design_scores_gemma":[0.000082584476,0.0002526586,0.0005513573,0.000046733243,0.000005316781,0.00013887002,0.00006202411,0.59285206,0.38276774,0.022592988,0.0005518225,0.00009588088],"about_ca_topic_score_codex":0.000012587905,"about_ca_topic_score_gemma":0.0000014708307,"teacher_disagreement_score":0.5925646,"about_ca_system_score_codex":0.00024891624,"about_ca_system_score_gemma":0.00045545978,"threshold_uncertainty_score":0.5041634},"labels":[],"label_agreement":null},{"id":"W2886584315","doi":"10.1109/civemsa.2018.8439957","title":"Adaptive Weighting with SMOTE for Learning from Imbalanced Datasets: A Case Study for Traffic Offence Prediction","year":2018,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Oversampling; Weighting; Computer science; Classifier (UML); Machine learning; Artificial intelligence; Ticket; A priori and a posteriori; Law enforcement; Data mining; Ensemble learning; Blacklist; Computer security; Bandwidth (computing)","score_opus":0.040649803799396214,"score_gpt":0.2873639045048225,"score_spread":0.24671410070542632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886584315","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09145178,0.0000063173193,0.90534955,0.00008230163,0.00010474379,0.0016704313,0.00048237178,0.00081165705,0.000040844265],"genre_scores_gemma":[0.6194917,8.6598e-7,0.37964547,0.000058134035,0.0001085742,0.00040193473,0.00023941178,0.000012681296,0.00004122509],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833405,0.00007313209,0.00030278202,0.00077883474,0.00020921652,0.00030199037],"domain_scores_gemma":[0.9983365,0.00035600917,0.00022557974,0.00076341524,0.00024642897,0.00007207312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045519893,0.00018359648,0.00019715226,0.000092812086,0.00046361412,0.00017490513,0.0006279101,0.000056341378,0.000005768776],"category_scores_gemma":[0.00012330902,0.00014883411,0.00003197523,0.00029562291,0.00008115239,0.0009829479,0.00013182842,0.000120070035,0.000005637367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002878117,0.0035750014,0.012493073,0.00016367348,0.0010127907,0.0005338676,0.034520343,0.0017882138,0.020038115,0.018557316,0.056253437,0.8481861],"study_design_scores_gemma":[0.0017493954,0.004001902,0.0008172784,0.000047282203,0.000038522234,0.00010525204,0.0025127993,0.9789564,0.008063828,0.00031416508,0.0030828877,0.0003103059],"about_ca_topic_score_codex":0.00015508705,"about_ca_topic_score_gemma":0.00021582095,"teacher_disagreement_score":0.97716814,"about_ca_system_score_codex":0.000068707566,"about_ca_system_score_gemma":0.000070992144,"threshold_uncertainty_score":0.6069279},"labels":[],"label_agreement":null},{"id":"W2887884712","doi":"10.11159/mvml18.104","title":"A Model Based on Clustering and Association Rules for Detection of Fraud in Banking Transactions","year":2018,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Association rule learning; Cluster analysis; Computer science; Association (psychology); Data modeling; Data mining; Artificial intelligence; Database; Psychology","score_opus":0.01023935273348222,"score_gpt":0.22075187410243785,"score_spread":0.21051252136895562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887884712","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08285524,0.000024041923,0.91648537,0.00011821573,0.00022094512,0.00021228965,0.0000019857616,0.000046879788,0.000035015593],"genre_scores_gemma":[0.98629224,0.0000047916983,0.013603235,0.00002350801,0.00002378564,0.000026379437,4.5171095e-8,0.0000036023055,0.00002241813],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920166,0.000004246009,0.0001834809,0.00024868868,0.00020910027,0.00015280019],"domain_scores_gemma":[0.9994921,0.000110622765,0.0001304591,0.0000841906,0.00014994151,0.000032682943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052337896,0.0000802466,0.00013797452,0.00032362438,0.00011453812,0.00012552482,0.00026694726,0.00003219816,2.5667363e-8],"category_scores_gemma":[0.000047243684,0.00006399241,0.000016194757,0.0005747723,0.000059295184,0.00023800066,0.000036746565,0.00009200244,2.0880083e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017942095,0.00029955656,0.0056801084,0.0013376216,0.000048285212,3.330888e-7,0.0012741962,0.10036104,0.3441574,0.291169,0.00014441487,0.25534862],"study_design_scores_gemma":[0.00015170229,0.00013030016,0.0021400454,0.00020517308,0.0000024152296,0.0000015130232,0.0000014942489,0.9733064,0.023829384,0.00013128293,0.000034013672,0.00006624895],"about_ca_topic_score_codex":0.000007603015,"about_ca_topic_score_gemma":0.0000018397895,"teacher_disagreement_score":0.903437,"about_ca_system_score_codex":0.00005897032,"about_ca_system_score_gemma":0.000017230877,"threshold_uncertainty_score":0.2609535},"labels":[],"label_agreement":null},{"id":"W2895206473","doi":"10.1007/978-3-030-01851-1_28","title":"SCUT-DS: Learning from Multi-class Imbalanced Canadian Weather Data","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Oversampling; Computer science; Class (philosophy); Data stream; Machine learning; Binary number; Data stream mining; Artificial intelligence; Binary classification; Data mining; Support vector machine; Mathematics","score_opus":0.04505112479481433,"score_gpt":0.2753153436189509,"score_spread":0.23026421882413656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895206473","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000024151337,0.00035807226,0.99281543,0.001030597,0.0015122561,0.00047908426,0.00016170382,0.0005727523,0.0030459277],"genre_scores_gemma":[0.06611789,0.00008791549,0.92794466,0.002846898,0.0007591583,0.000021084745,0.00047808327,0.000099305726,0.0016450108],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939687,0.00008419427,0.00066525704,0.0031751625,0.0010347667,0.0010718857],"domain_scores_gemma":[0.9925404,0.00037030282,0.00045560027,0.0058749453,0.00038797891,0.00037074886],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0012017204,0.00070539996,0.00063249125,0.0011004626,0.00049417885,0.001088565,0.013428571,0.0005714332,0.0001717154],"category_scores_gemma":[0.00035094618,0.0006874171,0.00008395176,0.00074541755,0.0010478268,0.0015620623,0.0036508306,0.0013741805,0.00044957368],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000986347,0.00006700305,0.0005631749,0.00004000471,0.000056234938,0.00020507294,0.0020381415,0.0025716517,0.0013832323,0.008278119,0.001888541,0.98289895],"study_design_scores_gemma":[0.00031467475,0.000091014466,0.00040669998,0.00035258348,0.000011177572,0.000023660807,5.1835866e-7,0.9004963,0.001635875,0.026449932,0.06915645,0.0010611108],"about_ca_topic_score_codex":0.0066029993,"about_ca_topic_score_gemma":0.02571802,"teacher_disagreement_score":0.98183787,"about_ca_system_score_codex":0.00080182997,"about_ca_system_score_gemma":0.0017963,"threshold_uncertainty_score":0.9999484},"labels":[],"label_agreement":null},{"id":"W2897650261","doi":"10.1016/j.eswa.2024.124863","title":"An empirical evaluation of imbalanced data strategies from a practitioner’s point of view","year":2024,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Support vector machine; Artificial intelligence; Gradient boosting; Classifier (UML); Boosting (machine learning); Binary classification; Computer science; Correlation; Random forest; Binary number; Pattern recognition (psychology); Cut-point; Correlation coefficient; Machine learning; Mathematics; Data mining; Statistics","score_opus":0.09491998972119446,"score_gpt":0.4088449582014986,"score_spread":0.3139249684803041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897650261","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047873732,0.0028932386,0.99306524,0.00064908183,0.00008311902,0.001185813,0.0003559973,0.0003923647,0.0008964048],"genre_scores_gemma":[0.89035755,0.00009296905,0.10660821,0.00003470359,0.00009809853,0.0018159003,0.0009686756,0.0000151975355,0.000008688356],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99781746,0.00022246974,0.0005159825,0.000641833,0.00067894364,0.0001233219],"domain_scores_gemma":[0.9960393,0.00015991951,0.00028555567,0.0029713898,0.0004819518,0.000061934086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009092326,0.00013477575,0.0002399626,0.00013076689,0.000059893115,0.00020859086,0.0014041299,0.000069733,0.00001633728],"category_scores_gemma":[0.000028722316,0.00010794428,0.000023286002,0.00066492864,0.00008673064,0.0020098125,0.0001239726,0.00009516704,0.000017877035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003245875,0.0011541281,0.0003792635,0.00054616854,0.00032888338,0.0000032489404,0.006360598,0.0011004274,0.18666366,0.68690455,0.032173652,0.08435295],"study_design_scores_gemma":[0.00036569184,0.00015794019,0.0016933742,0.00052706536,0.00007186831,0.000028181572,0.0017463869,0.91338515,0.012349921,0.0076439604,0.061663743,0.00036669537],"about_ca_topic_score_codex":0.00037582978,"about_ca_topic_score_gemma":0.000023991583,"teacher_disagreement_score":0.91228473,"about_ca_system_score_codex":0.00007911486,"about_ca_system_score_gemma":0.0005915921,"threshold_uncertainty_score":0.440184},"labels":[],"label_agreement":null},{"id":"W2898284823","doi":"10.3390/jrfm11040070","title":"Identification of Core Suppliers Based on E-Invoice Data Using Supervised Machine Learning","year":2018,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Purchasing; Weighting; Computer science; Invoice; Segmentation; Identification (biology); Artificial intelligence; Core (optical fiber); Data mining; Machine learning; Profit (economics); Operations management; Engineering; Database","score_opus":0.035439072268687366,"score_gpt":0.28298907240605414,"score_spread":0.24755000013736678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898284823","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02876917,0.000048624963,0.9706789,0.00008926056,0.00018670899,0.00010199391,0.000030547493,0.000019554049,0.00007522464],"genre_scores_gemma":[0.90009284,0.00026167737,0.09945145,0.00008166268,0.000079852594,9.282778e-7,0.000012099518,0.0000054893885,0.000013976868],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989039,0.000057619112,0.00043163105,0.00020411784,0.00029551462,0.000107230655],"domain_scores_gemma":[0.99858105,0.000049789684,0.0006048395,0.00057556044,0.00014957957,0.00003919037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010910953,0.00008346185,0.00015172495,0.0002603448,0.00013781873,0.00006205802,0.0008614766,0.00003326068,0.0000038087856],"category_scores_gemma":[0.00016357815,0.000074704214,0.0000283314,0.00029873158,0.0000680049,0.00042056627,0.0002498372,0.00014871686,0.0000019820422],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034149407,0.0004461683,0.023662731,0.00019912605,0.00004419907,0.00003898729,0.0009916564,0.0010118799,0.011990173,0.039824422,0.0033386077,0.91811055],"study_design_scores_gemma":[0.0009885265,0.00045425195,0.047519226,0.00015290856,0.00007813397,0.000008036364,0.000072709096,0.91368204,0.0067154495,0.0025154855,0.027613483,0.00019974727],"about_ca_topic_score_codex":0.000017184777,"about_ca_topic_score_gemma":0.0000042276624,"teacher_disagreement_score":0.9179108,"about_ca_system_score_codex":0.000033586854,"about_ca_system_score_gemma":0.000033472,"threshold_uncertainty_score":0.30463493},"labels":[],"label_agreement":null},{"id":"W2906781826","doi":"10.1109/icsai.2018.8599490","title":"Utility Balanced Classification for Automatic Electronic Medical Record Analysis","year":2018,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Classifier (UML); Data mining; Machine learning; Artificial intelligence; Data classification","score_opus":0.02903590348124573,"score_gpt":0.32074888442853766,"score_spread":0.2917129809472919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906781826","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034068436,0.000007378928,0.9885667,0.0028555037,0.00011305099,0.00034555054,0.000006632924,0.0012034696,0.0034948764],"genre_scores_gemma":[0.79127973,0.00001311696,0.20751709,0.00055406225,0.00007060861,0.00014394795,0.000051505616,0.000006668055,0.00036324665],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803096,0.00009074753,0.00043457336,0.00060309045,0.00043108803,0.0004095108],"domain_scores_gemma":[0.9978283,0.00019823671,0.00017893428,0.0013825508,0.00028917746,0.00012280245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096100464,0.00013367645,0.00024419208,0.000241134,0.00014962842,0.00010891973,0.0014608582,0.00013364328,0.0004649942],"category_scores_gemma":[0.00044391886,0.000116797906,0.00012567219,0.0015048453,0.00012562965,0.00045288523,0.00012270745,0.00011535784,0.000101215875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010939531,0.00016789815,0.0045217257,0.000019536921,0.00018787466,3.0558923e-7,0.00008300306,1.0373639e-7,0.0013675092,0.5127491,0.019857973,0.46103406],"study_design_scores_gemma":[0.00017276389,0.00012486672,0.03280864,0.0000048196775,0.000042062464,0.00000150188,0.00000791909,0.92711616,0.005253506,0.012621998,0.021687657,0.00015809824],"about_ca_topic_score_codex":0.000022171853,"about_ca_topic_score_gemma":0.00020413489,"teacher_disagreement_score":0.9271161,"about_ca_system_score_codex":0.00009521892,"about_ca_system_score_gemma":0.00027100244,"threshold_uncertainty_score":0.509136},"labels":[],"label_agreement":null},{"id":"W2910335025","doi":"10.1109/icmla.2018.00061","title":"Auction Fraud Classification Based on Clustering and Sampling Techniques","year":2018,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Cluster analysis; Computer science; Sampling (signal processing); Data mining; Artificial intelligence; Telecommunications","score_opus":0.05316376241522855,"score_gpt":0.31216881115615824,"score_spread":0.25900504874092967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910335025","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00046439352,0.0000028117631,0.9876083,0.0015185998,0.00010582835,0.00018458639,0.0000016418701,0.0014859928,0.00862785],"genre_scores_gemma":[0.5082196,0.0000059357385,0.49086705,0.0007101062,0.00007751517,0.00003600734,0.000005862014,0.0000067426718,0.00007120382],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999039,0.00003776393,0.00018405316,0.000411482,0.00017447316,0.00015320798],"domain_scores_gemma":[0.9989929,0.00005969041,0.00009016288,0.00069579826,0.00011251712,0.00004890381],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032574218,0.00010694257,0.00008342459,0.00019514815,0.00017142153,0.00018088211,0.00037852145,0.000078595396,0.000016185857],"category_scores_gemma":[0.000055791472,0.00009901348,0.00001666581,0.00027046344,0.00008439856,0.0005058675,0.00010416361,0.00009071018,0.000031652668],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021274755,0.00008882495,0.0006675521,0.000026605394,0.0000051089296,6.1489857e-7,0.00015883453,0.000008993041,0.10298733,0.12965709,0.0038371065,0.7625407],"study_design_scores_gemma":[0.00010762011,0.00023232165,0.012022048,0.00004898329,0.0000022657732,0.00000559629,0.000016470762,0.746623,0.21412835,0.0031043163,0.023472883,0.00023615806],"about_ca_topic_score_codex":0.000011666383,"about_ca_topic_score_gemma":0.000005739436,"teacher_disagreement_score":0.76230454,"about_ca_system_score_codex":0.00006404066,"about_ca_system_score_gemma":0.000023769231,"threshold_uncertainty_score":0.40376526},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.039533028929034666,"score_gpt":0.28726956888613375,"score_spread":0.2477365399570991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912895282","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06668311,0.00003273218,0.9309683,0.00047903086,0.00014541834,0.00060620235,0.0000062699564,0.00046702896,0.0006118909],"genre_scores_gemma":[0.8459752,0.0000017841154,0.15372731,0.000089612106,0.000040321356,0.000062000916,0.000029227607,0.000011443364,0.00006307198],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998585,0.000053185573,0.0003052262,0.0005663274,0.0001561135,0.00033415094],"domain_scores_gemma":[0.9990228,0.00014280148,0.00018534028,0.0005532581,0.0000529815,0.00004283051],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000312835,0.00014029263,0.00017741536,0.000117257114,0.00012724816,0.00015541945,0.0008109495,0.00006631316,0.0000010547135],"category_scores_gemma":[0.000079600424,0.00013045919,0.000046785495,0.00048462965,0.000020768075,0.0005119629,0.0002736837,0.00017966054,0.0000098053315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023163162,0.00018110231,0.022642631,0.00022998103,0.000003974572,0.0000033796568,0.0006091256,0.0012427762,0.023399603,0.06456565,0.00089103397,0.8862076],"study_design_scores_gemma":[0.00046811483,0.000054052758,0.053979818,0.00015813886,0.0000015381419,0.000008830089,0.000017877503,0.9235759,0.014950032,0.0031257959,0.00343443,0.00022548],"about_ca_topic_score_codex":0.000002921887,"about_ca_topic_score_gemma":5.9162574e-7,"teacher_disagreement_score":0.9223331,"about_ca_system_score_codex":0.000060651273,"about_ca_system_score_gemma":0.00006292711,"threshold_uncertainty_score":0.53199714},"labels":[],"label_agreement":null},{"id":"W2913025895","doi":"10.1109/bigdata.2018.8622044","title":"Service failure prediction in supply-chain networks","year":2018,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Supply chain; Random forest; Service (business); Classifier (UML); Association rule learning; Data mining; Reliability engineering; Machine learning; Artificial intelligence; Business; Engineering; Marketing","score_opus":0.01140658752533815,"score_gpt":0.2345417937837026,"score_spread":0.22313520625836444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913025895","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015671698,0.0000070970746,0.9891547,0.0041211317,0.00016205115,0.000152209,0.0000037133855,0.00070608617,0.004125853],"genre_scores_gemma":[0.84008175,0.000005995907,0.15735324,0.0019691975,0.00015356843,0.000040233725,0.000024594414,0.000006681305,0.00036475767],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991536,0.000042648928,0.00017879691,0.00029844156,0.00013145816,0.00019506477],"domain_scores_gemma":[0.99912876,0.000026934875,0.0000449143,0.0006508124,0.00010725399,0.00004129768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026459206,0.00007894301,0.00007308629,0.00010599889,0.00005032971,0.00008260026,0.00070608535,0.00008253564,0.000087797176],"category_scores_gemma":[0.000015991363,0.00007342223,0.000012023344,0.00074482826,0.00002844203,0.00063705747,0.00018775901,0.00010707577,0.00014603387],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017059449,0.00019413841,0.026219131,0.000023076678,0.000013266399,0.00000877112,0.0013124797,0.0002762619,0.0069297934,0.442667,0.41751805,0.10482097],"study_design_scores_gemma":[0.00021577744,0.00007126116,0.028416572,0.000025239111,0.0000010038581,0.000009663491,0.000044009306,0.9216902,0.007956089,0.0035200163,0.03789317,0.00015700178],"about_ca_topic_score_codex":0.00010637987,"about_ca_topic_score_gemma":0.0007488638,"teacher_disagreement_score":0.92141396,"about_ca_system_score_codex":0.000046941703,"about_ca_system_score_gemma":0.000024791554,"threshold_uncertainty_score":0.29940715},"labels":[],"label_agreement":null},{"id":"W2946285377","doi":"10.1007/978-3-030-18305-9_29","title":"Multi-class Ensemble Learning of Imbalanced Bidding Fraud Data","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Bidding; Class (philosophy); Ensemble learning; Artificial intelligence; Machine learning; Business","score_opus":0.0433814805568129,"score_gpt":0.29030384445495205,"score_spread":0.24692236389813915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946285377","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000036122783,0.00027370435,0.9952803,0.00027883498,0.0010314177,0.00046200526,0.000036483245,0.000282933,0.002318185],"genre_scores_gemma":[0.11584182,0.00012744643,0.8826236,0.00033239266,0.00015243236,0.0000052578557,0.000086034976,0.00004628283,0.0007847],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950128,0.00006496112,0.000869544,0.0022853545,0.0011029221,0.00066442083],"domain_scores_gemma":[0.9931595,0.0006157711,0.00089639146,0.0048548835,0.00035177628,0.00012169261],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.001652821,0.0005296677,0.000746017,0.0009723239,0.00017425924,0.00036283417,0.009906715,0.00040240705,0.000020077498],"category_scores_gemma":[0.00041117662,0.0005152582,0.00009330527,0.00079688977,0.0005869146,0.0013517835,0.0050806818,0.0011935387,0.00009043968],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007782583,0.00006231942,0.00030299937,0.00013152914,0.000023819917,0.000028884944,0.0004992628,0.018636717,0.017875254,0.017858418,0.000112993264,0.94446003],"study_design_scores_gemma":[0.00028446355,0.00011245427,0.00018909543,0.000525291,0.000007134399,0.000023600884,2.767332e-7,0.9703043,0.014356524,0.006351488,0.007237617,0.0006077606],"about_ca_topic_score_codex":0.000018958928,"about_ca_topic_score_gemma":0.000023026458,"teacher_disagreement_score":0.9516676,"about_ca_system_score_codex":0.0002478741,"about_ca_system_score_gemma":0.00081960973,"threshold_uncertainty_score":0.9997299},"labels":[],"label_agreement":null},{"id":"W2949130142","doi":"10.34133/2022/9758169","title":"Data-Driven Machine Learning Techniques for Self-Healing in Cellular Wireless Networks: Challenges and Solutions","year":2022,"lang":"en","type":"article","venue":"Intelligent Computing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Software deployment; Fault management; Cellular network; Artificial intelligence; Machine learning; Engineering; Computer network; Software engineering","score_opus":0.07561827249062149,"score_gpt":0.2963269271762478,"score_spread":0.22070865468562634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949130142","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011552295,0.0040082564,0.99220264,0.00072404824,0.0001722373,0.00053518923,0.000023882381,0.0011002512,0.00007824024],"genre_scores_gemma":[0.72310317,0.0013079306,0.27509218,0.00010632339,0.000092207025,0.000089228575,0.00017546525,0.000024104087,0.000009413058],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978729,0.0002607414,0.00046456055,0.00073749595,0.00022090855,0.00044337523],"domain_scores_gemma":[0.9984291,0.00042763923,0.00023266108,0.00078795216,0.00006366576,0.000058957496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018519188,0.00017532168,0.00023762952,0.0002501959,0.0005932972,0.00011037089,0.0015985909,0.00005493311,0.0000023970827],"category_scores_gemma":[0.00006582498,0.00020415004,0.000034957713,0.00031764296,0.000034413428,0.00031784445,0.0030687903,0.0005006662,9.272512e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011398208,0.0002670373,0.00066368637,0.00012216481,0.000042473286,0.000016404338,0.0030206698,0.027404346,0.0012474328,0.1034475,0.00029705526,0.8634598],"study_design_scores_gemma":[0.00007857465,0.00008689313,0.00005898988,0.000047017238,0.0000051360657,0.000015218498,0.00020750302,0.9706153,0.0015794949,0.0009334554,0.02616074,0.00021165176],"about_ca_topic_score_codex":0.00003689356,"about_ca_topic_score_gemma":0.0000225611,"teacher_disagreement_score":0.94321096,"about_ca_system_score_codex":0.0001661337,"about_ca_system_score_gemma":0.000045560202,"threshold_uncertainty_score":0.8324997},"labels":[],"label_agreement":null},{"id":"W2952361316","doi":"10.48550/arxiv.math/0510449","title":"Improving Classification When a Class Hierarchy is Available Using a Hierarchy-Based Prior","year":2005,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Hierarchy; Multinomial logistic regression; Class hierarchy; Computer science; Class (philosophy); Softmax function; Artificial intelligence; Multinomial distribution; Bayesian probability; Machine learning; Tree (set theory); Prior probability; Data mining; Mathematics; Statistics; Artificial neural network","score_opus":0.10409383479334591,"score_gpt":0.303829299863808,"score_spread":0.1997354650704621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952361316","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06568819,0.0004022904,0.92124975,0.0057428647,0.000751664,0.001618001,0.00014669125,0.0021641538,0.0022363977],"genre_scores_gemma":[0.34250614,0.00010063031,0.6494892,0.0034900943,0.00059015973,0.00053243275,0.00030653068,0.00014380124,0.0028409597],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99411035,0.00033821128,0.0012030264,0.0024696286,0.00090547104,0.00097331236],"domain_scores_gemma":[0.99256927,0.00019291296,0.0013114854,0.0050613172,0.0005633219,0.00030166656],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011121411,0.00077075657,0.000720711,0.00079874427,0.00046521265,0.0007647228,0.004316129,0.0007960946,0.0002500147],"category_scores_gemma":[0.00027546062,0.0008384601,0.00030839702,0.00068392215,0.00026149163,0.0012917253,0.0024166994,0.0016588478,0.00087530154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002085616,0.0019775678,0.14331731,0.0024955412,0.00048465142,0.00011374579,0.0046306094,0.00048141458,0.43875003,0.021357562,0.112367086,0.27381593],"study_design_scores_gemma":[0.00083504093,0.000099395416,0.0124480715,0.00053633325,0.00008787578,0.000017041704,0.000028138775,0.81194484,0.07983035,0.0019769713,0.09044023,0.0017557296],"about_ca_topic_score_codex":0.00038989825,"about_ca_topic_score_gemma":0.000017341721,"teacher_disagreement_score":0.8114634,"about_ca_system_score_codex":0.0016151754,"about_ca_system_score_gemma":0.0019273767,"threshold_uncertainty_score":0.9999026},"labels":[],"label_agreement":null},{"id":"W2963779314","doi":"","title":"Satisfying real-world goals with dataset constraints","year":2016,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Benchmark (surveying); Machine learning; Classifier (UML); Real world data; Data mining; Artificial intelligence; Training set; Set (abstract data type); Precision and recall; Data science","score_opus":0.027060350434579963,"score_gpt":0.27945208389443577,"score_spread":0.2523917334598558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963779314","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00079116714,0.000019382394,0.9919694,0.00095844467,0.00019496393,0.00039096214,0.0004166131,0.0008964903,0.0043625403],"genre_scores_gemma":[0.985028,0.000010656328,0.01394108,0.00041307046,0.00004144952,0.000095937,0.00028519868,0.000007943654,0.0001766456],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985244,0.000055173554,0.0005476813,0.00021066071,0.00040671398,0.00025533835],"domain_scores_gemma":[0.99847823,0.00006819407,0.00054578506,0.0005983948,0.00022706103,0.00008233493],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003627354,0.00015581612,0.0001680606,0.00023838032,0.00018785868,0.00080203766,0.00069584686,0.000046906596,0.000008881848],"category_scores_gemma":[0.000049699916,0.000095662435,0.000013910818,0.00045294155,0.00012185538,0.010012187,0.00009591576,0.000080818616,0.00011541141],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020762014,0.00002218677,0.0040457644,0.00045594477,0.00001647881,0.0000061067835,0.0007226337,0.00007417647,0.0039606923,0.07779823,0.03447925,0.87839776],"study_design_scores_gemma":[0.0055073653,0.0005909478,0.026438862,0.005661537,0.000046514953,0.001094169,0.00086748606,0.31409052,0.051921196,0.0014785391,0.58864784,0.0036550236],"about_ca_topic_score_codex":0.00004615391,"about_ca_topic_score_gemma":0.0000069415933,"teacher_disagreement_score":0.98423684,"about_ca_system_score_codex":0.00010031151,"about_ca_system_score_gemma":0.00012182467,"threshold_uncertainty_score":0.77340674},"labels":[],"label_agreement":null},{"id":"W2966227831","doi":"10.5539/ijef.v11n8p101","title":"Impact of Application of Data Mining in the Lebanese Banking Sector","year":2019,"lang":"en","type":"article","venue":"International Journal of Economics and Finance","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Business; Significant difference; Banking industry; Marketing; Accounting; Statistics; Mathematics","score_opus":0.035470194177272374,"score_gpt":0.3026903625135056,"score_spread":0.26722016833623324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966227831","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9618728,0.00008698086,0.03741267,0.00028921355,0.00008499942,0.000049731192,0.000033275155,0.0000011109821,0.00016918332],"genre_scores_gemma":[0.9806837,0.00046064326,0.01878976,0.000027548907,0.000027115115,8.2079333e-7,0.000005881062,0.0000018116704,0.0000027413919],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994519,0.000013345695,0.00033600722,0.00009586832,0.000061172585,0.000041738374],"domain_scores_gemma":[0.9988615,0.000093921364,0.00061971275,0.00031578788,0.0001037314,0.000005361089],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047799095,0.00003870167,0.00010569104,0.00009791267,0.0000055082155,0.000028936563,0.0014715212,0.000018627085,0.0000021819264],"category_scores_gemma":[0.000020991174,0.000029531662,0.000026562859,0.00005516272,0.000020479358,0.0006793963,0.00012869213,0.000055159606,4.6528288e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013193043,0.0002918717,0.19300586,0.000024056078,0.00014789401,0.000005888253,0.002257918,0.0072923535,0.0064534387,0.40749454,0.0005297005,0.38236454],"study_design_scores_gemma":[0.00082618213,0.00022908296,0.39255294,0.000116401294,0.000004569903,0.00013841066,0.000059028513,0.58320695,0.0022765016,0.015946245,0.004503561,0.00014011085],"about_ca_topic_score_codex":0.00003003301,"about_ca_topic_score_gemma":0.000006353422,"teacher_disagreement_score":0.5759146,"about_ca_system_score_codex":0.00003103302,"about_ca_system_score_gemma":0.000059634574,"threshold_uncertainty_score":0.27344772},"labels":[],"label_agreement":null},{"id":"W2970232071","doi":"10.48550/arxiv.1908.11553","title":"Credit Card Fraud Detection Using Autoencoder Neural Network","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Oversampling; Autoencoder; Artificial intelligence; Artificial neural network; Computer science; Noise (video); Noise reduction; Class (philosophy); Credit card fraud; Pattern recognition (psychology); Sample (material); Machine learning; Credit card; Data mining; Bandwidth (computing); Telecommunications","score_opus":0.09316145390117792,"score_gpt":0.20648849973169567,"score_spread":0.11332704583051775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970232071","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057442423,0.00004066931,0.9380277,0.000046553916,0.00221141,0.0003948909,0.00002410757,0.0009526426,0.00085961114],"genre_scores_gemma":[0.9762773,0.000052276293,0.022649009,0.00012830988,0.00030791742,0.0000015528401,0.000034363165,0.000027152664,0.0005221501],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99763644,0.00019540996,0.00025142933,0.0013102295,0.00014432981,0.00046216638],"domain_scores_gemma":[0.9969351,0.000077869605,0.0004210222,0.0022302198,0.00021315335,0.00012263538],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028159912,0.0003438989,0.00035589127,0.00025113818,0.00020889705,0.0002130683,0.0022255394,0.0004438245,0.000014280571],"category_scores_gemma":[0.000030157025,0.00042293145,0.00019780856,0.00073723163,0.00008983615,0.00077671284,0.002275907,0.0008091544,0.000085326894],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012407011,0.000024770392,0.0017898757,0.000042408534,0.000043898348,0.000049836897,0.000051750354,0.9810923,0.0002130081,0.014673012,0.00088665733,0.001120124],"study_design_scores_gemma":[0.00015085521,0.00003122567,0.0019686853,0.000057896104,0.000041436775,0.000008053751,0.000010107135,0.98350316,0.0005225466,0.011790605,0.0014848349,0.0004305608],"about_ca_topic_score_codex":0.00023846747,"about_ca_topic_score_gemma":0.000028421819,"teacher_disagreement_score":0.91883487,"about_ca_system_score_codex":0.00046843704,"about_ca_system_score_gemma":0.00020705398,"threshold_uncertainty_score":0.99982226},"labels":[],"label_agreement":null},{"id":"W2972580158","doi":"10.1002/int.22120","title":"Synthetic minority oversampling for function approximation problems","year":2019,"lang":"en","type":"article","venue":"International Journal of Intelligent Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Oversampling; Categorical variable; Computer science; Artificial intelligence; Machine learning; Function approximation; Preprocessor; Benchmark (surveying); Function (biology); Data mining; Mathematics; Algorithm; Artificial neural network","score_opus":0.030057870587504226,"score_gpt":0.27872686520023826,"score_spread":0.24866899461273403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972580158","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003937944,0.00017858592,0.98908114,0.00035717085,0.005241145,0.00047819017,0.00001185615,0.00006210843,0.0006518819],"genre_scores_gemma":[0.976511,0.00004417958,0.022590633,0.000072804636,0.0003740405,0.000033796347,0.000016181753,0.000009475591,0.000347873],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824136,0.000052138374,0.0007381464,0.0002116129,0.0006214133,0.00013530752],"domain_scores_gemma":[0.99732137,0.00018636303,0.0008842282,0.0003019397,0.0012545493,0.0000515823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096514693,0.00011278925,0.00019005212,0.00031054686,0.000031870648,0.0002851987,0.001129527,0.000066997796,0.000013348239],"category_scores_gemma":[0.00015200068,0.000098407814,0.00013233162,0.000115876,0.000015050023,0.00091700646,0.00007020243,0.00012446281,0.000053127995],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025460275,0.00047049372,0.0043790033,0.0004139423,0.0006090858,0.000006639592,0.00094696815,0.015349237,0.05842667,0.84957105,0.006617675,0.06295463],"study_design_scores_gemma":[0.0014619984,0.0010856931,0.0013198141,0.0013073912,0.000059973885,0.00062169565,0.0005282423,0.6593852,0.066203505,0.024253527,0.24308151,0.0006914231],"about_ca_topic_score_codex":0.000014527159,"about_ca_topic_score_gemma":5.564505e-7,"teacher_disagreement_score":0.97257304,"about_ca_system_score_codex":0.00026764037,"about_ca_system_score_gemma":0.00007169138,"threshold_uncertainty_score":0.4012954},"labels":[],"label_agreement":null},{"id":"W2978485913","doi":"","title":"Instance-incremental Classification of Imbalanced Bidding Fraud Data.","year":2019,"lang":"en","type":"article","venue":"International Conference on Agents and Artificial Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Bidding; Computer science; Artificial intelligence; Data mining; Business","score_opus":0.19936906124485476,"score_gpt":0.38169879399582235,"score_spread":0.1823297327509676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2978485913","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12754512,0.000022322996,0.83814204,0.003138149,0.0013317639,0.000511471,0.00021448791,0.00020223389,0.02889243],"genre_scores_gemma":[0.9880813,0.00018518478,0.0111308405,0.00025092324,0.000045473902,0.000013308698,0.00012245652,0.0000076892065,0.00016285003],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981314,0.00004525798,0.0005374154,0.0006223992,0.0004871087,0.00017643686],"domain_scores_gemma":[0.99841034,0.00006660308,0.0003322506,0.0008981312,0.0002309815,0.0000616859],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003656955,0.00015223328,0.00017108666,0.00018310305,0.00006168715,0.00020548578,0.0019311898,0.000064905544,0.00034804092],"category_scores_gemma":[0.000090426176,0.00014613708,0.000028572887,0.00021620901,0.00009952412,0.0008799127,0.00045018588,0.00015135993,0.00016132958],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022720407,0.000088156674,0.0010639576,0.000007991943,0.000015852038,0.000001194979,0.00012794869,0.000011363149,0.037564248,0.83770764,0.00017818938,0.12321074],"study_design_scores_gemma":[0.00010694953,0.00018207157,0.0118985595,0.00020980745,0.000005886711,0.000005289434,0.00051861984,0.83517224,0.09778217,0.04837469,0.0053578396,0.00038590195],"about_ca_topic_score_codex":0.000027683089,"about_ca_topic_score_gemma":0.000011631534,"teacher_disagreement_score":0.86053616,"about_ca_system_score_codex":0.000053940115,"about_ca_system_score_gemma":0.00006247926,"threshold_uncertainty_score":0.59592974},"labels":[],"label_agreement":null},{"id":"W2980984693","doi":"10.1145/3350546.3352550","title":"Detecting Anomalous Behaviour from Textual Content in Financial Records","year":2019,"lang":"en","type":"article","venue":"IEEE/WIC/ACM International Conference on Web Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Anomaly detection; Malpractice; Deep learning; Anomaly (physics); Base (topology); Artificial intelligence; Content (measure theory); Finance; Scale (ratio); Work (physics); Machine learning; Information retrieval; Mathematics; Business; Engineering","score_opus":0.09267781734851123,"score_gpt":0.3137047356491844,"score_spread":0.22102691830067317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980984693","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67230844,0.000031720196,0.30369052,0.002021611,0.004052209,0.0007514561,0.00023103763,0.00054302433,0.016369952],"genre_scores_gemma":[0.9771883,0.00009164848,0.02060851,0.00078842056,0.0001589453,0.000102889135,0.00005119824,0.000021908476,0.000988162],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9966226,0.00013597724,0.00083904667,0.0011362333,0.0007898111,0.0004763158],"domain_scores_gemma":[0.9971305,0.0003747403,0.00039663204,0.0014416865,0.00052993145,0.00012648362],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005125587,0.00036327346,0.0003571153,0.00044795455,0.00008005444,0.00037840722,0.004466897,0.00021880223,0.0007228927],"category_scores_gemma":[0.0007603713,0.0003782798,0.0001128644,0.00041007434,0.00010588425,0.00074263813,0.00050974265,0.0006882218,0.0012777181],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027253287,0.0007624439,0.11882475,0.000021079444,0.000057937654,0.00015039819,0.0012865638,0.00015791017,0.07409491,0.49440846,0.0018865955,0.30807644],"study_design_scores_gemma":[0.0014534049,0.0014254572,0.14701346,0.0013876588,0.000020164252,0.00008409245,0.0012985079,0.31447333,0.45422605,0.068985105,0.006876128,0.0027566457],"about_ca_topic_score_codex":0.0011136906,"about_ca_topic_score_gemma":0.00052395865,"teacher_disagreement_score":0.42542335,"about_ca_system_score_codex":0.00039963904,"about_ca_system_score_gemma":0.00040691538,"threshold_uncertainty_score":0.9998669},"labels":[],"label_agreement":null},{"id":"W2986656653","doi":"10.5430/afr.v8n4p219","title":"An Analysis of Information Systems Literature: Contributions to Fraud Research","year":2019,"lang":"en","type":"article","venue":"Accounting and Finance Research","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Information system; Ranking (information retrieval); Computer science; Decision support system; Data science; Management information systems; Information science; Accounting; Knowledge management; Library science; Information retrieval; Business; Data mining; Political science","score_opus":0.030770710996368935,"score_gpt":0.3958984900208582,"score_spread":0.3651277790244893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2986656653","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66175956,0.0006687178,0.33266282,0.0013827537,0.00014903012,0.0011523488,0.00027967594,0.00017592852,0.0017691498],"genre_scores_gemma":[0.99456793,0.00021017765,0.004912469,0.000029614579,0.000025678924,0.00007889111,0.00007658199,0.0000034425793,0.00009519811],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99772495,0.00028765312,0.00031340483,0.0003211518,0.00091146555,0.00044139932],"domain_scores_gemma":[0.99548286,0.0003937586,0.00008816104,0.0010935875,0.0028881636,0.000053496766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0071237576,0.00007108021,0.00020666173,0.0018309873,0.00026522344,0.00085091277,0.0010094573,0.00010523645,0.0000020238986],"category_scores_gemma":[0.0007078049,0.00006599343,0.000028004119,0.007141394,0.000083899955,0.002310943,0.0003247945,0.0004354168,0.00006532806],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020282841,0.00007138922,0.02010754,0.000106140134,0.000051242077,0.0000013385497,0.0023009323,0.00064378,0.007067873,0.93917406,0.002728374,0.027727066],"study_design_scores_gemma":[0.0003424007,0.00044938776,0.22990985,0.00038282436,0.000015344614,0.000004584429,0.0006825178,0.67133224,0.006657305,0.0031584008,0.086731784,0.00033337332],"about_ca_topic_score_codex":0.0003367243,"about_ca_topic_score_gemma":0.000006211666,"teacher_disagreement_score":0.93601567,"about_ca_system_score_codex":0.00009832697,"about_ca_system_score_gemma":0.00012541215,"threshold_uncertainty_score":0.82053715},"labels":[],"label_agreement":null},{"id":"W2986704102","doi":"10.1080/08839514.2019.1691341","title":"Semi-supervised Classification of Fraud Data in Commercial Auctions","year":2019,"lang":"en","type":"article","venue":"Applied Artificial Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Bidding; Common value auction; Anomaly detection; Cluster analysis; Data mining; Labeled data; Supervised learning; Training set; Machine learning; Artificial intelligence; Business","score_opus":0.10580755295657046,"score_gpt":0.32962345358737943,"score_spread":0.22381590063080897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2986704102","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02805693,0.000017924527,0.96408004,0.00086062966,0.0003125518,0.000608424,0.000047655885,0.0002316096,0.0057842326],"genre_scores_gemma":[0.9588204,0.000024366049,0.040740203,0.0001377669,0.000049091366,0.000052309217,0.00013687668,0.000012101341,0.000026856846],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978887,0.000059734204,0.0007228119,0.0007136719,0.00034318608,0.00027189835],"domain_scores_gemma":[0.9966986,0.00018979884,0.0002310846,0.0027245192,0.00010014123,0.000055860568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065723807,0.00015756492,0.00024826426,0.00025214776,0.00006494252,0.0000814925,0.0028762512,0.00012392866,0.00008894238],"category_scores_gemma":[0.00007803864,0.00016999358,0.000031382446,0.0010783746,0.00012615822,0.00065636064,0.000592206,0.00025236438,0.00049293606],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013573339,0.0001668455,0.00078136986,0.000015990561,0.000004762059,4.0694908e-7,0.00034512166,0.00008375405,0.08341025,0.7259891,0.0002890582,0.18889979],"study_design_scores_gemma":[0.00010915173,0.00008363251,0.021439683,0.000065768945,0.000010597258,0.0000037916093,0.00077365513,0.42915174,0.4236463,0.11854012,0.0055381153,0.0006374215],"about_ca_topic_score_codex":0.00009148078,"about_ca_topic_score_gemma":0.00010083361,"teacher_disagreement_score":0.9307635,"about_ca_system_score_codex":0.000061717255,"about_ca_system_score_gemma":0.00010671361,"threshold_uncertainty_score":0.6932137},"labels":[],"label_agreement":null},{"id":"W2989227906","doi":"10.3233/jifs-182656","title":"Bootstrapping and multiple imputation ensemble approaches for classification problems","year":2019,"lang":"en","type":"article","venue":"Journal of Intelligent & Fuzzy Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Toronto Rehabilitation Institute","funders":"","keywords":"Imputation (statistics); Missing data; Bootstrapping (finance); Computer science; Ensemble learning; Statistics; Classifier (UML); Artificial intelligence; Data mining; Econometrics; Machine learning; Mathematics","score_opus":0.08382729232445184,"score_gpt":0.27538636301930974,"score_spread":0.1915590706948579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2989227906","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019010743,0.000660968,0.97795254,0.0003196152,0.0006252898,0.00092894194,0.0000048799666,0.000066555054,0.00043048363],"genre_scores_gemma":[0.9772947,0.00011202662,0.022257453,0.000026334128,0.00011794114,0.000033014254,0.00000903213,0.000013492038,0.00013604248],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99831545,0.00008694411,0.00081602327,0.0002683057,0.00031723952,0.00019601198],"domain_scores_gemma":[0.99792254,0.00024526822,0.0009869324,0.00036150045,0.00039816342,0.0000855674],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011731085,0.00014040779,0.00027953743,0.00025994016,0.00006770297,0.0002969487,0.0005199243,0.00009437054,6.815063e-7],"category_scores_gemma":[0.00010863899,0.00011827433,0.00008659477,0.00020581376,0.000025215091,0.0008719551,0.0000509632,0.00014527455,0.000011351103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019826936,0.0006579631,0.025548697,0.002799041,0.00043232736,0.0000063205875,0.0067474623,0.022507517,0.2895423,0.41079533,0.007209633,0.23355514],"study_design_scores_gemma":[0.00057471904,0.00055701134,0.0030973635,0.00043363418,0.000021025267,0.00020925145,0.0012419199,0.9538614,0.02038372,0.0051872195,0.0141180195,0.00031469553],"about_ca_topic_score_codex":0.000008353689,"about_ca_topic_score_gemma":0.0000010188195,"teacher_disagreement_score":0.9582839,"about_ca_system_score_codex":0.00012023197,"about_ca_system_score_gemma":0.00007983438,"threshold_uncertainty_score":0.48230872},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.06413411072449375,"score_gpt":0.30277672764797725,"score_spread":0.23864261692348349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2999309192","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61752445,0.0002588032,0.37800395,0.0027383498,0.00019177521,0.0010323209,0.000015045968,0.000065903696,0.00016941577],"genre_scores_gemma":[0.9921369,0.00013896241,0.007411905,0.00020666987,0.000019725827,0.000047320587,0.000016087468,0.000007645372,0.000014815819],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987971,0.00019939303,0.00033836736,0.0002712177,0.00027740336,0.00011647211],"domain_scores_gemma":[0.998624,0.0002963247,0.00034331178,0.0006099952,0.00009703809,0.000029292742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007043112,0.00009019958,0.00009152911,0.000043158227,0.00013551519,0.00008727822,0.00065832183,0.000051661154,0.0000025846748],"category_scores_gemma":[0.0004460215,0.00006166106,0.000028560906,0.0003615876,0.00008994603,0.00027291986,0.00025907613,0.00011578562,0.000006102528],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016876866,0.00025290225,0.2719513,0.00016407394,0.000022784932,7.3836327e-7,0.011087177,0.022182241,0.28371543,0.19647112,0.004517326,0.20946614],"study_design_scores_gemma":[0.00017281425,0.000019640796,0.38632214,0.000011945057,0.000004903224,9.225787e-7,0.00009704454,0.6071351,0.0038571078,0.0008521849,0.0014672051,0.00005895816],"about_ca_topic_score_codex":0.000011362233,"about_ca_topic_score_gemma":0.00002783892,"teacher_disagreement_score":0.5849529,"about_ca_system_score_codex":0.00011398031,"about_ca_system_score_gemma":0.00016181439,"threshold_uncertainty_score":0.25144652},"labels":[],"label_agreement":null},{"id":"W3000555836","doi":"10.1016/j.knosys.2020.105534","title":"GEV-NN: A deep neural network architecture for class imbalance problem in binary classification","year":2020,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Microsoft (Canada)","funders":"Ministry of Science ICT and Future Planning; National Research Foundation of Korea","keywords":"Computer science; Component (thermodynamics); Artificial intelligence; Binary classification; Artificial neural network; Class (philosophy); Binary number; Deep learning; Gumbel distribution; Set (abstract data type); Architecture; Encoder; Machine learning; Pattern recognition (psychology); Support vector machine; Mathematics; Extreme value theory; Statistics","score_opus":0.036509853854062295,"score_gpt":0.27218487379926004,"score_spread":0.23567501994519774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3000555836","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00093686936,0.0012671854,0.9863531,0.005918547,0.0006427404,0.0024447804,0.000038911137,0.0011092738,0.0012885727],"genre_scores_gemma":[0.9392939,0.000006598572,0.057351004,0.00067318196,0.00061348896,0.0017703626,0.0001534167,0.000051741114,0.00008630474],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966674,0.00043372856,0.0008347383,0.0010688396,0.00030915102,0.0006861443],"domain_scores_gemma":[0.99758184,0.00039003667,0.00041315123,0.0011052581,0.00027944418,0.00023027278],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00074523716,0.00036950468,0.0005086016,0.00020992276,0.00018028637,0.0002839188,0.0017502069,0.00023556179,0.0000025768875],"category_scores_gemma":[0.00014194132,0.00035635193,0.00013787061,0.0015598265,0.00008645989,0.00039431252,0.00016672147,0.00040453684,0.000067406065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009431551,0.001713634,0.028614804,0.0072350665,0.00016111256,0.00008665668,0.007286091,0.2366592,0.10159008,0.30193898,0.18857148,0.12519974],"study_design_scores_gemma":[0.0008664532,0.0002480172,0.002145729,0.000166593,0.0000073123947,0.0000061317137,0.000039013128,0.9391878,0.0006827575,0.00053149334,0.055718727,0.0003999452],"about_ca_topic_score_codex":0.000012742496,"about_ca_topic_score_gemma":0.000040048297,"teacher_disagreement_score":0.93835706,"about_ca_system_score_codex":0.0002360752,"about_ca_system_score_gemma":0.00023822476,"threshold_uncertainty_score":0.99988884},"labels":[],"label_agreement":null},{"id":"W3001278818","doi":"10.1109/dsaa.2019.00034","title":"A Study on the Impact of Data Characteristics in Imbalanced Regression Tasks","year":2019,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Regression; Regression analysis; Artificial intelligence; Machine learning; Statistics; Mathematics","score_opus":0.08241202041512183,"score_gpt":0.3719947321635921,"score_spread":0.2895827117484703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3001278818","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9748356,0.0000033522297,0.021338928,0.0004122069,0.000068466245,0.00078666286,0.00006300845,0.00012828759,0.0023635216],"genre_scores_gemma":[0.9967402,0.0000051437164,0.0030134511,0.000066691144,0.000006553213,0.000014174752,0.000033905893,0.000005165121,0.000114688744],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99886507,0.00011705294,0.00027643816,0.00036538058,0.00023352567,0.00014253658],"domain_scores_gemma":[0.99620676,0.00017248317,0.00018526915,0.0033674065,0.000045502464,0.000022577125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066005526,0.00010440237,0.00018355549,0.00009083198,0.000020354924,0.000051524992,0.0026458548,0.000033515887,0.000037293987],"category_scores_gemma":[0.00010548191,0.000053807846,0.000022742055,0.00036328097,0.000020110403,0.00047041057,0.0007217013,0.00014193458,0.000060417726],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010804193,0.0023386476,0.83793473,0.000019368645,0.00005561737,0.000016947413,0.002016796,0.0000061140777,0.046132214,0.049198147,0.019923687,0.042249687],"study_design_scores_gemma":[0.00035868338,0.00036703676,0.97713315,0.000050093324,0.0000011687385,0.0000015399345,0.00010941393,0.01824763,0.0031292934,0.00041604083,0.0000802278,0.000105702864],"about_ca_topic_score_codex":0.00007356036,"about_ca_topic_score_gemma":0.000003414174,"teacher_disagreement_score":0.13919844,"about_ca_system_score_codex":0.000043994074,"about_ca_system_score_gemma":0.00006146298,"threshold_uncertainty_score":0.49167007},"labels":[],"label_agreement":null},{"id":"W3011219038","doi":"10.1109/ai4i46381.2019.00030","title":"Short Paper: Credit Card Fraud Detection using LightGBM with Asymmetric Error Control","year":2019,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Credit card; Credit card fraud; Computer science; Constant false alarm rate; False alarm; Confidentiality; Control (management); Error detection and correction; Computer security; Word error rate; Data mining; ALARM; Artificial intelligence; Algorithm; Engineering; World Wide Web","score_opus":0.01558655689854913,"score_gpt":0.24563548575864183,"score_spread":0.2300489288600927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011219038","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024534373,0.000027834029,0.96756536,0.00023326375,0.00029585251,0.00043678534,0.000006019169,0.00076284056,0.0061376537],"genre_scores_gemma":[0.917603,0.0000042077622,0.08160318,0.0004121993,0.00006495945,0.000025934698,0.0000041278654,0.000014310848,0.00026809264],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855125,0.00005309376,0.00022647667,0.00049749913,0.00039639146,0.00027527168],"domain_scores_gemma":[0.99858224,0.00007395685,0.00008574095,0.001010078,0.00016845841,0.00007949699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000256614,0.00016052433,0.00020597338,0.0002823817,0.00009048921,0.00016671538,0.00067883113,0.00009816408,0.000025149056],"category_scores_gemma":[0.000029453739,0.00012434328,0.000046245936,0.00095408974,0.000028696812,0.0011673789,0.00009207203,0.000158345,0.000120508],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015933141,0.00037600743,0.0693179,0.00010687733,0.00027316218,0.00003892103,0.0003345386,0.0009874554,0.41047058,0.058929723,0.0043872143,0.4546183],"study_design_scores_gemma":[0.0013313796,0.00073911477,0.07461279,0.000056561188,0.000051057315,0.00012944338,0.00006620216,0.55052865,0.33464602,0.00060326856,0.036201347,0.0010341532],"about_ca_topic_score_codex":0.00008440413,"about_ca_topic_score_gemma":0.000020057105,"teacher_disagreement_score":0.8930686,"about_ca_system_score_codex":0.00012468266,"about_ca_system_score_gemma":0.000058803882,"threshold_uncertainty_score":0.5070572},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"European Social Fund; Magyarország Kormánya","keywords":"Computer science; Algorithm; Sampling (signal processing); Detector; Telecommunications","score_opus":0.060195940013745536,"score_gpt":0.3177182528903892,"score_spread":0.2575223128766436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013276295","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005661537,0.00001378261,0.9927079,0.0031164214,0.00025925576,0.0005055277,0.00005595794,0.0013099227,0.0014650839],"genre_scores_gemma":[0.66808206,0.000010197763,0.32661688,0.004803022,0.0002311005,0.00019599132,0.000016070253,0.000026937303,0.00001773866],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99787015,0.00010865541,0.00034656114,0.00082469353,0.00047279146,0.00037712348],"domain_scores_gemma":[0.9979583,0.00024287732,0.00020677097,0.001284817,0.00011035945,0.00019685882],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031374447,0.00026553604,0.0002636491,0.00015696975,0.00015718878,0.00052809675,0.003162108,0.00014795682,0.000039508057],"category_scores_gemma":[0.00016175407,0.00026057998,0.00009196206,0.00080046465,0.00006684001,0.0010171458,0.00029046103,0.00036375577,0.000071780705],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000090899644,0.001012247,0.0037896798,0.00041640556,0.00006680464,0.00016367038,0.00045691882,0.0014565873,0.114917785,0.03135382,0.01835788,0.8279173],"study_design_scores_gemma":[0.00039247377,0.00021918736,0.0044475133,0.00010602757,0.000014040803,0.00000884635,0.0000049258574,0.4872396,0.48660764,0.0039396645,0.016300814,0.0007192672],"about_ca_topic_score_codex":0.000057357385,"about_ca_topic_score_gemma":0.0000017997272,"teacher_disagreement_score":0.827198,"about_ca_system_score_codex":0.0000955764,"about_ca_system_score_gemma":0.00011013267,"threshold_uncertainty_score":0.9999846},"labels":[],"label_agreement":null},{"id":"W3013316335","doi":"10.29007/h71z","title":"On relationships between imbalance and overlapping of datasets","year":2020,"lang":"en","type":"article","venue":"EPiC series in computing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; King Abdulaziz City for Science and Technology","keywords":"Support vector machine; Computer science; Precision and recall; Decision tree; Artificial intelligence; Data mining; Machine learning; Recall; k-nearest neighbors algorithm; Pattern recognition (psychology)","score_opus":0.05639342327698976,"score_gpt":0.2835915093782327,"score_spread":0.22719808610124292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013316335","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16275787,0.000077281846,0.8313447,0.0043281703,0.00008851292,0.00019444955,0.000054237258,0.0002848907,0.0008698624],"genre_scores_gemma":[0.9019071,0.0000069961184,0.097840525,0.00016731267,0.00003649841,0.0000016240068,0.00003369065,0.000004452423,0.0000017977104],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.999016,0.000103218474,0.00030368072,0.00030425147,0.00013736055,0.00013548743],"domain_scores_gemma":[0.99893695,0.00046824798,0.00015568962,0.00037304213,0.000019429239,0.000046646976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037108126,0.00008551565,0.00017022404,0.00006399094,0.000071989365,0.00004150329,0.00048638813,0.000043715772,0.0000020483244],"category_scores_gemma":[0.00056999014,0.00009273428,0.000012184257,0.0003919026,0.000059828726,0.0003938381,0.00035766116,0.00022273244,0.0000036215931],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023730081,0.000045845383,0.33224043,0.00022741828,0.000024439354,0.00001781096,0.008971783,0.00058848923,0.0025849768,0.59945273,0.0037123852,0.05210996],"study_design_scores_gemma":[0.00060658966,0.00025732393,0.84355277,0.00038293176,0.0000047935573,0.000010804634,0.00035327248,0.11230428,0.009860438,0.028298937,0.0038952257,0.000472637],"about_ca_topic_score_codex":0.000005001274,"about_ca_topic_score_gemma":7.811503e-7,"teacher_disagreement_score":0.7391492,"about_ca_system_score_codex":0.000020163878,"about_ca_system_score_gemma":0.000020042306,"threshold_uncertainty_score":0.3781594},"labels":[],"label_agreement":null},{"id":"W3025289572","doi":"10.1007/s00500-020-05023-2","title":"A design of information granule-based under-sampling method in imbalanced data classification","year":2020,"lang":"en","type":"article","venue":"Soft Computing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Support vector machine; Classifier (UML); Exploit; Artificial intelligence; Sampling (signal processing); Machine learning; Data mining; k-nearest neighbors algorithm; Oversampling; Suite; Data sampling; Pattern recognition (psychology); Bandwidth (computing)","score_opus":0.16694046794543763,"score_gpt":0.354027070377746,"score_spread":0.18708660243230837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3025289572","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002516599,0.000016552389,0.997121,0.0016367296,0.00006440496,0.0003708489,0.000015481986,0.00045800256,0.00006533508],"genre_scores_gemma":[0.42441526,0.0000013371892,0.57478803,0.00062629464,0.000016065702,0.000005051736,0.00014248301,0.0000052172977,2.3330732e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99809384,0.0002434633,0.0006826694,0.00043132075,0.0003102625,0.00023842901],"domain_scores_gemma":[0.9976024,0.00062100164,0.0005051637,0.0010660933,0.00014036812,0.000064987624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013963617,0.0001436237,0.00024072122,0.00019239727,0.000075646465,0.00012775419,0.0020091252,0.00007980884,0.0000017246094],"category_scores_gemma":[0.00052334485,0.00015576949,0.000025579544,0.0010565498,0.000034079247,0.0013863071,0.00046865566,0.00020759304,0.000012582948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008913013,0.00015936077,0.0027056525,0.00038188614,0.000028947332,0.000002200035,0.0037318158,0.26376674,0.07674161,0.06891296,0.00084713096,0.5826326],"study_design_scores_gemma":[0.0003892819,0.00003697332,0.0029978866,0.000058856145,0.0000032560906,0.0000010731233,0.000079846555,0.98766,0.007001875,0.0013755191,0.00024355331,0.00015189114],"about_ca_topic_score_codex":0.000014735807,"about_ca_topic_score_gemma":6.656615e-7,"teacher_disagreement_score":0.7238933,"about_ca_system_score_codex":0.000064339634,"about_ca_system_score_gemma":0.00019192313,"threshold_uncertainty_score":0.63520956},"labels":[],"label_agreement":null},{"id":"W3034271075","doi":"10.1145/3262579","title":"Session details: Special issue on learning from imbalanced datasets","year":2004,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Canadian Imperial Bank of Commerce (Canada)","funders":"","keywords":"Computer science; Session (web analytics); Machine learning; Data science; Artificial intelligence; World Wide Web","score_opus":0.037927200654235056,"score_gpt":0.28477606922886783,"score_spread":0.24684886857463278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034271075","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008008929,0.00001909062,0.93825734,0.0492662,0.000906585,0.00045813186,0.00014218275,0.001169885,0.0017716504],"genre_scores_gemma":[0.33378574,0.00012588402,0.61442584,0.031592593,0.011213247,0.0005770806,0.007502315,0.00010983858,0.00066744816],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978307,0.00014420498,0.00041863022,0.00078070234,0.00046153206,0.00036425228],"domain_scores_gemma":[0.99700755,0.00020817386,0.00020683609,0.002386504,0.0000756632,0.000115254894],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017711539,0.00026920903,0.00022633285,0.00021089085,0.00039545968,0.00042112335,0.0019409466,0.00013222104,0.00024671253],"category_scores_gemma":[0.00044308105,0.00025750464,0.000064150125,0.00054518937,0.00006758717,0.0023621344,0.0005267443,0.00045053763,0.0031942427],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039706847,0.00037079683,0.0006314472,0.000009276623,0.000044778513,0.00007641559,0.0025817913,0.0023420579,0.07868935,0.018976783,0.8267455,0.06949207],"study_design_scores_gemma":[0.0010959075,0.00018588266,0.0026257725,0.00010546145,0.000014621241,0.000006345567,0.00013356697,0.001201242,0.16474563,0.021924723,0.8072844,0.00067641435],"about_ca_topic_score_codex":0.000050483555,"about_ca_topic_score_gemma":0.000025475565,"teacher_disagreement_score":0.3257768,"about_ca_system_score_codex":0.00016118966,"about_ca_system_score_gemma":0.00008072608,"threshold_uncertainty_score":0.9999877},"labels":[],"label_agreement":null},{"id":"W3037068030","doi":"10.5539/mas.v14n7p92","title":"Analysis of Resampling Techniques on Predictive Performance of Credit Card Classification","year":2020,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Oversampling; Credit card fraud; Credit card; Resampling; Computer science; Database transaction; Sampling (signal processing); Machine learning; Data mining; Artificial intelligence; Database; World Wide Web; Telecommunications","score_opus":0.045067336965744796,"score_gpt":0.2771217666787532,"score_spread":0.2320544297130084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037068030","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04156495,0.000006558982,0.95243806,0.00025997107,0.000025055548,0.00028869632,0.00003861669,0.0003356654,0.005042408],"genre_scores_gemma":[0.92264843,0.000017171726,0.07707855,0.000159579,0.000017382377,0.000056294815,0.000012101193,0.0000061446303,0.0000043352666],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976287,0.000022453129,0.00046000912,0.0007325586,0.00092020637,0.00023608972],"domain_scores_gemma":[0.9979917,0.000079408266,0.00044129012,0.0010676114,0.00031554047,0.000104440915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074278034,0.00013856214,0.00032448128,0.0005789015,0.00013213554,0.000053474178,0.0021752915,0.00006290259,0.0000024034873],"category_scores_gemma":[0.000108361724,0.00013177848,0.00006647849,0.004181451,0.0005088239,0.00052356266,0.00030847805,0.00015238591,0.0000034945658],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003907465,0.000047834837,0.0010094633,0.000023619004,0.000030470643,1.338221e-7,0.0011584444,0.0013528082,0.935091,0.029268723,0.00005802786,0.031920377],"study_design_scores_gemma":[0.000033971643,0.000101250516,0.010870981,0.000009647812,0.000022397875,9.97483e-8,0.000020128286,0.5868629,0.40164143,0.0003037828,0.00005593026,0.00007746629],"about_ca_topic_score_codex":0.0000061487376,"about_ca_topic_score_gemma":4.7687973e-7,"teacher_disagreement_score":0.8810835,"about_ca_system_score_codex":0.00008994516,"about_ca_system_score_gemma":0.00017530477,"threshold_uncertainty_score":0.537377},"labels":[],"label_agreement":null},{"id":"W3037111244","doi":"","title":"Chunk-Based Incremental Classification of Fraud Data.","year":2020,"lang":"en","type":"article","venue":"The Florida AI Research Society","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Data mining","score_opus":0.2962385762875277,"score_gpt":0.4244676871028474,"score_spread":0.12822911081531968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037111244","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054985047,0.000101781516,0.90845835,0.083598934,0.00011652281,0.00074139115,0.00018722903,0.00041435484,0.00088292954],"genre_scores_gemma":[0.9534198,0.00007589968,0.04349125,0.0024063534,0.00024429327,0.00007463535,0.00023085017,0.00001558438,0.00004131788],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970812,0.00037712645,0.00031613212,0.0005664631,0.0012866909,0.00037237073],"domain_scores_gemma":[0.996389,0.00039670122,0.000121215766,0.0025771523,0.00039135836,0.00012461917],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0031989804,0.00011478257,0.00015251554,0.00003988667,0.00032614262,0.00016505267,0.005650324,0.00008163593,0.000035657606],"category_scores_gemma":[0.00042626602,0.00008685022,0.000079784215,0.0013632698,0.00045304943,0.00074942457,0.0016348617,0.00064278627,0.00008783609],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033336142,0.000120963654,0.0010191931,0.000117556505,0.00005349544,0.000001453313,0.002309082,0.000019255152,0.21008936,0.056744423,0.7164165,0.013075419],"study_design_scores_gemma":[0.0004668695,0.0001724733,0.008033062,0.00002820928,0.0000069002235,9.819266e-7,0.00050374167,0.7722769,0.14376774,0.0017916237,0.07274704,0.00020447363],"about_ca_topic_score_codex":0.000052937103,"about_ca_topic_score_gemma":0.0000020983896,"teacher_disagreement_score":0.94792134,"about_ca_system_score_codex":0.00010678041,"about_ca_system_score_gemma":0.00038567523,"threshold_uncertainty_score":0.9997296},"labels":[],"label_agreement":null},{"id":"W3041134523","doi":"10.1080/17517575.2020.1790043","title":"Valuing free-form text data from maintenance logs through transfer learning with CamemBERT","year":2020,"lang":"en","type":"article","venue":"Enterprise Information Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Exploit; Transfer of learning; Artificial intelligence; Machine learning; Scheduling (production processes); Engineering","score_opus":0.03381081355604557,"score_gpt":0.24673173730660453,"score_spread":0.21292092375055896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041134523","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019555595,0.00006536337,0.98867536,0.0011881342,0.00022746305,0.00047286894,0.0002357242,0.00091330195,0.0062662037],"genre_scores_gemma":[0.9681695,0.000053240015,0.029151486,0.0015344871,0.000109522145,0.00007393657,0.0008129335,0.000017260698,0.0000775986],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997909,0.00008874078,0.00070245453,0.00039796796,0.00060419244,0.00029764825],"domain_scores_gemma":[0.99766874,0.00009258762,0.00026643192,0.0016834794,0.00017299863,0.00011573289],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034164632,0.00022183103,0.000269354,0.00007050446,0.00015408534,0.00066265726,0.00286414,0.00008799947,0.00002132877],"category_scores_gemma":[0.00015151505,0.00018284055,0.000035591773,0.00039955796,0.00004675172,0.010785859,0.00053995405,0.00031802515,0.0004504833],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076377345,0.0002813554,0.023902893,0.001724442,0.00080993597,0.0001259564,0.2655079,0.014142239,0.005175533,0.13588898,0.44795072,0.103726245],"study_design_scores_gemma":[0.0010876536,0.00013431323,0.00065108744,0.00043152182,0.000014348167,0.000040977156,0.0017456382,0.57348675,0.0013886016,0.000111239206,0.42042828,0.00047960633],"about_ca_topic_score_codex":0.0003711245,"about_ca_topic_score_gemma":0.000007044412,"teacher_disagreement_score":0.966214,"about_ca_system_score_codex":0.00008956652,"about_ca_system_score_gemma":0.000085250846,"threshold_uncertainty_score":0.7819487},"labels":[],"label_agreement":null},{"id":"W3046322697","doi":"10.11159/mvml20.107","title":"Taxonomy of Modelling Strategies for Handling Imbalanced Datasets","year":2020,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Taxonomy (biology); Artificial intelligence; Data science; Machine learning; Data mining; Ecology; Biology","score_opus":0.025623809334562316,"score_gpt":0.2267311871030607,"score_spread":0.20110737776849838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046322697","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01766291,0.00018721522,0.9810873,0.00027194666,0.00024536694,0.0003941295,0.000012979347,0.00009529708,0.000042845724],"genre_scores_gemma":[0.9622361,0.000013457318,0.037600216,0.000046581008,0.000051361138,0.000039504826,4.69326e-7,0.0000045611273,0.000007751104],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989831,0.0000024408382,0.00025417772,0.0003567253,0.0002035903,0.00019995707],"domain_scores_gemma":[0.9993661,0.00008661282,0.00017468995,0.00013658576,0.0001518738,0.000084151965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029435495,0.000114787166,0.00022388899,0.0001278955,0.00010599171,0.00027396774,0.0008757026,0.000022627199,3.6467043e-8],"category_scores_gemma":[0.000033852048,0.000084837084,0.000025546842,0.0007302962,0.0001047128,0.00049586676,0.000211882,0.0001028339,4.7005244e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002026644,0.000026450005,0.00023117496,0.0004704671,0.00001704701,1.7120125e-7,0.00015686963,0.037067976,0.030213611,0.92521423,0.0008755501,0.0057062046],"study_design_scores_gemma":[0.00013380054,0.0001002577,0.00007283048,0.00014070359,0.0000033752704,0.0000025349384,0.0000066821867,0.9818145,0.016127905,0.00012422532,0.0013765517,0.000096657765],"about_ca_topic_score_codex":0.000004651942,"about_ca_topic_score_gemma":6.880091e-8,"teacher_disagreement_score":0.9447465,"about_ca_system_score_codex":0.000013154294,"about_ca_system_score_gemma":0.000042982847,"threshold_uncertainty_score":0.34595558},"labels":[],"label_agreement":null},{"id":"W3089158044","doi":"10.1007/s11548-020-02260-6","title":"Assessing and mitigating the effects of class imbalance in machine learning with application to X-ray imaging","year":2020,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University; Ontario Institute for Cancer Research; University of Toronto","funders":"","keywords":"Undersampling; Oversampling; Artificial intelligence; Machine learning; Computer science; Class (philosophy); Random forest; Convolutional neural network; Set (abstract data type); Pattern recognition (psychology); Data mining","score_opus":0.010023889547965447,"score_gpt":0.25633959272938545,"score_spread":0.24631570318142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089158044","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20602396,0.0003094037,0.7840157,0.009418706,0.00014047581,0.000062334264,5.722604e-7,0.00001855916,0.000010266577],"genre_scores_gemma":[0.9557629,0.000067157176,0.042633906,0.0014264379,0.000097085205,0.0000045270567,0.0000027032095,0.0000046420655,6.456825e-7],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989125,0.00023397562,0.00039894113,0.00017534815,0.00017923802,0.00009998298],"domain_scores_gemma":[0.9978397,0.0013811418,0.00044398187,0.00009353741,0.00018453159,0.00005711934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057340064,0.00008872449,0.00024225861,0.00017328437,0.000046268502,0.00010381517,0.00038957957,0.000031451815,3.4226974e-7],"category_scores_gemma":[0.00020544934,0.00006287176,0.000031725296,0.0001852153,0.000085062165,0.00038153716,0.00011524771,0.00025907453,2.1200408e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000085775464,0.000049756796,0.6369231,0.00006531431,0.00011977637,0.00015386095,0.0010900975,0.0011483256,0.028929142,0.0019046727,0.00041118258,0.32911903],"study_design_scores_gemma":[0.00045701335,0.00012795403,0.75311184,0.00034008824,0.000009620039,0.0008560408,0.000038255985,0.24146302,0.001892978,0.00018900892,0.0013735463,0.00014062438],"about_ca_topic_score_codex":0.000005397425,"about_ca_topic_score_gemma":8.429321e-7,"teacher_disagreement_score":0.74973893,"about_ca_system_score_codex":0.000024356197,"about_ca_system_score_gemma":0.00004356281,"threshold_uncertainty_score":0.2563836},"labels":[],"label_agreement":null},{"id":"W3091395179","doi":"10.1109/icbaie49996.2020.00045","title":"A Deep Neural Network Algorithm for Detecting Credit Card Fraud","year":2020,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Credit card fraud; Credit card; Skew; Database transaction; Artificial neural network; Support vector machine; Transaction data; Artificial intelligence; Government (linguistics); Algorithm; Deep learning; Machine learning; Data mining; Payment; Database; Telecommunications","score_opus":0.03341336381342805,"score_gpt":0.2654842006236173,"score_spread":0.23207083681018922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091395179","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000035620295,0.000044037257,0.9946886,0.0028210008,0.00027184378,0.000292652,0.000005825464,0.0012221126,0.0006183128],"genre_scores_gemma":[0.04547552,0.000002820352,0.9503405,0.0033722227,0.0006538543,0.00009064896,0.000011722728,0.000012423102,0.000040262148],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988961,0.00003018576,0.00020633376,0.00040442063,0.00015895556,0.0003040075],"domain_scores_gemma":[0.9991552,0.00013359866,0.00008331968,0.0004236317,0.000089905494,0.000114312716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016394889,0.000112016874,0.0001395783,0.00002434766,0.00013822778,0.00015912829,0.0008934144,0.00005637585,0.000009503571],"category_scores_gemma":[0.00010843546,0.00010563998,0.000064021224,0.00036997566,0.000019405872,0.0004242393,0.00025001736,0.000117520394,0.000022451819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025377103,0.0000071562135,0.000060345024,0.000008466275,0.000009361096,0.0000027953295,0.00018488603,0.00036832143,0.00047417928,0.0070433593,0.021209482,0.9706291],"study_design_scores_gemma":[0.00012270268,0.000090334346,0.00010759876,0.0000024704727,0.0000029488763,0.000003851659,0.00001636346,0.97253764,0.0053494982,0.001315589,0.020316185,0.0001348032],"about_ca_topic_score_codex":0.000009328932,"about_ca_topic_score_gemma":0.0000034155526,"teacher_disagreement_score":0.97216934,"about_ca_system_score_codex":0.000023245744,"about_ca_system_score_gemma":0.000021064712,"threshold_uncertainty_score":0.43078732},"labels":[],"label_agreement":null},{"id":"W3103349515","doi":"10.6084/m9.figshare.8281412.v1","title":"BUILDING HIGH-QUALITY AUCTION FRAUD DATASET","year":2019,"lang":"en","type":"article","venue":"Figshare","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Unavailability; Bidding; Quality (philosophy); Common value auction; USable; Computer security; Paillier cryptosystem; Artificial intelligence; World Wide Web; Business; Reliability engineering","score_opus":0.05053754155162595,"score_gpt":0.3279106271843663,"score_spread":0.2773730856327404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3103349515","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00043412735,0.00003310592,0.08792498,0.00054827915,0.00030287236,0.0004662348,0.90742576,0.0012887405,0.001575874],"genre_scores_gemma":[0.1241028,0.000001522351,0.1245002,0.0017027546,0.00014651538,0.00018770137,0.7490649,0.000019384743,0.0002741796],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99900174,0.000050109196,0.00017229399,0.0003823759,0.00022359235,0.00016986295],"domain_scores_gemma":[0.9984605,0.00007907701,0.00013130713,0.001215101,0.00006679292,0.00004723302],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00011191207,0.00009161668,0.000101941645,0.000063089436,0.000054275097,0.00015024742,0.0010329451,0.000066775014,0.021134535],"category_scores_gemma":[0.00027587375,0.000092036615,0.000023096987,0.00024719205,0.000003030036,0.0010021952,0.00040035107,0.00012245981,0.0072670365],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.578384e-7,0.000013728736,0.00001998201,0.0000409505,0.0000029364069,0.0000010930177,0.000010587004,0.000007289885,0.002602723,0.015118594,0.97593427,0.006246877],"study_design_scores_gemma":[0.0001207216,0.000021670856,0.009294325,0.00017090511,8.289017e-7,0.0000044898725,0.0000021414592,0.0018995383,0.035881866,0.0021483616,0.9502447,0.00021044299],"about_ca_topic_score_codex":0.000014531616,"about_ca_topic_score_gemma":9.2591534e-7,"teacher_disagreement_score":0.15836084,"about_ca_system_score_codex":0.000052227202,"about_ca_system_score_gemma":0.000034368102,"threshold_uncertainty_score":0.9935059},"labels":[],"label_agreement":null},{"id":"W3108553613","doi":"10.16929/ajas/2020.451.245","title":"A Supervised Hybrid Statistical Catch-Up System Built on GABECE Gambian Data","year":2020,"lang":"en","type":"article","venue":"African Journal of Applied Statistics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trusted Positioning (Canada)","funders":"","keywords":"Modal; Statistical learning; Statistical analysis; Computer science; Process (computing); Statistical hypothesis testing; Machine learning; Artificial intelligence; Mathematics education; Statistics; Psychology; Mathematics","score_opus":0.0627426612524957,"score_gpt":0.28413796665457236,"score_spread":0.22139530540207666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108553613","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022388785,0.00001865036,0.9933132,0.0013918503,0.00023487747,0.00021855102,0.0031182198,0.00016490143,0.0013158795],"genre_scores_gemma":[0.54610586,0.000013860577,0.45282522,0.0007589791,0.00012707527,0.000005140272,0.00013548156,0.000021706655,0.0000067147894],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99709475,0.00011947746,0.0009468871,0.0005481463,0.0009046652,0.0003860568],"domain_scores_gemma":[0.99651784,0.00060824794,0.0006876855,0.001385463,0.00030225128,0.0004984979],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006363867,0.00025741017,0.0005198882,0.00013551845,0.00012076394,0.00025585215,0.003597951,0.000049734215,0.0000240336],"category_scores_gemma":[0.00041907624,0.00023825883,0.000034083372,0.00042005442,0.00013534745,0.00031862457,0.000494382,0.0005010615,0.00009419327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020504066,0.00011122665,0.000022821127,0.0001364049,0.00007846838,0.00040510308,0.0009238351,0.000060674276,0.0015238286,0.6829215,0.2646392,0.04897189],"study_design_scores_gemma":[0.0054314705,0.0037241108,0.001981589,0.0003508816,0.00037783146,0.0007794395,0.0038103324,0.79277337,0.016100623,0.02559162,0.14670749,0.0023712316],"about_ca_topic_score_codex":0.000009291142,"about_ca_topic_score_gemma":0.0000016617192,"teacher_disagreement_score":0.7927127,"about_ca_system_score_codex":0.00014487568,"about_ca_system_score_gemma":0.0003946522,"threshold_uncertainty_score":0.9715913},"labels":[],"label_agreement":null},{"id":"W3112067326","doi":"10.1186/s12911-020-01356-y","title":"Explanation and prediction of clinical data with imbalanced class distribution based on pattern discovery and disentanglement","year":2021,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Computer science; Class (philosophy); Set (abstract data type); Machine learning; Artificial intelligence; Data mining; Notice; Data set; Data science","score_opus":0.07022578411285324,"score_gpt":0.36168835709779124,"score_spread":0.291462572984938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112067326","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045588173,0.000032895463,0.95373595,0.000096923475,0.00009500887,0.000112479465,0.00024860958,0.00003442698,0.000055553468],"genre_scores_gemma":[0.77429086,0.00025122354,0.2244901,0.00038466448,0.000025743679,0.0000067101946,0.00054610166,0.0000032842918,0.0000013031741],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981478,0.00006181005,0.0007224109,0.00024146697,0.00072104053,0.00010547103],"domain_scores_gemma":[0.99797666,0.00090457307,0.00030663767,0.00062596024,0.00008440414,0.0001017618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010886483,0.0000944403,0.00019979019,0.0000519419,0.0000710685,0.00018151825,0.00026626958,0.00008294758,0.000003938793],"category_scores_gemma":[0.000566515,0.00006881225,0.000014065978,0.00014528455,0.000091316295,0.00083508657,0.00046629988,0.00012558812,3.8502074e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006964864,0.00009727047,0.039171968,0.00014819644,0.000009698352,0.000005797254,0.00006939987,0.000024607145,0.0000061557553,0.004804675,0.0013949787,0.9541976],"study_design_scores_gemma":[0.0007931706,0.000114421855,0.048645604,0.0005551847,0.0000083902805,0.000015196297,0.000114758615,0.9485673,0.00007549311,0.00051110203,0.00052737055,0.0000720634],"about_ca_topic_score_codex":0.0000011944517,"about_ca_topic_score_gemma":0.000011728571,"teacher_disagreement_score":0.9541255,"about_ca_system_score_codex":0.00001537301,"about_ca_system_score_gemma":0.00013799469,"threshold_uncertainty_score":0.2806082},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.046809380387112055,"score_gpt":0.30194309305301315,"score_spread":0.25513371266590107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3113150236","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014577112,0.00025621406,0.96679854,0.016169067,0.00017423813,0.00031922146,0.0000016626692,0.0013282432,0.00037570135],"genre_scores_gemma":[0.98990464,0.000054876396,0.009809122,0.00015541245,0.00003771556,0.000029482533,3.8953485e-7,0.000005010435,0.000003366291],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989658,0.0000517532,0.00026005844,0.00028330158,0.0002638928,0.00017521778],"domain_scores_gemma":[0.997802,0.0012612649,0.0002174839,0.0006407357,0.00006422056,0.0000142492645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067167496,0.0000954257,0.000116983334,0.0000416177,0.0001637808,0.00016237951,0.0019234959,0.000049445243,0.0000015131417],"category_scores_gemma":[0.0038393568,0.00006313554,0.000036389323,0.0005775635,0.00011835573,0.000495592,0.00042737345,0.00018260954,0.00007367228],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015205146,0.000003971155,0.00069468934,0.000025801311,0.000004822694,0.0000015092226,0.00009473559,0.000022040647,0.0168257,0.08473836,0.0009814852,0.89659166],"study_design_scores_gemma":[0.000012909665,0.00028663067,0.00031304176,0.000101979065,0.0000031521631,0.0000011353,0.000061338156,0.0340235,0.9584293,0.0045110458,0.0021517721,0.00010423753],"about_ca_topic_score_codex":0.0000054647085,"about_ca_topic_score_gemma":9.631527e-7,"teacher_disagreement_score":0.9753275,"about_ca_system_score_codex":0.000020336558,"about_ca_system_score_gemma":0.00002244311,"threshold_uncertainty_score":0.45963463},"labels":[],"label_agreement":null},{"id":"W3113314849","doi":"10.1109/smc42975.2020.9283136","title":"Incremental Neural-Network Learning for Big Fraud Data","year":2020,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Scalability; Skew; Incremental learning; Artificial intelligence; Machine learning; Credit card fraud; Big data; Classifier (UML); Artificial neural network; Process (computing); Data mining; Credit card; Database","score_opus":0.12676889425614643,"score_gpt":0.30775879769771824,"score_spread":0.18098990344157181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3113314849","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018705375,0.00003178125,0.99034154,0.0068673114,0.00016002999,0.00022140854,0.00001330413,0.0009017207,0.0012758581],"genre_scores_gemma":[0.4430578,0.000014690092,0.5500814,0.005795336,0.00055985694,0.000033961525,0.00027249887,0.000013046137,0.00017143447],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897677,0.000037480426,0.00017057889,0.0004640383,0.0001467518,0.00020435451],"domain_scores_gemma":[0.9989234,0.00008832944,0.00007357279,0.0008046885,0.00003373467,0.00007626596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024010749,0.00008370469,0.00009621798,0.000018915847,0.00012264309,0.00015163037,0.0021162885,0.00003254899,0.000017123773],"category_scores_gemma":[0.00015011313,0.0000775932,0.000019742049,0.00027535154,0.000019179375,0.00060797634,0.0012018755,0.00011543221,0.00004347386],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013271646,0.000028216942,0.0023725873,0.000026675038,0.00001892511,0.0000026624166,0.00015879907,0.00036262727,0.0070118634,0.046201047,0.658953,0.2848503],"study_design_scores_gemma":[0.00014996066,0.00008160173,0.000560375,0.0000037509692,0.0000026002783,0.0000014075997,0.0000147510145,0.6854799,0.0043204464,0.00055052154,0.30870205,0.00013265846],"about_ca_topic_score_codex":0.000007649928,"about_ca_topic_score_gemma":0.000002531057,"teacher_disagreement_score":0.68511724,"about_ca_system_score_codex":0.000012598916,"about_ca_system_score_gemma":0.00002598684,"threshold_uncertainty_score":0.39326257},"labels":[],"label_agreement":null},{"id":"W3116827229","doi":"10.1007/978-3-030-71158-0_8","title":"Cost-Sensitive Semi-supervised Classification for Fraud Applications","year":2021,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Bidding; Scarcity; Machine learning; Labeled data; Artificial intelligence; Domain (mathematical analysis); Data mining; Business; Mathematics","score_opus":0.05000733513116704,"score_gpt":0.318667674835975,"score_spread":0.26866033970480796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116827229","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00053633784,0.00015338318,0.99133986,0.0032718664,0.0011472096,0.0028123658,0.00007329565,0.0006333239,0.0000323395],"genre_scores_gemma":[0.4080568,0.000040595645,0.58908725,0.0011181488,0.00022354748,0.0012725223,0.0001812063,0.000018724653,0.0000012231658],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949814,0.00015276327,0.0007095809,0.002636514,0.00078910287,0.00073060294],"domain_scores_gemma":[0.99388087,0.00080151024,0.00045681177,0.0035071145,0.0011684169,0.00018529235],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012724075,0.00048535256,0.00053648517,0.0007049759,0.00039083257,0.0015062394,0.0048154863,0.0004530985,0.0000033078816],"category_scores_gemma":[0.00033978326,0.0005106222,0.00016825073,0.0024120281,0.000519861,0.0008912623,0.0029232425,0.0009070012,0.000011112116],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005491378,0.00017890899,0.00018728265,0.00013414258,0.000013898707,0.0000062287368,0.0015523691,0.015507465,0.0123127615,0.0050172433,0.00008501108,0.9649992],"study_design_scores_gemma":[0.00021662135,0.00003830107,0.002242751,0.00017012276,0.000008246116,0.000015356725,0.000003941255,0.9036957,0.07006491,0.022437068,0.0005514204,0.00055554905],"about_ca_topic_score_codex":0.00003071331,"about_ca_topic_score_gemma":0.000038238344,"teacher_disagreement_score":0.9644436,"about_ca_system_score_codex":0.0006341061,"about_ca_system_score_gemma":0.0014210202,"threshold_uncertainty_score":0.9997345},"labels":[],"label_agreement":null},{"id":"W3118534316","doi":"10.1080/02664763.2020.1870669","title":"Adaptive kernel scaling support vector machine with application to a prostate cancer image study","year":2021,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Health Research","keywords":"Support vector machine; Computer science; Interpretability; Pattern recognition (psychology); Artificial intelligence; Kernel (algebra); Feature vector; Classifier (UML); Relevance vector machine; Radial basis function kernel; Scaling; Kernel method; Machine learning; Data mining; Mathematics","score_opus":0.01173480914352574,"score_gpt":0.2853612597932442,"score_spread":0.27362645064971847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118534316","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018516278,0.000015844895,0.9966555,0.00035478765,0.000065647546,0.00047414354,0.00025464632,0.000052379623,0.00027541493],"genre_scores_gemma":[0.38448778,0.000016817517,0.6150858,0.00021069741,0.000045483448,0.00007085072,0.00001431176,0.000014965909,0.000053333824],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984019,0.000037293015,0.0005051582,0.00030338773,0.00054810056,0.00020417634],"domain_scores_gemma":[0.9979719,0.00008578059,0.00052830164,0.00045394409,0.00081056065,0.0001495371],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037577839,0.00015280921,0.00027716093,0.000115375304,0.00008454232,0.00016218258,0.00052577496,0.000028257866,0.000015788763],"category_scores_gemma":[0.00003888639,0.00012747878,0.000020591382,0.00050622225,0.00003316056,0.00023079984,0.00014107347,0.00024370031,0.000014780232],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019166699,0.0037676094,0.0048519694,0.00020976042,0.00076816586,0.0015358164,0.026276194,0.0048351292,0.12076609,0.28037122,0.036767848,0.51793355],"study_design_scores_gemma":[0.018370416,0.01244904,0.19155839,0.0006409946,0.0011423158,0.0013462903,0.012662598,0.2898826,0.34686777,0.07018207,0.049494516,0.0054030037],"about_ca_topic_score_codex":0.000017236802,"about_ca_topic_score_gemma":0.000041405943,"teacher_disagreement_score":0.5125305,"about_ca_system_score_codex":0.00015611648,"about_ca_system_score_gemma":0.0004066577,"threshold_uncertainty_score":0.51984334},"labels":[],"label_agreement":null},{"id":"W3124595024","doi":"","title":"Deductible Contracts Against Fraudulent Claims: Evidence from Automobile Insurance","year":2001,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"HEC Montréal","funders":"","keywords":"Deductible; Actuarial science; Incentive; Business; Automobile insurance; Insurance policy; Damages; Economics; Microeconomics; Law","score_opus":0.01765492834572112,"score_gpt":0.2655670931807176,"score_spread":0.24791216483499645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3124595024","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22403434,0.005737108,0.7660072,0.0026606503,0.0004540135,0.00022282026,0.0000072473135,0.00046064454,0.00041600107],"genre_scores_gemma":[0.9564797,0.028125277,0.014125444,0.00052624015,0.00032407738,0.00003229961,0.000008097052,0.00002182594,0.00035698852],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99606955,0.00018662598,0.0005110991,0.0005526091,0.00056377595,0.0021163588],"domain_scores_gemma":[0.9980439,0.00019578284,0.0004037701,0.000956172,0.00023392586,0.00016647844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016281394,0.00024509456,0.0002666097,0.0001724659,0.00032294728,0.00034763094,0.0021549782,0.00012410921,0.000023884506],"category_scores_gemma":[0.00021763804,0.00022757138,0.000109633336,0.0005813083,0.00007641399,0.0024611864,0.00016256071,0.0018719493,0.00016124491],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010541375,0.0004894069,0.024022963,0.000009274808,0.00023763023,0.00010153438,0.00074939994,0.00025657858,0.053480953,0.20078358,0.004317721,0.7154455],"study_design_scores_gemma":[0.0020099652,0.00093801634,0.05588608,0.00063162507,0.000038647624,0.0019158206,0.0005886422,0.013582704,0.038949307,0.82670164,0.057132725,0.0016248089],"about_ca_topic_score_codex":0.00010247466,"about_ca_topic_score_gemma":0.00016622645,"teacher_disagreement_score":0.7518817,"about_ca_system_score_codex":0.0012186549,"about_ca_system_score_gemma":0.0020405469,"threshold_uncertainty_score":0.92800915},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.029274177312831263,"score_gpt":0.33077275706615017,"score_spread":0.3014985797533189,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126232929","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51271933,0.002180492,0.45863113,0.015171728,0.0027170554,0.0030339055,0.00031826587,0.0008298899,0.0043982207],"genre_scores_gemma":[0.94204485,0.0007553545,0.053163197,0.0013559419,0.00007308814,0.00028088348,0.00098885,0.000034501772,0.0013033159],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977421,0.00014925408,0.0005368413,0.0005956199,0.00062704476,0.00034913066],"domain_scores_gemma":[0.9976253,0.00036339695,0.0003491719,0.0012760708,0.00031780123,0.00006828783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017624275,0.00019703536,0.00020025224,0.00012602513,0.0003517381,0.00058337074,0.00073990796,0.000095512616,0.000032477732],"category_scores_gemma":[0.0006715515,0.00014895406,0.000029995717,0.00069287274,0.00010559551,0.0012346709,0.000704595,0.00018300196,0.000028347724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028766316,0.00036271213,0.10411163,0.0002320732,0.00007303976,0.000055861878,0.01516407,0.00079749955,0.024644421,0.035760794,0.09862348,0.7198868],"study_design_scores_gemma":[0.001067561,0.000031574982,0.050699215,0.00022630463,0.000016119164,0.000038756523,0.0012500271,0.88833654,0.007416944,0.00038092022,0.05020287,0.00033317623],"about_ca_topic_score_codex":0.000071341456,"about_ca_topic_score_gemma":0.00011562997,"teacher_disagreement_score":0.887539,"about_ca_system_score_codex":0.00016230629,"about_ca_system_score_gemma":0.00034145432,"threshold_uncertainty_score":0.607417},"labels":[],"label_agreement":null},{"id":"W3131108132","doi":"10.4018/978-1-7998-4963-6.ch015","title":"A Preliminary Framework to Fight Tax Evasion in the Home Renovation Market","year":2021,"lang":"en","type":"book-chapter","venue":"Advances in data mining and database management book series","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Evasion (ethics); Transactional leadership; Tax evasion; Analytics; Anomaly detection; Field (mathematics); Predictive analytics; Government (linguistics); Business; Computer security; Computer science; Data science; Economics; Artificial intelligence; Public economics","score_opus":0.031076810289643726,"score_gpt":0.28740053767081386,"score_spread":0.25632372738117015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131108132","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013870377,0.028480493,0.6293206,0.008223723,0.00081903476,0.0026278545,0.004914978,0.00042871467,0.32517073],"genre_scores_gemma":[0.00006951487,0.06382532,0.8215248,0.0039733094,0.00011583557,0.00031794148,0.01137738,0.00005058368,0.0987453],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99720997,0.00009160173,0.0005631575,0.0013382431,0.0004978916,0.0002991265],"domain_scores_gemma":[0.99490404,0.00034281946,0.0002643278,0.0043983785,0.00004361758,0.00004682878],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011216323,0.0003623713,0.00033999677,0.00047242004,0.00013562103,0.0003079603,0.0028953624,0.0001226636,0.0000678141],"category_scores_gemma":[0.00016278957,0.00032127745,0.00002069692,0.0003361375,0.00010516099,0.0056477315,0.0049374127,0.00034691187,0.000010031886],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010599772,0.00005093018,0.000049127142,0.0005128319,0.000023688799,0.00043056408,0.00048162855,0.00000467929,0.0000033986337,0.6697649,0.16769846,0.16087382],"study_design_scores_gemma":[0.00013653567,0.00008268179,0.0002327385,0.0026210544,0.00001889475,0.000019231704,0.00022936481,0.0004560592,0.000015593076,0.007963777,0.9878178,0.00040622108],"about_ca_topic_score_codex":0.0000048557336,"about_ca_topic_score_gemma":0.00012390822,"teacher_disagreement_score":0.8201194,"about_ca_system_score_codex":0.00006120038,"about_ca_system_score_gemma":0.00003465183,"threshold_uncertainty_score":0.99992394},"labels":[],"label_agreement":null},{"id":"W3132073112","doi":"10.1088/1742-6596/1752/1/012037","title":"Preprocessing Unbalanced Data using Support Vector Machine with Method K-Nearest Neighbors for Cerebral Infarction Classification","year":2021,"lang":"en","type":"article","venue":"Journal of Physics Conference Series","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Support vector machine; Preprocessor; Artificial intelligence; Cerebral infarction; Pattern recognition (psychology); Infarction; Computer science; Stroke (engine); Data pre-processing; Medicine; Ischemia; Cardiology; Internal medicine; Myocardial infarction; Engineering","score_opus":0.11437329644484402,"score_gpt":0.35435149959563106,"score_spread":0.23997820315078705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132073112","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014738964,0.000027555061,0.9966129,0.0012856419,0.00019658811,0.00014139558,0.00009244809,0.00006894536,0.0001006296],"genre_scores_gemma":[0.44220927,0.00002111561,0.5573616,0.00007808514,0.00013956263,0.0000060128946,0.00013117917,0.000013233952,0.000039929935],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99837226,0.000111422945,0.0004907336,0.00042386717,0.00038532613,0.0002164174],"domain_scores_gemma":[0.99632686,0.00010136417,0.0009575553,0.0010251901,0.0015094399,0.00007957862],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005207206,0.00017568398,0.00031938305,0.000074411815,0.0001773191,0.00048475814,0.001105797,0.00006290807,0.000011206973],"category_scores_gemma":[0.00017834599,0.0001509071,0.000049993498,0.0004826414,0.000103008046,0.004792825,0.0002381365,0.0002359663,9.4392e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028973655,0.00033068444,0.004934059,0.00030434606,0.00020779627,0.000019831687,0.00141895,0.00040976863,0.37234956,0.30103657,0.00070775935,0.31799093],"study_design_scores_gemma":[0.0009342248,0.0004493934,0.009709853,0.00027708476,0.00010075176,0.0004278965,0.00046156728,0.21864532,0.7404097,0.024595182,0.0035176817,0.0004713595],"about_ca_topic_score_codex":0.0000074366476,"about_ca_topic_score_gemma":0.000012991458,"teacher_disagreement_score":0.4407354,"about_ca_system_score_codex":0.00008573615,"about_ca_system_score_gemma":0.0012464321,"threshold_uncertainty_score":0.6153813},"labels":[],"label_agreement":null},{"id":"W3134539481","doi":"10.1038/s41598-021-84869-4","title":"Pattern discovery and disentanglement on relational datasets","year":2021,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data science; Data mining; Information retrieval; Computational biology; Biology","score_opus":0.02321418973549529,"score_gpt":0.26769385933271966,"score_spread":0.24447966959722436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134539481","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034295775,0.00014852345,0.9525517,0.0040787808,0.00588024,0.00030877016,0.00020125833,0.00032795945,0.002206951],"genre_scores_gemma":[0.9704247,0.000011558676,0.02354518,0.0005093616,0.000053866763,0.000036483252,0.0026152572,0.000009412017,0.0027941803],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99809533,0.00004457349,0.00029345296,0.00087229366,0.000528124,0.00016622175],"domain_scores_gemma":[0.9980348,0.000039611623,0.00015943455,0.0016228638,0.00007040825,0.00007290879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055797596,0.00009015396,0.00008520868,0.00008351624,0.00022400923,0.0008284487,0.00021271672,0.00002674879,0.00003214491],"category_scores_gemma":[0.000103914106,0.0000827214,0.00002665097,0.00032058143,0.00009640803,0.0009963324,0.00038385688,0.00007306613,0.000021651598],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000041680755,0.0005484378,0.042695846,0.00005109669,0.0000390744,0.0031322439,0.00041863116,0.000027185444,0.038950887,0.15762854,0.6382697,0.118234195],"study_design_scores_gemma":[0.0002456198,0.000048347152,0.068990715,0.00012810226,0.000012973107,0.00092380133,0.000052422118,0.0036883971,0.21202195,0.07343358,0.63987297,0.00058110757],"about_ca_topic_score_codex":0.0000031475497,"about_ca_topic_score_gemma":0.0000062444087,"teacher_disagreement_score":0.9361289,"about_ca_system_score_codex":0.000045909943,"about_ca_system_score_gemma":0.00011382414,"threshold_uncertainty_score":0.798875},"labels":[],"label_agreement":null},{"id":"W3136437899","doi":"10.1109/bigdata50022.2020.9378256","title":"Financial Fraud Detection using Deep Support Vector Data Description","year":2020,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Support vector machine; Computer science; Finance; Financial fraud; Business; Computer security; Accounting; Artificial intelligence","score_opus":0.13130823618456722,"score_gpt":0.2921565879658771,"score_spread":0.1608483517813099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136437899","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003201559,0.000007885601,0.99444526,0.0008291128,0.00023459361,0.00013931455,0.000013591371,0.0007609482,0.00036774148],"genre_scores_gemma":[0.7034918,0.000004655685,0.29492694,0.0013404529,0.00014282273,0.0000056059816,0.000057541925,0.0000069924504,0.000023173528],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988745,0.00003853235,0.00020824852,0.0005012394,0.00020535236,0.00017211479],"domain_scores_gemma":[0.998793,0.000015005327,0.0000880435,0.00097179424,0.00006380462,0.000068326546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000178323,0.000096291464,0.00009880218,0.000052122607,0.00010401841,0.0001701564,0.0013414238,0.00006854413,0.0000626709],"category_scores_gemma":[0.00020792757,0.000097248165,0.000019989684,0.0004223256,0.000023126066,0.00199158,0.00056742,0.00011644927,0.00012442486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030914507,0.0001035273,0.0009349896,0.00005002706,0.000015004536,0.000021628992,0.0007139178,0.00004586084,0.5963984,0.04267771,0.020974677,0.33803335],"study_design_scores_gemma":[0.00013641051,0.00008649233,0.0038536126,0.000004046864,0.0000060861908,0.000011615034,0.000010987458,0.8610637,0.10924056,0.00089256733,0.024487026,0.00020689468],"about_ca_topic_score_codex":0.00003161339,"about_ca_topic_score_gemma":0.0000198452,"teacher_disagreement_score":0.8610178,"about_ca_system_score_codex":0.000054232216,"about_ca_system_score_gemma":0.00008611198,"threshold_uncertainty_score":0.3965665},"labels":[],"label_agreement":null},{"id":"W3137652598","doi":"10.37394/23205.2020.19.22","title":"Data Level Approach for Multiclass Imbalance Financial Data","year":2020,"lang":"en","type":"article","venue":"WSEAS TRANSACTIONS ON COMPUTERS","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Oversampling; Artificial intelligence; Resampling; Computer science; Naive Bayes classifier; Machine learning; Decision tree; Logistic regression; Random forest; Classifier (UML); Overfitting; C4.5 algorithm; Support vector machine; Data mining; Artificial neural network; Bandwidth (computing)","score_opus":0.24476872946470218,"score_gpt":0.32461200277031477,"score_spread":0.07984327330561258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137652598","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010273522,0.000025174822,0.98764855,0.005081265,0.0003967576,0.0006820606,0.005203651,0.0008458855,0.00010639463],"genre_scores_gemma":[0.11327002,0.00002094191,0.8817882,0.0030778018,0.00015954163,0.00007705583,0.0015478915,0.000024623976,0.00003395489],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99735427,0.00007401056,0.00036036177,0.0014832746,0.00035402863,0.0003740619],"domain_scores_gemma":[0.99527067,0.00020521766,0.00012637649,0.004082572,0.00009657666,0.00021859235],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00031294354,0.00024865175,0.00026545135,0.00009540708,0.00027260865,0.00024198632,0.0076260143,0.00010223082,0.000002914667],"category_scores_gemma":[0.000085405314,0.00026108802,0.00006380454,0.00054461043,0.00008471946,0.0015907849,0.00025537715,0.00028970602,0.000022353504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019971868,0.001160178,0.00004164072,0.00024138685,0.00015502231,0.000011982695,0.0005908444,0.012763695,0.0014490876,0.016395811,0.2461103,0.7208803],"study_design_scores_gemma":[0.0006156806,0.00009736947,0.0002499892,0.000015315196,0.000016209417,0.000005372975,0.000009008109,0.939724,0.00093537936,0.00008721235,0.05795787,0.00028659598],"about_ca_topic_score_codex":0.000010085692,"about_ca_topic_score_gemma":0.00000502782,"teacher_disagreement_score":0.9269603,"about_ca_system_score_codex":0.000054094297,"about_ca_system_score_gemma":0.00020536028,"threshold_uncertainty_score":0.99998415},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.037752310959626376,"score_gpt":0.3249331132441325,"score_spread":0.2871808022845061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139397034","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21732098,0.00029585662,0.7693207,0.009341759,0.0016170299,0.0009808454,0.000026945376,0.000115647665,0.0009802441],"genre_scores_gemma":[0.99831176,0.00021745599,0.0005933002,0.00047152012,0.000041338833,0.00020928831,0.000017054941,0.000010103701,0.00012819876],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9979961,0.00039640165,0.00049113017,0.00035962588,0.0005452432,0.00021151657],"domain_scores_gemma":[0.9961813,0.0014581818,0.00041683047,0.0016773248,0.0002401651,0.000026206173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008150054,0.00013389644,0.00013217636,0.00006267447,0.00035852243,0.00043953618,0.0023551784,0.00007324928,0.000010569381],"category_scores_gemma":[0.0003795396,0.00007425178,0.00005997319,0.0011838841,0.00013756506,0.00064217695,0.0004476005,0.00025856498,0.0000083430195],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016062984,0.0007093283,0.11631,0.000053667485,0.000040164905,0.0000058715123,0.0012466102,0.03784282,0.016519915,0.7345913,0.018079676,0.074584566],"study_design_scores_gemma":[0.0001397703,0.000013603795,0.79350436,0.00005504698,0.0000071357144,0.000003412184,0.000043636468,0.18878837,0.014830869,0.0012736835,0.0012496841,0.00009045138],"about_ca_topic_score_codex":0.00004670306,"about_ca_topic_score_gemma":0.00013789785,"teacher_disagreement_score":0.7809908,"about_ca_system_score_codex":0.00015507216,"about_ca_system_score_gemma":0.0002427933,"threshold_uncertainty_score":0.43765467},"labels":[],"label_agreement":null},{"id":"W3139428258","doi":"10.2139/ssrn.3644708","title":"Cost-sensitive Multi-class AdaBoost for Understanding Driving Behavior with Telematics","year":2020,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Telematics; Class (philosophy); AdaBoost; Computer science; Artificial intelligence; Engineering; Machine learning; Telecommunications; Classifier (UML)","score_opus":0.08009445590500974,"score_gpt":0.29927346174542857,"score_spread":0.21917900584041883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139428258","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013820365,0.00005031017,0.9944656,0.003097132,0.00006046016,0.0006378336,0.000009709797,0.00023072277,0.000066217624],"genre_scores_gemma":[0.8590689,0.00013861303,0.14011386,0.0004042277,0.00010168058,0.00006104977,0.000008968894,0.000030389765,0.00007232935],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99752563,0.00006599344,0.0003151925,0.00034238774,0.00031448982,0.001436299],"domain_scores_gemma":[0.99893534,0.00013252275,0.00030958586,0.00028653987,0.0001833852,0.00015265423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007424141,0.00018996061,0.00022179076,0.000096736374,0.00034124948,0.00024991677,0.00074510515,0.00006769257,0.0000016313616],"category_scores_gemma":[0.0001307535,0.0001619282,0.00007179016,0.00032906522,0.000059495123,0.0006878294,0.00009497644,0.0009973106,0.0000071141776],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004650956,0.000121188605,0.00088386267,0.0000215908,0.00012273972,0.000019184145,0.001237997,0.000051283674,0.0056011365,0.9721907,0.00042006958,0.019283766],"study_design_scores_gemma":[0.01302004,0.0077473107,0.0029450168,0.0006089335,0.0005436687,0.0047873002,0.03258537,0.6285247,0.07480409,0.22257708,0.007937667,0.0039187833],"about_ca_topic_score_codex":0.000002624847,"about_ca_topic_score_gemma":0.000110857836,"teacher_disagreement_score":0.8576868,"about_ca_system_score_codex":0.0013872362,"about_ca_system_score_gemma":0.0012801223,"threshold_uncertainty_score":0.66032404},"labels":[],"label_agreement":null},{"id":"W3158115238","doi":"10.3390/math9090936","title":"Kernel Based Data-Adaptive Support Vector Machines for Multi-Class Classification","year":2021,"lang":"en","type":"article","venue":"Mathematics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Support vector machine; Artificial intelligence; Computer science; Interpretability; Machine learning; Kernel (algebra); Class (philosophy); Pattern recognition (psychology); Kernel method; Data mining; Mathematics","score_opus":0.189935942196783,"score_gpt":0.3587845443356013,"score_spread":0.1688486021388183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158115238","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000089578556,0.000018934428,0.99597985,0.0015528627,0.00018132477,0.00043875893,0.0004289989,0.00048789196,0.0008217842],"genre_scores_gemma":[0.025147859,0.000005211978,0.9723817,0.00044724502,0.00005208617,0.00016920992,0.0008494726,0.000028388833,0.00091883773],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983149,0.0000567721,0.000447156,0.00062040635,0.00030391867,0.0002568484],"domain_scores_gemma":[0.99626625,0.0003095931,0.00028446183,0.0027061792,0.0003556557,0.00007788153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005484203,0.00018744275,0.00025521067,0.000078938516,0.00012317729,0.0002101084,0.0016978177,0.0000971749,0.00003507689],"category_scores_gemma":[0.0005988262,0.0001778135,0.000065442604,0.00032943624,0.000051977524,0.00056519045,0.00038279867,0.00011248592,0.000086260035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010642292,0.0014059107,0.00012238121,0.0004299241,0.000074116404,0.00001687111,0.0007381566,0.000017604218,0.03332854,0.8897247,0.051441856,0.022689315],"study_design_scores_gemma":[0.00035587305,0.00003447232,0.0004483698,0.000026778347,0.000020082343,0.000010213296,0.00005376936,0.95695966,0.02321291,0.0060468176,0.012616403,0.00021466026],"about_ca_topic_score_codex":0.0000023475295,"about_ca_topic_score_gemma":0.000010694933,"teacher_disagreement_score":0.956942,"about_ca_system_score_codex":0.000075098345,"about_ca_system_score_gemma":0.00027069985,"threshold_uncertainty_score":0.7251024},"labels":[],"label_agreement":null},{"id":"W3160931074","doi":"10.1109/access.2021.3081040","title":"Adversarial Learning on Incomplete and Imbalanced Medical Data for Robust Survival Prediction of Liver Transplant Patients","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Artificial intelligence; Missing data; Machine learning; Imputation (statistics); Reliability (semiconductor); Deep learning; Receiver operating characteristic; Raw data; Scarcity; Class (philosophy); Data mining","score_opus":0.0944294974648969,"score_gpt":0.3110532291652467,"score_spread":0.2166237317003498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160931074","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033394586,0.00001607075,0.964607,0.00019989104,0.000649675,0.0002194156,0.0006518121,0.00013300398,0.00012851547],"genre_scores_gemma":[0.98420817,0.00013974876,0.014386795,0.000112121525,0.00012321743,0.000022608048,0.0009822217,0.000009840611,0.0000152786],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853206,0.00010850418,0.00027335342,0.0004812495,0.0004492301,0.00015559081],"domain_scores_gemma":[0.9986645,0.0002598725,0.00014015762,0.00069770764,0.00016804921,0.0000697162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003949081,0.00009934901,0.00017943158,0.000060131133,0.00008979061,0.0000870569,0.0013426994,0.0000890089,0.000010825491],"category_scores_gemma":[0.00027707854,0.000095701,0.000022915938,0.00018139103,0.000052926458,0.0008830372,0.00032682612,0.00015125865,0.0000011870478],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013021315,0.0027370288,0.43418315,0.0015205431,0.00050171174,0.0001308141,0.0022043833,0.0017040056,0.021047514,0.029585473,0.036179792,0.46890342],"study_design_scores_gemma":[0.003366112,0.00036141416,0.23753734,0.00028900552,0.000037983962,0.000010399561,0.000013557382,0.725052,0.025795419,0.0004629893,0.006735944,0.00033785388],"about_ca_topic_score_codex":0.000033926208,"about_ca_topic_score_gemma":0.00002639929,"teacher_disagreement_score":0.9508136,"about_ca_system_score_codex":0.000021467464,"about_ca_system_score_gemma":0.00009816101,"threshold_uncertainty_score":0.39025733},"labels":[],"label_agreement":null},{"id":"W3160953847","doi":"10.1007/s10994-021-06012-8","title":"RB-CCR: Radial-Based Combined Cleaning and Resampling algorithm for imbalanced data classification","year":2021,"lang":"en","type":"preprint","venue":"Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"Infrastruktura PL-Grid; Narodowe Centrum Nauki","keywords":"Resampling; Oversampling; Benchmark (surveying); Computer science; Artificial intelligence; Prior probability; Binary classification; Binary number; Pattern recognition (psychology); Class (philosophy); Data mining; Machine learning; Algorithm; Mathematics; Support vector machine; Bayesian probability","score_opus":0.06623426337024325,"score_gpt":0.321198295922057,"score_spread":0.25496403255181377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160953847","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006767655,0.0005301067,0.99401,0.0017444789,0.0005365028,0.0008405674,0.000248834,0.0012752349,0.0001375394],"genre_scores_gemma":[0.12172508,0.00016289967,0.86359704,0.0003294038,0.00021757545,0.00023549893,0.013537561,0.00007757984,0.000117385396],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99595976,0.0004015044,0.0007119604,0.0020028024,0.0004309624,0.00049300224],"domain_scores_gemma":[0.9949072,0.00068599737,0.00081472745,0.0031691012,0.0002780066,0.00014499108],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019247824,0.00046550823,0.0006231827,0.00030583478,0.00050080306,0.0012486214,0.002837503,0.00036799238,0.000008349968],"category_scores_gemma":[0.0010764452,0.000526445,0.000102642254,0.00036205733,0.000092882416,0.00062310114,0.0034173545,0.001298059,0.0000032382927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039557497,0.0001510266,0.003696268,0.0005159887,0.000120209435,0.000015761449,0.00053775683,0.0031076125,0.0057440265,0.0054882853,0.0012451065,0.9793384],"study_design_scores_gemma":[0.00077084854,0.00007567042,0.0023889395,0.0002684832,0.000035703637,0.0000061810515,0.00004929564,0.9829503,0.0010985129,0.0007696512,0.011045638,0.00054075255],"about_ca_topic_score_codex":0.000107891334,"about_ca_topic_score_gemma":0.000017499322,"teacher_disagreement_score":0.9798427,"about_ca_system_score_codex":0.00015238998,"about_ca_system_score_gemma":0.000325844,"threshold_uncertainty_score":0.99978817},"labels":[],"label_agreement":null},{"id":"W3161168558","doi":"10.1145/3447541","title":"TabReformer: Unsupervised Representation Learning for Erroneous Data Detection","year":2021,"lang":"en","type":"article","venue":"ACM/IMS Transactions on Data Science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); University of Alberta","funders":"","keywords":"Computer science; Pipeline (software); Range (aeronautics); Representation (politics); Encoder; Probabilistic logic; Artificial intelligence; Tuple; Machine learning; External Data Representation; Mixture model; Task (project management); Data mining; Mathematics","score_opus":0.13343075932399806,"score_gpt":0.3654867943384096,"score_spread":0.23205603501441152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161168558","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00079823984,0.000033790096,0.9952773,0.0017535045,0.0005526813,0.00037411024,0.00043726765,0.00056662183,0.00020647621],"genre_scores_gemma":[0.6590311,0.00022560952,0.33872512,0.00028761476,0.00005390662,0.00009201417,0.0012742889,0.000019498151,0.00029084747],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964529,0.00009665756,0.00038544595,0.0018902415,0.00072262355,0.0004520883],"domain_scores_gemma":[0.98963106,0.0003339193,0.0001586782,0.009361732,0.00037634253,0.00013824906],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0013516021,0.00018178522,0.00017546129,0.00029683992,0.0011809055,0.0006239695,0.008993422,0.00007802892,0.00003853769],"category_scores_gemma":[0.0013161858,0.00018547862,0.00003765209,0.002412387,0.00026690884,0.008841366,0.00057282473,0.00032228744,0.000052257124],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020939677,0.00018454305,0.000030885687,0.000020816673,0.000017151058,0.0000062174495,0.00018518824,0.00083744846,0.14071345,0.0009871443,0.000536599,0.8564596],"study_design_scores_gemma":[0.0004304949,0.00012974953,0.0007790657,0.000031485033,0.00002658232,0.000096183816,0.0002450694,0.6219256,0.34209043,0.0009421242,0.032948174,0.00035508245],"about_ca_topic_score_codex":0.00007904704,"about_ca_topic_score_gemma":0.00013005068,"teacher_disagreement_score":0.85610455,"about_ca_system_score_codex":0.00014561441,"about_ca_system_score_gemma":0.0004934566,"threshold_uncertainty_score":0.9963684},"labels":[],"label_agreement":null},{"id":"W3161799859","doi":"10.1007/978-3-030-76776-1_1","title":"Data Balancing for Credit Card Fraud Detection Using Complementary Neural Networks and SMOTE Algorithm","year":2021,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"","keywords":"Oversampling; Computer science; Credit card fraud; Credit card; Machine learning; Support vector machine; Class (philosophy); Artificial intelligence; Random forest; Algorithm; Artificial neural network; Boosting (machine learning); Logistic regression; Data mining; Bandwidth (computing); World Wide Web; Computer network","score_opus":0.0987028516425362,"score_gpt":0.3349643615855716,"score_spread":0.23626150994303538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161799859","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020905676,0.0004793784,0.99656796,0.00039314572,0.00042124346,0.0005307311,0.0002906873,0.00012129983,0.0011746624],"genre_scores_gemma":[0.009868597,0.0017553053,0.98559237,0.00097351643,0.00012004381,0.000031797386,0.001589773,0.000013997635,0.00005457726],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998089,0.00004393892,0.0007329467,0.00051457854,0.00035017717,0.00026934195],"domain_scores_gemma":[0.9952049,0.0002696089,0.00043913853,0.0035419378,0.0004482593,0.000096144075],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013325908,0.0002343582,0.0002865696,0.0004454237,0.000753128,0.0009559498,0.0037454653,0.00012994131,0.0000018618895],"category_scores_gemma":[0.000049766884,0.00026138825,0.000030537107,0.00037737997,0.00054059905,0.008815779,0.0059655057,0.00040534118,9.678341e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001456066,0.000008131499,0.00002200117,0.000031569096,0.00000928362,3.3726823e-7,0.00021785153,0.0005676866,0.000012863664,0.03351504,0.00021607305,0.9653977],"study_design_scores_gemma":[0.00019299815,0.000029197914,0.00027372476,0.00010432389,0.000009709659,0.000040932722,0.00001839732,0.9315436,0.000020438765,0.0009607923,0.06655981,0.00024608543],"about_ca_topic_score_codex":0.000044848744,"about_ca_topic_score_gemma":0.000036975427,"teacher_disagreement_score":0.9651516,"about_ca_system_score_codex":0.0001766624,"about_ca_system_score_gemma":0.00015006626,"threshold_uncertainty_score":0.99998385},"labels":[],"label_agreement":null},{"id":"W3164230923","doi":"10.1145/3441250.3441274","title":"Threshold Moving Approaches for Addressing the Class Imbalance Problem and their Application to Multi-label Classification","year":2020,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multi-label classification; Class (philosophy); Computer science; Relevance (law); Artificial intelligence; Binary classification; Training set; Binary number; Machine learning; Simple (philosophy); Pattern recognition (psychology); Data mining; Mathematics; Support vector machine","score_opus":0.20657720109120525,"score_gpt":0.3141587319339968,"score_spread":0.10758153084279154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164230923","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00054903806,0.00008225611,0.9638638,0.03235014,0.000023427045,0.0017215271,0.000018061877,0.0006204643,0.0007712874],"genre_scores_gemma":[0.5777394,0.000010109279,0.41869196,0.0024545104,0.0000531783,0.00096542994,0.000022660155,0.000015326525,0.000047387228],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984851,0.000044742068,0.0003151707,0.0007299698,0.00015659817,0.00026842466],"domain_scores_gemma":[0.99866724,0.00014236488,0.00017922171,0.0007715874,0.00011432788,0.00012524807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043309177,0.00019218648,0.00017028362,0.00005136807,0.0003097933,0.00037345596,0.0011724664,0.00008164007,7.06009e-7],"category_scores_gemma":[0.00008243734,0.00012975188,0.000032126787,0.00046479763,0.000073447525,0.00059724576,0.0003214551,0.00014560945,0.000010547989],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018664135,0.00009156236,0.0005897337,0.000094348936,0.00001676444,9.386724e-8,0.0024414621,0.000084199906,0.13865899,0.49342877,0.0043060128,0.36026943],"study_design_scores_gemma":[0.00024341648,0.000046157194,0.0014471236,0.000015454007,0.0000035073497,0.0000018329722,0.00027826673,0.9742014,0.015638504,0.0027180437,0.0052166125,0.00018967623],"about_ca_topic_score_codex":0.000004568035,"about_ca_topic_score_gemma":0.0000061897235,"teacher_disagreement_score":0.9741172,"about_ca_system_score_codex":0.000046236095,"about_ca_system_score_gemma":0.00004406391,"threshold_uncertainty_score":0.5291128},"labels":[],"label_agreement":null},{"id":"W3176378653","doi":"10.1007/s41060-021-00256-2","title":"Biased resampling strategies for imbalanced spatio-temporal forecasting","year":2021,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Resampling; Computer science; Relevance (law); Set (abstract data type); Machine learning; Sampling (signal processing); Data mining; Artificial intelligence","score_opus":0.16509422418002845,"score_gpt":0.38022736019206177,"score_spread":0.21513313601203332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176378653","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047449814,0.000053467793,0.991873,0.0026405076,0.0003612337,0.000041768737,0.00011688314,0.000019388515,0.00014871349],"genre_scores_gemma":[0.53967446,0.00006519698,0.45979863,0.00026569032,0.000114096496,7.942325e-7,0.00006586199,0.0000028913616,0.000012365606],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828386,0.000016755956,0.00042550603,0.00030339754,0.0008088168,0.0001616847],"domain_scores_gemma":[0.99618065,0.00018193404,0.00044035882,0.0004802408,0.0026355446,0.000081280545],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0016505617,0.000077784425,0.00013953213,0.0002581402,0.00013322684,0.0010617666,0.0028422163,0.000024884615,0.0000031655186],"category_scores_gemma":[0.0013708217,0.000068974696,0.000030192377,0.00049163966,0.00016635511,0.005578002,0.00062164984,0.00010406119,4.974691e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010594014,0.0003321528,0.009123576,0.0000686392,0.00024515705,0.00033250224,0.00084565295,0.0009987568,0.061404787,0.6227474,0.014534231,0.28926116],"study_design_scores_gemma":[0.0006972843,0.00010563862,0.00169026,0.00017385778,0.000021383688,0.0004401463,0.00064011355,0.9134382,0.0135272555,0.0472549,0.021780476,0.00023049528],"about_ca_topic_score_codex":0.000006099111,"about_ca_topic_score_gemma":0.0000136488225,"teacher_disagreement_score":0.9124394,"about_ca_system_score_codex":0.000069905815,"about_ca_system_score_gemma":0.0013299644,"threshold_uncertainty_score":0.9999752},"labels":[],"label_agreement":null},{"id":"W3181535716","doi":"10.1177/00131644211023569","title":"The Importance of Thinking Multivariately When Setting Subscale Cutoff Scores","year":2021,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Counterintuitive; Cutoff; Test (biology); Psychology; Mathematics; Value (mathematics); Econometrics; Psychometrics; Property (philosophy); Process (computing); Cognitive psychology; Statistics; Computer science; Epistemology","score_opus":0.1154940239194557,"score_gpt":0.335637612308858,"score_spread":0.22014358838940234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3181535716","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18871115,0.010561527,0.56526923,0.21577072,0.0027662134,0.00097343227,0.000034239856,0.0004212847,0.015492195],"genre_scores_gemma":[0.8717427,0.00009614215,0.12692338,0.00094448443,0.0000908536,0.00005687463,0.000008892345,0.0000036238362,0.00013302962],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9986185,0.00012536805,0.00028203466,0.00033407402,0.00049060833,0.00014944612],"domain_scores_gemma":[0.9987624,0.0002279764,0.00015323947,0.00043699355,0.00036844343,0.000050914627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010066108,0.00008445328,0.00009210178,0.000020456995,0.00023784056,0.000106180094,0.0004948961,0.000040664887,0.000037394177],"category_scores_gemma":[0.0004901616,0.000055450248,0.000032461987,0.00015380279,0.00008603011,0.00013569939,0.000110346526,0.00011372554,0.0000050966305],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014506218,0.0005885706,0.0801587,0.00002113916,0.0000349354,0.000002234899,0.0008780784,0.0000016798473,0.016977688,0.83888346,0.018091043,0.044347957],"study_design_scores_gemma":[0.00015563464,0.0000459229,0.7286816,0.000049762984,0.000003856598,0.000020945314,0.000060125258,0.00011977054,0.007573583,0.2554416,0.007719437,0.00012774098],"about_ca_topic_score_codex":0.000003886345,"about_ca_topic_score_gemma":0.0000075214525,"teacher_disagreement_score":0.68303156,"about_ca_system_score_codex":0.000035797566,"about_ca_system_score_gemma":0.00008852758,"threshold_uncertainty_score":0.22611955},"labels":[],"label_agreement":null},{"id":"W3183445774","doi":"10.1109/tie.2021.3095804","title":"An Optimal Transport-Embedded Similarity Measure for Diagnostic Knowledge Transferability Analytics Across Machines","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Electronics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Similarity (geometry); Computer science; Feature (linguistics); Artificial intelligence; Transferability; Similarity measure; Measure (data warehouse); Pattern recognition (psychology); Transfer of learning; Data mining; Domain (mathematical analysis); Machine learning; Mathematics","score_opus":0.05944745029323178,"score_gpt":0.3329656525030846,"score_spread":0.2735182022098528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3183445774","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019220216,0.00013950877,0.9766337,0.00084604457,0.0007155753,0.0008588251,0.00086881523,0.0006639925,0.000053295284],"genre_scores_gemma":[0.9822226,0.00011841064,0.016753046,0.0001285964,0.00017487165,0.00033557802,0.00012948988,0.00004504233,0.00009234836],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9966859,0.00031898648,0.0006907799,0.001050886,0.00041474542,0.0008387007],"domain_scores_gemma":[0.9967531,0.0008126407,0.00011317906,0.0015009617,0.00056550733,0.00025463905],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00097421155,0.00040163903,0.000508995,0.00012068166,0.00059837836,0.00021576259,0.0011174716,0.00055896817,0.00003907825],"category_scores_gemma":[0.00014317768,0.00043391823,0.00033685705,0.0011371667,0.00012487333,0.0008453292,0.000002902315,0.0011755802,0.000006302823],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012536398,0.008757699,0.00019764526,0.00016731738,0.0006240053,0.000039642306,0.0036360323,0.06582469,0.02941852,0.011564619,0.0013211495,0.87719506],"study_design_scores_gemma":[0.003983775,0.0015020298,0.0001847015,0.000067088054,0.0002353651,0.00003951579,0.000093910865,0.20202751,0.77966875,0.0017472819,0.009370218,0.0010798359],"about_ca_topic_score_codex":0.00001488585,"about_ca_topic_score_gemma":0.0006876257,"teacher_disagreement_score":0.9630024,"about_ca_system_score_codex":0.00041389026,"about_ca_system_score_gemma":0.0013709834,"threshold_uncertainty_score":0.99981123},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.031423922936257245,"score_gpt":0.2878609277436617,"score_spread":0.25643700480740445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186353005","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005576069,0.000031957126,0.9924652,0.000074650154,0.0001535222,0.0002791654,0.0000076733895,0.001375669,0.00003607921],"genre_scores_gemma":[0.928438,0.00003555997,0.071145914,0.0000068317145,0.000106887666,0.00020323556,0.000024708947,0.000019704536,0.00001913752],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998636,0.000025718147,0.0004302181,0.00038454344,0.00025796233,0.00026552755],"domain_scores_gemma":[0.99870634,0.00017128613,0.00015108669,0.0006967733,0.00020745955,0.00006706232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036469157,0.00014320834,0.00015803553,0.00041394302,0.00017269781,0.00007839646,0.0008180671,0.000090995476,0.000006030982],"category_scores_gemma":[0.0001595256,0.00017021978,0.00006245099,0.002148592,0.000051394225,0.00029358192,0.00017238875,0.00023535818,0.00011256084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018156657,0.00002166653,0.000020165016,0.00003205146,0.00001087399,7.9055013e-7,0.0002500756,0.6297704,0.07600216,0.034747094,0.000012535754,0.25913036],"study_design_scores_gemma":[0.0000056852564,0.000018288256,0.00007608997,0.000015083998,0.0000040805703,0.000002534964,0.00009694992,0.7943521,0.20077902,0.0022910202,0.0022270998,0.00013200384],"about_ca_topic_score_codex":0.000081368584,"about_ca_topic_score_gemma":0.0000076225033,"teacher_disagreement_score":0.92286193,"about_ca_system_score_codex":0.00009366658,"about_ca_system_score_gemma":0.00003306873,"threshold_uncertainty_score":0.69413614},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.09531188645907628,"score_gpt":0.40848284267087265,"score_spread":0.31317095621179636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186924568","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0076103243,0.03903184,0.95225155,0.00016010168,0.0002938123,0.00048571013,0.00002404213,0.000121203004,0.0000214312],"genre_scores_gemma":[0.7857246,0.08723909,0.1241367,0.001971164,0.00014216104,0.00018847453,0.00037800524,0.000045727047,0.00017407218],"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848497,0.00025483215,0.00042135597,0.00048302548,0.0002019676,0.00015387168],"domain_scores_gemma":[0.9987595,0.000068072455,0.00022642256,0.00080047303,0.0001078948,0.000037629346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069912634,0.00011673918,0.0002547683,0.000120893805,0.000077186356,0.00046447694,0.0009857827,0.000050984163,0.0000033711256],"category_scores_gemma":[0.0005553522,0.000109057844,0.000015117645,0.0008796505,0.000012976864,0.0019852775,0.00069728086,0.00020276442,0.0000019622935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050271246,0.00080927904,0.025667477,0.45081475,0.00018800345,0.0016447265,0.0053343596,0.0001841157,0.06130847,0.0018901611,0.0031549742,0.44895342],"study_design_scores_gemma":[0.00055903895,0.00007974231,0.0013732619,0.1734722,0.00008383441,0.0003872548,0.000052769436,0.70686334,0.109921694,0.0007680224,0.0055626403,0.0008761898],"about_ca_topic_score_codex":0.000018691006,"about_ca_topic_score_gemma":0.0000700424,"teacher_disagreement_score":0.8281148,"about_ca_system_score_codex":0.000060021604,"about_ca_system_score_gemma":0.00006274406,"threshold_uncertainty_score":0.44789618},"labels":[],"label_agreement":null},{"id":"W3187962531","doi":"10.48550/arxiv.2108.02932","title":"Incremental Feature Learning For Infinite Data","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Feature (linguistics); Transfer of learning; Database transaction; Artificial intelligence; Machine learning; Incremental learning; Credit card fraud; Credit card; Database","score_opus":0.14545334106907012,"score_gpt":0.23314352792380297,"score_spread":0.08769018685473284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3187962531","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00801872,0.00006274778,0.9892721,0.0002955463,0.0003347127,0.00039135327,0.0001450208,0.0006055592,0.0008742318],"genre_scores_gemma":[0.91270125,0.00022875944,0.082785465,0.00018585831,0.000084506566,0.0000037221284,0.0023791236,0.000022142993,0.0016091884],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99780273,0.00013468885,0.00016120635,0.0015152433,0.00009753322,0.000288589],"domain_scores_gemma":[0.9960608,0.00013608139,0.0002972213,0.0032025366,0.00020736363,0.00009600658],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00038237346,0.00025367018,0.00027035113,0.00018987528,0.00019745325,0.00033683336,0.0047029546,0.00030533024,0.00001531105],"category_scores_gemma":[0.00016542344,0.0003183176,0.0001036311,0.0004613722,0.0000658809,0.0010192448,0.008628629,0.00076434977,0.000016143787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017911875,0.0007857132,0.019958021,0.0013374022,0.0010495345,0.0009328305,0.0014548672,0.05991261,0.006315609,0.7639214,0.105131835,0.039021064],"study_design_scores_gemma":[0.0005188167,0.000055844608,0.001588343,0.00017191557,0.000072542214,0.000007943384,0.00018594983,0.9468207,0.0021363064,0.006554476,0.04116023,0.0007269842],"about_ca_topic_score_codex":0.000044263623,"about_ca_topic_score_gemma":0.000026878739,"teacher_disagreement_score":0.90648663,"about_ca_system_score_codex":0.00017445812,"about_ca_system_score_gemma":0.00027526522,"threshold_uncertainty_score":0.99992687},"labels":[],"label_agreement":null},{"id":"W3192068992","doi":"10.1109/icekim52309.2021.00091","title":"A Machine Learning Model for Product Fraud Detection Based On SVM","year":2021,"lang":"en","type":"article","venue":"2021 2nd International Conference on Education, Knowledge and Information Management (ICEKIM)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Support vector machine; Computer science; Machine learning; Product (mathematics); Artificial intelligence; Mathematics","score_opus":0.02788209290694559,"score_gpt":0.2930754788741815,"score_spread":0.2651933859672359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3192068992","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014492105,0.00005311709,0.87657243,0.0049467566,0.0008240136,0.0005169093,0.000032003107,0.0001486456,0.1167612],"genre_scores_gemma":[0.9080254,0.0008299615,0.07006011,0.0028561791,0.00023421124,0.0009731173,0.0017980747,0.000019456264,0.01520349],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855787,0.000061512605,0.00043890162,0.00041802553,0.00033920148,0.00018447252],"domain_scores_gemma":[0.99789023,0.000057511334,0.000261609,0.0004974973,0.0012165571,0.00007662052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003829082,0.00020071292,0.00013755905,0.0005174264,0.00026587246,0.0005616041,0.00052341825,0.000058938844,0.00015670178],"category_scores_gemma":[0.00020485601,0.00020921345,0.000057234196,0.00038844574,0.000028934455,0.002447692,0.00013740177,0.00018002292,0.00012352588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026888285,0.00025284753,0.000057510293,0.00009111804,0.000029296729,1.7924219e-7,0.00056728354,0.00084157183,0.00016215596,0.61319387,0.0055377954,0.3792395],"study_design_scores_gemma":[0.00033847475,0.000062264065,0.00053720095,0.00007946141,0.000009395659,0.0000015029904,0.00016639898,0.7749571,0.0022809387,0.0041950247,0.21718533,0.00018687577],"about_ca_topic_score_codex":0.0000049091523,"about_ca_topic_score_gemma":0.00001002741,"teacher_disagreement_score":0.9078805,"about_ca_system_score_codex":0.0001726458,"about_ca_system_score_gemma":0.00031697485,"threshold_uncertainty_score":0.8531477},"labels":[],"label_agreement":null},{"id":"W3193852816","doi":"10.1016/j.knosys.2021.107382","title":"Con2Vec: Learning embedding representations for contrast sets","year":2021,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Contrast (vision); Embedding; Artificial intelligence; Feature vector; Computer science; Set (abstract data type); Similarity (geometry); Pattern recognition (psychology); Support vector machine; Vector space; Feature (linguistics); Mathematics; Image (mathematics)","score_opus":0.03885619592808201,"score_gpt":0.3398254438502533,"score_spread":0.3009692479221713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193852816","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004972055,0.0006770658,0.9902252,0.0004380521,0.0009756536,0.0005675292,0.000042431908,0.0008498631,0.005726994],"genre_scores_gemma":[0.94707525,0.000006236279,0.049027443,0.000083355575,0.0001621526,0.0006379435,0.00022521157,0.00002880706,0.0027535867],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980293,0.0003348409,0.0004646839,0.0006228322,0.00020626868,0.0003420587],"domain_scores_gemma":[0.9971356,0.0008106918,0.00022401949,0.00090699625,0.00080774445,0.000114951894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065394305,0.00017148005,0.0002868733,0.00015054378,0.000340979,0.000462347,0.00060644397,0.00010336522,0.00001111757],"category_scores_gemma":[0.00069839176,0.00018358325,0.00010942057,0.000552151,0.000046640696,0.00038695207,0.00010453007,0.00017015332,0.000097022494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004534202,0.0008871781,0.0076064123,0.0015965473,0.00024993173,0.000091278656,0.0036078892,0.010316161,0.16676459,0.6354017,0.12663019,0.046802778],"study_design_scores_gemma":[0.0009253396,0.0000581107,0.0003701526,0.00021957861,0.000015523352,0.000026959617,0.00033783828,0.8006602,0.06551605,0.00035600355,0.13117664,0.00033761983],"about_ca_topic_score_codex":0.000013651535,"about_ca_topic_score_gemma":0.000013111978,"teacher_disagreement_score":0.9465781,"about_ca_system_score_codex":0.000132881,"about_ca_system_score_gemma":0.00041838104,"threshold_uncertainty_score":0.74863076},"labels":[],"label_agreement":null},{"id":"W3196700564","doi":"10.1145/3472163.3472175","title":"Explainable Data Analytics for Disease and Healthcare Informatics","year":2021,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; University of Manitoba","keywords":"Computer science; Data science; Interpretability; Big data; Analytics; Health informatics; Informatics; Data analysis; Health care; Component (thermodynamics); Variety (cybernetics); Disease; Data modeling; Data mining; Artificial intelligence; Medicine; Database; Engineering","score_opus":0.09696791973435473,"score_gpt":0.33326499634163415,"score_spread":0.23629707660727942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196700564","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007687309,0.00012938229,0.9919192,0.006953807,0.00003940878,0.00014862475,0.00015714944,0.000183427,0.0003921041],"genre_scores_gemma":[0.030390834,0.0002034581,0.965335,0.0024894483,0.00002324161,0.000029826619,0.00065004756,0.000005230646,0.00087288267],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934256,0.000014023404,0.00018812803,0.00019719612,0.00011272006,0.00014539478],"domain_scores_gemma":[0.998002,0.00006964788,0.00005523036,0.0015939273,0.00015836842,0.000120817276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001934902,0.000059335456,0.000079865225,0.00003689716,0.000090736925,0.00019452193,0.00071590155,0.000022317792,0.00000361103],"category_scores_gemma":[0.00015754318,0.00005551561,0.000010326715,0.00019238217,0.000018822122,0.0011069836,0.0007630619,0.000032864933,0.0000028368545],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004292054,0.000044556964,0.0008619246,0.000313018,0.00001317498,0.000006593244,0.00021105101,0.0000035270753,0.0000491868,0.84247696,0.09904037,0.056975365],"study_design_scores_gemma":[0.00019094326,0.00002233697,0.00075418473,0.00002025416,0.000008916176,0.0000071345994,0.00021965482,0.7816365,0.0017035592,0.018922638,0.19634934,0.00016456477],"about_ca_topic_score_codex":0.000004226501,"about_ca_topic_score_gemma":0.000010663842,"teacher_disagreement_score":0.8235543,"about_ca_system_score_codex":0.000018428176,"about_ca_system_score_gemma":0.00019261616,"threshold_uncertainty_score":0.2263861},"labels":[],"label_agreement":null},{"id":"W3197720659","doi":"10.1190/segam2021-3580872.1","title":"Pitfalls and insights from a machine learning contest on log facies classification","year":2021,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"CONTEST; Facies; Computer science; Artificial intelligence; Machine learning; Natural language processing; Geology; Philosophy; Paleontology","score_opus":0.03202404632800689,"score_gpt":0.2515952865697584,"score_spread":0.21957124024175148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197720659","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029502597,0.00044026316,0.9552139,0.0032466748,0.000097470824,0.00012234879,0.000017119655,0.0007924619,0.010567161],"genre_scores_gemma":[0.94042134,0.00017533057,0.056795754,0.0008278712,0.000016523267,0.000017516875,0.00012652484,0.0000070048436,0.0016121124],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989706,0.000101549995,0.00018105576,0.00045432925,0.00017750663,0.00011490783],"domain_scores_gemma":[0.9990011,0.00020431509,0.00008507055,0.0005505501,0.00010157244,0.000057386937],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006973654,0.00011185147,0.00012734177,0.00006873671,0.00012337392,0.00021982161,0.00032533414,0.000060507773,0.000029823905],"category_scores_gemma":[0.00017238034,0.00009717926,0.000020272506,0.00021220709,0.000048780887,0.0004160914,0.00017351002,0.00017126687,0.00007474341],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035938233,0.000068551904,0.0025887354,0.0000043577284,0.000010881568,0.000010781376,0.0004930643,0.0000036155482,0.13141759,0.84329355,0.0007527551,0.021352513],"study_design_scores_gemma":[0.00083404814,0.00022405303,0.16771303,0.0000855627,0.000011291029,0.000023439712,0.00044969335,0.31546152,0.3432423,0.031795356,0.13944784,0.000711897],"about_ca_topic_score_codex":0.00004663114,"about_ca_topic_score_gemma":0.000044486653,"teacher_disagreement_score":0.9109188,"about_ca_system_score_codex":0.000031231975,"about_ca_system_score_gemma":0.00003672582,"threshold_uncertainty_score":0.39628553},"labels":[],"label_agreement":null},{"id":"W3198495944","doi":"10.1017/asb.2021.22","title":"COST-SENSITIVE MULTI-CLASS ADABOOST FOR UNDERSTANDING DRIVING BEHAVIOR BASED ON TELEMATICS","year":2021,"lang":"en","type":"article","venue":"Astin Bulletin","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Telematics; Boosting (machine learning); Computer science; Class (philosophy); AdaBoost; Machine learning; Artificial intelligence; Telecommunications; Classifier (UML)","score_opus":0.10822607461215591,"score_gpt":0.31464518146825504,"score_spread":0.20641910685609913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198495944","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026022026,0.000005704651,0.992273,0.0053607374,0.00020465055,0.0006600692,0.000060053942,0.00038758572,0.0007880314],"genre_scores_gemma":[0.39767197,0.0000024125413,0.60044724,0.0011447264,0.000039673043,0.00024678855,0.000074015006,0.000025143201,0.00034803618],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983592,0.00011765109,0.00032047235,0.00054923224,0.00030048753,0.00035297318],"domain_scores_gemma":[0.9977285,0.0009905073,0.00017631832,0.00076884025,0.00024068162,0.00009513613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004159218,0.00019172333,0.00021499854,0.00010930827,0.0002348865,0.00021329909,0.00046395062,0.00009393471,0.000049478105],"category_scores_gemma":[0.000849022,0.00020379155,0.00008046782,0.0002687314,0.00005975645,0.000084561754,0.00016199377,0.00018151157,0.00007703503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001543218,0.003382026,0.0055642202,0.0004874502,0.00012737825,0.00076695415,0.002043285,0.001852281,0.0720218,0.5609517,0.22239907,0.13024953],"study_design_scores_gemma":[0.0027579137,0.00041153553,0.006960478,0.000720071,0.00006356081,0.000056868572,0.00089384586,0.68633306,0.21551505,0.001138014,0.08393101,0.0012185841],"about_ca_topic_score_codex":0.0000032574926,"about_ca_topic_score_gemma":0.000008933953,"teacher_disagreement_score":0.6844808,"about_ca_system_score_codex":0.00027037165,"about_ca_system_score_gemma":0.00013221173,"threshold_uncertainty_score":0.8310378},"labels":[],"label_agreement":null},{"id":"W3199888448","doi":"10.1109/ijcnn52387.2021.9533313","title":"Multi-Class Mobile Money Service Financial Fraud Detection by Integrating Supervised Learning with Adversarial Autoencoders","year":2021,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Concordia University","funders":"Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Computer science; Autoencoder; Artificial intelligence; Machine learning; Database transaction; Anomaly detection; Credit card fraud; Financial services; Audit; Deep learning; Payment; Credit card; Finance; Accounting","score_opus":0.01044714421245992,"score_gpt":0.23011605972855187,"score_spread":0.21966891551609194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199888448","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011525479,0.000023979097,0.9858071,0.0004214627,0.00019194884,0.00023954087,0.000008177313,0.0011233907,0.0006589049],"genre_scores_gemma":[0.49907988,0.000011744268,0.4991612,0.0008877758,0.000054354347,0.00014744028,0.00008148927,0.000021951326,0.00055413763],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824333,0.0001524835,0.00028927604,0.00066066236,0.00032954584,0.0003246944],"domain_scores_gemma":[0.9987099,0.000087357046,0.00013460158,0.00059380033,0.00038064137,0.00009367043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020747406,0.00020872812,0.00019894466,0.000083990846,0.00029712138,0.00026179748,0.00061196653,0.00014399888,0.000046611756],"category_scores_gemma":[0.0001931036,0.00018899473,0.000045131008,0.0009408333,0.000035685112,0.0010248718,0.00023714014,0.00043533978,0.000040494077],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007010644,0.0004291623,0.0009662637,0.00007595761,0.00005402279,0.000046121462,0.0039375857,0.0051853945,0.8167104,0.0027798254,0.003918775,0.16582635],"study_design_scores_gemma":[0.00063984364,0.00011970106,0.00023774352,0.000023648028,0.0000061526252,0.00001500627,0.00048502878,0.74141276,0.2476647,0.000038977134,0.009096433,0.00026001708],"about_ca_topic_score_codex":0.00032989233,"about_ca_topic_score_gemma":0.0006399085,"teacher_disagreement_score":0.73622733,"about_ca_system_score_codex":0.00013027833,"about_ca_system_score_gemma":0.00023181645,"threshold_uncertainty_score":0.77069813},"labels":[],"label_agreement":null},{"id":"W3204024137","doi":"","title":"Geo-Spatiotemporal Features and Shape-Based Prior Knowledge for Fine-grained Imbalanced Data Classification","year":2021,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal; University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Data mining","score_opus":0.034219366023810996,"score_gpt":0.27585715098773667,"score_spread":0.24163778496392568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204024137","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038104646,0.0009392185,0.96511924,0.024829123,0.00011899974,0.000553088,0.00023069374,0.00058665295,0.0038125273],"genre_scores_gemma":[0.44542474,0.00011977341,0.54819113,0.00024332256,0.00002522565,0.00014847273,0.0031753522,0.000030285471,0.0026416858],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99606305,0.0016601951,0.00047225252,0.0011601374,0.00029628127,0.00034807387],"domain_scores_gemma":[0.99147755,0.0016845119,0.0003774229,0.004104472,0.0021936754,0.00016236742],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0033578253,0.00025281412,0.00028030024,0.00015873408,0.00046135037,0.00063922105,0.0023075205,0.00016778999,0.000022191374],"category_scores_gemma":[0.0028489057,0.00027046062,0.00007586058,0.00070965936,0.00018473362,0.0007376106,0.00095916964,0.00022657837,0.000012557485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021072938,0.00070411566,0.0014676761,0.00017435479,0.000040772367,0.0000034540449,0.0017366753,0.0000022331592,0.046352014,0.4889553,0.019484326,0.44105804],"study_design_scores_gemma":[0.0017262909,0.000002174953,0.045900818,0.0005637213,0.00003228836,0.000024874147,0.00006556338,0.6106152,0.2567152,0.0053013815,0.07839116,0.0006613473],"about_ca_topic_score_codex":0.00005314083,"about_ca_topic_score_gemma":0.00063644163,"teacher_disagreement_score":0.6106129,"about_ca_system_score_codex":0.00007973939,"about_ca_system_score_gemma":0.00052979554,"threshold_uncertainty_score":0.9999748},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Class (philosophy); Computational biology; Computer science; Biology; Chemistry; Artificial intelligence","score_opus":0.013955494857205746,"score_gpt":0.3723376864885252,"score_spread":0.35838219163131946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3207601856","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012966973,0.003268911,0.9652421,0.0121222,0.00064485293,0.0001203807,0.0000035362152,0.00044819407,0.018136883],"genre_scores_gemma":[0.003855226,0.00016280438,0.9912066,0.0018771279,0.00008562802,0.000052153046,0.0000069546854,0.000009647805,0.002743846],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99814624,0.0006577484,0.00021111181,0.00044047617,0.00026939125,0.00027501181],"domain_scores_gemma":[0.9972653,0.00069972663,0.000112141766,0.0015800236,0.00028761703,0.00005522381],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001738654,0.00011941763,0.00013440839,0.000032755514,0.00025079903,0.00029736545,0.0015224667,0.00022970204,0.0000063457223],"category_scores_gemma":[0.00075489935,0.00008193837,0.00006269118,0.0007841483,0.0000633254,0.00028692695,0.0003730097,0.0007781714,0.000019521587],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013636547,0.000015282132,0.000057760863,0.000006036728,0.000008963164,0.0000070919373,0.000036249934,8.1338953e-7,0.025972156,0.64759076,0.029222094,0.2970814],"study_design_scores_gemma":[0.0000611337,0.000008867461,0.0011022995,0.000008772625,0.0000022290046,0.000030215846,0.000007857522,0.0027530342,0.20157816,0.057417277,0.73692286,0.000107294116],"about_ca_topic_score_codex":8.8841796e-7,"about_ca_topic_score_gemma":0.000003003493,"teacher_disagreement_score":0.7077008,"about_ca_system_score_codex":0.000053833854,"about_ca_system_score_gemma":0.00014765868,"threshold_uncertainty_score":0.3380811},"labels":[],"label_agreement":null},{"id":"W3211419495","doi":"","title":"Divide-and-Conquer Hard-thresholding Rules in High-dimensional Imbalanced Classification","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Divide and conquer algorithms; Thresholding; Artificial intelligence; Computer science; Curse of dimensionality; Class (philosophy); Linear discriminant analysis; Pattern recognition (psychology); Machine learning; Population; Feature (linguistics); Data mining; Algorithm","score_opus":0.08232278468603461,"score_gpt":0.20927570650396352,"score_spread":0.1269529218179289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211419495","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47094685,0.000099452205,0.52720994,0.00049368775,0.0002992911,0.00026926576,0.00003497742,0.0003625666,0.00028398389],"genre_scores_gemma":[0.97956085,0.00034137923,0.019257559,0.00020380333,0.000043946297,0.000008681596,0.0002630422,0.00002173715,0.00029898138],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971585,0.00022238048,0.00037757517,0.0016898101,0.00017105324,0.00038063634],"domain_scores_gemma":[0.9974113,0.00014714948,0.00036939973,0.0017061688,0.00022711657,0.00013888114],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045274355,0.00035683552,0.00044811133,0.00046439748,0.00013818353,0.00029156098,0.0014771356,0.00039544166,0.000026988011],"category_scores_gemma":[0.00009205631,0.0004335311,0.00010708715,0.000593547,0.00015906659,0.0009102322,0.0023300715,0.0007321184,0.000032568758],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036830945,0.0002551621,0.03396668,0.00016059434,0.00009519587,0.00037345305,0.00030250027,0.013256329,0.0076880697,0.93754554,0.0010239161,0.0052957553],"study_design_scores_gemma":[0.0010109786,0.000036989906,0.30761564,0.0005149762,0.000052392632,0.000015912616,0.000067660105,0.56007797,0.004242972,0.12471951,0.00047165263,0.0011733642],"about_ca_topic_score_codex":0.00020984904,"about_ca_topic_score_gemma":0.000043609125,"teacher_disagreement_score":0.812826,"about_ca_system_score_codex":0.00037765704,"about_ca_system_score_gemma":0.00025582543,"threshold_uncertainty_score":0.99981165},"labels":[],"label_agreement":null},{"id":"W3211602915","doi":"10.1007/s11227-021-04177-6","title":"A binary PSO-based ensemble under-sampling model for rebalancing imbalanced training data","year":2021,"lang":"en","type":"article","venue":"The Journal of Supercomputing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Artificial intelligence; Ensemble learning; Machine learning; Sampling (signal processing); Selection (genetic algorithm); Binary number; Binary classification; Data mining; Pattern recognition (psychology); Support vector machine; Mathematics","score_opus":0.2111408925881917,"score_gpt":0.35105609274242977,"score_spread":0.13991520015423808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211602915","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032048184,0.00035335164,0.9637471,0.003258025,0.00025676505,0.00013494109,0.000019517693,0.00012926839,0.000052876145],"genre_scores_gemma":[0.53384656,0.000020226727,0.46531403,0.0006352442,0.00013526459,0.0000012842899,0.000021246693,0.000015075351,0.000011065548],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99785924,0.00018536152,0.00076390884,0.0003517713,0.00041404617,0.0004256907],"domain_scores_gemma":[0.9963803,0.0011461343,0.00044445487,0.0014473012,0.0004884768,0.00009328985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034050096,0.0001843621,0.00036056567,0.00013345761,0.00040101862,0.00021196996,0.0027783671,0.00007336003,0.0000016809968],"category_scores_gemma":[0.00050458295,0.00014625896,0.000107209955,0.0004548247,0.00005036182,0.001021084,0.0006305681,0.00040442272,0.0000014074917],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007593414,0.00017453048,0.00014964517,0.00013349146,0.00011823574,0.000038255395,0.005360699,0.38824853,0.48250225,0.011683257,0.0031573125,0.10835786],"study_design_scores_gemma":[0.000516972,0.00005446681,0.00014714229,0.0002538899,0.000028437205,0.00022537292,0.00061097095,0.98141146,0.011543576,0.0047290293,0.00030471588,0.000173966],"about_ca_topic_score_codex":0.00000437432,"about_ca_topic_score_gemma":0.0000047280764,"teacher_disagreement_score":0.59316295,"about_ca_system_score_codex":0.00010695942,"about_ca_system_score_gemma":0.0007650533,"threshold_uncertainty_score":0.5964267},"labels":[],"label_agreement":null},{"id":"W3211945175","doi":"10.1145/3488269","title":"Towards a Consistent Interpretation of AIOps Models","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Huawei Technologies (Canada); Queen's University","funders":"","keywords":"Consistency (knowledge bases); Interpretation (philosophy); Computer science; Machine learning; Randomness; Consistency model; Artificial intelligence; Hyperparameter; Data mining; Econometrics; Statistics; Algorithm; Mathematics; Correctness","score_opus":0.09577591198243182,"score_gpt":0.316722677026575,"score_spread":0.22094676504414315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211945175","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010767775,0.00017010841,0.99782765,0.000282966,0.00023699473,0.000056683082,0.000014916184,0.00031374002,0.000020150632],"genre_scores_gemma":[0.2043355,0.000110159854,0.7953929,0.000090090725,0.0000043994787,0.000026414798,0.0000042596307,0.0000065818613,0.000029702236],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991991,0.00013534613,0.00020408878,0.00025650626,0.000087820525,0.000117121424],"domain_scores_gemma":[0.998484,0.00072343927,0.0000472393,0.00058032596,0.00012033126,0.000044646218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033286994,0.00009400652,0.00019542674,0.0001345042,0.00003301829,0.000016782205,0.00025442487,0.00008276553,0.0000054611614],"category_scores_gemma":[0.0006452624,0.000098929384,0.000051187304,0.00023051893,0.000030996183,0.00018974375,0.000021163196,0.00014291577,9.713511e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022770151,0.00009831651,0.000014722834,0.00013883827,0.0001035873,0.000010990785,0.0015448686,0.050390124,0.01718625,0.05618871,0.000036165093,0.87426466],"study_design_scores_gemma":[0.00061791367,0.00027357403,0.0011311434,0.00017158568,0.00006722621,0.00033027923,0.00013680292,0.452937,0.5096563,0.032527372,0.0016794341,0.00047135903],"about_ca_topic_score_codex":0.000008072182,"about_ca_topic_score_gemma":0.0000012929029,"teacher_disagreement_score":0.8737933,"about_ca_system_score_codex":0.000022634058,"about_ca_system_score_gemma":0.00005656571,"threshold_uncertainty_score":0.40342233},"labels":[],"label_agreement":null},{"id":"W3212266938","doi":"","title":"Comparing Multiclass AUC ROC Methods","year":2021,"lang":"en","type":"article","venue":"Student Research Proceedings","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"","keywords":"Receiver operating characteristic; Pairwise comparison; Metric (unit); Class (philosophy); Mathematics; Statistics; Artificial intelligence; Macro; Computer science; Machine learning; Data mining","score_opus":0.3339980917634996,"score_gpt":0.5449204526442908,"score_spread":0.2109223608807912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212266938","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062761635,0.00045167675,0.8470854,0.0072619994,0.00037147285,0.0010644072,0.0000032798393,0.0017457139,0.07925438],"genre_scores_gemma":[0.47932926,0.00010939994,0.51778626,0.00013242438,0.000096668926,0.00021833974,0.0000049081827,0.000017396322,0.0023053435],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.996524,0.00017770649,0.00033939377,0.0008315235,0.0013815823,0.0007458267],"domain_scores_gemma":[0.997025,0.00033402623,0.00008094408,0.0006085435,0.0017482439,0.00020323957],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0035157772,0.00015538675,0.00024244236,0.00028666758,0.0003973445,0.0010645319,0.0024667005,0.00008230099,0.000027196638],"category_scores_gemma":[0.0012014238,0.00015126291,0.00005921597,0.0017084861,0.000144588,0.0010047046,0.002925671,0.00066604326,0.0001279448],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009929873,0.0005580475,0.03214212,0.00018415984,0.00007321566,0.000049572875,0.0065394915,0.0000015307243,0.26722527,0.60315573,0.052582797,0.03747814],"study_design_scores_gemma":[0.00083369645,0.00017841064,0.068192415,0.00020420483,0.000007810348,0.00006347619,0.0028720533,0.024151187,0.6846371,0.020075679,0.19817781,0.00060612365],"about_ca_topic_score_codex":0.000017589931,"about_ca_topic_score_gemma":0.000006256164,"teacher_disagreement_score":0.58308005,"about_ca_system_score_codex":0.0003587652,"about_ca_system_score_gemma":0.00025752746,"threshold_uncertainty_score":0.99997246},"labels":[],"label_agreement":null},{"id":"W3216438119","doi":"10.1109/iri51335.2021.00009","title":"Evaluating Deep Neural Nets and Optimized Hyperparameters Random Forest for Decision Support Systems","year":2021,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Hyperparameter; Random forest; Support vector machine; Computer science; Artificial intelligence; Machine learning; Deep learning; Artificial neural network; Decision support system; Decision tree; Data mining","score_opus":0.062339084361170694,"score_gpt":0.3471295184346636,"score_spread":0.2847904340734929,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216438119","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0094185285,0.00013660187,0.9885241,0.00041606408,0.00034182915,0.0005998404,0.0000062990143,0.00027539427,0.0002813436],"genre_scores_gemma":[0.22351764,0.000018042065,0.77574724,0.00032638825,0.000019761232,0.00017479759,0.000030885152,0.000009653766,0.00015561504],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985269,0.0000996186,0.0003667791,0.00049605814,0.0002711245,0.00023952655],"domain_scores_gemma":[0.9977404,0.0011430949,0.00011775763,0.000662509,0.0002491417,0.00008711122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008059631,0.00012808174,0.00025054964,0.00007114414,0.00012837102,0.0004374417,0.00043398442,0.000061652376,0.000010159805],"category_scores_gemma":[0.0008889852,0.000109178094,0.00005863594,0.00019292344,0.000030962867,0.00055851927,0.00023179316,0.00006357505,0.00000519578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042987324,0.00014188781,0.0011538104,0.00012739797,0.00007214662,0.000039747567,0.00043813486,0.017703444,0.018664872,0.05131913,0.011061062,0.8988485],"study_design_scores_gemma":[0.0018992381,0.00009725483,0.000292756,0.000018875873,0.000009737462,0.00007779341,0.00003486167,0.9926864,0.0028783497,0.0010380592,0.00082342885,0.00014326595],"about_ca_topic_score_codex":0.000009732282,"about_ca_topic_score_gemma":0.000005563623,"teacher_disagreement_score":0.9749829,"about_ca_system_score_codex":0.000031273816,"about_ca_system_score_gemma":0.0000616145,"threshold_uncertainty_score":0.44521534},"labels":[],"label_agreement":null},{"id":"W33863052","doi":"10.1007/978-3-642-38457-8_22","title":"Detecting and Categorizing Indices in Lecture Video Using Supervised Machine Learning","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Supervised learning; Pattern recognition (psychology); Artificial neural network","score_opus":0.024337151493192592,"score_gpt":0.2533469240577634,"score_spread":0.22900977256457078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W33863052","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023783422,0.0010658323,0.9946077,0.0003077665,0.0004172852,0.000491031,0.0000031750435,0.0003310597,0.0003978108],"genre_scores_gemma":[0.49673885,0.00009651793,0.5024645,0.00045595376,0.00014623335,0.000013071758,0.000008139473,0.00004209579,0.00003467745],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99598014,0.000096871845,0.0006705272,0.0017642707,0.00072835607,0.0007598106],"domain_scores_gemma":[0.997618,0.0005580313,0.0004542414,0.0010436121,0.00017441162,0.00015170647],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012294754,0.0005957069,0.00060876284,0.0016001348,0.00039637703,0.0010358993,0.0024389874,0.00044157731,0.000018123656],"category_scores_gemma":[0.0002799829,0.0005679677,0.00006388179,0.0009932463,0.00046017737,0.0014936028,0.0016678232,0.0017857172,0.000011594359],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044469343,0.000017049018,0.0018034237,0.00009785621,0.00000908973,0.00005912514,0.0018682017,0.013974769,0.008317969,0.003098692,0.0000022804265,0.9707471],"study_design_scores_gemma":[0.00023789688,0.000089975016,0.00038867048,0.00047559864,0.0000053959952,0.00010581503,6.5306324e-7,0.9501142,0.00842049,0.039099295,0.00036191096,0.00070011854],"about_ca_topic_score_codex":0.00038853366,"about_ca_topic_score_gemma":0.00026862847,"teacher_disagreement_score":0.970047,"about_ca_system_score_codex":0.0004395545,"about_ca_system_score_gemma":0.0003299546,"threshold_uncertainty_score":0.9996772},"labels":[],"label_agreement":null},{"id":"W4200081114","doi":"10.1109/pst52912.2021.9647807","title":"Using CGAN to Deal with Class Imbalance and Small Sample Size in Cybersecurity Problems","year":2021,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Sample (material); Sample size determination; Process (computing); Class (philosophy); Set (abstract data type); Domain (mathematical analysis); Data mining; Intrusion detection system; Computer security; Machine learning; Artificial intelligence; Statistics; Mathematics","score_opus":0.03975333358073592,"score_gpt":0.27002433792356945,"score_spread":0.23027100434283354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200081114","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12182867,0.000023852694,0.8750277,0.0015086384,0.000020478137,0.00023946793,0.0000109974835,0.00023159164,0.0011086062],"genre_scores_gemma":[0.35794976,0.000007870675,0.6413172,0.00063254486,0.00000843407,0.000017695653,0.0000028415845,0.0000059603626,0.00005769265],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99881196,0.000059377373,0.00019276759,0.00051490066,0.00015461758,0.00026637266],"domain_scores_gemma":[0.9990099,0.00020046266,0.000052717896,0.0005287305,0.00010775295,0.00010040517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021722873,0.00011984378,0.00015837545,0.000060749473,0.000056774992,0.00017455258,0.00038129085,0.00005018839,0.000009855147],"category_scores_gemma":[0.000087206776,0.0001078699,0.000012106119,0.0006383539,0.000037296155,0.0003444994,0.0003114313,0.00012082833,0.0000034255959],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050695366,0.00059355644,0.27996704,0.00022646294,0.00004479648,0.00019974998,0.004719562,0.0005165962,0.16184236,0.50502497,0.0015605228,0.04525366],"study_design_scores_gemma":[0.0032446315,0.0006040321,0.3850611,0.0006883307,0.000022227916,0.00056478207,0.0007399347,0.19728307,0.2820414,0.0631837,0.063776515,0.0027902662],"about_ca_topic_score_codex":0.00044371097,"about_ca_topic_score_gemma":0.0022418362,"teacher_disagreement_score":0.44184127,"about_ca_system_score_codex":0.0000766655,"about_ca_system_score_gemma":0.0001349959,"threshold_uncertainty_score":0.43988067},"labels":[],"label_agreement":null},{"id":"W4200468553","doi":"10.21742/ijsbt.2021.9.2.03","title":"Ensemble Techniques for Credit Card Fraud Detection","year":2021,"lang":"en","type":"article","venue":"International Journal of Smart Business and Technology","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Credit card fraud; Credit card; Computer science; Ensemble learning; Volatility (finance); Machine learning; Artificial intelligence; Business; Finance; World Wide Web; Payment","score_opus":0.013610888339946675,"score_gpt":0.2655516955389598,"score_spread":0.25194080719901313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200468553","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007380251,0.00025958708,0.9766835,0.0143489335,0.0009383122,0.0000759829,0.000009988414,0.00016342013,0.00014003347],"genre_scores_gemma":[0.8245091,0.0004175521,0.17451757,0.00020624095,0.00024254102,0.000027308575,0.0000059471186,0.000008918363,0.000064850894],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991361,0.000014099584,0.0003331225,0.00018618863,0.00021515119,0.00011532052],"domain_scores_gemma":[0.99641937,0.00005827603,0.00030106373,0.00022732936,0.0029657043,0.000028266966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020987443,0.00008956083,0.00017119979,0.0004938724,0.00005734995,0.00011819342,0.0006662572,0.00014084278,0.0000031545028],"category_scores_gemma":[0.00036301554,0.000084064646,0.000042639385,0.0004531704,0.000069464106,0.000515861,0.00021080759,0.00014715227,0.0000011345259],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003172233,0.00009129258,0.00078374223,0.000016895405,0.0000851374,0.0000924348,0.000025635129,0.0000012819088,0.18968627,0.071606085,0.00208219,0.7354973],"study_design_scores_gemma":[0.0003332216,0.00011414984,0.0013860998,0.000063562504,0.000010424384,0.0014638917,0.000025880188,0.00052936946,0.7590151,0.051618416,0.18532006,0.0001198447],"about_ca_topic_score_codex":0.000005843464,"about_ca_topic_score_gemma":0.000013261345,"teacher_disagreement_score":0.81712884,"about_ca_system_score_codex":0.0000583468,"about_ca_system_score_gemma":0.00012035412,"threshold_uncertainty_score":0.34280568},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.026763444414693062,"score_gpt":0.33052858593000745,"score_spread":0.30376514151531436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205471456","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.1348978e-9,0.5876225,0.4096781,0.000046853205,0.000041898093,0.001996116,0.000034086333,0.00024090167,0.00033950256],"genre_scores_gemma":[4.8996935e-7,0.9339164,0.049872473,0.0000655711,0.00014295288,0.01579303,0.00011918409,0.000029097951,0.00006078505],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974954,0.0002144478,0.00095158495,0.0008083131,0.00032887116,0.00020135599],"domain_scores_gemma":[0.99655795,0.00011858028,0.0011050137,0.0017177291,0.00042944867,0.00007127494],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037701227,0.000360848,0.0014021905,0.00021144279,0.00013467124,0.00008457749,0.0008906742,0.00021895874,0.000003926672],"category_scores_gemma":[0.000059419883,0.0002821191,0.0001165059,0.0013758161,0.000094651245,0.00036940735,0.00019621148,0.00023156236,0.0000065740337],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.3447873e-7,0.000031437386,1.6870388e-7,0.026621122,0.000014796392,0.0000014632674,0.000012321704,9.796213e-9,0.0000036954732,0.008570126,0.0010659193,0.9636786],"study_design_scores_gemma":[0.00002994953,0.000046385358,1.9554194e-7,0.06113016,0.000045949375,0.00021748808,0.0000049734645,0.000006591794,0.00017348064,0.00002901368,0.9380403,0.00027548452],"about_ca_topic_score_codex":0.000017858814,"about_ca_topic_score_gemma":0.0000041597145,"teacher_disagreement_score":0.9634031,"about_ca_system_score_codex":0.00013557375,"about_ca_system_score_gemma":0.0004200467,"threshold_uncertainty_score":0.9999631},"labels":[],"label_agreement":null},{"id":"W4205966115","doi":"10.37394/23203.2021.16.31","title":"A Perceptron Based Neural Network Data Analytics Architecture for the Detection of Fraud in Credit Card Transactions in Financial Legacy Systems","year":2021,"lang":"en","type":"article","venue":"WSEAS TRANSACTIONS ON SYSTEMS AND CONTROL","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Credit card fraud; Credit card; Computer science; Financial services; Architecture; Backup; Financial transaction; Payment processor; Analytics; Computer security; Artificial intelligence; Finance; Business; Data science; Database transaction; World Wide Web; Payment; Database","score_opus":0.028073423423967084,"score_gpt":0.2539206916271523,"score_spread":0.22584726820318524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205966115","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007381275,0.0010733792,0.99514914,0.0007950959,0.0006969741,0.0010130531,0.0004524631,0.000070123635,0.000011628984],"genre_scores_gemma":[0.99794674,0.000047960108,0.0012826207,0.00008146426,0.00011192629,0.00045974832,0.00002253974,0.000012799084,0.00003417447],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981953,0.00027323316,0.0005150483,0.0004890961,0.00025292172,0.00027440884],"domain_scores_gemma":[0.9981126,0.0004970267,0.00014098828,0.0010555241,0.00013744348,0.000056422643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005800568,0.00017161295,0.0003709002,0.00018655452,0.0001988575,0.00020477992,0.000531782,0.0001339221,0.0000022487734],"category_scores_gemma":[0.000029301724,0.00014346374,0.00009078691,0.0006803939,0.00005332376,0.00039628852,0.00000517996,0.00033849303,4.0404782e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023720296,0.00023373745,0.00015645228,0.00024491834,0.000073071365,0.000008984897,0.00031460397,0.89949316,0.0029558903,0.0012437173,0.00007021489,0.09496804],"study_design_scores_gemma":[0.001336947,0.000106957494,0.0029444015,0.00012053323,0.000054276083,0.000018878067,0.00022774059,0.9907289,0.00019445045,0.000034663477,0.0040873094,0.00014494927],"about_ca_topic_score_codex":0.00074536394,"about_ca_topic_score_gemma":0.0019709049,"teacher_disagreement_score":0.99720865,"about_ca_system_score_codex":0.0000803464,"about_ca_system_score_gemma":0.00021158771,"threshold_uncertainty_score":0.5850281},"labels":[],"label_agreement":null},{"id":"W4206899722","doi":"10.1007/s41060-021-00296-8","title":"The validation of chest tube management after lung resection surgery using a random forest classifier","year":2022,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa; Dalhousie University","funders":"Department of Medicine, Ottawa Hospital; Ontario Medical Association; Ontario Ministry of Health and Long-Term Care","keywords":"Random forest; Classifier (UML); Lung; Medicine; Chest tube; Resection; Radiology; Computer science; Surgery; Artificial intelligence; Internal medicine","score_opus":0.06469924393754112,"score_gpt":0.3353173416258536,"score_spread":0.27061809768831246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206899722","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07681984,0.0001872887,0.9178229,0.0036253128,0.0011318814,0.00013533143,0.00009518071,0.000014820149,0.00016744272],"genre_scores_gemma":[0.98596865,0.00033883442,0.013488363,0.0000921491,0.00006797112,0.0000033875212,0.000014188189,0.0000030283363,0.000023419832],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976914,0.00007025553,0.00047126116,0.00020416622,0.001440519,0.00012242363],"domain_scores_gemma":[0.9980155,0.00020586293,0.00054635614,0.0005048538,0.00068471464,0.000042673415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004385635,0.00006161583,0.00010752556,0.00044778574,0.00027831158,0.00034479192,0.0025844064,0.000011925423,0.0000053508447],"category_scores_gemma":[0.00027646217,0.00004633648,0.000036857247,0.0006886004,0.00022608302,0.002597259,0.0013366699,0.00013422908,2.3364696e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002615894,0.0015012388,0.21986656,0.00025192523,0.0016943235,0.0006440362,0.0022291734,0.01190244,0.03465063,0.17604196,0.05904172,0.4895601],"study_design_scores_gemma":[0.0007703405,0.00008666329,0.025650753,0.000123039,0.000071829585,0.00040067374,0.0005152845,0.9340694,0.0058264993,0.004627405,0.027640698,0.0002174426],"about_ca_topic_score_codex":0.0000090015365,"about_ca_topic_score_gemma":0.0000032141763,"teacher_disagreement_score":0.92216694,"about_ca_system_score_codex":0.00017875247,"about_ca_system_score_gemma":0.00026176497,"threshold_uncertainty_score":0.48025128},"labels":[],"label_agreement":null},{"id":"W4210759718","doi":"10.1016/j.mlwa.2022.100269","title":"Fraud prediction using machine learning: The case of investment advisors in Canada","year":2022,"lang":"en","type":"article","venue":"Machine Learning with Applications","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Royal Roads University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Investment (military); Machine learning; Artificial intelligence; Computer science; Business; Data science; Political science; Law","score_opus":0.012469568711235928,"score_gpt":0.23282159807448718,"score_spread":0.22035202936325127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210759718","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10086572,0.000344876,0.894242,0.0020328932,0.000046561803,0.0013124536,0.00013457889,0.00034888746,0.0006720281],"genre_scores_gemma":[0.97687626,0.000011082253,0.021838399,0.00023298501,0.000012312017,0.00079089706,0.00010674343,0.000018092202,0.00011320207],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998471,0.00032370476,0.00033400982,0.00036522243,0.00029786245,0.00020820617],"domain_scores_gemma":[0.9988352,0.00014664645,0.0003387419,0.0005656483,0.00005823116,0.000055509827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047835117,0.00013641825,0.00014999649,0.00015716357,0.0006909971,0.00003279891,0.0006892242,0.000019596675,0.0000317184],"category_scores_gemma":[0.00004333504,0.00011184765,0.000022131335,0.0011791626,0.000054011867,0.00013821895,0.00035349603,0.0007590158,0.0000011482865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030438505,0.00025438998,0.31622615,0.00004994307,0.000052246818,0.0000952377,0.0017479857,0.5946586,0.0025616344,0.060190745,0.00034593616,0.02378668],"study_design_scores_gemma":[0.0002685295,0.00009869732,0.006103755,0.000007679304,0.000011719656,0.00038916487,0.00038943402,0.93723845,0.00041632954,0.00034607612,0.054584384,0.00014576696],"about_ca_topic_score_codex":0.55523306,"about_ca_topic_score_gemma":0.19825831,"teacher_disagreement_score":0.8760106,"about_ca_system_score_codex":0.00054605457,"about_ca_system_score_gemma":0.0005279917,"threshold_uncertainty_score":0.8163714},"labels":[],"label_agreement":null},{"id":"W4213324003","doi":"10.5220/0010812700003116","title":"Incremental Feature Learning for Fraud Data Stream","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 14th International Conference on Agents and Artificial Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Feature (linguistics); Data stream; Artificial intelligence; Data mining","score_opus":0.15878673349318617,"score_gpt":0.3545600555866735,"score_spread":0.1957733220934873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213324003","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2055355,0.00010837172,0.6518966,0.095586896,0.005580163,0.003977252,0.0017688181,0.00082186516,0.034724522],"genre_scores_gemma":[0.9902862,0.000032554122,0.008732796,0.00033299724,0.0000582526,0.00006552386,0.00003667209,0.000007036788,0.0004479882],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986945,0.0000135251885,0.0002484278,0.00043307318,0.0004655824,0.00014490017],"domain_scores_gemma":[0.99912626,0.0000443127,0.00029685657,0.00024800614,0.0002483045,0.000036263402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045012796,0.00011262076,0.000105553525,0.00009150342,0.0003611885,0.00022222415,0.003078237,0.000028261036,0.00008402535],"category_scores_gemma":[0.00021148553,0.00009313002,0.0000352117,0.00017995798,0.0000818349,0.00045894246,0.0018514172,0.0002578401,0.0000023870705],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004081721,0.0001034356,0.000611703,0.000011539181,0.000021140771,1.7998914e-7,0.00029519157,0.000033668257,0.009436227,0.91570216,0.004314096,0.06942983],"study_design_scores_gemma":[0.00009823455,0.00038336127,0.0013329696,0.000086378124,0.000014532059,0.000012217802,0.002099182,0.7037352,0.13822378,0.113754615,0.039919052,0.000340489],"about_ca_topic_score_codex":0.000014402012,"about_ca_topic_score_gemma":0.0000016153003,"teacher_disagreement_score":0.80194753,"about_ca_system_score_codex":0.000050520204,"about_ca_system_score_gemma":0.000038615974,"threshold_uncertainty_score":0.57201815},"labels":[],"label_agreement":null},{"id":"W4220674692","doi":"10.1109/icais53314.2022.9742830","title":"An Analysis on Fraud Detection in Credit Card Transactions using Machine Learning Techniques","year":2022,"lang":"en","type":"article","venue":"2022 Second International Conference on Artificial Intelligence and Smart Energy (ICAIS)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Credit card; Decision tree; Random forest; Computer science; Credit card fraud; Payment; Digitization; Feature selection; Classifier (UML); Machine learning; Artificial intelligence; Computer security; World Wide Web","score_opus":0.05931907610652261,"score_gpt":0.3084561019291918,"score_spread":0.24913702582266922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220674692","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0355643,0.000018044628,0.96108264,0.00054061477,0.00044126774,0.00012550523,0.0001129522,0.0002627838,0.0018518809],"genre_scores_gemma":[0.9956931,0.00010203817,0.0031033333,0.00047099084,0.00006353479,0.00015315847,0.00015202427,0.000014628924,0.0002472081],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976006,0.0003142482,0.00052703725,0.00075649616,0.0005468496,0.00025472796],"domain_scores_gemma":[0.99897903,0.00009294362,0.0002067911,0.00046673144,0.00015779593,0.00009669137],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00056020194,0.00022184345,0.00026100932,0.0012443069,0.0004726907,0.00029659714,0.000912395,0.000087579996,0.0018004634],"category_scores_gemma":[0.000035543086,0.0002479054,0.000108142216,0.0010351102,0.00008085208,0.0006753822,0.00011318979,0.00061302807,0.0000065058766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017843531,0.00060004415,0.000511781,0.000005074171,0.00016479415,0.000029192508,0.0008212644,0.022734554,0.0839383,0.5317621,0.000018242483,0.35923618],"study_design_scores_gemma":[0.000026787378,0.00039429634,0.00020304887,0.000007788494,0.000015388217,0.000008216728,0.00035605955,0.79522204,0.19133785,0.0072434186,0.004943762,0.00024131071],"about_ca_topic_score_codex":0.0012590698,"about_ca_topic_score_gemma":0.0028975073,"teacher_disagreement_score":0.9601288,"about_ca_system_score_codex":0.00028162534,"about_ca_system_score_gemma":0.00007826228,"threshold_uncertainty_score":0.9999973},"labels":[],"label_agreement":null},{"id":"W4220749037","doi":"10.1155/2022/7451152","title":"Empirical Analysis of Machine Learning Algorithms for Multiclass Prediction","year":2022,"lang":"en","type":"article","venue":"Wireless Communications and Mobile Computing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada; New Brunswick Innovation Foundation","keywords":"Machine learning; Artificial intelligence; Computer science; Overfitting; Random forest; Decision tree; Big data; Convolutional neural network; Naive Bayes classifier; Ensemble learning; Deep learning; Context (archaeology); Algorithm; Artificial neural network; Data mining; Support vector machine","score_opus":0.0497489368496772,"score_gpt":0.33622477843731763,"score_spread":0.28647584158764045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220749037","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039996635,0.0004563719,0.9584167,0.00030220693,0.0000440824,0.00035326078,0.000121831756,0.00024978543,0.00005911289],"genre_scores_gemma":[0.8343043,0.0001267023,0.16494042,0.000046120127,0.000006567682,0.00024479302,0.00030248577,0.0000073061638,0.000021341028],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987635,0.00025362804,0.0003874042,0.00028298906,0.0001659644,0.00014650087],"domain_scores_gemma":[0.9977522,0.00059513876,0.00027967297,0.0011956255,0.0001368532,0.000040493152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007428492,0.000091417736,0.00023422249,0.00031972135,0.0008570968,0.000050944356,0.001228825,0.000029663572,0.000002193879],"category_scores_gemma":[0.000033962428,0.00010098584,0.000086130916,0.0011203209,0.00008918974,0.00013550896,0.0017002978,0.00023886265,1.3837251e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012701933,0.0006559963,0.043926936,0.000047488946,0.00049795065,4.6501776e-7,0.0058274753,0.02688484,0.0058529135,0.026340714,0.00023181064,0.88972074],"study_design_scores_gemma":[0.0001823706,0.0001193167,0.0037550817,0.0000054222373,0.000063763815,0.0000027868557,0.00022755061,0.97778714,0.00031088653,0.00007650805,0.017380128,0.00008906881],"about_ca_topic_score_codex":0.000045513938,"about_ca_topic_score_gemma":0.0000065378454,"teacher_disagreement_score":0.9509023,"about_ca_system_score_codex":0.00006162244,"about_ca_system_score_gemma":0.00003361494,"threshold_uncertainty_score":0.65921825},"labels":[],"label_agreement":null},{"id":"W4220884181","doi":"10.1371/journal.pone.0265674","title":"Evaluating factors contributing to the failure of information system in the banking industry","year":2022,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"TOPSIS; Failure mode and effects analysis; Rough set; Computer science; Order (exchange); Key (lock); Field (mathematics); Risk analysis (engineering); Information system; Empirical research; Business; Computer security; Data mining; Finance; Operations research; Reliability engineering; Engineering; Mathematics; Statistics","score_opus":0.08864077543066802,"score_gpt":0.2869646086909101,"score_spread":0.1983238332602421,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220884181","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91031754,0.000009120719,0.08544467,0.0027928676,0.000041222156,0.0008302598,0.00004598444,0.000156733,0.00036162528],"genre_scores_gemma":[0.9888255,1.2889438e-7,0.010687159,0.00028222593,0.000013249916,0.00016911187,0.000017160712,0.0000023976093,0.0000030793929],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984354,0.0002833745,0.0003080613,0.00010505818,0.0006942632,0.00017387359],"domain_scores_gemma":[0.99889565,0.0002272021,0.00023720702,0.0005299591,0.00009670972,0.000013295686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025960833,0.000058800477,0.00010216539,0.000102001504,0.0002829272,0.00009313867,0.0012598742,0.00003529666,0.0000070320507],"category_scores_gemma":[0.00042522032,0.00003954116,0.000015712989,0.00074641156,0.000009850434,0.00041941582,0.0004988053,0.00039712363,0.0000038453695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004677724,0.0010882829,0.19506124,0.0008180299,0.00023597691,0.0000058225623,0.150689,0.008668649,0.06965493,0.52294546,0.0026004617,0.04818536],"study_design_scores_gemma":[0.0011201182,0.00064928917,0.15136859,0.001013393,0.00007728858,0.000018362647,0.059964333,0.5700218,0.21157502,0.0012624682,0.0022147365,0.0007146081],"about_ca_topic_score_codex":0.000031971096,"about_ca_topic_score_gemma":0.0000030595454,"teacher_disagreement_score":0.56135315,"about_ca_system_score_codex":0.00014504761,"about_ca_system_score_gemma":0.000051501993,"threshold_uncertainty_score":0.23411807},"labels":[],"label_agreement":null},{"id":"W4220918566","doi":"10.18280/isi.270114","title":"Detecting and Mitigating Bias in Data Using Machine Learning with Pre-Training Metrics","year":2022,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Metric (unit); Divergence (linguistics); Computer science; Performance metric; Sampling bias; Sample (material); Artificial intelligence; Statistics; Pattern recognition (psychology); False positive rate; Work (physics); Machine learning; Sample size determination; Mathematics; Engineering","score_opus":0.08069774931360683,"score_gpt":0.283910502966973,"score_spread":0.20321275365336616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220918566","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29659075,0.00009561084,0.7023653,0.00003371403,0.00005403553,0.00023450104,0.000026359066,0.00032335572,0.00027643712],"genre_scores_gemma":[0.7906161,0.000008364594,0.20911904,0.00006748928,0.000009197436,0.0000318961,0.00013542116,0.00000827041,0.000004246851],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841374,0.00018533178,0.00050217856,0.0002499316,0.0003788304,0.0002699907],"domain_scores_gemma":[0.9986357,0.00020306716,0.0005065513,0.0005296385,0.000080017206,0.00004498845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019645744,0.0001365537,0.00016863424,0.00061472727,0.0006641185,0.00044889605,0.0007862649,0.000036101595,0.0000036737727],"category_scores_gemma":[0.00092815916,0.00014028345,0.000011033965,0.001628475,0.00005701484,0.0063114557,0.0011432297,0.00038947613,8.269286e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036384336,0.000030947875,0.08389889,0.00035137558,0.00003593399,0.0000207213,0.05316053,0.020791259,0.0023998378,0.0047156336,0.000021798434,0.8345367],"study_design_scores_gemma":[0.000244362,0.00007176583,0.002760379,0.00008651519,0.0000045321003,0.00022441866,0.0023753052,0.9917577,0.00079478073,0.0005022968,0.0009787768,0.00019919807],"about_ca_topic_score_codex":0.0002862309,"about_ca_topic_score_gemma":0.00003510884,"teacher_disagreement_score":0.9709664,"about_ca_system_score_codex":0.00032860378,"about_ca_system_score_gemma":0.000116605406,"threshold_uncertainty_score":0.5720593},"labels":[],"label_agreement":null},{"id":"W4225649457","doi":"10.1007/978-3-030-98358-1_21","title":"Mining Minority-Class Examples with Uncertainty Estimates","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Simon Fraser University; Huawei Technologies (Canada)","funders":"","keywords":"Computer science; Class (philosophy); Data mining; Artificial intelligence","score_opus":0.02613424390481921,"score_gpt":0.2570335863880409,"score_spread":0.2308993424832217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225649457","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006997859,0.00021678736,0.98972595,0.00095424027,0.00059907575,0.00046297183,0.0000253452,0.00065930816,0.0072863204],"genre_scores_gemma":[0.0269416,0.00004522851,0.9710503,0.0012272155,0.0002003626,0.00007028768,0.000059675407,0.00004669795,0.00035860352],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99504286,0.000049264632,0.0005574897,0.0021285764,0.0014412814,0.0007805369],"domain_scores_gemma":[0.9956839,0.00091128284,0.00047458956,0.0024987485,0.0002579514,0.00017350815],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0009702725,0.00065096456,0.00061176915,0.0009649648,0.00053003285,0.00071252766,0.0055858023,0.0002237359,0.00009376991],"category_scores_gemma":[0.00013537283,0.000575256,0.00008860485,0.0009616001,0.0009876258,0.001051956,0.0022989467,0.0009427145,0.000017397906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020301724,0.00007201035,0.00047778166,0.00010405863,0.000033770953,0.00025362888,0.0011019883,0.03328325,0.0005146262,0.22029206,0.00035054237,0.743496],"study_design_scores_gemma":[0.0005511907,0.0007750031,0.0005488696,0.00054419384,0.000029564804,0.00038081376,0.000001486075,0.8038399,0.0047190674,0.1312369,0.05508389,0.002289106],"about_ca_topic_score_codex":0.00008737321,"about_ca_topic_score_gemma":0.00012674618,"teacher_disagreement_score":0.7705567,"about_ca_system_score_codex":0.0006488796,"about_ca_system_score_gemma":0.00083905243,"threshold_uncertainty_score":0.9997945},"labels":[],"label_agreement":null},{"id":"W4226071104","doi":"10.1080/01621459.2024.2402567","title":"Neyman-Pearson Multi-Class Classification via Cost-Sensitive Learning","year":2024,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; National Institute on Aging; National Institutes of Health; National Science Foundation","keywords":"Oracle; Computer science; Class (philosophy); Consistency (knowledge bases); Binary number; Binary classification; Machine learning; Word error rate; Artificial intelligence; Algorithm; Mathematics; Support vector machine; Programming language","score_opus":0.020154951574805853,"score_gpt":0.31093661223476,"score_spread":0.29078166065995414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226071104","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024072914,0.00002795655,0.9892517,0.007231723,0.00053874945,0.0001511148,0.000029605202,0.00014818324,0.00021368175],"genre_scores_gemma":[0.8980001,0.000064915825,0.10082045,0.00044812492,0.00015947939,0.000008878721,0.000009266878,0.000017257405,0.00047150513],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99760556,0.00061350095,0.00054607366,0.00024361105,0.0007394743,0.00025176228],"domain_scores_gemma":[0.99680305,0.0011378903,0.0012427171,0.0002730358,0.00045167608,0.000091614944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010816357,0.00013489231,0.00027537314,0.00015818898,0.00015331777,0.0003284083,0.0006173185,0.00005359784,0.0000057241505],"category_scores_gemma":[0.0018048609,0.00009966737,0.000118707336,0.0008102391,0.00010419916,0.00058763736,0.00011169492,0.00069228077,0.00006090787],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050540286,0.00024519154,0.006132131,0.000038411566,0.00029100638,0.000057909416,0.0011651759,0.00025918602,0.05809845,0.101615466,0.040918175,0.79112834],"study_design_scores_gemma":[0.00028252852,0.00028088223,0.28838798,0.00010926335,0.00008561785,0.00008209271,0.00018765697,0.6729854,0.003779053,0.004441396,0.029104514,0.00027364574],"about_ca_topic_score_codex":0.000026233178,"about_ca_topic_score_gemma":0.0000040938585,"teacher_disagreement_score":0.8955928,"about_ca_system_score_codex":0.001081012,"about_ca_system_score_gemma":0.00016865684,"threshold_uncertainty_score":0.40643173},"labels":[],"label_agreement":null},{"id":"W4226102193","doi":"10.1109/ictmod52902.2021.9739308","title":"Current Research Landscape of Machine Learning Algorithms in Online Identity Fraud Prediction and Detection","year":2021,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Machine learning; Computer science; Identity theft; Identity (music); Artificial intelligence; Algorithm; Statistical classification; Support vector machine; Data science; Computer security","score_opus":0.05547059434204534,"score_gpt":0.36181242540563924,"score_spread":0.3063418310635939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226102193","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07607203,0.0006363863,0.92255837,0.0002141984,0.00011331706,0.000093798466,0.000014439667,0.00014146202,0.0001560229],"genre_scores_gemma":[0.96337986,0.0010375119,0.03539674,0.000008165035,0.000031982006,0.00001216488,0.00005415645,0.000004171948,0.00007523471],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988806,0.000196105,0.00020645629,0.0002767913,0.00031378656,0.00012626276],"domain_scores_gemma":[0.99934727,0.00007650841,0.00005013924,0.00027241898,0.00022217647,0.000031501342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008168571,0.00005048965,0.00008933667,0.00024597574,0.00006231796,0.00006583242,0.00020867371,0.000042247633,0.0000137777615],"category_scores_gemma":[0.00023754103,0.000049439364,0.0000130986455,0.00088445016,0.00003191618,0.0006543822,0.00029722688,0.00034183532,0.0000024282333],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007875607,0.00033831186,0.099871755,0.00008044246,0.000006780995,0.000005863431,0.00034430617,0.000035531604,0.041104343,0.008994656,0.00018060993,0.84902954],"study_design_scores_gemma":[0.00030700746,0.0000924681,0.25824755,0.000054861473,0.000001645938,0.000014028709,0.00010282525,0.6404195,0.09469179,0.0032378207,0.002746432,0.00008409981],"about_ca_topic_score_codex":0.00010393654,"about_ca_topic_score_gemma":0.0003259364,"teacher_disagreement_score":0.8873078,"about_ca_system_score_codex":0.000035845904,"about_ca_system_score_gemma":0.000041175856,"threshold_uncertainty_score":0.20160788},"labels":[],"label_agreement":null},{"id":"W4226428024","doi":"10.1609/aaai.v36i11.21465","title":"Knowledge Sharing via Domain Adaptation in Customs Fraud Detection","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Ministry of Science and ICT, South Korea; Institute for Basic Science; National Research Foundation","keywords":"Safeguarding; Business; Adaptation (eye); Revenue; Knowledge sharing; Tax revenue; Computer security; Knowledge management; Finance; Computer science; Public economics; Economics","score_opus":0.08251334886681946,"score_gpt":0.3011480409752738,"score_spread":0.21863469210845435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226428024","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12965713,0.000034390672,0.8574195,0.0017754427,0.00069306826,0.0008535225,0.000008427147,0.0003455939,0.009212934],"genre_scores_gemma":[0.99359494,0.000007988929,0.0059527503,0.00008622031,0.0000280191,0.00020505731,0.0000012033969,0.000011460525,0.00011238319],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99814767,0.00003752347,0.0005431225,0.0005528384,0.0004426229,0.0002762558],"domain_scores_gemma":[0.998837,0.00005737337,0.0003926886,0.00038614715,0.00028191356,0.000044896613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009579688,0.00016535065,0.00018731933,0.0003265033,0.00031162854,0.00014450906,0.0024469462,0.000057361547,0.000045249646],"category_scores_gemma":[0.00015327698,0.00015319826,0.00006600525,0.0014450703,0.00011372221,0.00057672994,0.0008497036,0.00046659552,0.00004062756],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038645318,0.00018145452,0.00018492862,0.00001891103,0.0000040284885,3.3751076e-7,0.0032395474,0.00020093107,0.14116503,0.6847888,0.000033293378,0.17014405],"study_design_scores_gemma":[0.00002419322,0.0001299318,0.0004806469,0.00004517625,0.0000023678515,0.0000048958846,0.00096088945,0.2966401,0.43624926,0.26498452,0.00031190767,0.00016612433],"about_ca_topic_score_codex":0.00007410366,"about_ca_topic_score_gemma":0.00004933489,"teacher_disagreement_score":0.8639378,"about_ca_system_score_codex":0.00024061221,"about_ca_system_score_gemma":0.000074114956,"threshold_uncertainty_score":0.6247244},"labels":[],"label_agreement":null},{"id":"W4229521098","doi":"10.4018/978-1-4666-6078-6.ch003","title":"A Measure Optimized Cost-Sensitive Learning Framework for Imbalanced Data Classification","year":2014,"lang":"en","type":"book-chapter","venue":"Advances in data mining and database management book series","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Machine learning; Computer science; Particle swarm optimization; Artificial intelligence; Classifier (UML); Benchmark (surveying); Measure (data warehouse); Artificial neural network; Data mining; Feature (linguistics); Support vector machine","score_opus":0.0668525753557907,"score_gpt":0.3211394183207882,"score_spread":0.2542868429649975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229521098","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.6425241e-7,0.0034624517,0.9522832,0.0007070117,0.00030333945,0.0015302299,0.0051183724,0.00047971,0.03611554],"genre_scores_gemma":[0.000051618194,0.037212253,0.8774215,0.00045913053,0.00014580763,0.00026709266,0.05771785,0.00007828543,0.026646467],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954846,0.00011511026,0.00079161447,0.002588339,0.00052645314,0.00049392163],"domain_scores_gemma":[0.9907568,0.00074820215,0.0008479372,0.0073949103,0.00013870068,0.000113412934],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001745857,0.00061121094,0.0007300305,0.0003879841,0.00032765078,0.00041770804,0.004549048,0.00024415116,0.000012656902],"category_scores_gemma":[0.00065859384,0.00065024366,0.00003901691,0.00014025209,0.00031784803,0.007649741,0.0064472468,0.00051432586,0.000013399128],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015864252,0.000019048239,0.000012523646,0.00041850933,0.00008318884,0.000023784121,0.00008543955,0.000017999066,0.000007835463,0.71569306,0.01255256,0.2709274],"study_design_scores_gemma":[0.000651129,0.000070020906,0.000016580985,0.0017309685,0.00009970155,0.000011692054,0.00017802735,0.038997203,0.000031910444,0.0063143442,0.95115274,0.0007456991],"about_ca_topic_score_codex":0.0000031370623,"about_ca_topic_score_gemma":0.000038407135,"teacher_disagreement_score":0.9386002,"about_ca_system_score_codex":0.00008530464,"about_ca_system_score_gemma":0.00006399063,"threshold_uncertainty_score":0.99959487},"labels":[],"label_agreement":null},{"id":"W4229904893","doi":"10.21203/rs.3.rs-28409/v2","title":"Explanation and Prediction of Clinical Data with Imbalanced Class Distribution based on Pattern Discovery and Disentanglement","year":2020,"lang":"en","type":"preprint","venue":"Research Square","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Class (philosophy); Distribution (mathematics); Artificial intelligence; Computer science; Econometrics; Mathematics","score_opus":0.18006147141839787,"score_gpt":0.43483386384350653,"score_spread":0.25477239242510863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229904893","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009914596,0.000058356818,0.974509,0.0045069703,0.000120455916,0.0011271945,0.009544522,0.0001493522,0.000069552705],"genre_scores_gemma":[0.9814473,0.00046116117,0.004559742,0.00005790196,0.0001052388,0.00013867566,0.0132077765,0.000014085672,0.000008118005],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996112,0.0006157362,0.00056435855,0.0012245289,0.001230912,0.00025246944],"domain_scores_gemma":[0.9967773,0.0004334633,0.0003234247,0.0020263465,0.00028723016,0.00015221232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019997712,0.00019005136,0.00034104093,0.00015062746,0.00010709529,0.00033344878,0.0011144648,0.00017918796,0.0000023161404],"category_scores_gemma":[0.00047170965,0.00015787753,0.000031304116,0.00028888462,0.00023796412,0.00061523315,0.0024829176,0.0008174858,0.0000014020177],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012803084,0.0018723895,0.53619474,0.006020948,0.0002706733,0.00009141201,0.00057120144,0.00018780032,0.0012220005,0.023993691,0.052907027,0.37538782],"study_design_scores_gemma":[0.00090279063,0.0010180888,0.44112462,0.0011439561,0.000017026563,0.0000017527408,0.00008426081,0.55104727,0.0014155492,0.0010389872,0.0019885749,0.0002171143],"about_ca_topic_score_codex":0.0000548002,"about_ca_topic_score_gemma":0.000018313443,"teacher_disagreement_score":0.9715327,"about_ca_system_score_codex":0.00011834581,"about_ca_system_score_gemma":0.0002984568,"threshold_uncertainty_score":0.64380586},"labels":[],"label_agreement":null},{"id":"W4230493536","doi":"10.1007/978-1-4614-6170-8_351","title":"Multi-classifier System for Sentiment Analysis and Opinion Mining","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Sentiment analysis; Computer science; Classifier (UML); Artificial intelligence","score_opus":0.04305890097531758,"score_gpt":0.2805933723426814,"score_spread":0.2375344713673638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230493536","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.827852e-7,0.000084528816,0.95494497,0.00017748843,0.00025465817,0.00045852913,0.00005016487,0.00055014936,0.043478906],"genre_scores_gemma":[0.0016226051,0.00004236324,0.70005065,0.00013416843,0.00009825342,0.000104545186,0.00020605802,0.000032370175,0.297709],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982711,0.000020699574,0.000443018,0.0008118724,0.0002507938,0.00020248225],"domain_scores_gemma":[0.9981063,0.00012625923,0.00038223097,0.0011323002,0.00015777996,0.000095137315],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039604647,0.00028783834,0.00049120834,0.00049696217,0.00011263679,0.00022047595,0.0006525426,0.00025918943,0.00001592436],"category_scores_gemma":[0.000013352853,0.00026100306,0.00018502487,0.00008946728,0.000047487243,0.00015061899,0.00030025534,0.00009808437,0.00002553166],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003829783,0.000011584897,0.000047890546,0.00023749897,0.0005571825,0.0000011795743,0.00006649215,0.0000024152787,0.0002567451,0.94737285,0.011034063,0.040408235],"study_design_scores_gemma":[0.0005774958,0.00010291981,0.00025715784,0.00030657373,0.0004303443,0.000011261981,0.000022471446,0.39874566,0.0027337528,0.0007792728,0.59508044,0.0009526845],"about_ca_topic_score_codex":0.0000067370825,"about_ca_topic_score_gemma":0.0000070429674,"teacher_disagreement_score":0.9465936,"about_ca_system_score_codex":0.000115970244,"about_ca_system_score_gemma":0.000032950364,"threshold_uncertainty_score":0.9999842},"labels":[],"label_agreement":null},{"id":"W4230603371","doi":"10.1109/asonam.2016.7752356","title":"Spectral graph-based semi-supervised learning for imbalanced classes","year":2016,"lang":"en","type":"article","venue":"2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Artificial intelligence; Graph; Machine learning; Semi-supervised learning; Theoretical computer science","score_opus":0.03140565970496059,"score_gpt":0.3221481992779155,"score_spread":0.29074253957295493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230603371","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011199326,0.000166071,0.98343694,0.0025492287,0.00041271822,0.00020033607,0.00003952682,0.00017826764,0.001817586],"genre_scores_gemma":[0.96108055,0.0017701342,0.035751596,0.0003044002,0.00032607265,0.0001537028,0.000073871066,0.000017452907,0.0005222358],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99774295,0.00013260731,0.0005017217,0.0007840148,0.00040058902,0.0004381203],"domain_scores_gemma":[0.998149,0.0006499353,0.00040313718,0.00038948102,0.00031986414,0.00008862598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005153536,0.00027948,0.00045380264,0.00039027457,0.00025764736,0.00023437609,0.0012232636,0.00015204583,0.00006776122],"category_scores_gemma":[0.0002398042,0.00022293116,0.000216447,0.0007401966,0.00018213686,0.000801383,0.00011942228,0.00020476544,0.000004180357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041341747,0.0003176761,0.098015524,0.000035271954,0.00066137896,0.000013560791,0.00059073314,0.012378216,0.005888041,0.3124527,0.0034945193,0.5657389],"study_design_scores_gemma":[0.0018505362,0.00026558986,0.019061135,0.00035140634,0.000101520876,0.0000014915299,0.00020969287,0.94560295,0.0015367338,0.017160542,0.01303033,0.00082807295],"about_ca_topic_score_codex":0.000010329543,"about_ca_topic_score_gemma":0.00009989721,"teacher_disagreement_score":0.9498812,"about_ca_system_score_codex":0.00013918201,"about_ca_system_score_gemma":0.00009442384,"threshold_uncertainty_score":0.9090869},"labels":[],"label_agreement":null},{"id":"W4231178192","doi":"10.1007/978-1-4939-7131-2_100383","title":"Financial Fraud Detection","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Business; Finance","score_opus":0.019283274154672472,"score_gpt":0.23124033363486154,"score_spread":0.21195705948018906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231178192","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.6482805e-7,0.000013681263,0.5613703,0.0000768755,0.00030767787,0.00009741871,0.0000065690333,0.0006436295,0.4374834],"genre_scores_gemma":[0.0006890652,0.000055944733,0.103779,0.00075805816,0.00052003947,0.000021949365,0.000024832303,0.000028649636,0.8941225],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99884415,0.000007339504,0.00023540301,0.000506459,0.00025287754,0.00015375146],"domain_scores_gemma":[0.99845326,0.00002281609,0.00017552653,0.001155923,0.00015391191,0.00003857093],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00013328131,0.00020061422,0.0001693194,0.0001723187,0.00008472094,0.00010581943,0.0010156052,0.0003568153,0.0007008784],"category_scores_gemma":[0.000033707976,0.00019334714,0.00007275076,0.00004407937,0.00007389388,0.00031454014,0.00028726592,0.00022743395,0.0022814341],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011629049,0.0000034241693,1.6835769e-7,0.0000049345476,0.0000035033004,0.000002225101,0.000015762746,1.4414638e-8,0.000214516,0.83072686,0.064436674,0.104590744],"study_design_scores_gemma":[0.000034014985,0.000058706315,0.000018285275,0.000020111313,0.0000029429289,0.00000724376,1.5255402e-7,0.00033821719,0.01045572,0.23869562,0.75015473,0.00021426605],"about_ca_topic_score_codex":0.0000040229065,"about_ca_topic_score_gemma":0.000020535179,"teacher_disagreement_score":0.68571806,"about_ca_system_score_codex":0.00008449453,"about_ca_system_score_gemma":0.00008751803,"threshold_uncertainty_score":0.9984954},"labels":[],"label_agreement":null},{"id":"W4235709741","doi":"10.32920/ryerson.14653605","title":"Athlete Health Prediction Using Machine Learning Methods","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Machine learning; Random forest; Computer science; Artificial intelligence; Boosting (machine learning); Ensemble learning; Predictive modelling; Task (project management); Class (philosophy); Upsampling; Data mining; Engineering","score_opus":0.09394424712436228,"score_gpt":0.3969218102149389,"score_spread":0.3029775630905766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235709741","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001897879,0.0007921321,0.99416184,0.0011717866,0.00079645216,0.00031009872,0.000022116357,0.0018647228,0.00069104723],"genre_scores_gemma":[0.004214746,0.0004576594,0.9939139,0.00055639434,0.0000859521,0.0000376464,0.0003449052,0.000023243385,0.00036557898],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968814,0.000962822,0.00055172056,0.00096976146,0.00032448166,0.00030979948],"domain_scores_gemma":[0.99759334,0.00008924951,0.0005044732,0.0015216887,0.00017535756,0.00011591008],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019168656,0.00025228492,0.00040052767,0.00021956983,0.00020972433,0.00049900624,0.0011554763,0.00022692778,0.00003756488],"category_scores_gemma":[0.00017290507,0.00025825232,0.00011377217,0.00035822502,0.00003076155,0.00042564538,0.0028096465,0.0010812506,0.0000048508455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006212521,0.0002185212,0.002575634,0.0008250635,0.00018639586,0.000020836169,0.0025127388,0.0073342593,0.043467518,0.044517342,0.0024316744,0.8959038],"study_design_scores_gemma":[0.00006504403,0.00003261042,0.0004612509,0.00015802946,0.00000613572,0.000023627848,0.000021781902,0.9700399,0.016652549,0.0013899185,0.01090822,0.00024095607],"about_ca_topic_score_codex":0.0006454742,"about_ca_topic_score_gemma":0.000014316564,"teacher_disagreement_score":0.9627056,"about_ca_system_score_codex":0.00038252116,"about_ca_system_score_gemma":0.0005649249,"threshold_uncertainty_score":0.99998695},"labels":[],"label_agreement":null},{"id":"W4237477351","doi":"10.21203/rs.3.rs-28409/v1","title":"Explanation and Prediction of Clinical Data with Imbalanced Class Distribution based on Pattern Discovery and Disentanglement","year":2020,"lang":"en","type":"preprint","venue":"Research Square","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Class (philosophy); Computer science; Data mining; Artificial intelligence; Pattern recognition (psychology); Econometrics; Mathematics","score_opus":0.18006147141839787,"score_gpt":0.43483386384350653,"score_spread":0.25477239242510863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237477351","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009914596,0.000058356818,0.974509,0.0045069703,0.000120455916,0.0011271945,0.009544522,0.0001493522,0.000069552705],"genre_scores_gemma":[0.9814473,0.00046116117,0.004559742,0.00005790196,0.0001052388,0.00013867566,0.0132077765,0.000014085672,0.000008118005],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996112,0.0006157362,0.00056435855,0.0012245289,0.001230912,0.00025246944],"domain_scores_gemma":[0.9967773,0.0004334633,0.0003234247,0.0020263465,0.00028723016,0.00015221232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019997712,0.00019005136,0.00034104093,0.00015062746,0.00010709529,0.00033344878,0.0011144648,0.00017918796,0.0000023161404],"category_scores_gemma":[0.00047170965,0.00015787753,0.000031304116,0.00028888462,0.00023796412,0.00061523315,0.0024829176,0.0008174858,0.0000014020177],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012803084,0.0018723895,0.53619474,0.006020948,0.0002706733,0.00009141201,0.00057120144,0.00018780032,0.0012220005,0.023993691,0.052907027,0.37538782],"study_design_scores_gemma":[0.00090279063,0.0010180888,0.44112462,0.0011439561,0.000017026563,0.0000017527408,0.00008426081,0.55104727,0.0014155492,0.0010389872,0.0019885749,0.0002171143],"about_ca_topic_score_codex":0.0000548002,"about_ca_topic_score_gemma":0.000018313443,"teacher_disagreement_score":0.9715327,"about_ca_system_score_codex":0.00011834581,"about_ca_system_score_gemma":0.0002984568,"threshold_uncertainty_score":0.64380586},"labels":[],"label_agreement":null},{"id":"W4240488179","doi":"10.32920/ryerson.14653605.v1","title":"Athlete Health Prediction Using Machine Learning Methods","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Machine learning; Random forest; Computer science; Artificial intelligence; Boosting (machine learning); Ensemble learning; Predictive modelling; Task (project management); Upsampling; Class (philosophy); Data mining; Engineering","score_opus":0.09394424712436228,"score_gpt":0.3969218102149389,"score_spread":0.3029775630905766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240488179","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001897879,0.0007921321,0.99416184,0.0011717866,0.00079645216,0.00031009872,0.000022116357,0.0018647228,0.00069104723],"genre_scores_gemma":[0.004214746,0.0004576594,0.9939139,0.00055639434,0.0000859521,0.0000376464,0.0003449052,0.000023243385,0.00036557898],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968814,0.000962822,0.00055172056,0.00096976146,0.00032448166,0.00030979948],"domain_scores_gemma":[0.99759334,0.00008924951,0.0005044732,0.0015216887,0.00017535756,0.00011591008],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019168656,0.00025228492,0.00040052767,0.00021956983,0.00020972433,0.00049900624,0.0011554763,0.00022692778,0.00003756488],"category_scores_gemma":[0.00017290507,0.00025825232,0.00011377217,0.00035822502,0.00003076155,0.00042564538,0.0028096465,0.0010812506,0.0000048508455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006212521,0.0002185212,0.002575634,0.0008250635,0.00018639586,0.000020836169,0.0025127388,0.0073342593,0.043467518,0.044517342,0.0024316744,0.8959038],"study_design_scores_gemma":[0.00006504403,0.00003261042,0.0004612509,0.00015802946,0.00000613572,0.000023627848,0.000021781902,0.9700399,0.016652549,0.0013899185,0.01090822,0.00024095607],"about_ca_topic_score_codex":0.0006454742,"about_ca_topic_score_gemma":0.000014316564,"teacher_disagreement_score":0.9627056,"about_ca_system_score_codex":0.00038252116,"about_ca_system_score_gemma":0.0005649249,"threshold_uncertainty_score":0.99998695},"labels":[],"label_agreement":null},{"id":"W4242929057","doi":"10.1007/978-0-387-39940-9_2303","title":"Copy Transparency","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Transparency (behavior); Computer science; Computer security","score_opus":0.02116825140017607,"score_gpt":0.24750415077588186,"score_spread":0.2263358993757058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242929057","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.520806e-7,0.0017881868,0.29378074,0.00009094041,0.0008305771,0.0006341817,0.0018466794,0.00046523486,0.7005629],"genre_scores_gemma":[0.0015602802,0.016795186,0.09834822,0.00017271026,0.0009777175,0.00014939927,0.0047522546,0.00015330933,0.87709093],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967012,0.000057954145,0.0011584098,0.00092086906,0.00082834635,0.00033323697],"domain_scores_gemma":[0.9953083,0.00012057763,0.0008849751,0.0032941827,0.00022596144,0.00016599696],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004762849,0.00050007564,0.0007876926,0.00037889762,0.00006720001,0.00007319796,0.002513801,0.00034053225,0.000076824814],"category_scores_gemma":[0.000043985794,0.0004968309,0.00015957702,0.00012294197,0.000100050514,0.00077474944,0.00021063715,0.00043765997,0.00025783715],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005047331,0.000042215946,0.00001380296,0.00031873886,0.000039375736,0.00004382575,0.00009317219,0.0000021211863,0.00011398247,0.87893337,0.09546658,0.024927743],"study_design_scores_gemma":[0.00017797116,0.000101146084,0.000018891988,0.0008154004,0.00003389433,0.000026979526,0.000003730129,0.00023063038,0.00031014762,0.003127846,0.99460226,0.0005510802],"about_ca_topic_score_codex":0.000053257656,"about_ca_topic_score_gemma":0.000006869994,"teacher_disagreement_score":0.8991357,"about_ca_system_score_codex":0.00009201533,"about_ca_system_score_gemma":0.0002797059,"threshold_uncertainty_score":0.99974835},"labels":[],"label_agreement":null},{"id":"W4243294319","doi":"10.21203/rs.3.rs-28409/v3","title":"Explanation and Prediction of Clinical Data with Imbalanced Class Distribution based on Pattern Discovery and Disentanglement","year":2020,"lang":"en","type":"preprint","venue":"Research Square","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Interpretability; Computer science; Class (philosophy); Set (abstract data type); Notice; Machine learning; Artificial intelligence; Data mining; Data set","score_opus":0.18006147141839787,"score_gpt":0.43483386384350653,"score_spread":0.25477239242510863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243294319","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009914596,0.000058356818,0.974509,0.0045069703,0.000120455916,0.0011271945,0.009544522,0.0001493522,0.000069552705],"genre_scores_gemma":[0.9814473,0.00046116117,0.004559742,0.00005790196,0.0001052388,0.00013867566,0.0132077765,0.000014085672,0.000008118005],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996112,0.0006157362,0.00056435855,0.0012245289,0.001230912,0.00025246944],"domain_scores_gemma":[0.9967773,0.0004334633,0.0003234247,0.0020263465,0.00028723016,0.00015221232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019997712,0.00019005136,0.00034104093,0.00015062746,0.00010709529,0.00033344878,0.0011144648,0.00017918796,0.0000023161404],"category_scores_gemma":[0.00047170965,0.00015787753,0.000031304116,0.00028888462,0.00023796412,0.00061523315,0.0024829176,0.0008174858,0.0000014020177],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012803084,0.0018723895,0.53619474,0.006020948,0.0002706733,0.00009141201,0.00057120144,0.00018780032,0.0012220005,0.023993691,0.052907027,0.37538782],"study_design_scores_gemma":[0.00090279063,0.0010180888,0.44112462,0.0011439561,0.000017026563,0.0000017527408,0.00008426081,0.55104727,0.0014155492,0.0010389872,0.0019885749,0.0002171143],"about_ca_topic_score_codex":0.0000548002,"about_ca_topic_score_gemma":0.000018313443,"teacher_disagreement_score":0.9715327,"about_ca_system_score_codex":0.00011834581,"about_ca_system_score_gemma":0.0002984568,"threshold_uncertainty_score":0.64380586},"labels":[],"label_agreement":null},{"id":"W4248447296","doi":"10.21203/rs.3.rs-28409/v4","title":"Explanation and Prediction of Clinical Data with Imbalanced Class Distribution Based on Pattern Discovery and Disentanglement","year":2020,"lang":"en","type":"preprint","venue":"Research Square","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Class (philosophy); Artificial intelligence; Computer science; Data mining; Pattern recognition (psychology); Machine learning","score_opus":0.18006147141839787,"score_gpt":0.43483386384350653,"score_spread":0.25477239242510863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248447296","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009914596,0.000058356818,0.974509,0.0045069703,0.000120455916,0.0011271945,0.009544522,0.0001493522,0.000069552705],"genre_scores_gemma":[0.9814473,0.00046116117,0.004559742,0.00005790196,0.0001052388,0.00013867566,0.0132077765,0.000014085672,0.000008118005],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996112,0.0006157362,0.00056435855,0.0012245289,0.001230912,0.00025246944],"domain_scores_gemma":[0.9967773,0.0004334633,0.0003234247,0.0020263465,0.00028723016,0.00015221232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019997712,0.00019005136,0.00034104093,0.00015062746,0.00010709529,0.00033344878,0.0011144648,0.00017918796,0.0000023161404],"category_scores_gemma":[0.00047170965,0.00015787753,0.000031304116,0.00028888462,0.00023796412,0.00061523315,0.0024829176,0.0008174858,0.0000014020177],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012803084,0.0018723895,0.53619474,0.006020948,0.0002706733,0.00009141201,0.00057120144,0.00018780032,0.0012220005,0.023993691,0.052907027,0.37538782],"study_design_scores_gemma":[0.00090279063,0.0010180888,0.44112462,0.0011439561,0.000017026563,0.0000017527408,0.00008426081,0.55104727,0.0014155492,0.0010389872,0.0019885749,0.0002171143],"about_ca_topic_score_codex":0.0000548002,"about_ca_topic_score_gemma":0.000018313443,"teacher_disagreement_score":0.9715327,"about_ca_system_score_codex":0.00011834581,"about_ca_system_score_gemma":0.0002984568,"threshold_uncertainty_score":0.64380586},"labels":[],"label_agreement":null},{"id":"W4249075176","doi":"10.1007/978-1-4614-6170-8_100080","title":"Financial Fraud Detection","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Business; Finance","score_opus":0.014765825143714443,"score_gpt":0.21701455610955034,"score_spread":0.2022487309658359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249075176","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.2195521e-7,0.000012414197,0.5716543,0.00011550449,0.00023903357,0.00008834378,0.0000036028896,0.0006320671,0.42725462],"genre_scores_gemma":[0.002415319,0.0000543605,0.08469522,0.0011169596,0.00035367368,0.000025937026,0.000027769263,0.000031203428,0.91127956],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988631,0.000010010533,0.00024374451,0.00048332766,0.00025148093,0.00014831404],"domain_scores_gemma":[0.9984841,0.00003572998,0.00018623566,0.0011534018,0.000100676676,0.000039892457],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015901131,0.00020332859,0.00019614818,0.00016886534,0.000073811156,0.00009873423,0.0009786672,0.00034961046,0.00014821501],"category_scores_gemma":[0.000039286413,0.00019666292,0.00007972716,0.000035213397,0.000040850013,0.00017247243,0.00023485819,0.00027689745,0.001068443],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.19841e-7,0.000001376582,1.4184167e-7,0.000004570999,0.0000018190018,9.411658e-7,0.0000035369085,7.49431e-8,0.00012155706,0.7776466,0.014964763,0.20725408],"study_design_scores_gemma":[0.000039626946,0.0000407602,0.00002338988,0.000019836716,0.0000030560184,0.0000064651294,5.573697e-8,0.00088539784,0.005419379,0.16458571,0.8287476,0.00022875528],"about_ca_topic_score_codex":0.000004880471,"about_ca_topic_score_gemma":0.000015350392,"teacher_disagreement_score":0.8137828,"about_ca_system_score_codex":0.000071892,"about_ca_system_score_gemma":0.000062297244,"threshold_uncertainty_score":0.99970937},"labels":[],"label_agreement":null},{"id":"W4254827090","doi":"10.1002/9781119302872.ch4","title":"EVALUATING PATTERN RECOGNITION PROBLEM","year":2018,"lang":"en","type":"other","venue":"Pattern Recognition","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Pattern recognition (psychology); Confusion matrix; Computer science; Confusion; Artificial intelligence; Quality (philosophy); Maximization; Machine learning; Data mining; Mathematics; Psychology","score_opus":0.10650189245111907,"score_gpt":0.33870648614346716,"score_spread":0.23220459369234808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254827090","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000531509,0.000049316455,0.80963606,0.00023977595,0.0007278162,0.0010300981,0.00044938608,0.0024647175,0.18534967],"genre_scores_gemma":[0.0033398452,0.00082534784,0.82063943,0.004423011,0.0056477506,0.003444209,0.020262647,0.002069788,0.13934799],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99679905,0.00032355302,0.00057429884,0.0011747426,0.0006535624,0.00047476368],"domain_scores_gemma":[0.99744284,0.000077828045,0.00091352937,0.0011476426,0.00030435142,0.00011382728],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00069543824,0.00047423368,0.00037751865,0.000584139,0.00011334846,0.0003152827,0.0010474521,0.0004842188,0.0044271485],"category_scores_gemma":[0.00008657385,0.000503134,0.000119525444,0.00036687322,0.0000778206,0.00047873022,0.000301158,0.00032147975,0.016183667],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012843855,0.000050698924,0.00006286632,0.00012623347,0.000025182087,0.000003972627,0.00004715152,1.4952038e-8,0.00014077732,0.0000017334867,0.22766827,0.7718718],"study_design_scores_gemma":[0.0044947425,0.00244407,0.0015820351,0.01766928,0.0005130604,0.0003535687,0.000091781396,0.037094194,0.038754087,0.051789816,0.8362869,0.008926465],"about_ca_topic_score_codex":0.00021148096,"about_ca_topic_score_gemma":0.00011314041,"teacher_disagreement_score":0.76294535,"about_ca_system_score_codex":0.00013639647,"about_ca_system_score_gemma":0.00007746733,"threshold_uncertainty_score":0.99974203},"labels":[],"label_agreement":null},{"id":"W4255479603","doi":"10.1109/icse.1998.671609","title":"An investigation on the use of machine learned models for estimating correction costs","year":2002,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Reuse; Computer science; Software; Division (mathematics); Fault (geology); Asset (computer security); Product (mathematics); Artificial intelligence; Machine learning; Software engineering; Reliability engineering; Data mining; Engineering; Mathematics; Programming language","score_opus":0.18746635208566734,"score_gpt":0.30459132983930826,"score_spread":0.11712497775364092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255479603","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022946275,0.0000019863412,0.99521977,0.0014754947,0.00012438536,0.00030562494,0.000005853641,0.00028772338,0.0002845424],"genre_scores_gemma":[0.43177837,0.0000022147674,0.567397,0.00053082244,0.000011725887,0.000045506178,0.000013579605,0.0000048146035,0.00021592857],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934894,0.00006663035,0.00016995531,0.00019299125,0.00013595616,0.000085515],"domain_scores_gemma":[0.99886996,0.00031201806,0.0001318131,0.0005554024,0.00010278994,0.000028028326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023482881,0.00006448363,0.00006513093,0.000059674,0.00009928973,0.000099086385,0.00035319902,0.0000323768,0.000009167092],"category_scores_gemma":[0.00019669255,0.00004566758,0.000019011057,0.00018906336,0.000033254393,0.0010477625,0.000028693228,0.000062733285,0.000004696998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008144122,0.00010918697,0.00013609954,0.000010185763,0.000006513837,1.15862214e-7,0.00068145315,0.03632438,0.011182807,0.48334134,0.030374102,0.43782568],"study_design_scores_gemma":[0.000057746358,0.000100322635,0.000056790162,0.00001403103,0.0000013227314,0.0000010051295,0.0000054401016,0.9575068,0.036175855,0.0058708503,0.00015765395,0.000052208725],"about_ca_topic_score_codex":0.0000690385,"about_ca_topic_score_gemma":0.000008685494,"teacher_disagreement_score":0.9211824,"about_ca_system_score_codex":0.000037885187,"about_ca_system_score_gemma":0.0000074922555,"threshold_uncertainty_score":0.186227},"labels":[],"label_agreement":null},{"id":"W4280544582","doi":"10.1101/2022.04.21.489108","title":"METAbolomics data Balancing with Over-sampling Algorithms (META-BOA): an online resource for addressing class imbalance","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Overfitting; Class (philosophy); Sampling (signal processing); Data mining; Machine learning; Random forest; Visualization; Sample (material); Resource (disambiguation); Artificial intelligence; Algorithm; Artificial neural network","score_opus":0.12695888967369867,"score_gpt":0.31435461819749305,"score_spread":0.18739572852379438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280544582","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013946726,0.0019987684,0.96967554,0.00062910625,0.00076441624,0.0019102455,0.008438879,0.0026301132,0.000006174883],"genre_scores_gemma":[0.11588094,0.00017911322,0.8805685,0.0011551047,0.00071886886,0.0010477358,0.00014093227,0.00029973174,0.0000090513495],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9922378,0.0004333655,0.0011768049,0.0038635333,0.001128937,0.0011595283],"domain_scores_gemma":[0.9859518,0.00039328597,0.0016329358,0.010973602,0.0006351881,0.00041322244],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0028814846,0.0010916896,0.0015089831,0.0005359846,0.0007547127,0.0013856738,0.009312817,0.0005204662,0.000025799898],"category_scores_gemma":[0.0004974565,0.0010913804,0.00023096944,0.0012371999,0.00020185979,0.0019088037,0.006311474,0.0017557588,0.0000034795512],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006274822,0.0040467805,0.008337432,0.004112037,0.008472292,0.0003656599,0.00023931694,0.01226841,0.9001435,0.042774104,0.017740268,0.0008727022],"study_design_scores_gemma":[0.001974985,0.00039355585,0.021512894,0.000652685,0.0019190196,4.9421703e-7,0.000030836338,0.5792584,0.07443198,0.000052715706,0.3152599,0.004512553],"about_ca_topic_score_codex":0.00006854359,"about_ca_topic_score_gemma":0.000010297957,"teacher_disagreement_score":0.82571155,"about_ca_system_score_codex":0.00056302,"about_ca_system_score_gemma":0.001293812,"threshold_uncertainty_score":0.99965096},"labels":[],"label_agreement":null},{"id":"W4280557195","doi":"10.1016/j.knosys.2022.108966","title":"A new classifier for imbalanced data with iterative learning process and ensemble operating process","year":2022,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Ensemble learning; Artificial intelligence; Computer science; Classifier (UML); Machine learning; Process (computing); Pattern recognition (psychology)","score_opus":0.039006438045110864,"score_gpt":0.3154224940669649,"score_spread":0.27641605602185404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280557195","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003015383,0.0004925618,0.9926417,0.00028720812,0.00023254842,0.0014967587,0.00008469586,0.00058510253,0.0011640516],"genre_scores_gemma":[0.9670037,0.0000015455341,0.029419728,0.00007469132,0.00013768995,0.0014875948,0.00030700504,0.000042138498,0.0015259143],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99743676,0.00028201632,0.0004152432,0.0010837008,0.0003843319,0.00039796284],"domain_scores_gemma":[0.9977279,0.00028398802,0.00033122138,0.0011136557,0.00039997997,0.00014329767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096017617,0.000269885,0.00036375824,0.00018112612,0.00085315394,0.0005980409,0.0017315581,0.0000589513,0.000006319991],"category_scores_gemma":[0.00017362015,0.00023702219,0.000023974619,0.00077050127,0.00004776475,0.0009701008,0.00039674898,0.00034928558,0.000005244832],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020405194,0.003521314,0.07687565,0.018576067,0.0011630371,0.00018371522,0.121014886,0.11412216,0.116668545,0.15852001,0.15508674,0.23222737],"study_design_scores_gemma":[0.0014976965,0.0005707719,0.00011976844,0.0002397049,0.000017197139,0.00004398042,0.0013314687,0.9670384,0.007260064,0.0001511796,0.02124551,0.000484291],"about_ca_topic_score_codex":0.000019122686,"about_ca_topic_score_gemma":0.00001727618,"teacher_disagreement_score":0.9639883,"about_ca_system_score_codex":0.00012703419,"about_ca_system_score_gemma":0.0010001122,"threshold_uncertainty_score":0.96654844},"labels":[],"label_agreement":null},{"id":"W4281383153","doi":"10.1002/sim.9442","title":"A classification for complex imbalanced data in disease screening and early diagnosis","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; Canadian Institutes of Health Research","keywords":"Computer science; Artificial intelligence; Machine learning","score_opus":0.1130163235397242,"score_gpt":0.3732825950494658,"score_spread":0.26026627150974163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281383153","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015647751,0.00015334939,0.99163955,0.0045328443,0.000081787075,0.0005435731,0.0013770836,0.00006998813,0.000037062553],"genre_scores_gemma":[0.5261646,0.00010674974,0.47141877,0.00040832913,0.00003047299,0.00061782764,0.001226231,0.000009662618,0.000017343547],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9984828,0.00011646597,0.00037249902,0.0005070894,0.0003208923,0.00020024955],"domain_scores_gemma":[0.998078,0.00068435393,0.00014529134,0.00096653786,0.00004765983,0.00007816916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010105371,0.00009939364,0.00019506172,0.00024397328,0.00011555596,0.000030560765,0.0010675507,0.000016619399,0.000019790961],"category_scores_gemma":[0.0010276878,0.0001034553,0.0000054298853,0.0004477252,0.00011221447,0.0002306793,0.0005856226,0.00017226789,4.5351288e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010718198,0.0002057926,0.3139416,0.00014000267,0.000011070015,0.000051317536,0.0016049107,0.000039233488,0.00084624445,0.46369943,0.04675098,0.1726022],"study_design_scores_gemma":[0.00083691836,0.00010009321,0.6462744,0.000038985916,0.0000055757296,0.0000013626975,0.00010627684,0.31756383,0.0000040620444,0.02267299,0.012285032,0.00011046623],"about_ca_topic_score_codex":0.00013229622,"about_ca_topic_score_gemma":0.000048514947,"teacher_disagreement_score":0.52459985,"about_ca_system_score_codex":0.00007822986,"about_ca_system_score_gemma":0.000050393,"threshold_uncertainty_score":0.4218785},"labels":[],"label_agreement":null},{"id":"W4281769597","doi":"10.30534/ijeter/2022/081062022","title":"Comparing Supervised Machine Learning Algorithms on Classification Efficiency of multiclass classifications problem","year":2022,"lang":"en","type":"article","venue":"International Journal of Emerging Trends in Engineering Research","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Northwest University; Natural Sciences and Engineering Research Council of Canada; Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Artificial intelligence; Machine learning; Naive Bayes classifier; Computer science; Binary classification; Random forest; Receiver operating characteristic; Multiclass classification; Precision and recall; Cross-validation; Statistical classification; Class (philosophy); Support vector machine; Data mining","score_opus":0.10069936090835747,"score_gpt":0.382273824648056,"score_spread":0.2815744637396985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281769597","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.110627525,0.00033474402,0.8779432,0.0068862615,0.0014539927,0.0002910841,0.000038075745,0.00024697479,0.0021781158],"genre_scores_gemma":[0.95766133,0.00005210916,0.042011686,0.000009932028,0.000065043496,0.00004541071,0.000029843692,0.00001909816,0.000105543964],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962784,0.00030454452,0.0008711814,0.00030856524,0.0018869011,0.0003504091],"domain_scores_gemma":[0.9979604,0.00046686878,0.00038197893,0.00039609618,0.00071744993,0.00007719417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035326951,0.00013793807,0.00024002888,0.0035691618,0.0001659978,0.00009586862,0.0026191561,0.000042102893,0.00004338967],"category_scores_gemma":[0.00045585955,0.00014589242,0.00010028627,0.0019290016,0.000057917277,0.00042239446,0.0005359166,0.0013571137,0.0000025484753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015331458,0.0016508825,0.017842418,0.00005570959,0.00016240904,0.00009525387,0.003803932,0.6080103,0.10741779,0.10820765,0.0008501297,0.1517502],"study_design_scores_gemma":[0.0006440264,0.000232061,0.012210714,0.000092983195,0.0000025404856,0.00003773459,0.0001890274,0.9775375,0.004705212,0.0002052952,0.004010403,0.00013247019],"about_ca_topic_score_codex":0.00004033125,"about_ca_topic_score_gemma":0.000003052392,"teacher_disagreement_score":0.8470338,"about_ca_system_score_codex":0.0006786719,"about_ca_system_score_gemma":0.00010763276,"threshold_uncertainty_score":0.5949321},"labels":[],"label_agreement":null},{"id":"W4283741364","doi":"10.1002/for.2885","title":"Predicting earnings management through machine learning ensemble classifiers","year":2022,"lang":"en","type":"article","venue":"Journal of Forecasting","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University; Concordia University","funders":"Social Sciences and Humanities Research Council of Canada; New Brunswick Innovation Foundation","keywords":"Artificial intelligence; Computer science; Ensemble forecasting; Support vector machine; Ensemble learning; Machine learning; Principal component analysis; Random subspace method; Context (archaeology); Feature selection; Pattern recognition (psychology); Classifier (UML)","score_opus":0.04131222352818766,"score_gpt":0.2561634504400872,"score_spread":0.21485122691189953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283741364","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04265976,0.00014094634,0.9436274,0.00073001155,0.0005199466,0.00012812705,0.0000025223092,0.00020694608,0.011984317],"genre_scores_gemma":[0.7428754,0.000025969013,0.25637767,0.0001507015,0.000084772975,0.000010795388,0.000003295971,0.000015431766,0.00045594553],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99801785,0.00018730444,0.0005977693,0.00022435411,0.00067829806,0.00029442427],"domain_scores_gemma":[0.9982416,0.00014635987,0.0011677897,0.0002601127,0.0001210087,0.000063104235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001608104,0.00012643989,0.00020220882,0.00023124895,0.0006492697,0.00012278586,0.0010715335,0.000026308371,0.000032507465],"category_scores_gemma":[0.00021651607,0.00012443232,0.00010465732,0.00057251955,0.000025754336,0.0009277394,0.00072478683,0.00086939055,0.0000025392649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019142352,0.0004579089,0.12865649,0.00027783288,0.00051540765,0.0016399089,0.016369253,0.049222462,0.01851786,0.07403336,0.014193762,0.69592434],"study_design_scores_gemma":[0.0014308844,0.0012481611,0.004578315,0.000235136,0.000062357096,0.0031652222,0.0026613988,0.77404726,0.0076549742,0.007430702,0.19691181,0.00057375606],"about_ca_topic_score_codex":0.000008931564,"about_ca_topic_score_gemma":5.5390893e-7,"teacher_disagreement_score":0.7248248,"about_ca_system_score_codex":0.00022121743,"about_ca_system_score_gemma":0.000050325132,"threshold_uncertainty_score":0.50742024},"labels":[],"label_agreement":null},{"id":"W4285018642","doi":"10.22215/etd/2022-15049","title":"Fraud Detection in Non-Network Knowledge Graph","year":2022,"lang":"en","type":"dissertation","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Graph; Knowledge graph; Credit card fraud; Data mining; Machine learning; Data science; Artificial intelligence; Credit card; Theoretical computer science; World Wide Web","score_opus":0.010653247050996604,"score_gpt":0.2821746145797026,"score_spread":0.271521367528706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285018642","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022583955,0.0004788929,0.8540292,0.00006581472,0.0038317533,0.0008954013,0.000009957488,0.0013523791,0.13707821],"genre_scores_gemma":[0.80610466,0.0007256186,0.11852696,0.00045597926,0.00056144345,0.0033697062,0.0034670057,0.00015793245,0.06663068],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982827,0.000099415054,0.00039707677,0.00065378717,0.00026855816,0.00029846368],"domain_scores_gemma":[0.9986411,0.000071392016,0.00022197151,0.0009375718,0.00008234695,0.000045649413],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043239765,0.00022846548,0.0002468856,0.0005132016,0.00015879405,0.000112385336,0.001392187,0.00023095851,0.00015573794],"category_scores_gemma":[0.000030453532,0.0002485896,0.00008266511,0.0016814145,0.000011550513,0.0003804843,0.00016350552,0.0005821696,0.00008813486],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048726644,0.00039349397,0.00029964666,0.00025149187,0.000046150715,0.000021757782,0.0030553185,0.00011691076,0.0042429003,0.1080677,0.064580075,0.81887585],"study_design_scores_gemma":[0.0017251916,0.00075195637,0.15288611,0.00059288245,0.000058342248,0.000029449637,0.0015579503,0.11198241,0.1348051,0.12883343,0.4620529,0.0047242665],"about_ca_topic_score_codex":0.000107809465,"about_ca_topic_score_gemma":0.0021589554,"teacher_disagreement_score":0.8141516,"about_ca_system_score_codex":0.00019632808,"about_ca_system_score_gemma":0.000117934724,"threshold_uncertainty_score":0.99999666},"labels":[],"label_agreement":null},{"id":"W4285185773","doi":"10.1007/978-981-19-0898-9_50","title":"A Big Data Deep Learning Approach for Credit Card Fraud Detection","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes on data engineering and communications technologies","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Credit card fraud; Undersampling; Credit card; Oversampling; Computer science; Artificial intelligence; Convolutional neural network; Sampling (signal processing); Random forest; Big data; Machine learning; Data mining; World Wide Web; Detector; Telecommunications","score_opus":0.08072228257363258,"score_gpt":0.26509509209801063,"score_spread":0.18437280952437807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285185773","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.17335e-7,0.00576096,0.984646,0.0013666486,0.00013615617,0.00055789825,0.0012912136,0.0046104095,0.0016301853],"genre_scores_gemma":[0.033586696,0.013521192,0.92743367,0.000079413825,0.00011172469,0.00060665864,0.02412253,0.00012450533,0.00041358196],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99799716,0.000029490366,0.00034629466,0.0011027392,0.00025643955,0.00026789177],"domain_scores_gemma":[0.9825667,0.0007657543,0.00026200415,0.016297892,0.00007658468,0.000031071602],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00045245167,0.00040807156,0.00037736987,0.00054275664,0.0005555813,0.00024852794,0.01376703,0.00047737037,0.0000016210066],"category_scores_gemma":[0.001363882,0.0004119822,0.00004593582,0.00024312199,0.00016055844,0.00044801697,0.012457601,0.0017600692,0.0000025382756],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004761166,0.000025768071,9.644764e-7,0.00009232833,0.00007751015,6.371859e-7,0.00003601237,0.0021761053,0.0002741288,0.06657006,0.0004353001,0.93030643],"study_design_scores_gemma":[0.0000802161,0.00009451044,0.0000021313185,0.00004259254,0.000039628107,0.00001524137,0.00001167355,0.41164637,0.00042729868,0.003320135,0.5839541,0.00036612328],"about_ca_topic_score_codex":0.00001549725,"about_ca_topic_score_gemma":0.000017598215,"teacher_disagreement_score":0.9299403,"about_ca_system_score_codex":0.000110459514,"about_ca_system_score_gemma":0.00004356346,"threshold_uncertainty_score":0.9998332},"labels":[],"label_agreement":null},{"id":"W4285326639","doi":"10.1109/csci54926.2021.00091","title":"A Deep Learning BERT-Based Approach to Person-Job Fit in Talent Recruitment","year":2021,"lang":"en","type":"article","venue":"2021 International Conference on Computational Science and Computational Intelligence (CSCI)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Margin (machine learning); Workload; Computer science; Process (computing); Variety (cybernetics); The Internet; World Wide Web; Data science; Artificial intelligence; Machine learning; Operating system","score_opus":0.16738991597742203,"score_gpt":0.36257764610365123,"score_spread":0.1951877301262292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285326639","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003798023,0.000045660072,0.97187245,0.00816399,0.00036052236,0.0004917936,0.000020999114,0.0001182602,0.015128275],"genre_scores_gemma":[0.7525861,0.000025558715,0.24478519,0.0019339502,0.000054075357,0.000216147,0.00013040072,0.000011615694,0.00025695635],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948735,0.00017483665,0.00060914963,0.0015204394,0.002316249,0.00050579506],"domain_scores_gemma":[0.9963141,0.00042944093,0.00021870098,0.00038244398,0.0023411599,0.00031413708],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001124059,0.00033354227,0.0002920866,0.00089843693,0.00043513783,0.0010464367,0.0017642826,0.00008856767,0.00021745004],"category_scores_gemma":[0.000490784,0.0003546545,0.00007977487,0.0022859324,0.00038205594,0.0010349774,0.00046889973,0.0004270236,0.00015688884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016812257,0.00024203694,0.00035600533,0.000007420946,0.000011207101,0.000016934615,0.00050977373,0.48624778,0.00020905842,0.4627604,0.00014927812,0.049473308],"study_design_scores_gemma":[0.00021186544,0.00013058567,0.009069628,0.00010499296,0.0000030147235,0.000041436313,0.00065128517,0.9562613,0.00086981466,0.031329945,0.000937014,0.00038911696],"about_ca_topic_score_codex":0.000042074233,"about_ca_topic_score_gemma":0.000020481162,"teacher_disagreement_score":0.74878806,"about_ca_system_score_codex":0.00062148785,"about_ca_system_score_gemma":0.0014256559,"threshold_uncertainty_score":0.9999906},"labels":[],"label_agreement":null},{"id":"W4285445692","doi":"10.20533/jitst.2046.3723.2021.0091","title":"Oversampling Techniques in Machine Learning Detection of Credit Card Fraud","year":2021,"lang":"en","type":"article","venue":"Journal of Internet Technology and Secured Transaction","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Credit card fraud; Oversampling; Credit card; Computer science; Computer security; Machine learning; Artificial intelligence; Business; World Wide Web; Telecommunications","score_opus":0.00928993757197922,"score_gpt":0.2381884595590167,"score_spread":0.2288985219870375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285445692","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08937336,0.00063931016,0.90913856,0.0004873059,0.0001494178,0.000048395883,0.0000018343225,0.00011413994,0.000047679445],"genre_scores_gemma":[0.9645191,0.000643231,0.034773063,0.000018154087,0.000016845548,0.0000036406932,0.0000017726737,0.000005564259,0.000018659202],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99907863,0.000063971675,0.00044952714,0.00016506859,0.00013590565,0.000106921056],"domain_scores_gemma":[0.9992067,0.00004512777,0.00035287515,0.00015634083,0.00021634302,0.000022565007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033640326,0.00009044254,0.00022987797,0.00079787424,0.000026356915,0.000023849572,0.00025044268,0.00023366784,0.000004692528],"category_scores_gemma":[0.00009681745,0.00008887172,0.000055099434,0.0006005709,0.000059481812,0.00045086347,0.000029527362,0.0006719544,2.8571284e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008385504,0.0001117426,0.0024375487,0.00006202403,0.000062961364,0.00006351785,0.0006949998,0.000051366478,0.71798545,0.0069331126,0.000018816165,0.2714946],"study_design_scores_gemma":[0.00027541304,0.00030007443,0.0007786317,0.00014230901,0.000010642361,0.000510142,0.00013355323,0.00796375,0.9835932,0.0036771812,0.0025346605,0.00008042246],"about_ca_topic_score_codex":0.000019826013,"about_ca_topic_score_gemma":0.00005278558,"teacher_disagreement_score":0.87514573,"about_ca_system_score_codex":0.000065356566,"about_ca_system_score_gemma":0.000036733636,"threshold_uncertainty_score":0.36240837},"labels":[],"label_agreement":null},{"id":"W4286009680","doi":"10.1101/2022.07.18.500262","title":"Class imbalance should not throw you off balance: Choosing the right classifiers and performance metrics for brain decoding with imbalanced data","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University; 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":"Computer science; Magnetoencephalography; Metric (unit); Artificial intelligence; Robustness (evolution); Binary classification; Machine learning; Decoding methods; Random forest; Class (philosophy); Receiver operating characteristic; Performance metric; Electroencephalography; Binary number; Sensitivity (control systems); Pattern recognition (psychology); Support vector machine; Mathematics; Psychology; Algorithm","score_opus":0.044767843900555215,"score_gpt":0.2714744256389494,"score_spread":0.2267065817383942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286009680","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.087454185,0.0030741477,0.8840716,0.011994001,0.00264329,0.0046849367,0.0033291292,0.00266977,0.00007895372],"genre_scores_gemma":[0.8355865,0.0013699315,0.15915401,0.0021774736,0.00035962032,0.0011339302,0.000018127499,0.00017476307,0.00002563333],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9934077,0.00031900202,0.0009458036,0.0029508024,0.0012149303,0.0011617278],"domain_scores_gemma":[0.9896861,0.0007783944,0.0012892674,0.007391749,0.0005605331,0.0002940124],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0034487927,0.00095523504,0.0009615654,0.00051380094,0.0012364385,0.0013702606,0.0075065694,0.0004946852,0.000014643797],"category_scores_gemma":[0.0007489779,0.0007964838,0.00011930565,0.0019392192,0.00044660928,0.0016230845,0.004885363,0.0018601633,0.0000055394225],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011923155,0.0012390012,0.16403253,0.006237525,0.0022406913,0.00022491944,0.0004310595,0.0011277776,0.6083468,0.12391763,0.088758536,0.0022511696],"study_design_scores_gemma":[0.0022776427,0.0004380153,0.12316212,0.00086054223,0.00026444774,9.96801e-7,0.000027279777,0.5502915,0.12418852,0.000040694216,0.19506167,0.0033866165],"about_ca_topic_score_codex":0.0000152230505,"about_ca_topic_score_gemma":0.0000036761671,"teacher_disagreement_score":0.74813235,"about_ca_system_score_codex":0.0006688273,"about_ca_system_score_gemma":0.0010407021,"threshold_uncertainty_score":0.9996664},"labels":[],"label_agreement":null},{"id":"W4287064118","doi":"10.48550/arxiv.2107.14194","title":"On the combined effect of class imbalance and concept complexity in deep\\n learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Alberta","funders":"","keywords":"Artificial intelligence; Overfitting; MNIST database; Machine learning; Deep learning; Computer science; Class (philosophy); Scarcity; Simple (philosophy); Artificial neural network; Economics","score_opus":0.059201851419720744,"score_gpt":0.20934918404861444,"score_spread":0.15014733262889368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287064118","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7133704,0.00005800703,0.28455067,0.00020436344,0.00011808835,0.0004056807,0.000009316129,0.00016537451,0.0011181067],"genre_scores_gemma":[0.9989539,0.00010954691,0.0007114576,0.000074303956,0.000007129949,0.0000029548914,0.000031094572,0.000009328073,0.000100297904],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979539,0.0007427098,0.00020866212,0.0007768021,0.00010282696,0.00021509007],"domain_scores_gemma":[0.99752456,0.0008592352,0.00032365668,0.001141571,0.00009671414,0.00005426855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005212304,0.00023400021,0.00041102973,0.00014700722,0.000097787895,0.000086552645,0.001397849,0.00018005299,0.000013201403],"category_scores_gemma":[0.00022259938,0.00021172487,0.000084708954,0.0005170048,0.0003474894,0.00019157113,0.0015521037,0.000835785,0.0000039652773],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009050479,0.00010876539,0.03060634,0.00016094244,0.000057619065,0.00011208411,0.0005319847,0.017799282,0.00056548795,0.9487555,0.00013758393,0.0010738928],"study_design_scores_gemma":[0.0011824564,0.00041612508,0.053706933,0.00043606394,0.000029445297,0.000003914565,0.000142417,0.9018767,0.009043194,0.032540593,0.00010135303,0.00052080705],"about_ca_topic_score_codex":0.000096702875,"about_ca_topic_score_gemma":0.000038119175,"teacher_disagreement_score":0.91621494,"about_ca_system_score_codex":0.00012835427,"about_ca_system_score_gemma":0.000060354378,"threshold_uncertainty_score":0.86338896},"labels":[],"label_agreement":null},{"id":"W4287183744","doi":"10.48550/arxiv.2105.04009","title":"RB-CCR: Radial-Based Combined Cleaning and Resampling algorithm for\\n imbalanced data classification","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Resampling; Oversampling; Benchmark (surveying); Computer science; Binary classification; Artificial intelligence; Binary number; Prior probability; Class (philosophy); Data mining; Machine learning; Pattern recognition (psychology); Algorithm; Mathematics; Support vector machine; Bayesian probability","score_opus":0.16626608004527077,"score_gpt":0.2443103710650201,"score_spread":0.07804429101974933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287183744","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046350304,0.000069914495,0.9926188,0.00032524203,0.00045465556,0.0006975093,0.00030024935,0.00072112604,0.00017747674],"genre_scores_gemma":[0.6293393,0.0002149565,0.3673206,0.00017335906,0.00008383174,0.000009834324,0.0027036343,0.000033116095,0.000121388766],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966407,0.00019958345,0.00037675773,0.0022318484,0.00014376729,0.00040734388],"domain_scores_gemma":[0.99432933,0.00039625517,0.0005458129,0.004205588,0.00035194808,0.0001710354],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00076594995,0.00037163697,0.0004577396,0.00030733307,0.0003073059,0.0005056702,0.0035024616,0.0003756458,0.0000048276347],"category_scores_gemma":[0.00020132185,0.00048018096,0.0001052607,0.0006087742,0.00016266826,0.0009690059,0.002933715,0.00054255925,0.000004644862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029006277,0.0010862831,0.008057262,0.001312936,0.00071243563,0.00036731994,0.000868837,0.02388442,0.007814935,0.6361327,0.009348078,0.3101247],"study_design_scores_gemma":[0.00084519474,0.00004767708,0.0019286429,0.00016047769,0.000059906015,0.0000024879955,0.00009273364,0.9875354,0.0009696552,0.0065699723,0.0012799999,0.0005078284],"about_ca_topic_score_codex":0.00005927201,"about_ca_topic_score_gemma":0.0000175523,"teacher_disagreement_score":0.963651,"about_ca_system_score_codex":0.0002469575,"about_ca_system_score_gemma":0.00044438877,"threshold_uncertainty_score":0.999765},"labels":[],"label_agreement":null},{"id":"W4292975728","doi":"10.1109/icdh55609.2022.00038","title":"Detection of Erythropoietin in Blood to Uncover Doping in Sports using Machine Learning","year":2022,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"World Anti-Doping Agency","funders":"","keywords":"Erythropoietin; Computer science; Doping; Artificial intelligence; Machine learning; Medicine; Materials science; Optoelectronics; Internal medicine","score_opus":0.016727464574953187,"score_gpt":0.25649218897587595,"score_spread":0.23976472440092275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292975728","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.567972,0.000014333419,0.4314108,0.000111155954,0.00006280577,0.00013156721,0.0000012003497,0.00009623086,0.00019991367],"genre_scores_gemma":[0.9346941,0.0000046391074,0.065134384,0.000091176116,0.0000048248107,0.000018614795,0.0000025318982,0.000005623793,0.000044069726],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99898225,0.00009692596,0.00027382615,0.00025931664,0.00024473987,0.0001429668],"domain_scores_gemma":[0.99955124,0.000028097873,0.00009943577,0.00028040612,0.000020464702,0.000020333195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005775295,0.00006515023,0.00011239409,0.0003922631,0.000059569695,0.000018356921,0.00032376917,0.000019671686,0.000040933734],"category_scores_gemma":[0.000048214144,0.00007365122,0.00001712367,0.0011051184,0.000009164018,0.00024281196,0.00043034693,0.00020222114,9.082574e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002651789,0.0003063326,0.35941023,0.000035945875,0.0000048184083,0.000047130943,0.0016380843,0.039643556,0.54860467,0.005167055,0.000019666404,0.045095995],"study_design_scores_gemma":[0.0006330283,0.000228936,0.07146553,0.000065182765,0.0000035263413,0.00005215421,0.00028194726,0.35455456,0.56924194,0.0010719955,0.0020384272,0.00036274665],"about_ca_topic_score_codex":0.0011546047,"about_ca_topic_score_gemma":0.0002322463,"teacher_disagreement_score":0.36672214,"about_ca_system_score_codex":0.00013363743,"about_ca_system_score_gemma":0.000036255216,"threshold_uncertainty_score":0.30034098},"labels":[],"label_agreement":null},{"id":"W4294300752","doi":"10.21203/rs.3.rs-1996324/v1","title":"Supply Chain Fraud Prediction with Machine Learning and Artificial intelligence","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Roads University","funders":"","keywords":"Supply chain; Computer science; Artificial intelligence; Machine learning; Supply chain management; Business intelligence; Data mining; Business; Marketing","score_opus":0.07297806651677202,"score_gpt":0.3786026916440712,"score_spread":0.30562462512729915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294300752","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032860385,0.0007646114,0.9887282,0.0032914202,0.0001742594,0.001372925,0.00031389698,0.00096707774,0.0011015468],"genre_scores_gemma":[0.940692,0.001550138,0.054895725,0.000033719007,0.0001821013,0.0011200424,0.0008110126,0.00005006288,0.0006651845],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956651,0.0008787391,0.0003404574,0.0011006115,0.001498541,0.0005165677],"domain_scores_gemma":[0.997883,0.0003401921,0.00015028569,0.0011124195,0.0003599488,0.00015414432],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0028589247,0.0002263565,0.0002412577,0.0006771637,0.00062614505,0.00066701014,0.001465876,0.00017667156,0.00018710441],"category_scores_gemma":[0.000388221,0.00021122675,0.000041307947,0.0008705311,0.00023444774,0.00032878842,0.0043688277,0.003203276,0.000019729478],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024978872,0.0005300555,0.04003077,0.0014952593,0.000115764116,0.00020131045,0.0053814496,0.0032728466,0.001923088,0.3090326,0.0031123844,0.6346547],"study_design_scores_gemma":[0.00015971431,0.0019891923,0.012896361,0.0008012335,0.000012460744,0.00005954745,0.001272128,0.8296186,0.010655838,0.07680391,0.06479248,0.00093858875],"about_ca_topic_score_codex":0.00025383697,"about_ca_topic_score_gemma":0.000034302262,"teacher_disagreement_score":0.937406,"about_ca_system_score_codex":0.00029519963,"about_ca_system_score_gemma":0.0003460232,"threshold_uncertainty_score":0.9990964},"labels":[],"label_agreement":null},{"id":"W4295135780","doi":"10.1007/978-3-031-15471-3_32","title":"Assessment of Creditworthiness Models Privacy-Preserving Training with Synthetic Data","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Synthetic data; Scarcity; Quality (philosophy); Training set; Work (physics); Data quality; Credit risk; Data mining; Artificial intelligence; Finance; Business; Metric (unit)","score_opus":0.07513686561004515,"score_gpt":0.30561069643383176,"score_spread":0.2304738308237866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295135780","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000018247689,0.000117512354,0.99090195,0.0006290593,0.0005363579,0.00049947755,0.00008287255,0.0002832319,0.0069313105],"genre_scores_gemma":[0.21275997,0.000042275322,0.7866608,0.00023658757,0.00010355798,0.000026267451,0.00007791744,0.000037723188,0.000054902277],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946107,0.00007212,0.000690994,0.0022089987,0.0018658442,0.00055132364],"domain_scores_gemma":[0.9911161,0.0005961807,0.00070691743,0.007158237,0.0003039795,0.00011858522],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0020377217,0.00047792587,0.0006679896,0.00081992795,0.00027198603,0.00038438188,0.016736642,0.0001614846,0.00005847755],"category_scores_gemma":[0.00014296571,0.000422477,0.000057526355,0.0009010111,0.00064901833,0.0026889157,0.011448628,0.0010051671,0.0000010391963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009628536,0.0001029004,0.00009981136,0.000198104,0.00004701722,0.00011716579,0.0018044745,0.17702761,0.00035237236,0.24386948,0.000117757074,0.57625365],"study_design_scores_gemma":[0.00013673103,0.0001253494,0.00012842855,0.00039347785,0.000010304559,0.000057161807,5.050352e-7,0.90404063,0.00023098638,0.09328539,0.0011371437,0.00045388658],"about_ca_topic_score_codex":0.000034153956,"about_ca_topic_score_gemma":0.000028580644,"teacher_disagreement_score":0.727013,"about_ca_system_score_codex":0.00030739498,"about_ca_system_score_gemma":0.0015552663,"threshold_uncertainty_score":0.9998227},"labels":[],"label_agreement":null},{"id":"W4295833879","doi":"10.2139/ssrn.4216426","title":"Ranking Loss and Sequestering Learning for Reducing Image Search Bias in Histopathology","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Ranking (information retrieval); Histopathology; Artificial intelligence; Computer science; Image (mathematics); Machine learning; Pattern recognition (psychology); Medicine; Pathology","score_opus":0.03102909287148709,"score_gpt":0.29584827914889483,"score_spread":0.26481918627740775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295833879","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19218478,0.00064236345,0.8056771,0.001083095,0.000098053184,0.00014531345,9.627141e-7,0.00009241128,0.0000759294],"genre_scores_gemma":[0.97932327,0.00045507372,0.019814953,0.00005986281,0.000049936152,0.00004620203,0.0000040774653,0.000015770822,0.00023085775],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99766344,0.0003262429,0.00026491197,0.0003112764,0.00019621273,0.0012379222],"domain_scores_gemma":[0.99946445,0.00010818429,0.0001401311,0.00020339372,0.000048898204,0.00003496017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005241948,0.00009576522,0.0001463293,0.00031465502,0.00049731263,0.00012058274,0.0006098722,0.000028891074,0.0000035691219],"category_scores_gemma":[0.00011771112,0.00010677557,0.00003489768,0.0002765877,0.00004072739,0.0004855402,0.0003724431,0.0019118842,8.2471774e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000109769135,0.00009778375,0.01067365,0.000049659553,0.000025845307,0.00011150062,0.004785716,0.002111753,0.124661334,0.54015046,0.000068870744,0.31715366],"study_design_scores_gemma":[0.005360983,0.0036854222,0.010955115,0.00017281467,0.00003001264,0.029048173,0.006273697,0.2588979,0.015889714,0.6497514,0.01826208,0.0016726626],"about_ca_topic_score_codex":0.00003111191,"about_ca_topic_score_gemma":0.000021740943,"teacher_disagreement_score":0.78713846,"about_ca_system_score_codex":0.001434616,"about_ca_system_score_gemma":0.00073918706,"threshold_uncertainty_score":0.83062917},"labels":[],"label_agreement":null},{"id":"W4297129241","doi":"10.1007/978-981-19-5727-7_86","title":"The Detection and Prediction of Financial Frauds","year":2022,"lang":"en","type":"book-chapter","venue":"Applied economics and policy studies","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Finance; Actuarial science; Predictive modelling; Flag (linear algebra); Computer science; Business; Accounting; Machine learning; Mathematics","score_opus":0.026470891923053984,"score_gpt":0.24357878913618172,"score_spread":0.21710789721312773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297129241","genre_codex":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003429265,0.022065591,0.028201906,0.011306583,0.002374774,0.0032246322,0.001908803,0.0007730976,0.9267154],"genre_scores_gemma":[0.29632536,0.6655926,0.0047607417,0.0015859177,0.0014425223,0.0007258179,0.00005916498,0.000095838455,0.029412068],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993737,0.0000047987382,0.0002398059,0.0002496386,0.00003956911,0.00009253586],"domain_scores_gemma":[0.9992924,0.00010838563,0.00025054865,0.00030664768,0.000022905322,0.000019166568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018173,0.00012705146,0.00019885626,0.00008925473,0.0003453619,0.00003835068,0.0001985939,0.00007189377,9.4757377e-7],"category_scores_gemma":[0.000016342594,0.0001111983,0.000023719735,0.000021341171,0.0001752272,0.000071113114,0.00046582145,0.00012784803,0.0000010051997],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035784312,0.0000011369746,0.0000015463373,0.000009982312,0.000028654546,2.7608651e-8,0.0001894785,0.0000012446075,0.000018754206,0.87981504,0.0004256537,0.11950491],"study_design_scores_gemma":[0.0000835504,0.000050477505,0.0005809933,0.000004916111,0.00001072555,0.0000022472125,0.000021780272,0.00017041854,0.00022682102,0.28790247,0.7108447,0.00010090537],"about_ca_topic_score_codex":0.000015375936,"about_ca_topic_score_gemma":0.000039421695,"teacher_disagreement_score":0.8973033,"about_ca_system_score_codex":0.00007070021,"about_ca_system_score_gemma":0.000046856338,"threshold_uncertainty_score":0.4534535},"labels":[],"label_agreement":null},{"id":"W4298004843","doi":"10.32388/1vzc8w","title":"Supply Chain Fraud Prediction with Machine Learning and Artificial intelligence","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Roads University","funders":"","keywords":"Supply chain; Artificial intelligence; Computer science; Machine learning; Supply chain management; Business intelligence; Data mining; Business; Marketing","score_opus":0.026301651108874457,"score_gpt":0.27017809034311685,"score_spread":0.2438764392342424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298004843","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000681112,0.00012774626,0.993914,0.0015514926,0.00022359456,0.00041103203,0.000072246774,0.0012692269,0.0017495371],"genre_scores_gemma":[0.5819755,0.000515122,0.414929,0.00021467272,0.00011090576,0.00041949953,0.00057686295,0.000035310513,0.0012231034],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980518,0.00014758037,0.0003291954,0.0008530935,0.00040499686,0.00021328851],"domain_scores_gemma":[0.99879867,0.00007706717,0.00022697698,0.00075412414,0.00007173095,0.00007141179],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055560004,0.00022696673,0.00021154288,0.00022976611,0.00022832041,0.0003552328,0.0009307265,0.00012417666,0.00023519115],"category_scores_gemma":[0.000055706292,0.00020325762,0.000030227606,0.00028300853,0.000081669335,0.00028429655,0.0022782802,0.0010793048,0.000008491282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005873441,0.00019805669,0.014314511,0.00017679745,0.0000753314,0.000031527725,0.0017551469,0.003437749,0.0010562853,0.49483186,0.0013302328,0.4827338],"study_design_scores_gemma":[0.000054655808,0.0003758941,0.0023963898,0.000077468714,0.00001589628,0.000041841504,0.00017704717,0.92395395,0.009932563,0.03941629,0.022980984,0.0005770139],"about_ca_topic_score_codex":0.00014550776,"about_ca_topic_score_gemma":0.000023903362,"teacher_disagreement_score":0.9205162,"about_ca_system_score_codex":0.00009780876,"about_ca_system_score_gemma":0.00010649197,"threshold_uncertainty_score":0.8288605},"labels":[],"label_agreement":null},{"id":"W4298150045","doi":"10.18280/ria.360415","title":"Online Transaction Fraud Detection Using Efficient Dimensionality Reduction and Machine Learning Techniques","year":2022,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Dimensionality reduction; Machine learning; Database transaction; Payment; Artificial intelligence; Transaction data; Reduction (mathematics); Curse of dimensionality; Data mining; Database; World Wide Web","score_opus":0.053298937610603996,"score_gpt":0.2895001731950913,"score_spread":0.2362012355844873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298150045","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10209497,0.00017220236,0.8961585,0.0003979528,0.000255367,0.00028753345,0.0000143504985,0.0005620818,0.00005705233],"genre_scores_gemma":[0.9530635,0.00006310065,0.04654962,0.000041434992,0.000043209697,0.00005407332,0.000029741976,0.00001506815,0.00014023557],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982618,0.00023744041,0.00040618362,0.00057728356,0.00028877793,0.00022848179],"domain_scores_gemma":[0.99908626,0.00006192135,0.00021012197,0.00048190448,0.00009735811,0.00006243457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077977986,0.00015306215,0.00015800323,0.00023743408,0.00091117737,0.000078084384,0.0003571212,0.000056078847,0.00005303921],"category_scores_gemma":[0.000050790808,0.00017264414,0.00005626351,0.0007525734,0.00007488102,0.00028604726,0.00022163858,0.00047731126,0.0000059261797],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029425628,0.00041695227,0.000059588503,0.000035519475,0.000010669533,0.0000051867773,0.00085565535,0.100810915,0.60302085,0.004520392,0.00001293369,0.29022193],"study_design_scores_gemma":[0.000014150967,0.00009212028,0.000040064795,0.000011396784,0.00000485478,0.00013250847,0.0002362662,0.600056,0.39599732,0.0006128234,0.002679523,0.00012295855],"about_ca_topic_score_codex":0.00013603954,"about_ca_topic_score_gemma":0.00000478647,"teacher_disagreement_score":0.85096854,"about_ca_system_score_codex":0.00023698864,"about_ca_system_score_gemma":0.00003183334,"threshold_uncertainty_score":0.7040224},"labels":[],"label_agreement":null},{"id":"W4298237571","doi":"10.48550/arxiv.1803.03877","title":"On dynamic ensemble selection and data preprocessing for multi-class\\n imbalance learning","year":2018,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Preprocessor; Ensemble learning; Computer science; Artificial intelligence; Class (philosophy); Machine learning; Selection (genetic algorithm); Data pre-processing; Data mining; Binary number; Pattern recognition (psychology); Mathematics","score_opus":0.14781214856598615,"score_gpt":0.27220805457910935,"score_spread":0.1243959060131232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298237571","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06352011,0.000072604,0.93353456,0.000085715,0.00046501405,0.0011510914,0.00014036536,0.0007088015,0.0003217298],"genre_scores_gemma":[0.9377538,0.00067847717,0.057974704,0.00009047833,0.00009467748,0.000009412873,0.0003831723,0.00006439381,0.0029508902],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9935133,0.00034290898,0.0005266885,0.004645929,0.0001873923,0.0007837984],"domain_scores_gemma":[0.9940742,0.00042674254,0.0011432667,0.0034117654,0.00069868524,0.00024530955],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012994194,0.00069770584,0.0006208635,0.00048502441,0.0011459045,0.00063877867,0.0040238583,0.0006243307,0.000016252676],"category_scores_gemma":[0.0006852992,0.000889957,0.000119410615,0.0010028185,0.00039075522,0.0019556002,0.004259564,0.0011323387,0.00006865695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003905168,0.00460834,0.028647026,0.007671222,0.0018557466,0.00023149163,0.0041937777,0.40720284,0.0503618,0.31938028,0.008568003,0.16337429],"study_design_scores_gemma":[0.0010005898,0.0003535499,0.0010642381,0.00053990603,0.00011319902,0.0000148488225,0.00006425394,0.98271567,0.0018718893,0.009419021,0.0019802742,0.00086255645],"about_ca_topic_score_codex":0.000057046374,"about_ca_topic_score_gemma":0.00010875588,"teacher_disagreement_score":0.87555987,"about_ca_system_score_codex":0.0005955566,"about_ca_system_score_gemma":0.00047966663,"threshold_uncertainty_score":0.99935514},"labels":[],"label_agreement":null},{"id":"W4298343014","doi":"10.18280/ria.360401","title":"Ensemble Learning with Supervised Machine Learning Models to Predict Credit Card Fraud Transactions","year":2022,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Credit card fraud; Confusion matrix; Credit card; Machine learning; Ensemble learning; Artificial intelligence; Boosting (machine learning); Payment; Confusion; Gradient boosting; Voting; Majority rule; Supervised learning; Random forest; World Wide Web; Artificial neural network","score_opus":0.053967717607796166,"score_gpt":0.25298740370822115,"score_spread":0.19901968610042498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298343014","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035574737,0.00010021973,0.9911607,0.0011777227,0.00019026149,0.0004875337,0.000028726121,0.0009288733,0.0023685154],"genre_scores_gemma":[0.9406754,0.00004783237,0.054338265,0.00019006482,0.000042904903,0.00040462392,0.0000535696,0.00003790089,0.0042094365],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975316,0.00024046272,0.0004418208,0.00078635226,0.0005117444,0.00048804987],"domain_scores_gemma":[0.99844384,0.0001661572,0.00013472655,0.0009188094,0.00015380011,0.00018268912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066338474,0.00023256773,0.00026210863,0.00029811903,0.0010382188,0.00017546913,0.001340793,0.000053927783,0.00029901837],"category_scores_gemma":[0.00004780863,0.0002435706,0.00009116714,0.001394263,0.00005344643,0.00062394445,0.00024700843,0.00085193117,0.00012344656],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002656593,0.00009881867,0.00010116519,0.000015897618,0.000015458048,0.000015416714,0.003953169,0.94270617,0.005684836,0.004224398,0.00033255506,0.04282556],"study_design_scores_gemma":[0.00004709807,0.00053592277,0.000008463246,0.000025038056,0.000009765375,0.00005778817,0.001192892,0.9234522,0.040217847,0.0006832865,0.033480413,0.00028929499],"about_ca_topic_score_codex":0.0001796797,"about_ca_topic_score_gemma":0.000026083311,"teacher_disagreement_score":0.93711793,"about_ca_system_score_codex":0.00017488629,"about_ca_system_score_gemma":0.000102874714,"threshold_uncertainty_score":0.9932521},"labels":[],"label_agreement":null},{"id":"W4304161247","doi":"10.3389/fdata.2022.961039","title":"The determinants of investment fraud: A machine learning and artificial intelligence approach","year":2022,"lang":"en","type":"article","venue":"Frontiers in Big Data","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Royal Roads University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Investment (military); Artificial intelligence; Artificial neural network; Machine learning; Business; Computer science; Law; Political science","score_opus":0.09281099944046155,"score_gpt":0.29500667616988857,"score_spread":0.202195676729427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4304161247","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00079266715,0.0010489196,0.9968409,0.0002759712,0.00044950758,0.0002187679,0.0001283331,0.00005549248,0.00018946425],"genre_scores_gemma":[0.35216463,0.00072724005,0.6461755,0.0002688964,0.000043169635,0.00014879674,0.00031433484,0.000016001419,0.00014145729],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986663,0.00020390388,0.00029704144,0.00040321818,0.00025758814,0.00017196579],"domain_scores_gemma":[0.9985389,0.000062155654,0.00016450556,0.0011894231,0.000014634473,0.00003035023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011485874,0.00008250956,0.00013261415,0.00012089882,0.0002564405,0.00006732007,0.0024774582,0.000022203916,0.000001170378],"category_scores_gemma":[0.00016907489,0.00006883668,0.000010086986,0.000419922,0.0001395334,0.00023607869,0.0029721565,0.00025369917,4.643294e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001634849,0.00008230476,0.018470477,0.000014241334,0.0000074000905,0.0000038608796,0.00043890788,0.000038568236,0.000081098144,0.012591912,0.004424411,0.9638305],"study_design_scores_gemma":[0.000049179744,0.00006515543,0.0008461443,0.000007423819,0.0000032682453,0.00001005652,0.00050992524,0.9153048,0.0014314712,0.015617954,0.0660286,0.00012601982],"about_ca_topic_score_codex":0.000042740787,"about_ca_topic_score_gemma":0.000014765813,"teacher_disagreement_score":0.96370447,"about_ca_system_score_codex":0.0000457293,"about_ca_system_score_gemma":0.000052345455,"threshold_uncertainty_score":0.4603775},"labels":[],"label_agreement":null},{"id":"W4304757181","doi":"10.1093/bioinformatics/btac649","title":"METAbolomics data Balancing with Over-sampling Algorithms (META-BOA): an online resource for addressing class imbalance","year":2022,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Overfitting; Sampling (signal processing); Class (philosophy); Data mining; Machine learning; Sample (material); Visualization; Random forest; Resource (disambiguation); Artificial intelligence; Algorithm; Artificial neural network","score_opus":0.1940735828464191,"score_gpt":0.3426043390083074,"score_spread":0.1485307561618883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4304757181","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008626782,0.00018212218,0.9944239,0.00049598934,0.00015046707,0.00063195644,0.002376019,0.000699202,0.00017765447],"genre_scores_gemma":[0.0060134744,0.0000212582,0.98790926,0.0018813825,0.0001137959,0.00016068338,0.003788806,0.00003872508,0.000072626404],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99732876,0.000092059214,0.0007538872,0.0005830904,0.0007032741,0.0005389275],"domain_scores_gemma":[0.9954299,0.00025286782,0.0006969867,0.0033431337,0.000134509,0.00014262079],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014541211,0.00030917913,0.000490038,0.00021120303,0.0007263645,0.00045732077,0.004167087,0.00007237141,0.0000125393135],"category_scores_gemma":[0.00014663833,0.0002683201,0.000078853074,0.0006764086,0.00008076401,0.0028180722,0.0019197961,0.0003851502,0.0000024820763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050541776,0.0023869001,0.0014466551,0.0015111323,0.0027563574,0.000040901192,0.010170514,0.031132126,0.0064052735,0.10164551,0.13882138,0.70317787],"study_design_scores_gemma":[0.00043147933,0.00015929308,0.00017669733,0.000015612295,0.00011212924,0.000039735136,0.0004443669,0.80101293,0.0004976821,0.00021282081,0.1965528,0.00034443353],"about_ca_topic_score_codex":0.000014596421,"about_ca_topic_score_gemma":0.000010957745,"teacher_disagreement_score":0.76988083,"about_ca_system_score_codex":0.00015337353,"about_ca_system_score_gemma":0.00023838802,"threshold_uncertainty_score":0.9999769},"labels":[],"label_agreement":null},{"id":"W4311543568","doi":"10.1016/j.inffus.2022.12.014","title":"TSK fuzzy system fusion at sensitivity-ensemble-level for imbalanced data classification","year":2022,"lang":"en","type":"article","venue":"Information Fusion","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Interpretability; Computer science; Overfitting; Artificial intelligence; Sensitivity (control systems); Pattern recognition (psychology); Classifier (UML); Data mining; Machine learning; Fuzzy logic; Cluster analysis; Object (grammar); Artificial neural network","score_opus":0.07055398628152022,"score_gpt":0.2824415405203966,"score_spread":0.2118875542388764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311543568","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033871518,0.000014477748,0.98581165,0.0015542598,0.00086055044,0.0012794764,0.001388809,0.00122319,0.004480446],"genre_scores_gemma":[0.9017204,0.000020415207,0.0847496,0.0010206221,0.00008164985,0.00047674868,0.011595033,0.000018507631,0.00031704354],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99730647,0.00024282206,0.0007668054,0.0005094342,0.0008244019,0.00035009944],"domain_scores_gemma":[0.9961232,0.00023472634,0.00074674096,0.002460204,0.00033775362,0.000097397075],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0021590248,0.0002192293,0.00023255656,0.00035678188,0.0013782263,0.0002475797,0.0016119649,0.00008946272,0.000017891976],"category_scores_gemma":[0.00019373553,0.00022958942,0.00006385517,0.0006707014,0.00003287974,0.004174841,0.002824808,0.0002244479,0.0001715356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031202912,0.00019356103,0.0004984434,0.0004542314,0.00003255503,0.0000062219065,0.003000365,0.0007485869,0.1489428,0.24755086,0.1852671,0.41299322],"study_design_scores_gemma":[0.0007710889,0.0000988066,0.004200726,0.000034947345,0.000010537841,0.00009787418,0.00046726465,0.7154127,0.0067949714,0.00031651874,0.27143618,0.00035843218],"about_ca_topic_score_codex":0.000030275929,"about_ca_topic_score_gemma":0.000011022685,"teacher_disagreement_score":0.901062,"about_ca_system_score_codex":0.0007684682,"about_ca_system_score_gemma":0.00014390267,"threshold_uncertainty_score":0.99992186},"labels":[],"label_agreement":null},{"id":"W4313033418","doi":"10.33965/mccsis2022_202206c031","title":"CLASSIFIER RANK - A NEW CLASSIFICATION ASSESSMENT METHOD","year":2022,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Classifier (UML); Confusion matrix; Computer science; Artificial intelligence; Confusion; Pattern recognition (psychology); Machine learning; Quadratic classifier; Margin classifier; Multiclass classification; Support vector machine","score_opus":0.05124846867724971,"score_gpt":0.35619200890922387,"score_spread":0.3049435402319742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313033418","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000317592,0.000017259557,0.9432646,0.011849309,0.00030219075,0.00031114352,0.000011130872,0.0010595345,0.043153077],"genre_scores_gemma":[0.043681145,0.000008747598,0.94324607,0.0021702836,0.00005369846,0.0003166138,0.000067632405,0.000015187036,0.010440603],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99773425,0.00035439755,0.00035430896,0.000636632,0.00064135913,0.00027904953],"domain_scores_gemma":[0.9980404,0.00013349309,0.00018931534,0.001442305,0.0000653589,0.00012915765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001029026,0.00014886222,0.00016602469,0.0002146971,0.00036436552,0.0001925131,0.0018513505,0.000043591972,0.0008877221],"category_scores_gemma":[0.000031949963,0.00014795264,0.00007278243,0.00086877635,0.00002050413,0.00066345447,0.00077018363,0.0003361624,0.00008764689],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031984534,0.00008201395,0.000117741285,0.0000024499202,0.0000103195225,0.0000042718893,0.000079801495,0.000025001467,0.013177514,0.7161253,0.121116385,0.14925602],"study_design_scores_gemma":[0.00044369505,0.00011341811,0.01096914,0.0000022198853,0.000007412399,0.000062239735,0.00014140157,0.23966084,0.0038514037,0.025822576,0.71859086,0.0003347731],"about_ca_topic_score_codex":0.00005510337,"about_ca_topic_score_gemma":0.0000027364895,"teacher_disagreement_score":0.6903027,"about_ca_system_score_codex":0.00034631777,"about_ca_system_score_gemma":0.00042648276,"threshold_uncertainty_score":0.9719935},"labels":[],"label_agreement":null},{"id":"W4313421115","doi":"10.1007/s10994-022-06282-w","title":"Automated imbalanced classification via layered learning","year":2022,"lang":"en","type":"article","venue":"Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Ottawa; Dalhousie University","funders":"Canada Research Chairs","keywords":"Overfitting; Artificial intelligence; Computer science; Machine learning; Decision boundary; Cluster analysis; Resampling; Benchmark (surveying); Class (philosophy); Binary classification; Data mining; Oversampling; Pattern recognition (psychology); Support vector machine; Artificial neural network","score_opus":0.016691511570374844,"score_gpt":0.2665123368446004,"score_spread":0.24982082527422556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313421115","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009930589,0.00012321069,0.9730046,0.0017282062,0.00027488562,0.00029988374,0.000007740566,0.010606279,0.004024646],"genre_scores_gemma":[0.9669545,0.000013022086,0.030677391,0.000274288,0.000037672806,0.00019305304,0.00028137237,0.000034393754,0.0015342585],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99733204,0.00071378896,0.00038187453,0.000636253,0.0005373704,0.00039866279],"domain_scores_gemma":[0.99864763,0.00012603874,0.00038487779,0.00067705964,0.000080253805,0.00008411343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009349755,0.0002051699,0.00021973324,0.0002729133,0.0011489181,0.00017983821,0.0012954049,0.000056372242,0.00019060777],"category_scores_gemma":[0.00021344634,0.00022940552,0.00007065932,0.0010140262,0.000034854747,0.0004761965,0.00079548196,0.0010066384,0.00009646784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000082844505,0.00044651818,0.09495447,0.000070718226,0.000103609345,0.000076505894,0.0035365035,0.10885536,0.44034752,0.05093165,0.009484034,0.29111025],"study_design_scores_gemma":[0.00028510852,0.00013288984,0.015030418,0.000004700892,0.000003425651,0.000038694452,0.000063897605,0.90038586,0.0014009076,0.0003263898,0.082074136,0.00025358298],"about_ca_topic_score_codex":0.00006474913,"about_ca_topic_score_gemma":0.0000028168379,"teacher_disagreement_score":0.957024,"about_ca_system_score_codex":0.00023708762,"about_ca_system_score_gemma":0.00005948366,"threshold_uncertainty_score":0.9354885},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.007893058798280584,"score_gpt":0.2351205030355744,"score_spread":0.22722744423729382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313421210","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016878983,0.0023672471,0.93469894,0.014269397,0.0005359176,0.0009831137,0.000005267758,0.0032665855,0.02699455],"genre_scores_gemma":[0.97917527,0.000076776036,0.017633988,0.00027232958,0.000027873273,0.00025959357,0.00002543767,0.000021608002,0.0025071148],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977947,0.000683082,0.00029896785,0.00042141398,0.00039907306,0.0004028009],"domain_scores_gemma":[0.99893445,0.00027693596,0.00021176513,0.000503498,0.00003239681,0.000040945062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001594122,0.00013668288,0.00013848103,0.00013023999,0.0012278405,0.00021338221,0.0015562477,0.00002933665,0.000033992503],"category_scores_gemma":[0.00021618223,0.00011778397,0.00004187259,0.0008189601,0.00004274244,0.000287173,0.0010787491,0.0013303531,0.000025589365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003796087,0.00013185722,0.25378188,0.00002802194,0.000021857964,0.000064633365,0.0032148256,0.11169622,0.0058720927,0.15799898,0.0013897537,0.46576193],"study_design_scores_gemma":[0.00019433776,0.00009053003,0.008757674,0.0000059059703,9.981333e-7,0.00002240645,0.00012486012,0.60501,0.00016435425,0.001644659,0.38382113,0.00016317861],"about_ca_topic_score_codex":0.000076874174,"about_ca_topic_score_gemma":0.000044139288,"teacher_disagreement_score":0.9622963,"about_ca_system_score_codex":0.00018045653,"about_ca_system_score_gemma":0.00003920694,"threshold_uncertainty_score":0.9443681},"labels":[],"label_agreement":null},{"id":"W4315796317","doi":"10.3390/e25010150","title":"Mining Mobile Network Fraudsters with Augmented Graph Neural Networks","year":2023,"lang":"en","type":"article","venue":"Entropy","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Natural Science Foundation of China","keywords":"Computer science; Graph; Data mining; Classifier (UML); Multilayer perceptron; Computer network; Artificial intelligence; Machine learning; Artificial neural network; Theoretical computer science","score_opus":0.0124707243906881,"score_gpt":0.2409000323079597,"score_spread":0.2284293079172716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315796317","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014912297,0.000071645925,0.98163223,0.00046217325,0.00043026125,0.00029284242,0.000002735036,0.001959524,0.00023630346],"genre_scores_gemma":[0.9043801,0.00005387683,0.09373132,0.00081623724,0.00025866425,0.00027945597,0.00009356132,0.000031250755,0.00035554945],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998594,0.00006854266,0.00019462127,0.0004065556,0.00025345638,0.0004828315],"domain_scores_gemma":[0.9989282,0.00008809746,0.00011491281,0.0007370467,0.00004283443,0.00008889759],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020160573,0.00014974088,0.00014606728,0.00010951253,0.00015857199,0.00015770811,0.00079090404,0.000052409985,0.00001523454],"category_scores_gemma":[0.000009692756,0.00012757051,0.000041846466,0.0013761439,0.000058071037,0.0003832266,0.00021740781,0.0001424818,0.00004768003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010573025,0.00013637356,0.03813976,0.000031702737,0.00016251719,0.00025018957,0.0012616486,0.25917962,0.001765038,0.08728318,0.51237845,0.099305764],"study_design_scores_gemma":[0.00038797734,0.00020549649,0.0075377687,0.00003562107,0.0000072459843,0.0000119078495,0.000059058264,0.977053,0.000672094,0.0006151332,0.013131058,0.00028365228],"about_ca_topic_score_codex":0.0000053487197,"about_ca_topic_score_gemma":0.0000023521275,"teacher_disagreement_score":0.8894678,"about_ca_system_score_codex":0.000032904823,"about_ca_system_score_gemma":0.00001689649,"threshold_uncertainty_score":0.5202175},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.19159291031325643,"score_gpt":0.46640891991508493,"score_spread":0.2748160096018285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4316469706","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007340113,0.000023886267,0.99098873,0.0008116769,0.00006457167,0.00034682537,0.000036857884,0.00014306772,0.00024424915],"genre_scores_gemma":[0.2953897,0.00002009535,0.7036268,0.00004480202,0.000009318019,0.00004715758,0.0008535706,0.000004113036,0.000004403564],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989897,0.000030454961,0.00047367424,0.00020444971,0.0001530755,0.00014866407],"domain_scores_gemma":[0.9983493,0.00045810486,0.00041367149,0.00060441304,0.00014391463,0.000030598658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096834754,0.0000886963,0.0001551233,0.00029327246,0.00007535575,0.0001030364,0.00054210075,0.000057462228,0.0000013367776],"category_scores_gemma":[0.000332891,0.000087682914,0.000011015857,0.00044681723,0.000041229796,0.002283878,0.00015940587,0.00006780628,0.000002547192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000065319844,0.00006155464,0.02665085,0.0003214801,0.000031099422,6.1800115e-8,0.009385664,0.0011031553,0.006587048,0.28798798,0.0015610664,0.6662447],"study_design_scores_gemma":[0.00035508352,0.000045111883,0.047128797,0.00007044253,0.000005008169,0.000001509578,0.0005735024,0.94191915,0.0021923066,0.0032437216,0.0043458627,0.0001195354],"about_ca_topic_score_codex":0.000029682857,"about_ca_topic_score_gemma":0.000014038791,"teacher_disagreement_score":0.940816,"about_ca_system_score_codex":0.00005303537,"about_ca_system_score_gemma":0.000103821454,"threshold_uncertainty_score":0.35756055},"labels":[],"label_agreement":null},{"id":"W4318604573","doi":"10.1109/ssci51031.2022.10022190","title":"Training and Testing Cascades for Imbalanced Data Classification","year":2022,"lang":"en","type":"article","venue":"2022 IEEE Symposium Series on Computational Intelligence (SSCI)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Cascade; Computer science; Artificial intelligence; Training set; Machine learning; Data modeling; Data mining; Data set; Class (philosophy); Set (abstract data type); Synthetic data; Test data; Recall rate; Pattern recognition (psychology); Database; Engineering","score_opus":0.17285391089432167,"score_gpt":0.34399103030252615,"score_spread":0.17113711940820447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318604573","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001563103,0.00006149049,0.9906075,0.00441109,0.0007591667,0.00072211516,0.00064971915,0.000545019,0.00068077416],"genre_scores_gemma":[0.69223785,0.00003653483,0.30465105,0.000962518,0.00014755887,0.0006070461,0.0010356226,0.00003652121,0.00028527697],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99698544,0.00016980169,0.0005848201,0.0011848758,0.00067849504,0.0003965559],"domain_scores_gemma":[0.9970438,0.0010980695,0.00037744065,0.0011112422,0.00025711104,0.000112371454],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010834252,0.0002663679,0.0002679127,0.0002683035,0.0010940001,0.00034464092,0.0023516465,0.0000591903,0.00002031711],"category_scores_gemma":[0.0002696181,0.0003028416,0.00004534386,0.00088983204,0.00017261728,0.0013289251,0.0007768256,0.00033686776,0.000010165206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015068887,0.0003499728,0.0004314706,0.00011696225,0.00008928684,0.000015939164,0.0037755405,0.13459976,0.029393457,0.6143514,0.010040062,0.20668548],"study_design_scores_gemma":[0.0001288476,0.00055159756,0.00067345833,0.00002411158,0.000010591158,0.00011709448,0.00092396344,0.94453543,0.0044159554,0.03502974,0.013166385,0.00042285325],"about_ca_topic_score_codex":0.0000142519275,"about_ca_topic_score_gemma":0.0000050682333,"teacher_disagreement_score":0.8099356,"about_ca_system_score_codex":0.00018739027,"about_ca_system_score_gemma":0.00027096178,"threshold_uncertainty_score":0.99994236},"labels":[],"label_agreement":null},{"id":"W4319863485","doi":"10.1109/tkde.2023.3240431","title":"Cost-Sensitive Learning for Medical Insurance Fraud Detection With Temporal Information","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data mining","score_opus":0.027099778289374654,"score_gpt":0.27910290259692533,"score_spread":0.2520031243075507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319863485","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017127445,0.000011523273,0.9965991,0.00009370383,0.00023640286,0.00027667242,0.00010539868,0.0009292041,0.0000352938],"genre_scores_gemma":[0.98364985,0.00008567925,0.015859347,0.000026837528,0.00003319685,0.00014216613,0.00015985468,0.000011579977,0.000031473995],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992069,0.000018162009,0.00017765528,0.00025547258,0.00016494846,0.000176889],"domain_scores_gemma":[0.9991713,0.00018900227,0.000042776483,0.0004281383,0.000087595035,0.0000811972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003465258,0.000116252144,0.00010960978,0.0002636708,0.00017106313,0.00009541166,0.0003496463,0.00007940979,0.0000013397087],"category_scores_gemma":[0.00004432672,0.000109804656,0.000015855825,0.00054851413,0.000022383325,0.0017523174,0.000011768044,0.0002351262,0.000033095814],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004582504,0.00004791928,0.00004752927,0.00015269291,0.000042384123,0.0000039818074,0.0008909871,0.011938898,0.0016532826,0.0003964685,0.0004954418,0.9842846],"study_design_scores_gemma":[0.00036430036,0.00010057779,0.00081290345,0.00007377037,0.0000054254106,0.000018096027,0.000036381807,0.95672643,0.023777807,0.000009169043,0.017915444,0.00015967494],"about_ca_topic_score_codex":0.00000740256,"about_ca_topic_score_gemma":0.000023931398,"teacher_disagreement_score":0.9841249,"about_ca_system_score_codex":0.000031603755,"about_ca_system_score_gemma":0.000048055976,"threshold_uncertainty_score":0.4477704},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.10998735913183141,"score_gpt":0.36279671487678333,"score_spread":0.2528093557449519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321214126","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039828117,0.00022323284,0.9644635,0.027894419,0.0008631662,0.0010407153,0.00010581817,0.00080318394,0.0006231703],"genre_scores_gemma":[0.9387665,0.00034134425,0.054829586,0.0015479717,0.00028157138,0.0009967815,0.0007729403,0.00006939482,0.0023939372],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975507,0.0002870343,0.00049098453,0.00060057244,0.0006539651,0.00041670157],"domain_scores_gemma":[0.9942104,0.0027754407,0.00047846045,0.0022677372,0.0002188182,0.00004914254],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004527626,0.00018973264,0.00015001085,0.00020212469,0.0020259724,0.0014435645,0.0025468036,0.00010238495,0.0000044579733],"category_scores_gemma":[0.0017641303,0.000101471494,0.00007332858,0.0023705594,0.00018220485,0.0008307789,0.0005902674,0.00023587517,0.00008865461],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009181811,0.000065025815,0.0016170777,0.000038780618,0.00006402737,0.0000042681704,0.002719463,0.00059087115,0.009261704,0.15718496,0.44647434,0.38188767],"study_design_scores_gemma":[0.00024582812,0.00010288902,0.013934743,0.00005681081,0.00002881783,0.000014721703,0.0023239823,0.60296786,0.003380282,0.0010246678,0.37566796,0.00025146888],"about_ca_topic_score_codex":0.000011519151,"about_ca_topic_score_gemma":0.0000058206306,"teacher_disagreement_score":0.93478364,"about_ca_system_score_codex":0.00016728048,"about_ca_system_score_gemma":0.00022916222,"threshold_uncertainty_score":0.999593},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.16010305571121192,"score_gpt":0.4134479746721709,"score_spread":0.253344918960959,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321380810","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.098007e-8,0.4414683,0.5552712,0.000097187614,0.00031434293,0.0025069895,0.000012377258,0.00028282037,0.00004674129],"genre_scores_gemma":[0.000024558061,0.979463,0.012252173,0.0003092865,0.000009157578,0.007776627,0.000019464424,0.00004158191,0.000104159415],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99520797,0.0014076107,0.0014788999,0.0007755241,0.0008372163,0.0002927818],"domain_scores_gemma":[0.99794155,0.00038720664,0.0006789878,0.00074847345,0.00012973863,0.00011404107],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0026710748,0.0004746275,0.0015265484,0.0007720346,0.00016349366,0.00015485703,0.0005847948,0.00016749348,0.0000145122585],"category_scores_gemma":[0.00015014005,0.0003994233,0.00028159845,0.0011820932,0.000032779324,0.00024565656,0.000007764257,0.000651011,0.0001295362],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015195325,0.0001000744,9.749202e-8,0.2506253,0.00010476528,0.0000020288655,0.00008858191,0.000020302552,0.0000027962683,0.00022065663,0.000059520306,0.74877435],"study_design_scores_gemma":[0.00031284132,0.00028268824,0.0000014136632,0.9510655,0.00074149016,0.00001739346,0.000074959346,0.0007833231,0.0011985069,0.00007869612,0.04474948,0.00069371576],"about_ca_topic_score_codex":0.000015790103,"about_ca_topic_score_gemma":0.000018433564,"teacher_disagreement_score":0.7480806,"about_ca_system_score_codex":0.00093764433,"about_ca_system_score_gemma":0.00015820355,"threshold_uncertainty_score":0.99984574},"labels":[],"label_agreement":null},{"id":"W4321494133","doi":"10.1088/1742-6596/2428/1/012039","title":"Performance Analysis of Machine Learning Methods","year":2023,"lang":"en","type":"article","venue":"Journal of Physics Conference Series","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Artificial intelligence; Support vector machine; Machine learning; Computer science; Convolutional neural network; Artificial neural network; Pattern recognition (psychology); k-nearest neighbors algorithm; Image (mathematics); Convolution (computer science)","score_opus":0.05317323566249844,"score_gpt":0.33822813302424154,"score_spread":0.2850548973617431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321494133","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027139988,0.000022980337,0.97186726,0.00030672082,0.00010275447,0.000030473768,0.000006556159,0.00009077558,0.00043247707],"genre_scores_gemma":[0.829436,0.00037452398,0.1699599,0.000015055617,0.000027083806,0.0000018268506,0.000009210139,0.000004768659,0.00017163278],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988625,0.00014387307,0.00042952748,0.00012532691,0.00029992577,0.0001388204],"domain_scores_gemma":[0.998218,0.00012939876,0.0007181292,0.0003369944,0.0005543914,0.00004306659],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007781244,0.00009598853,0.00037057014,0.00037874104,0.00006695726,0.00007065185,0.00082715694,0.00003239932,0.000013983766],"category_scores_gemma":[0.00011456784,0.000081566875,0.00013398819,0.0023647095,0.00007974786,0.0013061541,0.00016653084,0.00022255236,0.000004370061],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023668306,0.000052209212,0.012314969,0.000054110802,0.00055039773,0.0000052860296,0.0020741548,0.0027438616,0.078536525,0.13666682,0.00022445743,0.76675355],"study_design_scores_gemma":[0.00012269229,0.00028883968,0.038771473,0.00004882513,0.00016128382,0.000008032161,0.00015209202,0.2944417,0.6558837,0.0076334463,0.0023184465,0.00016942952],"about_ca_topic_score_codex":0.0000041144885,"about_ca_topic_score_gemma":0.0000011459874,"teacher_disagreement_score":0.80229604,"about_ca_system_score_codex":0.0000191677,"about_ca_system_score_gemma":0.00011439194,"threshold_uncertainty_score":0.33262008},"labels":[],"label_agreement":null},{"id":"W4321599030","doi":"10.1111/johs.12399","title":"Box Store Detention","year":2023,"lang":"en","type":"article","venue":"Sociology Lens","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.04393673555026284,"score_gpt":0.29942720649089405,"score_spread":0.2554904709406312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321599030","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0691607,0.00007305318,0.90236753,0.017076723,0.0009941189,0.00022084545,0.000019689713,0.004719532,0.005367785],"genre_scores_gemma":[0.9761678,0.00007823977,0.021613985,0.0008509581,0.00007451023,0.000038711358,0.00007696031,0.000007919703,0.0010909329],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99929345,0.000078474084,0.000107727916,0.00024198301,0.000074788135,0.00020356585],"domain_scores_gemma":[0.9993692,0.000067615096,0.00005228289,0.00044812003,0.000041820822,0.000020934442],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002765736,0.000059307476,0.00007941998,0.00008517629,0.0000966748,0.000014616941,0.00049602333,0.00011134707,0.000012471849],"category_scores_gemma":[0.00006447382,0.00005777923,0.00003745314,0.00020586679,0.0001289967,0.00024016073,0.00015633513,0.00011612267,0.0012235163],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015506283,0.000022846967,0.0059615416,0.000008769549,0.00001832139,0.000013948272,0.0014636349,0.0000035723328,0.02472882,0.80935067,0.14019065,0.018235687],"study_design_scores_gemma":[0.0005609934,0.0002340457,0.3521575,0.000019658943,0.000012215154,0.000025281146,0.00027022194,0.008177276,0.022586247,0.38996586,0.22533527,0.00065543066],"about_ca_topic_score_codex":0.0000027010083,"about_ca_topic_score_gemma":0.0000011783553,"teacher_disagreement_score":0.9070071,"about_ca_system_score_codex":0.000037541624,"about_ca_system_score_gemma":0.000029839079,"threshold_uncertainty_score":0.99955416},"labels":[],"label_agreement":null},{"id":"W4323647344","doi":"10.1007/978-3-031-25599-1_11","title":"Explainable Machine Learning for Drug Shortage Prediction in a Pandemic Setting","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Thales (Canada)","funders":"","keywords":"Computer science; Supply chain; Task (project management); Economic shortage; Benchmark (surveying); Product (mathematics); Feature (linguistics); Operations research; Machine learning; Artificial intelligence; Schedule; Business; Engineering","score_opus":0.023296296595037673,"score_gpt":0.2637352871264486,"score_spread":0.24043899053141093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323647344","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006000554,0.00012711581,0.99604887,0.00047972956,0.0007902598,0.0008317203,0.000029377808,0.0010057075,0.000627229],"genre_scores_gemma":[0.12639329,0.00020750519,0.86562,0.00086087076,0.00056566973,0.00033674057,0.00023858677,0.0001382103,0.0056390837],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99628204,0.000053393334,0.00066765293,0.0016045746,0.00067827007,0.0007140617],"domain_scores_gemma":[0.9974565,0.00087122555,0.0003460808,0.0010582074,0.00017331316,0.00009469186],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002509882,0.00041847603,0.00044410594,0.0013106469,0.00029979122,0.00040802115,0.0025564004,0.00027750625,0.0000057875427],"category_scores_gemma":[0.0003799425,0.0004245918,0.0000929968,0.0008878272,0.00023712886,0.0009106626,0.0010497167,0.0010957394,0.000021652242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016447868,0.000041815798,0.004501858,0.00022283343,0.000013448479,0.000074409065,0.002382775,0.05785351,0.0010203603,0.025408627,0.00030803555,0.90815586],"study_design_scores_gemma":[0.00023549474,0.00008377825,0.00038996863,0.00044798115,0.0000035692826,0.00002025912,6.326041e-7,0.9175177,0.0011897188,0.076647244,0.0030409945,0.0004226225],"about_ca_topic_score_codex":0.000044612276,"about_ca_topic_score_gemma":0.00018004791,"teacher_disagreement_score":0.90773326,"about_ca_system_score_codex":0.00052660605,"about_ca_system_score_gemma":0.00034900315,"threshold_uncertainty_score":0.9998206},"labels":[],"label_agreement":null},{"id":"W4323654755","doi":"10.18280/isi.280117","title":"Ensemble Model for Multiclass Imbalanced Data Using Cluster Computing of Spark","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"SPARK (programming language); Cluster (spacecraft); Computer science; Artificial intelligence; Data mining; Machine learning; Operating system","score_opus":0.08354625269483926,"score_gpt":0.31633657703407875,"score_spread":0.2327903243392395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323654755","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02296989,0.0000078540415,0.97513324,0.00006129063,0.00020911345,0.00057550427,0.00015971414,0.0006140411,0.00026935854],"genre_scores_gemma":[0.6198567,0.000004770797,0.37956187,0.00009036417,0.000019683976,0.000019761785,0.00042003614,0.000008044257,0.000018746108],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983959,0.000039171668,0.0007237603,0.00023999995,0.00027221246,0.00032893196],"domain_scores_gemma":[0.9976967,0.00017393054,0.0005328327,0.0011851758,0.00036187467,0.000049505656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010098236,0.00014735693,0.00022895346,0.00031198838,0.00020449194,0.00020661404,0.0013397321,0.00009301375,3.908499e-7],"category_scores_gemma":[0.00043685883,0.00015172693,0.00004400248,0.0007027596,0.00007710555,0.005209332,0.0007163363,0.00007671929,0.000014925325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012767366,0.000116003954,0.0015484288,0.0029580947,0.00014046417,0.0000017462968,0.026484925,0.3215639,0.04987261,0.07651472,0.021196418,0.49947503],"study_design_scores_gemma":[0.0003485537,0.00002112074,0.00042986,0.00010236261,0.000006585841,0.0000056204894,0.00011750745,0.98669237,0.0075995196,0.004092993,0.00042014624,0.00016338665],"about_ca_topic_score_codex":0.000021069667,"about_ca_topic_score_gemma":0.0000035988805,"teacher_disagreement_score":0.66512847,"about_ca_system_score_codex":0.00014920256,"about_ca_system_score_gemma":0.00012776101,"threshold_uncertainty_score":0.6187244},"labels":[],"label_agreement":null},{"id":"W4328094596","doi":"10.54691/bcpbm.v38i.3803","title":"The Causes, Consequences and Countermeasures of Financial Fraud Based on the Case of Luckin Coffee","year":2023,"lang":"en","type":"article","venue":"BCP Business & Management","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Guard (computer science); Financial fraud; Reputation; Business; Audit; Accounting; Government (linguistics); Quarter (Canadian coin); Corporate governance; Constructive fraud; Finance; Law; Political science","score_opus":0.02727385235718678,"score_gpt":0.2596478715295101,"score_spread":0.2323740191723233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4328094596","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61321187,0.0008871342,0.28061077,0.09003891,0.0022384387,0.0061567193,0.00042449354,0.0017434694,0.0046881614],"genre_scores_gemma":[0.99787277,0.00016193347,0.0014919059,0.00027686264,0.000011415024,0.000091528505,0.0000048547677,0.000005446513,0.00008328359],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990342,0.000085304135,0.00023610373,0.00022397186,0.0002699678,0.00015042946],"domain_scores_gemma":[0.99856144,0.00027006702,0.00018812262,0.00079533795,0.00016908628,0.000015926094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007719707,0.00010164531,0.00011984728,0.00011231854,0.000189919,0.00006815587,0.00070593075,0.000025799072,0.000003572059],"category_scores_gemma":[0.00015002691,0.000060856775,0.000021746973,0.000793082,0.00043386267,0.00010710061,0.00023452063,0.00005167223,0.000004838173],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051578958,0.000116426694,0.00031915933,0.00035583822,0.000042582935,0.0005045925,0.00022061571,0.00037926334,0.0012075474,0.4497229,0.042949468,0.50413007],"study_design_scores_gemma":[0.0007003261,0.000040707364,0.8853117,0.00042639818,0.00004926136,0.000045280758,0.00027173242,0.03151616,0.01656713,0.026020559,0.038659304,0.00039143776],"about_ca_topic_score_codex":0.00013272173,"about_ca_topic_score_gemma":0.000064903616,"teacher_disagreement_score":0.88499254,"about_ca_system_score_codex":0.000018442934,"about_ca_system_score_gemma":0.0000553064,"threshold_uncertainty_score":0.24816673},"labels":[],"label_agreement":null},{"id":"W4360592738","doi":"10.2139/ssrn.4396572","title":"An Improved Gan to Oversample Imbalanced Datasets","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Materials science; Environmental science; Business; Optoelectronics","score_opus":0.012914024810391871,"score_gpt":0.29099465831181354,"score_spread":0.27808063350142165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360592738","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069081937,0.000043728247,0.9892321,0.0023059445,0.0002330347,0.00020707145,0.0000883976,0.0008555469,0.00012594131],"genre_scores_gemma":[0.97589767,0.00054083834,0.021625055,0.00089544867,0.00024982542,0.000039114977,0.00034955918,0.000034160967,0.0003683176],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966189,0.000094583585,0.00029124375,0.00046176426,0.00032871234,0.002204748],"domain_scores_gemma":[0.99837977,0.00004375445,0.00013899482,0.0011393789,0.00008018922,0.00021791761],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018359539,0.00016684712,0.00016446326,0.00029887562,0.00025542633,0.00029584946,0.0022127226,0.000063673644,0.000009059875],"category_scores_gemma":[0.00011510871,0.00015913733,0.00005254782,0.0010383506,0.000022779652,0.0011900244,0.00017756152,0.0008689188,0.00024384065],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005034344,0.00015271864,0.00062223367,0.000008475884,0.00008891567,0.000019593326,0.00046220527,0.000103822815,0.17347331,0.55265564,0.02781033,0.2445524],"study_design_scores_gemma":[0.0020156023,0.002773637,0.011391384,0.000049809885,0.000028352235,0.00080567045,0.0010995705,0.07300035,0.04227037,0.7001405,0.16476136,0.0016633872],"about_ca_topic_score_codex":0.00005008116,"about_ca_topic_score_gemma":0.00018754193,"teacher_disagreement_score":0.9689895,"about_ca_system_score_codex":0.00057507853,"about_ca_system_score_gemma":0.0010670709,"threshold_uncertainty_score":0.6489432},"labels":[],"label_agreement":null},{"id":"W4360977633","doi":"10.59200/iconic.2022.032","title":"Improving Accuracy of Credit Card Fraud Detection Using Supervised Machine Learning Models and Dimension Reduction","year":2022,"lang":"en","type":"article","venue":"International Conference on Intelligent and Innovative Computing Applications","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Science North","funders":"","keywords":"Credit card; Credit card fraud; Dimensionality reduction; Dimension (graph theory); Machine learning; Computer science; Artificial intelligence; Identity theft; Reduction (mathematics); Computer security; Mathematics; Payment","score_opus":0.09455430942438646,"score_gpt":0.32403022526563896,"score_spread":0.2294759158412525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360977633","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0829231,0.000043915916,0.91554683,0.0003826605,0.00016722838,0.00033141318,0.00002887331,0.00013340323,0.0004425818],"genre_scores_gemma":[0.9708525,0.000056826462,0.02878407,0.000053557735,0.00005014274,0.000077716126,0.00008614554,0.000010153598,0.000028908187],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855506,0.00009900087,0.00042704795,0.0004559577,0.00033235803,0.00013054439],"domain_scores_gemma":[0.99832606,0.00012365654,0.00046364396,0.00024875876,0.00080264336,0.000035229907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041745984,0.0001444986,0.0001523754,0.0003819367,0.0004808032,0.00011119424,0.00043730118,0.000039239694,0.000014092575],"category_scores_gemma":[0.00008511184,0.00015890486,0.000024064882,0.0006490532,0.000091993,0.00039673256,0.00060496456,0.00037577696,0.0000011836976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030491983,0.0001020909,0.0003044805,0.000019106708,0.000037792663,3.889649e-7,0.0010804951,0.0053613414,0.21890298,0.484526,0.000020652435,0.28961417],"study_design_scores_gemma":[0.00011688118,0.00009131697,0.00013750533,0.00002375962,0.000004178371,0.000020200376,0.00039312377,0.9410304,0.049620375,0.007798687,0.00062078185,0.00014281446],"about_ca_topic_score_codex":0.00016702207,"about_ca_topic_score_gemma":0.0000012184331,"teacher_disagreement_score":0.93566906,"about_ca_system_score_codex":0.00014074329,"about_ca_system_score_gemma":0.00006408384,"threshold_uncertainty_score":0.64799523},"labels":[],"label_agreement":null},{"id":"W4360982798","doi":"10.1007/978-3-031-26422-1_48","title":"ImbalancedLearningRegression - A Python Package to Tackle the Imbalanced Regression Problem","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Python (programming language); Computer science; Regression; Machine learning; Regression analysis; Artificial intelligence; R package; Extensibility; Source code; Programming language; Data mining; Statistics; Mathematics","score_opus":0.021747517430019972,"score_gpt":0.27800159908360444,"score_spread":0.2562540816535845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360982798","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000026779066,0.00015437901,0.98701805,0.0053758994,0.0015048397,0.0012565439,0.00002131134,0.0013871586,0.0032550152],"genre_scores_gemma":[0.04444487,0.0003526079,0.94068974,0.004394154,0.0009276902,0.0002845681,0.000073457326,0.00023003091,0.008602882],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99377155,0.00012004772,0.0008059946,0.002448355,0.0017753908,0.0010786807],"domain_scores_gemma":[0.9941364,0.00070494384,0.000663041,0.0038177192,0.0003963759,0.00028150532],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0019699065,0.0007925854,0.0006982921,0.001061617,0.0006697348,0.0009352158,0.007372392,0.00046572587,0.000017772594],"category_scores_gemma":[0.00039108886,0.0005301938,0.00016704094,0.0020068637,0.0006329737,0.0007834108,0.0036956756,0.0015326659,0.0004392321],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021290185,0.000037802154,0.00009967433,0.000074261516,0.000012676112,0.00010972119,0.0014552163,0.003796098,0.0053655608,0.034008253,0.003096433,0.951923],"study_design_scores_gemma":[0.0010654185,0.00106196,0.0025170464,0.010008579,0.000029542703,0.00021560462,0.0000029598145,0.32271737,0.050087888,0.54741,0.060825437,0.0040581934],"about_ca_topic_score_codex":0.000017653072,"about_ca_topic_score_gemma":0.000038878152,"teacher_disagreement_score":0.94786483,"about_ca_system_score_codex":0.00047118776,"about_ca_system_score_gemma":0.0005229719,"threshold_uncertainty_score":0.999715},"labels":[],"label_agreement":null},{"id":"W4360996447","doi":"10.1109/icct56141.2022.10073400","title":"Telecom Fraud Detection via Imbalanced Graph Learning","year":2022,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Natural Science Foundation of China","keywords":"Computer science; Graph; Node (physics); Multilayer perceptron; Detector; Data mining; Artificial neural network; Artificial intelligence; Computer network; Telecommunications; Theoretical computer science; Engineering","score_opus":0.008522006508991329,"score_gpt":0.22314774348112126,"score_spread":0.21462573697212994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360996447","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034566354,0.00001967702,0.9900521,0.00041263585,0.00024795622,0.00013911023,0.000001492129,0.001685307,0.0039851097],"genre_scores_gemma":[0.9440022,0.000007133254,0.054454952,0.00042191925,0.000022688102,0.00015618306,0.000012314121,0.000009811498,0.0009127608],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987634,0.00013850171,0.00018664669,0.0003806351,0.0003059797,0.00022488087],"domain_scores_gemma":[0.99919236,0.00004747197,0.000110729176,0.00055807305,0.000045095527,0.00004626789],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003470506,0.00009857978,0.00010017968,0.00018769439,0.0005137002,0.000086392996,0.0008981136,0.000029023286,0.00018734547],"category_scores_gemma":[0.000029435745,0.00010436111,0.000047548652,0.0008117704,0.000020963826,0.0004126049,0.00047141945,0.00035707807,0.00005140831],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016362535,0.00016343663,0.0033616738,0.00001105091,0.000025142393,0.000012368431,0.00045426915,0.0008626907,0.30815956,0.047922898,0.005013079,0.63399744],"study_design_scores_gemma":[0.0006457437,0.0006723561,0.019183235,0.0000048417905,0.0000069410526,0.00014484486,0.00019310253,0.27527282,0.41153643,0.031555142,0.25992647,0.0008580633],"about_ca_topic_score_codex":0.000039061462,"about_ca_topic_score_gemma":0.0000057297075,"teacher_disagreement_score":0.9405456,"about_ca_system_score_codex":0.00010177303,"about_ca_system_score_gemma":0.000024117364,"threshold_uncertainty_score":0.42557228},"labels":[],"label_agreement":null},{"id":"W4362725573","doi":"10.23977/acss.2023.070212","title":"Assessing the feasibility of machine learning-based modelling and prediction of credit fraud outcomes using hyperparameter tuning","year":2023,"lang":"en","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Credit card fraud; Undersampling; Machine learning; Credit card; Computer science; Random forest; AdaBoost; Artificial intelligence; Support vector machine; Hyperparameter; Feature selection; Naive Bayes classifier; Data mining","score_opus":0.1135348121537195,"score_gpt":0.3510707992363098,"score_spread":0.2375359870825903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362725573","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21294147,0.0010658996,0.78546757,0.000035980906,0.00019456013,0.00019163248,0.000009640352,0.00008649076,0.0000067787687],"genre_scores_gemma":[0.9384435,0.00011933967,0.06137018,0.00001600354,0.000025684278,0.000010216458,0.000006116852,0.000006858726,0.0000020910984],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848026,0.0002681746,0.0005193344,0.0003300939,0.00024837028,0.00015374673],"domain_scores_gemma":[0.9984572,0.0007211526,0.00034297092,0.00035387298,0.00009642949,0.000028393879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012623458,0.00012281477,0.00032363815,0.00017552124,0.0001045266,0.00013783622,0.00030122756,0.000052146694,2.775976e-7],"category_scores_gemma":[0.000039985764,0.00008966669,0.000033077147,0.0004064127,0.000103926315,0.0009148742,0.00015935938,0.00014321381,1.2847423e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034036923,0.000023697261,0.17217502,0.00021217037,0.000009446885,0.0000014629834,0.0003099636,0.8172401,0.0016162533,0.00048037348,0.0000036339468,0.007924437],"study_design_scores_gemma":[0.00017925347,0.000065613574,0.007063867,0.0002419576,0.0000043887812,0.0000039438437,0.000042506064,0.9911814,0.00052243134,0.0005668741,0.00005269538,0.00007508289],"about_ca_topic_score_codex":0.000066265995,"about_ca_topic_score_gemma":0.0000014526607,"teacher_disagreement_score":0.725502,"about_ca_system_score_codex":0.000021036305,"about_ca_system_score_gemma":0.000025015906,"threshold_uncertainty_score":0.36565015},"labels":[],"label_agreement":null},{"id":"W4364381349","doi":"10.1007/s10994-023-06326-9","title":"Understanding CNN fragility when learning with imbalanced data","year":2023,"lang":"en","type":"article","venue":"Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"Office of Naval Research","keywords":"Convolutional neural network; Class (philosophy); Artificial intelligence; Computer science; Feature (linguistics); Focus (optics); Pattern recognition (psychology); Set (abstract data type); Machine learning; Image (mathematics)","score_opus":0.14952743444589864,"score_gpt":0.30261477515111007,"score_spread":0.15308734070521143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4364381349","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025296859,0.000036475645,0.98738486,0.0020168193,0.00008950529,0.00017166979,0.000011432226,0.0039536622,0.0038058937],"genre_scores_gemma":[0.9279655,0.000045511748,0.06925254,0.00015357012,0.00006118517,0.000021379787,0.0006673097,0.000038685474,0.0017943165],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976045,0.00028135133,0.0002697555,0.0008801569,0.00047874937,0.00048549825],"domain_scores_gemma":[0.9978097,0.0002592376,0.00021043222,0.0015688682,0.00005287277,0.00009887269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013867014,0.00021483879,0.00023715949,0.00023855126,0.0005575525,0.00034323902,0.002092936,0.00007623041,0.000048502006],"category_scores_gemma":[0.00044781383,0.00019092903,0.000028580731,0.0010137912,0.000076593475,0.0011482297,0.0014251599,0.0007737989,0.0001629912],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015517803,0.00019826695,0.6480634,0.0003277371,0.00028611603,0.00034947862,0.008970428,0.024839967,0.017001318,0.15444791,0.032385536,0.11297463],"study_design_scores_gemma":[0.00043101516,0.00013281727,0.009986797,0.00006458494,0.00000898988,0.000017494418,0.00022839895,0.927022,0.00053162687,0.004402128,0.05677562,0.00039856107],"about_ca_topic_score_codex":0.00008095434,"about_ca_topic_score_gemma":0.000030035104,"teacher_disagreement_score":0.92543584,"about_ca_system_score_codex":0.00014270683,"about_ca_system_score_gemma":0.00006486328,"threshold_uncertainty_score":0.778586},"labels":[],"label_agreement":null},{"id":"W4365510574","doi":"10.1287/ijoc.2023.1297","title":"Black-Box Attack-Based Security Evaluation Framework for Credit Card Fraud Detection Models","year":2023,"lang":"en","type":"article","venue":"INFORMS journal on computing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Black box; Construct (python library); Machine learning; Key (lock); Artificial intelligence; Big data; Joint (building); Computer security; Data mining; Engineering","score_opus":0.07981210267639172,"score_gpt":0.35616892560789665,"score_spread":0.27635682293150493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365510574","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029649975,0.000011733236,0.96659636,0.00077545625,0.0012491565,0.0005356482,0.000012875686,0.0008259783,0.0003428116],"genre_scores_gemma":[0.8576793,0.000010236645,0.14101139,0.000643609,0.0005685557,0.000028086617,0.00003044534,0.00002038363,0.000007994362],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973608,0.00009322873,0.0006881371,0.00035468445,0.0010163529,0.0004867822],"domain_scores_gemma":[0.9971354,0.0006480216,0.0006548347,0.0006324962,0.0007794452,0.00014982466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003304826,0.00022059216,0.00024279837,0.00051714847,0.00060784904,0.0005978983,0.0009796965,0.000205435,0.000004718722],"category_scores_gemma":[0.00080072135,0.00019958413,0.00017762168,0.000974547,0.0000472715,0.0013643664,0.00015710367,0.00068401895,0.0000687239],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006037969,0.00006143189,0.00008289452,0.00006217285,0.000048198275,0.0000073770534,0.0017932313,0.5033934,0.00028667733,0.034033373,0.0069983355,0.45317248],"study_design_scores_gemma":[0.00042631596,0.00020204394,0.0003363565,0.0001495178,0.00000940385,0.000015811072,0.000051652536,0.8894308,0.0061782436,0.10077966,0.0022031544,0.0002170109],"about_ca_topic_score_codex":0.000003428448,"about_ca_topic_score_gemma":0.0000015298253,"teacher_disagreement_score":0.82802933,"about_ca_system_score_codex":0.00039496078,"about_ca_system_score_gemma":0.00025401125,"threshold_uncertainty_score":0.81388044},"labels":[],"label_agreement":null},{"id":"W4366089693","doi":"10.21203/rs.3.rs-2768547/v1","title":"Handling the Class Imbalance Problem using an improved Sine Cosine Algorithm for Optimal Instance Selection","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"Najran University","keywords":"Algorithm; Classifier (UML); Binary number; Computer science; Class (philosophy); Trigonometric functions; Sine; Particle swarm optimization; Set (abstract data type); Selection (genetic algorithm); Convergence (economics); Fitness function; Optimization problem; Artificial intelligence; Machine learning; Mathematics; Mathematical optimization; Genetic algorithm","score_opus":0.14716992947694132,"score_gpt":0.42253591151817055,"score_spread":0.2753659820412292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366089693","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011629486,0.00018295787,0.99120146,0.0017237037,0.00030498012,0.0038013128,0.0003581707,0.0012237293,0.000040765215],"genre_scores_gemma":[0.053748697,0.0002388212,0.9415477,0.00006899133,0.0006990617,0.0025075476,0.00054257346,0.00011786132,0.00052875536],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950385,0.0005736768,0.0006053873,0.0015674488,0.0011239793,0.0010910009],"domain_scores_gemma":[0.99457884,0.00052596105,0.0003648016,0.0020711876,0.0022878917,0.000171309],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004543234,0.00037964794,0.00041636493,0.0005078423,0.001024744,0.0013679689,0.0032400948,0.00040716588,0.000003089989],"category_scores_gemma":[0.00035324338,0.00031958323,0.00013659026,0.0016409716,0.00024776865,0.00083857635,0.0022298505,0.0018023064,0.000011561719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003370498,0.0017569194,0.0007129167,0.0051366384,0.0004482831,0.00005124082,0.0032479996,0.044751372,0.17253028,0.038430538,0.018259587,0.71433717],"study_design_scores_gemma":[0.00030895643,0.00028204382,0.00029717232,0.00056386326,0.0000069775288,0.000009432341,0.00007833824,0.97784746,0.011504079,0.005508014,0.0032399674,0.00035369126],"about_ca_topic_score_codex":0.00027600772,"about_ca_topic_score_gemma":0.00008991385,"teacher_disagreement_score":0.9330961,"about_ca_system_score_codex":0.0008198569,"about_ca_system_score_gemma":0.0010865192,"threshold_uncertainty_score":0.9999256},"labels":[],"label_agreement":null},{"id":"W4372324482","doi":"10.54691/bcpbm.v44i.4839","title":"Multiple Machine Learning Models on Credit Card Fraud Detection","year":2023,"lang":"en","type":"article","venue":"BCP Business & Management","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Confusion matrix; Computer science; Decision tree; Support vector machine; Machine learning; Categorical variable; Artificial intelligence; Credit card; F1 score; Receiver operating characteristic; Logistic regression; Set (abstract data type); Database transaction; Data mining; Data set; Test set; Tree (set theory); Database; Mathematics","score_opus":0.04229496765723449,"score_gpt":0.24735261702532316,"score_spread":0.20505764936808868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4372324482","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061809123,0.000024665842,0.98681927,0.001047374,0.00058873714,0.00046613964,0.000009935231,0.0031292995,0.0017336726],"genre_scores_gemma":[0.97618264,0.00020623594,0.021064939,0.00016900984,0.0000910348,0.00024359292,0.00011260292,0.000028424422,0.0019014918],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984118,0.00005718358,0.00022504247,0.000548816,0.0004487969,0.0003084072],"domain_scores_gemma":[0.99882704,0.00005091754,0.000114329334,0.0008464922,0.00011438177,0.000046835346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003476458,0.00017662387,0.00014657472,0.00043400197,0.00022633772,0.00013898863,0.0007905711,0.000054956356,0.000006320297],"category_scores_gemma":[0.000051690484,0.00017636249,0.00004189255,0.0016007286,0.000023090624,0.00060282846,0.00055321393,0.00015340777,0.00036389267],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012578201,0.000052247753,0.00004668639,0.00006774423,0.00002451252,0.000031398595,0.000079657344,0.04029295,0.00080371206,0.0055642603,0.00295944,0.95006484],"study_design_scores_gemma":[0.00035989788,0.000010804407,0.0906103,0.000050985964,0.000010615085,0.000002048823,0.000023976087,0.8396419,0.0030893353,0.004735082,0.06117785,0.0002871775],"about_ca_topic_score_codex":0.00009891346,"about_ca_topic_score_gemma":0.000015870299,"teacher_disagreement_score":0.97000176,"about_ca_system_score_codex":0.00010274312,"about_ca_system_score_gemma":0.000009868587,"threshold_uncertainty_score":0.7191854},"labels":[],"label_agreement":null},{"id":"W4376464555","doi":"10.1109/tai.2023.3275133","title":"Margin-Aware Adaptive-Weighted-Loss for Deep Learning Based Imbalanced Data Classification","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Overfitting; Computer science; Softmax function; Margin (machine learning); Artificial intelligence; Machine learning; Discriminative model; MNIST database; Leverage (statistics); Robustness (evolution); Class (philosophy); Pattern recognition (psychology); Deep learning; Artificial neural network","score_opus":0.14057980307582246,"score_gpt":0.34483369803144504,"score_spread":0.20425389495562257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376464555","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019050286,0.000010104097,0.9940888,0.0016846537,0.000790284,0.0007652748,0.00024950958,0.0021232166,0.00009763159],"genre_scores_gemma":[0.92515767,0.000077694116,0.07337638,0.00020798083,0.000084129104,0.0004971808,0.00031412006,0.000043935615,0.00024089502],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969789,0.00016654022,0.0006385333,0.001188885,0.00047476278,0.0005523719],"domain_scores_gemma":[0.9965624,0.00070482877,0.0002354961,0.0020414041,0.00031367695,0.00014219919],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008159376,0.00029690206,0.00026196145,0.00050874345,0.00065977126,0.0002642402,0.0023969277,0.00017766467,0.00005245198],"category_scores_gemma":[0.000066700944,0.00031733856,0.000118133,0.0018253197,0.00016153442,0.0009911814,0.000020246014,0.0004446219,0.0006661916],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001516654,0.00030898888,0.000009445979,0.000040420065,0.000035946938,0.000008306361,0.0002564092,0.02534718,0.008988457,0.027834555,0.0007428716,0.9362758],"study_design_scores_gemma":[0.000052451967,0.00014932343,0.00006707632,0.000035985307,0.000013342689,0.0000022317972,0.00014364897,0.82751864,0.16370575,0.0049023456,0.0031108027,0.00029838437],"about_ca_topic_score_codex":0.000019851988,"about_ca_topic_score_gemma":0.000060568913,"teacher_disagreement_score":0.93597734,"about_ca_system_score_codex":0.0001450707,"about_ca_system_score_gemma":0.00014295992,"threshold_uncertainty_score":0.9999279},"labels":[],"label_agreement":null},{"id":"W4377289092","doi":"10.1038/s41746-023-00816-9","title":"Theory and rationale of interpretable all-in-one pattern discovery and disentanglement system","year":2023,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Computer science; Artificial intelligence; Inference; Masking (illustration); Machine learning; Cluster analysis; Association (psychology); Closing (real estate); Knowledge extraction; Class (philosophy); Data mining; Data science; Psychology","score_opus":0.03190714840485959,"score_gpt":0.2765683581320183,"score_spread":0.2446612097271587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377289092","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2434953,0.00035097904,0.7468653,0.0033899809,0.00018394578,0.0005570875,0.00011308724,0.000338559,0.004705773],"genre_scores_gemma":[0.9992707,0.000052421838,0.000257523,0.000115774936,0.00002165827,0.000027741416,0.000056623834,0.000004856653,0.00019269428],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9992027,0.000029643315,0.00023907278,0.00021521673,0.00020156708,0.000111756206],"domain_scores_gemma":[0.9993875,0.00021463745,0.00007443575,0.0002599549,0.000023383982,0.000040111754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003523298,0.00007342065,0.00015510716,0.0001281717,0.000015594593,0.000060286635,0.00019272428,0.000019296782,0.0000024324327],"category_scores_gemma":[0.00009413492,0.000058292662,0.000008832162,0.00020077937,0.00010118719,0.00080315344,0.00022000924,0.00004169223,0.000003526638],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046359426,0.00014496614,0.043966956,0.00075022987,0.00007269905,0.000041812964,0.003829717,0.0000031056695,0.01591366,0.6387327,0.003786905,0.29271093],"study_design_scores_gemma":[0.0073928125,0.00216328,0.6842173,0.008713538,0.00010082416,0.00017903473,0.011771989,0.068777606,0.030462634,0.1756845,0.008929668,0.0016068174],"about_ca_topic_score_codex":0.000008044671,"about_ca_topic_score_gemma":0.000002471014,"teacher_disagreement_score":0.7557754,"about_ca_system_score_codex":0.000029135146,"about_ca_system_score_gemma":0.0000114850955,"threshold_uncertainty_score":0.23771058},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Class (philosophy); Support vector machine; Data science","score_opus":0.059589895066658856,"score_gpt":0.3534783318788895,"score_spread":0.29388843681223065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378417908","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.7154518e-8,0.72192883,0.2639842,0.0001056191,0.00017775626,0.0017277002,0.000008947967,0.0071962215,0.0048707137],"genre_scores_gemma":[0.0000031039722,0.9328093,0.064718984,0.0010104273,0.00023934875,0.0005255278,0.00020514798,0.00015793867,0.00033025228],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99468374,0.0003519537,0.0015564535,0.0018013018,0.00074994325,0.00085658947],"domain_scores_gemma":[0.99449116,0.0012397169,0.0016434846,0.0023454332,0.00012495411,0.00015526064],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019820612,0.0009204366,0.0025658675,0.0004995829,0.00040899706,0.00033127549,0.0040041404,0.0004801251,0.000005453289],"category_scores_gemma":[0.0003797013,0.00084560557,0.00047886677,0.0023463594,0.000093161165,0.00017600774,0.0016356335,0.0019502015,0.0013428781],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.3376153e-7,0.000023708868,1.8943528e-7,0.02131077,0.000041026746,0.000011796034,0.00001705521,0.0000016976255,0.0000033511826,0.025056293,0.007811601,0.9457221],"study_design_scores_gemma":[0.00004410763,0.000040594176,5.3506733e-7,0.07730808,0.00007920319,0.000028742912,0.0000020984673,0.0006641617,0.000030524014,0.00044707546,0.92058414,0.0007707304],"about_ca_topic_score_codex":0.000004151225,"about_ca_topic_score_gemma":3.3940447e-7,"teacher_disagreement_score":0.94495136,"about_ca_system_score_codex":0.00035044318,"about_ca_system_score_gemma":0.00030854053,"threshold_uncertainty_score":0.9994347},"labels":[],"label_agreement":null},{"id":"W4378418328","doi":"10.18280/ria.370229","title":"A Study on Imbalanced Data Classification for Various Applications","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.18103146320605035,"score_gpt":0.37794030659804384,"score_spread":0.1969088433919935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378418328","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00069277396,0.000016117781,0.9918427,0.0018634574,0.00020887252,0.0023832617,0.00012198655,0.0014504052,0.0014204661],"genre_scores_gemma":[0.9633084,0.000046433306,0.031085288,0.00022716259,0.00014705112,0.0029128245,0.00071269664,0.000035240166,0.0015249194],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975576,0.000074171214,0.0005444192,0.0011620559,0.00027030712,0.000391441],"domain_scores_gemma":[0.9945598,0.00047968794,0.000213547,0.004474242,0.00018373865,0.000088969464],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010725028,0.00019158101,0.00021092892,0.00028871678,0.000337922,0.00021679829,0.0035033228,0.000078993,0.00000802973],"category_scores_gemma":[0.00026183037,0.00019597869,0.00005306294,0.0017449766,0.00005817133,0.0004901511,0.00051893253,0.000161602,0.0014173688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003694945,0.0018125366,0.0007491224,0.00008514008,0.000060459297,0.000012092687,0.0027081482,0.0024589913,0.014575159,0.54470456,0.03770283,0.395094],"study_design_scores_gemma":[0.0001017336,0.00031682174,0.0018381622,0.000028122466,0.000013614842,0.0000060786374,0.0012160742,0.90063465,0.0140033895,0.012925817,0.06855439,0.00036117938],"about_ca_topic_score_codex":0.0000061577725,"about_ca_topic_score_gemma":0.0000057022,"teacher_disagreement_score":0.9626156,"about_ca_system_score_codex":0.00007233969,"about_ca_system_score_gemma":0.00007225307,"threshold_uncertainty_score":0.99936014},"labels":[],"label_agreement":null},{"id":"W4380537293","doi":"10.5267/j.ijdns.2023.6.003","title":"EFN-SMOTE: An effective oversampling technique for credit card fraud detection by utilizing noise filtering and fuzzy c-means clustering","year":2023,"lang":"en","type":"article","venue":"International Journal of Data and Network Science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Credit card fraud; Oversampling; Credit card; Computer science; Noise (video); Artificial intelligence; Fuzzy logic; Cluster analysis; Data mining; Machine learning; Pattern recognition (psychology); Payment; Telecommunications","score_opus":0.03746760467933118,"score_gpt":0.33554616885843186,"score_spread":0.29807856417910067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380537293","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012328401,0.000079313606,0.986097,0.0002646392,0.00076950795,0.00022749895,0.00011615612,0.000084675725,0.000032799697],"genre_scores_gemma":[0.77969986,0.00025952118,0.2194864,0.000092650414,0.00039105208,0.000019688416,0.000037915313,0.000009021504,0.0000038726703],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998467,0.00004185835,0.00031721263,0.00044037084,0.00048307658,0.00025046372],"domain_scores_gemma":[0.9986411,0.00022502904,0.00029841115,0.0004053016,0.0003129966,0.00011718593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025054659,0.00011434006,0.00014846263,0.00028683225,0.0002824406,0.00053937716,0.0020463297,0.00004823639,5.138259e-7],"category_scores_gemma":[0.00026479777,0.00010897176,0.000023500172,0.0004844535,0.00015952646,0.0040946114,0.0011013506,0.0001730219,4.6838915e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008354972,0.000028857366,0.0007371244,0.00002719671,0.000034935398,0.000015451562,0.0004167849,0.0011666557,0.51917607,0.001393842,0.0018968666,0.47502267],"study_design_scores_gemma":[0.0005313414,0.00035978272,0.0067755566,0.00030289014,0.000016119737,0.0003366997,0.00013642544,0.9229328,0.05504441,0.0058234343,0.007433669,0.000306842],"about_ca_topic_score_codex":0.000016384716,"about_ca_topic_score_gemma":0.000010842159,"teacher_disagreement_score":0.92176616,"about_ca_system_score_codex":0.000085023494,"about_ca_system_score_gemma":0.000059275975,"threshold_uncertainty_score":0.52012265},"labels":[],"label_agreement":null},{"id":"W4381487215","doi":"10.1016/j.jbi.2023.104426","title":"A statistical comparison between Matthews correlation coefficient (MCC), prevalence threshold, and Fowlkes–Mallows index","year":2023,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Statistics; Correlation coefficient; Cohen's kappa; Correlation; Statistic; Brier score; Kappa; Mathematics; Computer science; Data mining; Econometrics","score_opus":0.030001227563461325,"score_gpt":0.3158772012061198,"score_spread":0.2858759736426585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381487215","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035461806,0.00003528599,0.96294963,0.0008410544,0.0002610543,0.00015564445,0.000041212857,0.00012965714,0.00012465702],"genre_scores_gemma":[0.8800969,0.00014088793,0.11935079,0.00022235262,0.00009408479,0.000005177051,0.000043949723,0.000008541653,0.000037314498],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971308,0.000056266475,0.0014066491,0.00010408613,0.0010263665,0.00027584622],"domain_scores_gemma":[0.9979228,0.00045009516,0.0008274393,0.00032631413,0.00019134681,0.00028205107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015714477,0.00013690343,0.00033742978,0.0004427839,0.000101034224,0.00019324946,0.00080736127,0.00014134374,0.000014510617],"category_scores_gemma":[0.0003556814,0.000106924184,0.00004547893,0.00073348975,0.00025333115,0.00081068074,0.0003145054,0.00030506658,0.000050960265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086922126,0.0006225736,0.20851752,0.0015006439,0.00022145556,0.00007992755,0.013632523,0.0007693158,0.00052710465,0.05092364,0.30545565,0.4176627],"study_design_scores_gemma":[0.0005958104,0.00043443087,0.13283373,0.00020632983,0.00002850409,0.00008576199,0.00028449844,0.845311,0.0001366304,0.002725428,0.017162021,0.00019587051],"about_ca_topic_score_codex":0.0000010216077,"about_ca_topic_score_gemma":2.5374283e-7,"teacher_disagreement_score":0.84463507,"about_ca_system_score_codex":0.00007200355,"about_ca_system_score_gemma":0.00013670498,"threshold_uncertainty_score":0.4360242},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.08644324549238729,"score_gpt":0.317593803694679,"score_spread":0.2311505582022917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382196087","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07152924,0.00029128746,0.87640667,0.04234805,0.0010376346,0.0023000392,0.000695324,0.0030661502,0.002325607],"genre_scores_gemma":[0.92080635,0.0010633281,0.07042202,0.005891896,0.000238012,0.000249962,0.00032619407,0.00009890658,0.00090331683],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965854,0.0001370146,0.0004492671,0.0013730375,0.0006698498,0.00078540517],"domain_scores_gemma":[0.9951777,0.0010645409,0.00033417615,0.0031222205,0.00016411967,0.00013725218],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015506742,0.00037230935,0.0003808747,0.00029387584,0.0007095723,0.00068570295,0.0034991356,0.00012255063,0.0000036081617],"category_scores_gemma":[0.0006447655,0.00026920426,0.000050365205,0.002118497,0.00031987426,0.0020997187,0.001107667,0.0005030368,0.00002184526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046218678,0.00023106871,0.047755823,0.00074790587,0.00017849063,0.00014969906,0.0011542746,0.00019235002,0.16250779,0.04832892,0.4328455,0.305446],"study_design_scores_gemma":[0.0010126017,0.0002466268,0.06768133,0.00008609117,0.000026514666,0.000066482644,0.00004991933,0.80630904,0.016746717,0.0003689828,0.106836535,0.0005691343],"about_ca_topic_score_codex":0.000004473407,"about_ca_topic_score_gemma":0.000007029324,"teacher_disagreement_score":0.84927714,"about_ca_system_score_codex":0.000075655305,"about_ca_system_score_gemma":0.00013002087,"threshold_uncertainty_score":0.99997604},"labels":[],"label_agreement":null},{"id":"W4382994301","doi":"10.2139/ssrn.4498130","title":"Pseudo Oversampling Based on Feature Transformation and Fuzzy Membership Functions for Imbalanced and Overlapping Data","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Oversampling; Feature (linguistics); Transformation (genetics); Fuzzy logic; Artificial intelligence; Pattern recognition (psychology); Computer science; Data mining; Mathematics; Biology; Linguistics","score_opus":0.05631966215033283,"score_gpt":0.30332711057299966,"score_spread":0.24700744842266684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382994301","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00092067284,0.0003896787,0.9894304,0.0073421644,0.00046035222,0.000633673,0.00028320556,0.00037654937,0.00016329555],"genre_scores_gemma":[0.87199533,0.007936474,0.11478922,0.000781985,0.0007992852,0.00024579195,0.0025417202,0.00012880817,0.0007813695],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997184,0.000091744616,0.00036679124,0.00079971313,0.00036325032,0.0011945096],"domain_scores_gemma":[0.997952,0.0002805073,0.0003897189,0.0011480686,0.00012916508,0.00010056132],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0025915997,0.00030728296,0.0003114385,0.00036209676,0.0004330619,0.00059834647,0.0012675687,0.0002943622,9.817552e-7],"category_scores_gemma":[0.00019081162,0.00030174942,0.00007863141,0.00023548573,0.00004631787,0.00084808073,0.00040855966,0.0026551883,0.000002521706],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039729744,0.00016870585,0.0007406081,0.0009020089,0.00064305554,0.00000519031,0.0011933548,0.0035092877,0.00265817,0.8285367,0.009330239,0.15191542],"study_design_scores_gemma":[0.0013785979,0.0003280211,0.0015983067,0.0004986053,0.000107799984,0.00013845258,0.00049696455,0.54913646,0.00013927183,0.44155505,0.0039333063,0.00068915036],"about_ca_topic_score_codex":0.00001963729,"about_ca_topic_score_gemma":0.00012612213,"teacher_disagreement_score":0.8746412,"about_ca_system_score_codex":0.0006033581,"about_ca_system_score_gemma":0.0014137628,"threshold_uncertainty_score":0.99994344},"labels":[],"label_agreement":null},{"id":"W4383560118","doi":"10.1007/s11042-023-15888-8","title":"Majority biased facial emotion recognition using residual variational autoencoders","year":2023,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Autoencoder; Computer science; Oversampling; Artificial intelligence; Undersampling; Pattern recognition (psychology); Hyperparameter; Residual; Confusion matrix; Classifier (UML); Machine learning; Deep learning; Algorithm; Bandwidth (computing)","score_opus":0.10084916773086365,"score_gpt":0.30873211048493593,"score_spread":0.20788294275407226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383560118","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006381712,0.0000073829046,0.9903708,0.0010892923,0.0000864407,0.0005356168,0.00043551152,0.00085036946,0.00024286254],"genre_scores_gemma":[0.08657812,0.000074378775,0.90919137,0.0002408284,0.00035256104,0.00081526465,0.0026297122,0.000019632427,0.00009815528],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888617,0.00005043015,0.00024329186,0.00039975077,0.00022677387,0.00019361035],"domain_scores_gemma":[0.9991394,0.00018315903,0.000116010284,0.0003622189,0.000120057986,0.00007913257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030637858,0.000108076456,0.00010232619,0.00016872307,0.0003300602,0.00020252737,0.00028800222,0.00009045716,0.000017171935],"category_scores_gemma":[0.000106530315,0.000117330455,0.000026708258,0.0007083375,0.000064824475,0.00068085245,0.00011567191,0.00010970718,0.0001556043],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004798534,0.00012347284,0.0008109617,0.000028373302,0.000019808256,0.000001671464,0.00053765846,0.00028197165,0.015439343,0.019452859,0.0032664249,0.96003264],"study_design_scores_gemma":[0.00038048846,0.000017708608,0.06345506,0.0000149163925,0.000012676803,0.0000049471437,0.00005603758,0.90668315,0.0026733805,0.018659206,0.0077778087,0.0002646202],"about_ca_topic_score_codex":0.00003232673,"about_ca_topic_score_gemma":0.0000038334497,"teacher_disagreement_score":0.95976806,"about_ca_system_score_codex":0.000051204508,"about_ca_system_score_gemma":0.0000760945,"threshold_uncertainty_score":0.47845972},"labels":[],"label_agreement":null},{"id":"W4383560185","doi":"10.54254/2755-2721/4/2023333","title":"Impact of different transaction features on credit card fraud detection by neural networks","year":2023,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Credit card fraud; Credit card; Database transaction; Feature (linguistics); Computer science; Artificial neural network; Transaction data; Chargeback; ATM card; Card security code; Machine learning; Artificial intelligence; Data mining; Database; Payment; World Wide Web","score_opus":0.006430267088186143,"score_gpt":0.22088885033128416,"score_spread":0.21445858324309802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383560185","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10086858,0.000015585922,0.8984919,0.00003925356,0.00009331548,0.000090477995,0.000012041025,0.0003600902,0.000028729362],"genre_scores_gemma":[0.9979925,0.0000098627725,0.0018196077,0.000015089398,0.000040732844,0.00002975657,0.00007975018,0.000008705024,0.0000039800057],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993919,0.0000069348735,0.00012689918,0.00018961057,0.00016136344,0.00012326846],"domain_scores_gemma":[0.9996734,0.000102744954,0.000044234544,0.00011562807,0.000023277304,0.00004066082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000050561765,0.00010721269,0.00010780644,0.0001215562,0.00004619652,0.000040767765,0.00012874874,0.00004941244,8.1874725e-7],"category_scores_gemma":[0.0000038954427,0.00009765437,0.00003929168,0.00027191802,0.000011060401,0.000097860866,0.000021636299,0.00011859388,0.0000010989748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000877696,0.000014698442,0.000025513596,0.000009261451,0.000019043711,3.3671841e-7,0.000046371588,0.93073034,0.011367366,0.0056756777,0.00027902922,0.051823594],"study_design_scores_gemma":[0.00012676092,0.00006208175,0.05801556,0.000005223994,0.0000025181037,0.0000027573285,0.0000023756397,0.93768156,0.0034194982,0.0005746163,0.00001892083,0.000088141984],"about_ca_topic_score_codex":0.0000072268444,"about_ca_topic_score_gemma":2.4657368e-7,"teacher_disagreement_score":0.89712393,"about_ca_system_score_codex":0.00003586267,"about_ca_system_score_gemma":0.000004745615,"threshold_uncertainty_score":0.39822295},"labels":[],"label_agreement":null},{"id":"W4383620205","doi":"10.1007/s10601-023-09348-1","title":"SAT-based optimal classification trees for non-binary data","year":2023,"lang":"en","type":"article","venue":"Constraints","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Microsoft Research","keywords":"Interpretability; Computer science; Overfitting; Pruning; Machine learning; Artificial intelligence; Decision tree; Categorical variable; Heuristic; Incremental decision tree; Binary decision diagram; Heuristics; Data mining; Decision tree learning; Algorithm; Artificial neural network","score_opus":0.11473907008261876,"score_gpt":0.345109813977273,"score_spread":0.23037074389465423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383620205","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002089283,0.0000064671835,0.9916302,0.0030222929,0.00024040246,0.0004999892,0.0005572353,0.001157463,0.00079665496],"genre_scores_gemma":[0.7230383,0.0000066809775,0.2739247,0.00026660052,0.000057304194,0.00017083167,0.0023576275,0.000014901757,0.00016303694],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852884,0.000036665726,0.00026782745,0.00065904687,0.00020623048,0.00030136856],"domain_scores_gemma":[0.9973133,0.00026797087,0.00012900546,0.0021041918,0.00010688546,0.00007864819],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061712734,0.00013428273,0.00014165124,0.00019541044,0.00014290103,0.00014371546,0.0023556696,0.00008713615,0.000018326102],"category_scores_gemma":[0.00024168061,0.00013852064,0.000040763913,0.0005387778,0.00023297418,0.0006256591,0.0003453909,0.000090668866,0.0002495404],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026048172,0.00017289602,0.0011087939,0.00007816513,0.000034558645,0.000020054053,0.00019215037,0.00007826277,0.08357356,0.06579575,0.25102207,0.5978977],"study_design_scores_gemma":[0.00047405763,0.00006451203,0.026448984,0.000034786248,0.000007285498,0.0000041941835,0.0000632122,0.94687945,0.0069690347,0.00086807524,0.01794692,0.00023949805],"about_ca_topic_score_codex":0.0000017503213,"about_ca_topic_score_gemma":0.000001794078,"teacher_disagreement_score":0.9468012,"about_ca_system_score_codex":0.000042079155,"about_ca_system_score_gemma":0.00025221505,"threshold_uncertainty_score":0.5648708},"labels":[],"label_agreement":null},{"id":"W4384026624","doi":"10.1109/icbc56567.2023.10174907","title":"Towards Improved Illicit Node Detection with Positive-Unlabelled Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Database transaction; Task (project management); Graph; Random forest; Node (physics); Feature learning; Representation (politics); Feature (linguistics); Data mining; Pattern recognition (psychology); Theoretical computer science","score_opus":0.012130275273365196,"score_gpt":0.2432536760720499,"score_spread":0.2311234007986847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384026624","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008612464,0.0000031287545,0.97978276,0.00082000444,0.00006661975,0.0001882254,0.0000019993688,0.0032105977,0.0073142084],"genre_scores_gemma":[0.88865596,0.000019419187,0.10700256,0.00029565312,0.000030090541,0.00007611647,0.000023030978,0.000018096243,0.0038790973],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99896014,0.00005418996,0.00014514274,0.00038231348,0.0002060468,0.0002521635],"domain_scores_gemma":[0.99923414,0.000050118033,0.00007801344,0.0004542432,0.00012840879,0.00005510529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026016537,0.00011645177,0.000110382294,0.00017688483,0.00018043949,0.00014384101,0.00048941403,0.000056759785,0.000014563018],"category_scores_gemma":[0.000058806276,0.00009326865,0.000025677355,0.0010506252,0.000030962856,0.00051093,0.00019462084,0.00016913003,0.00019399598],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003054808,0.000043500462,0.00046339942,0.000016486287,0.000034675842,0.00001378504,0.0005650124,0.00011765206,0.6171637,0.017413804,0.0010510711,0.36308637],"study_design_scores_gemma":[0.00036626632,0.00025615215,0.013043249,0.000016537548,0.000004744705,0.00001575452,0.000064200736,0.37838504,0.6010284,0.0005922486,0.0059485324,0.0002788993],"about_ca_topic_score_codex":0.00009568944,"about_ca_topic_score_gemma":0.000017996641,"teacher_disagreement_score":0.8800435,"about_ca_system_score_codex":0.0000586477,"about_ca_system_score_gemma":0.000044041775,"threshold_uncertainty_score":0.38033855},"labels":[],"label_agreement":null},{"id":"W4384068188","doi":"10.3390/jrfm16070327","title":"A Comparative Study of Traditional, Ensemble and Neural Network-Based Natural Language Processing Algorithms","year":2023,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial neural network; Artificial intelligence; Machine learning; Audit; Standardization; Task (project management); Ensemble forecasting; Data mining; Accounting; Engineering","score_opus":0.03069553444208621,"score_gpt":0.28187941681763784,"score_spread":0.2511838823755516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384068188","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5717567,0.0008945906,0.42662477,0.00012246797,0.00020327806,0.00027830192,0.000007985445,0.000053855016,0.00005804596],"genre_scores_gemma":[0.9753413,0.00009996142,0.024430966,0.000035126115,0.00007039295,0.0000064797177,0.0000023602352,0.0000027690824,0.000010644201],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99919736,0.000057929155,0.00027000785,0.00013057486,0.00023213413,0.000112011214],"domain_scores_gemma":[0.99941206,0.00006362828,0.0003086454,0.000108844746,0.00007479904,0.000031995714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003852378,0.0000773404,0.00019312827,0.0001733838,0.000107503394,0.000061867366,0.00021110149,0.00001726785,3.9018116e-7],"category_scores_gemma":[0.000016536933,0.00006398056,0.000024331572,0.00042328855,0.00003528713,0.00027897744,0.00008460252,0.00013108215,2.826663e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008380743,0.0003979418,0.0032752536,0.00008268394,0.00002873759,0.0001554081,0.0064293,0.0015063749,0.00009673487,0.0038506398,0.004006152,0.980087],"study_design_scores_gemma":[0.0026732008,0.0013231866,0.6074311,0.00018692308,0.00008296568,0.00002944273,0.0032670426,0.3787059,0.00033970852,0.004068892,0.0016055962,0.00028603256],"about_ca_topic_score_codex":0.0000060705333,"about_ca_topic_score_gemma":0.000006247783,"teacher_disagreement_score":0.97980094,"about_ca_system_score_codex":0.000013070241,"about_ca_system_score_gemma":0.000018765093,"threshold_uncertainty_score":0.26090515},"labels":[],"label_agreement":null},{"id":"W4384133663","doi":"10.1016/j.jbi.2023.104436","title":"Generating synthetic clinical data that capture class imbalanced distributions with generative adversarial networks: Example using antiretroviral therapy for HIV","year":2023,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Wellcome Trust","keywords":"Computer science; Machine learning; Artificial intelligence; Autoencoder; Adversarial system; Class (philosophy); Data mining; Artificial neural network","score_opus":0.11194027274448816,"score_gpt":0.3553270268300627,"score_spread":0.24338675408557453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384133663","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013974841,0.000049982747,0.98338133,0.00089001126,0.000913577,0.000309895,0.00034286344,0.00012850537,0.000009011023],"genre_scores_gemma":[0.17273428,0.0003442841,0.82410645,0.00069668016,0.0010224248,0.000012020792,0.0010432905,0.000021540254,0.00001905468],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99715054,0.00014056682,0.0013707819,0.0002155959,0.00069936353,0.0004231416],"domain_scores_gemma":[0.9966101,0.00057068124,0.0013226202,0.0009238081,0.00033947328,0.00023330656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024524878,0.00020733538,0.00047170007,0.00020975094,0.00027957794,0.00029775302,0.0018811282,0.00021289299,0.000003853327],"category_scores_gemma":[0.00043132645,0.00014201233,0.00011910023,0.0008003597,0.000311906,0.0017123368,0.00040328433,0.00043757985,0.0000027625156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008876782,0.0013155753,0.0066028084,0.00030314823,0.0015796939,0.00016026279,0.005955976,0.016584303,0.005142317,0.01619585,0.5852843,0.35998812],"study_design_scores_gemma":[0.0013837081,0.0004879902,0.0002137246,0.00009557433,0.000030015817,0.000094702016,0.00029591378,0.9741469,0.00029236474,0.00015636283,0.022610122,0.00019264201],"about_ca_topic_score_codex":0.000005264031,"about_ca_topic_score_gemma":0.0000013617561,"teacher_disagreement_score":0.95756257,"about_ca_system_score_codex":0.00009804008,"about_ca_system_score_gemma":0.0004945102,"threshold_uncertainty_score":0.5791095},"labels":[],"label_agreement":null},{"id":"W4384644022","doi":"10.48550/arxiv.2307.07881","title":"Graph Embedded Intuitionistic Fuzzy Random Vector Functional Link Neural Network for Class Imbalance Learning","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Indian Institute of Technology Indore; Ministry of Electronics and Information technology; Eisai; Department of Science and Technology, Ministry of Science and Technology, India; Pfizer; Novartis Pharmaceuticals Corporation; Council of Scientific and Industrial Research, India; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Computer science; Artificial intelligence; Machine learning; Embedding; Outlier; Weighting; Generalization; Class (philosophy); Graph; Classifier (UML); Data mining; Algorithm; Theoretical computer science; Mathematics","score_opus":0.08860652604235353,"score_gpt":0.21579619812492598,"score_spread":0.12718967208257245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384644022","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003021546,0.000041030144,0.99062383,0.0006416326,0.0021210068,0.0008377289,0.00010601079,0.0021711013,0.00043611173],"genre_scores_gemma":[0.9828869,0.00016330827,0.011858962,0.00018306442,0.00069940503,0.000051363542,0.00085396727,0.00005685331,0.0032461616],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99695754,0.00027329015,0.00040284503,0.0015712668,0.00018074375,0.0006142907],"domain_scores_gemma":[0.9967906,0.00071666413,0.0005582019,0.0013500513,0.00041385126,0.00017065473],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006174932,0.00042878222,0.00051125936,0.00032243427,0.00057420897,0.00032239157,0.001855676,0.00041282672,0.000015735277],"category_scores_gemma":[0.00027026274,0.0005218217,0.00037007668,0.0010533355,0.00018355333,0.0004679085,0.001312021,0.0010541264,0.00010396911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020079946,0.000044779306,0.0011837791,0.00012956682,0.00012577428,0.000051534982,0.0000542617,0.6345447,0.00013603496,0.3482272,0.0146518415,0.00064977363],"study_design_scores_gemma":[0.0011478784,0.00008798535,0.003467637,0.00011085729,0.00006706624,0.000004634815,0.000018733239,0.7972199,0.00007321332,0.19471768,0.0025169048,0.0005675574],"about_ca_topic_score_codex":0.000025889816,"about_ca_topic_score_gemma":0.000020553261,"teacher_disagreement_score":0.9798654,"about_ca_system_score_codex":0.00027154564,"about_ca_system_score_gemma":0.00023958202,"threshold_uncertainty_score":0.9997233},"labels":[],"label_agreement":null},{"id":"W4384696939","doi":"10.22215/etd/2023-15487","title":"Insurance Premium Calculation Using Machine Learning Methodologies","year":2023,"lang":"en","type":"dissertation","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Indemnity; Computer science; Insurance premium; Machine learning; Artificial intelligence; Data mining; Actuarial science; Business","score_opus":0.11534110263797832,"score_gpt":0.3821682339095083,"score_spread":0.26682713127153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384696939","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006337582,0.0001749235,0.98529357,0.00006959098,0.001017737,0.00033414338,0.000014809345,0.003844348,0.0029132846],"genre_scores_gemma":[0.03969037,0.00024160778,0.92934465,0.00005838971,0.00008988237,0.000085195104,0.0020825001,0.00007292256,0.028334491],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979656,0.00027359082,0.0004213429,0.0006472422,0.0004284463,0.00026381903],"domain_scores_gemma":[0.99827594,0.00028409724,0.0004347985,0.00072476844,0.00024027862,0.000040097046],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007914668,0.00026231888,0.00031321074,0.00035257422,0.00018988362,0.00020649047,0.001018875,0.00035606496,0.000011044898],"category_scores_gemma":[0.0007189101,0.00025193728,0.00008471574,0.0007609071,0.000019659794,0.0006044481,0.00014987707,0.00053150766,0.00006490042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012047716,0.00012668909,0.016349923,0.0014960788,0.00031241126,0.000056163164,0.0063360604,0.0064648786,0.32298943,0.1374941,0.006909186,0.5013446],"study_design_scores_gemma":[0.00029955225,0.000088269735,0.09771304,0.0003889414,0.000039016926,0.000014529721,0.00030031364,0.64204335,0.23901318,0.012464581,0.0061714756,0.001463728],"about_ca_topic_score_codex":0.00037298028,"about_ca_topic_score_gemma":0.00012252537,"teacher_disagreement_score":0.6355785,"about_ca_system_score_codex":0.00011397636,"about_ca_system_score_gemma":0.00011565419,"threshold_uncertainty_score":0.99999326},"labels":[],"label_agreement":null},{"id":"W4385386991","doi":"10.18280/ijsse.130308","title":"Fraud Detection in Utilities Using Data Analytics and Geospatial Analysis","year":2023,"lang":"en","type":"article","venue":"International Journal of Safety and Security Engineering","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Geospatial analysis; Analytics; Data analysis; Computer science; Data science; Crime analysis; Computer security; Data mining; Geography; Remote sensing; Psychology; Criminology","score_opus":0.03280895564309121,"score_gpt":0.28471651269627424,"score_spread":0.251907557053183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385386991","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14142677,0.000102842394,0.8578868,0.00027964363,0.00020273139,0.000022434177,0.000033522014,0.000037296395,0.000007969269],"genre_scores_gemma":[0.9888637,0.0006061723,0.0104298135,0.000015470683,0.00006438993,2.6185992e-7,0.000015560669,0.0000029944042,0.0000016124527],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920577,0.000017708438,0.00031514297,0.00013481682,0.00024016455,0.000086412416],"domain_scores_gemma":[0.99946165,0.00009598265,0.000121204655,0.00017509352,0.000109029024,0.000037022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005694146,0.00006340698,0.00013823417,0.00071313063,0.000024623563,0.0000964204,0.0005175398,0.000038157574,0.0000017201749],"category_scores_gemma":[0.00014808253,0.0000654152,0.000025608482,0.0005304222,0.00001708418,0.00085089076,0.00030557287,0.00015036571,2.4438265e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048362577,0.00032669425,0.071629085,0.0003174031,0.00636891,0.0009353328,0.018465698,0.39751765,0.027163135,0.082286924,0.00021151689,0.39429402],"study_design_scores_gemma":[0.0001424526,0.000010457479,0.02847786,0.000026112864,0.000020810205,0.000039278155,0.00005437715,0.9694632,0.0004761578,0.0006139845,0.00061428716,0.000060970953],"about_ca_topic_score_codex":0.0000489184,"about_ca_topic_score_gemma":0.000050278657,"teacher_disagreement_score":0.847457,"about_ca_system_score_codex":0.00005135201,"about_ca_system_score_gemma":0.000020340683,"threshold_uncertainty_score":0.26675546},"labels":[],"label_agreement":null},{"id":"W4385789921","doi":"10.3233/ida-220383","title":"Oversampling method based on GAN for tabular binary classification problems","year":2023,"lang":"en","type":"article","venue":"Intelligent Data Analysis","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Oversampling; Artificial intelligence; Regularization (linguistics); Binary number; Computer science; Resampling; Pattern recognition (psychology); Skew; Binary classification; Machine learning; Generalization; Class (philosophy); Algorithm; Mathematics; Support vector machine","score_opus":0.19096625181643756,"score_gpt":0.4044797046661944,"score_spread":0.2135134528497568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385789921","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000054767526,0.000025286856,0.9956587,0.0020528869,0.000103440594,0.00046874845,0.0006301289,0.00087681453,0.00012923717],"genre_scores_gemma":[0.118460536,0.00019334239,0.8599785,0.00072937197,0.00008331777,0.00037839328,0.01989088,0.000037713664,0.00024794406],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973104,0.00014321963,0.0005088405,0.0012082354,0.00048114304,0.00034814383],"domain_scores_gemma":[0.99428374,0.00068212824,0.00027197142,0.0044859485,0.00018030334,0.00009589529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021186823,0.00020130184,0.00030769667,0.0012853708,0.0001914972,0.00027736474,0.0032158443,0.000097274795,0.000026661377],"category_scores_gemma":[0.00043570623,0.00019316096,0.00018006958,0.0047213924,0.000033508797,0.00064105,0.0003685088,0.00013286664,0.00015594557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008744849,0.00085195835,0.004493386,0.00026392154,0.0021500327,0.000018482733,0.00058363203,0.34687787,0.025292523,0.116422966,0.09762337,0.40533438],"study_design_scores_gemma":[0.000069691,0.000052076055,0.00082420226,0.000017181686,0.0002014027,1.3684767e-7,0.00004320355,0.9326627,0.006895186,0.0016876239,0.05734092,0.00020563642],"about_ca_topic_score_codex":0.000046528774,"about_ca_topic_score_gemma":0.000014065152,"teacher_disagreement_score":0.58578485,"about_ca_system_score_codex":0.00010846018,"about_ca_system_score_gemma":0.00007538739,"threshold_uncertainty_score":0.78768754},"labels":[],"label_agreement":null},{"id":"W4386162847","doi":"10.1007/s10489-023-04846-4","title":"A new boundary-degree-based oversampling method for imbalanced data","year":2023,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Oversampling; Boundary (topology); Computer science; Degree (music); Decision boundary; Artificial intelligence; Benchmark (surveying); Pattern recognition (psychology); Data mining; Mathematics; Classifier (UML); Bandwidth (computing); Mathematical analysis; Physics","score_opus":0.15595479187359954,"score_gpt":0.38468136347658854,"score_spread":0.228726571602989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386162847","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008394747,0.00003213348,0.9944669,0.0012197612,0.00027361815,0.00072345865,0.00011693011,0.0018689458,0.0012898276],"genre_scores_gemma":[0.012391004,0.000031160253,0.9855472,0.00092708995,0.00011562039,0.00021138422,0.00049192086,0.000030875548,0.0002537493],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974935,0.000031238596,0.0004320207,0.0011358628,0.00037302257,0.00053434126],"domain_scores_gemma":[0.9955644,0.0008186198,0.00019552451,0.0031749192,0.00009735037,0.00014921084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011710678,0.00023548155,0.00026038225,0.00022792531,0.0002222006,0.00033361398,0.004666286,0.000111877715,0.000027007713],"category_scores_gemma":[0.0002593292,0.00024175613,0.00005841144,0.0013864837,0.000056092187,0.0005097876,0.0008795651,0.00018540287,0.0003405418],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024390742,0.00002089737,0.000014521441,0.000033201995,0.00001592053,0.0000018015728,0.00015128014,0.00034379316,0.011139851,0.29433498,0.045024432,0.64889497],"study_design_scores_gemma":[0.00018445893,0.00004851978,0.00014694131,0.000028958159,0.000009986881,0.0000024583976,0.00005193144,0.6040969,0.16258754,0.085185,0.1472588,0.00039850723],"about_ca_topic_score_codex":0.000049770308,"about_ca_topic_score_gemma":0.000009853859,"teacher_disagreement_score":0.64849645,"about_ca_system_score_codex":0.00007659046,"about_ca_system_score_gemma":0.00040151438,"threshold_uncertainty_score":0.9858529},"labels":[],"label_agreement":null},{"id":"W4386198763","doi":"10.1007/978-981-99-3734-9_12","title":"Handling Class Imbalance Problem Using Support Vector Machine","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Support vector machine; Outlier; Class (philosophy); Computer science; Machine learning; Artificial intelligence; Hazard; Test data; Data mining","score_opus":0.030586551040804308,"score_gpt":0.255297312766796,"score_spread":0.2247107617259917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386198763","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000067533656,0.003230303,0.98817044,0.00018789372,0.0012417,0.00075618376,0.0000483386,0.00056928484,0.0057891067],"genre_scores_gemma":[0.89311457,0.004968272,0.056843154,0.0010817755,0.0040901685,0.00032409866,0.00095592526,0.0006190382,0.038003016],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974279,0.00006637372,0.00072676165,0.0009265158,0.00036389747,0.0004885771],"domain_scores_gemma":[0.9980194,0.00033549222,0.00048818934,0.0009544461,0.00010191939,0.00010053228],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00067348685,0.00048352373,0.00073397724,0.00027065823,0.00014202386,0.0004156676,0.00079207355,0.0007020488,0.000005702566],"category_scores_gemma":[0.00003975914,0.00043625114,0.00008587319,0.00021789983,0.00008030023,0.0002024756,0.00034939963,0.0008623468,0.0000109205075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006194738,0.0000632506,0.0027576846,0.0019884699,0.00034063912,0.00062633737,0.0007481931,0.26008818,0.0009501488,0.6494696,0.0047719437,0.0781336],"study_design_scores_gemma":[0.00020369253,0.00006442555,0.00005416751,0.0012864138,0.00001776647,0.00009882983,7.630933e-7,0.9694546,0.000027853155,0.008634254,0.019544676,0.0006125748],"about_ca_topic_score_codex":0.000092582406,"about_ca_topic_score_gemma":0.00010663628,"teacher_disagreement_score":0.9313273,"about_ca_system_score_codex":0.00016510043,"about_ca_system_score_gemma":0.000091988826,"threshold_uncertainty_score":0.9998089},"labels":[],"label_agreement":null},{"id":"W4386566652","doi":"10.18653/v1/2023.eacl-main.195","title":"On Evaluation of Document Classification with RVL-CDIP","year":2023,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Atomic Energy of Canada Limited","keywords":"Benchmarking; Benchmark (surveying); Computer science; Scope (computer science); Resource (disambiguation); Artificial intelligence; Task (project management); Machine learning; Information retrieval; Data mining; Pattern recognition (psychology); Engineering; Business","score_opus":0.07528893480864146,"score_gpt":0.3406554908920777,"score_spread":0.26536655608343623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386566652","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025100673,0.000004555716,0.9448231,0.0025289333,0.00008941888,0.0005472607,0.0000035926337,0.00097163615,0.025930865],"genre_scores_gemma":[0.9705768,0.0000073035544,0.028734108,0.000111642774,0.000008394933,0.00013549652,0.000035667577,0.0000055935675,0.0003849516],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985216,0.0000931595,0.00018702334,0.00028091253,0.0007990722,0.00011819048],"domain_scores_gemma":[0.9986335,0.00008630177,0.00012864439,0.0008236055,0.00029851182,0.000029418972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011450471,0.000073169664,0.00007804992,0.00019886268,0.000040274677,0.000044026652,0.0004711847,0.000033358443,0.000041627158],"category_scores_gemma":[0.000084313295,0.000055586825,0.000016694385,0.00081280863,0.000030390514,0.00036758697,0.000058483496,0.00004777772,0.00019185182],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006123006,0.000037333608,0.00014344718,0.0000063700513,0.0000073572837,2.832236e-7,0.000100553654,0.00015896582,0.006262791,0.9052433,0.0090468265,0.078986645],"study_design_scores_gemma":[0.00090713525,0.00045297804,0.11057175,0.00006894339,0.000023254082,0.00000317335,0.00011006066,0.5500532,0.17069703,0.16432758,0.0024661128,0.00031881212],"about_ca_topic_score_codex":0.0000075671132,"about_ca_topic_score_gemma":0.0000034559243,"teacher_disagreement_score":0.9454762,"about_ca_system_score_codex":0.00008676811,"about_ca_system_score_gemma":0.000090699665,"threshold_uncertainty_score":0.24659312},"labels":[],"label_agreement":null},{"id":"W4386641256","doi":"10.54254/2754-1169/19/20230138","title":"M-score and F-score from the Financial Statement for Company Fraud Prediction","year":2023,"lang":"en","type":"article","venue":"Advances in Economics Management and Political Sciences","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Accrual; Statement (logic); Financial statement; Work (physics); Accounting; Actuarial science; Predictive modelling; F1 score; Net income; Income statement; Business; Psychology; Balance sheet; Computer science; Audit; Statistics; Artificial intelligence; Political science; Mathematics; Engineering; Law","score_opus":0.03161224420063031,"score_gpt":0.28909420967440924,"score_spread":0.25748196547377894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386641256","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3855705,0.0012463591,0.5782982,0.021080283,0.0013639221,0.0019293731,0.00038850054,0.0004694838,0.009653361],"genre_scores_gemma":[0.96158546,0.004990972,0.03162775,0.0013459077,0.00010941188,0.0002118574,0.0000403646,0.000005085928,0.00008316916],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989518,0.000021247693,0.00023154054,0.00039434648,0.000076678676,0.00032438996],"domain_scores_gemma":[0.9993906,0.00029075582,0.000060454953,0.00019436477,0.000010279424,0.00005356281],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047936465,0.000087366054,0.00010200733,0.00007663804,0.00022678805,0.00019535632,0.0004985405,0.000023004151,0.0000021018384],"category_scores_gemma":[0.000033466615,0.00006672246,0.000014663222,0.0001856294,0.00033068995,0.0008763884,0.0003038746,0.000046855483,0.0000036986823],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025965016,0.00000748186,0.015887234,0.000008961952,0.0000020566347,3.2863136e-7,0.00006972137,0.00006505177,0.000001245372,0.9221035,0.0003516102,0.06150016],"study_design_scores_gemma":[0.00023887778,0.00007368281,0.1521942,0.000022175966,0.000004353374,4.0978043e-7,0.0002505977,0.09709961,0.00007261779,0.65904266,0.090879574,0.00012124141],"about_ca_topic_score_codex":0.000022927039,"about_ca_topic_score_gemma":0.000059043214,"teacher_disagreement_score":0.576015,"about_ca_system_score_codex":0.000036758218,"about_ca_system_score_gemma":0.0000150126225,"threshold_uncertainty_score":0.2720863},"labels":[],"label_agreement":null},{"id":"W4386708240","doi":"10.32920/24133128.v1","title":"Evaluation methodology for deep learning imputation models","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Toronto Metropolitan University; Vector Institute","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Imputation (statistics); Mean squared error; Computer science; Deep learning; Artificial intelligence; Missing data; Machine learning; Regression; Data mining; Artificial neural network; Statistics; Mathematics","score_opus":0.41068016756779663,"score_gpt":0.44568761988089683,"score_spread":0.03500745231310021,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386708240","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004324561,0.000064278975,0.99349755,0.001172132,0.0007331156,0.0013628231,0.000009502528,0.0022730306,0.00084434834],"genre_scores_gemma":[0.028260667,0.00006087217,0.968467,0.000113397866,0.00008362018,0.0018950647,0.0005964893,0.000029836438,0.0004930381],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970646,0.0008350227,0.00042661128,0.0008879651,0.0005371604,0.0002486275],"domain_scores_gemma":[0.9968338,0.00083851337,0.00039085886,0.0008928868,0.0010010791,0.000042880794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007522088,0.00019318495,0.00026622863,0.00033075007,0.00011380881,0.00021132991,0.0011572622,0.00033824483,0.000008614352],"category_scores_gemma":[0.0015091301,0.00019958722,0.00010655477,0.0002271017,0.000023856928,0.00045031117,0.0010558184,0.00037030585,0.000036688783],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034545799,0.000013556402,0.0000048366755,0.000060145554,0.000040742056,2.749192e-7,0.00053766766,0.2192081,0.0004966766,0.22776648,0.0013678878,0.55050015],"study_design_scores_gemma":[0.00007305433,0.000020233503,0.0000627175,0.00000980051,0.000019107069,6.9371146e-7,0.000015175405,0.54723674,0.0014082816,0.4508645,0.00017380375,0.00011588248],"about_ca_topic_score_codex":0.00004781903,"about_ca_topic_score_gemma":0.000018382758,"teacher_disagreement_score":0.5503843,"about_ca_system_score_codex":0.0002362649,"about_ca_system_score_gemma":0.00025648432,"threshold_uncertainty_score":0.8138931},"labels":[],"label_agreement":null},{"id":"W4386708429","doi":"10.32920/24133128","title":"Evaluation methodology for deep learning imputation models","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Toronto Metropolitan University; Vector Institute","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Imputation (statistics); Computer science; Mean squared error; Deep learning; Artificial intelligence; Missing data; Machine learning; Regression; Data mining; Artificial neural network; Pattern recognition (psychology); Statistics; Mathematics","score_opus":0.41068016756779663,"score_gpt":0.44568761988089683,"score_spread":0.03500745231310021,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386708429","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004324561,0.000064278975,0.99349755,0.001172132,0.0007331156,0.0013628231,0.000009502528,0.0022730306,0.00084434834],"genre_scores_gemma":[0.028260667,0.00006087217,0.968467,0.000113397866,0.00008362018,0.0018950647,0.0005964893,0.000029836438,0.0004930381],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970646,0.0008350227,0.00042661128,0.0008879651,0.0005371604,0.0002486275],"domain_scores_gemma":[0.9968338,0.00083851337,0.00039085886,0.0008928868,0.0010010791,0.000042880794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007522088,0.00019318495,0.00026622863,0.00033075007,0.00011380881,0.00021132991,0.0011572622,0.00033824483,0.000008614352],"category_scores_gemma":[0.0015091301,0.00019958722,0.00010655477,0.0002271017,0.000023856928,0.00045031117,0.0010558184,0.00037030585,0.000036688783],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034545799,0.000013556402,0.0000048366755,0.000060145554,0.000040742056,2.749192e-7,0.00053766766,0.2192081,0.0004966766,0.22776648,0.0013678878,0.55050015],"study_design_scores_gemma":[0.00007305433,0.000020233503,0.0000627175,0.00000980051,0.000019107069,6.9371146e-7,0.000015175405,0.54723674,0.0014082816,0.4508645,0.00017380375,0.00011588248],"about_ca_topic_score_codex":0.00004781903,"about_ca_topic_score_gemma":0.000018382758,"teacher_disagreement_score":0.5503843,"about_ca_system_score_codex":0.0002362649,"about_ca_system_score_gemma":0.00025648432,"threshold_uncertainty_score":0.8138931},"labels":[],"label_agreement":null},{"id":"W4386952443","doi":"10.1109/iceccme57830.2023.10253185","title":"An Efficient Resampling Technique for Financial Statements Fraud Detection: A Comparative Study","year":2023,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Financial statement; Computer science; Artificial neural network; Audit; Machine learning; Financial ratio; Artificial intelligence; Benchmark (surveying); Metric (unit); Finance; Resampling; Accounting; Business","score_opus":0.09714873008454457,"score_gpt":0.41944388816339806,"score_spread":0.3222951580788535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386952443","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024842216,0.0000015293658,0.9707019,0.00009313674,0.0001646717,0.002305737,0.000023299051,0.0017171755,0.00015035157],"genre_scores_gemma":[0.8415568,8.0623875e-7,0.15636638,0.00006131239,0.00003462574,0.0018693641,0.000021231812,0.000008329561,0.000081158025],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99848545,0.00008626131,0.00031897842,0.0005523134,0.00027133254,0.0002856439],"domain_scores_gemma":[0.99872285,0.00010309051,0.00011079434,0.0008048249,0.00019181512,0.00006659616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008724632,0.00013751465,0.0001689226,0.00026361324,0.00030378185,0.00015742339,0.0008410645,0.000051733885,0.0000049218534],"category_scores_gemma":[0.000058190035,0.0001285705,0.000034693836,0.0009937648,0.000027440612,0.00044903878,0.00018398752,0.00010182205,0.00004232571],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004021099,0.0066628256,0.002242081,0.00016435579,0.00015269827,0.00004549788,0.025328673,0.011757977,0.59544057,0.23044,0.028815603,0.09854764],"study_design_scores_gemma":[0.00094768807,0.0019228071,0.011378182,0.000022784743,0.000008567244,0.0000033617043,0.0010900865,0.42013904,0.5495095,0.0078090895,0.0066348943,0.0005339524],"about_ca_topic_score_codex":0.000023011053,"about_ca_topic_score_gemma":0.0000342834,"teacher_disagreement_score":0.8167146,"about_ca_system_score_codex":0.00008211235,"about_ca_system_score_gemma":0.00006546777,"threshold_uncertainty_score":0.5242953},"labels":[],"label_agreement":null},{"id":"W4387099797","doi":"10.54254/2755-2721/6/20230334","title":"Feature selection in text classification: Identifying spurious words with causal inference methods","year":2023,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Spurious relationship; Computer science; Inference; Causal inference; Artificial intelligence; Weighting; Feature selection; Feature (linguistics); Machine learning; Propensity score matching; Matching (statistics); Selection (genetic algorithm); Model selection; Selection bias; Pattern recognition (psychology); Data mining; Statistics; Mathematics","score_opus":0.023988210522339418,"score_gpt":0.3065342753834491,"score_spread":0.28254606486110967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387099797","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061320295,0.000023847191,0.99223745,0.0005123335,0.000043711996,0.00014932238,0.0000016651951,0.0006774468,0.00022217714],"genre_scores_gemma":[0.6011531,0.00000970028,0.39863706,0.00003604238,0.00002136062,0.00007948544,0.000025831581,0.000008742597,0.00002868108],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991033,0.000019283663,0.00014581419,0.00034744487,0.00019616041,0.00018797924],"domain_scores_gemma":[0.9994978,0.00021886456,0.000057582594,0.000132226,0.00004657495,0.00004698578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027691765,0.00012802768,0.00012329197,0.00032076228,0.000076306475,0.00015499089,0.00023056472,0.00006154027,0.0000013918885],"category_scores_gemma":[0.000023027877,0.00012831992,0.000011185778,0.0013666232,0.000020105414,0.00029127856,0.00008847457,0.00019675551,0.000010785986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000843852,0.000023074448,0.000846001,0.00006483166,0.000020568848,0.0000069443286,0.00063692924,0.19322897,0.01728277,0.6928881,0.00028429157,0.0947091],"study_design_scores_gemma":[0.00019216194,0.0000142997,0.11594623,0.000029970264,0.0000023226687,0.000016888427,0.000034374094,0.87625116,0.0009103737,0.005542979,0.0008794189,0.00017981551],"about_ca_topic_score_codex":0.0000039548463,"about_ca_topic_score_gemma":0.0000026129942,"teacher_disagreement_score":0.6873451,"about_ca_system_score_codex":0.0000559779,"about_ca_system_score_gemma":0.000050403836,"threshold_uncertainty_score":0.52327347},"labels":[],"label_agreement":null},{"id":"W4387350749","doi":"10.1109/tfuzz.2023.3321768","title":"Deep Fuzzy Envelope Sample Generation Mechanism for Imbalanced Ensemble Classification","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Fuzzy Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Artificial intelligence; Pattern recognition (psychology); Cluster analysis; Classifier (UML); Computer science; Fuzzy logic; Sample (material); Consistency (knowledge bases); Data mining; Algorithm; Mathematics","score_opus":0.06262172125483034,"score_gpt":0.2857836802399207,"score_spread":0.22316195898509034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387350749","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006484118,0.000014548972,0.991382,0.0008442412,0.0028233223,0.001452365,0.00017815242,0.0021488783,0.0005080959],"genre_scores_gemma":[0.9353045,0.00010659399,0.060440667,0.00018783119,0.00020830313,0.0026031565,0.00020687387,0.000049548464,0.00089251116],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973927,0.00016167581,0.0006266051,0.00083622965,0.00049121614,0.0004915404],"domain_scores_gemma":[0.9975856,0.00034197915,0.00025924374,0.0012829069,0.00039429692,0.00013596105],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006535123,0.00028666688,0.00030278697,0.0005071797,0.00056021067,0.00036502138,0.00084451016,0.00022667229,0.0000040686527],"category_scores_gemma":[0.000045680026,0.00029772095,0.00013954456,0.001122263,0.000035561523,0.0007577582,0.00000532967,0.00019016095,0.00034131654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038755516,0.00023434998,0.000016896001,0.00017241755,0.0001005431,0.0000034811385,0.00077672943,0.011271156,0.40402934,0.51371074,0.011105671,0.058539942],"study_design_scores_gemma":[0.000598355,0.00018839496,0.00015614888,0.000045950997,0.000022519454,0.000013247845,0.00016160366,0.8285309,0.15584491,0.010449277,0.0034998565,0.00048881356],"about_ca_topic_score_codex":0.000075965676,"about_ca_topic_score_gemma":0.00005424699,"teacher_disagreement_score":0.9346561,"about_ca_system_score_codex":0.00026279315,"about_ca_system_score_gemma":0.00011337608,"threshold_uncertainty_score":0.9999475},"labels":[],"label_agreement":null},{"id":"W4387640457","doi":"10.1007/978-3-031-45676-3_32","title":"MEDKD: Enhancing Medical Image Classification with Multiple Expert Decoupled Knowledge Distillation for Long-Tail Data","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Contextual image classification; Class (philosophy); Machine learning; Artificial intelligence; Distillation; Image (mathematics); Task (project management); Data mining; Noise (video); Pattern recognition (psychology)","score_opus":0.05536565858843196,"score_gpt":0.325771751090763,"score_spread":0.27040609250233105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387640457","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016442222,0.00017786284,0.99459684,0.0017222083,0.001050211,0.0011026651,0.00007372295,0.00086432823,0.00039573503],"genre_scores_gemma":[0.05560696,0.00018480435,0.9413133,0.00047982673,0.00079477124,0.00018477546,0.00089581264,0.000115853516,0.00042387107],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99426216,0.00005357031,0.0008450967,0.002652165,0.0014805855,0.00070640986],"domain_scores_gemma":[0.99245745,0.0020739725,0.0005495282,0.0040118317,0.00064566114,0.00026152885],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0023464607,0.00057600706,0.000583442,0.00080893934,0.0003831714,0.00065785646,0.0073889764,0.0004793725,0.00001495907],"category_scores_gemma":[0.0015029918,0.00049574324,0.0000755449,0.0009187296,0.0008112906,0.0016501811,0.0023309847,0.00064676197,0.000066030356],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003109683,0.00008591709,0.00019250276,0.00016896558,0.000028909977,0.0000377218,0.000732242,0.0002823857,0.0015844611,0.016227877,0.00075229903,0.9798756],"study_design_scores_gemma":[0.0004475878,0.00011545788,0.00080635026,0.0007256056,0.000009700978,0.000031747382,6.450359e-7,0.98014,0.0035581912,0.0108573055,0.002631212,0.0006762499],"about_ca_topic_score_codex":0.000021236267,"about_ca_topic_score_gemma":0.0014691422,"teacher_disagreement_score":0.97985756,"about_ca_system_score_codex":0.00044529338,"about_ca_system_score_gemma":0.0013856913,"threshold_uncertainty_score":0.9997494},"labels":[],"label_agreement":null},{"id":"W4387951364","doi":"10.1109/ccece58730.2023.10288946","title":"Exploring Gene Expression and Clinical Data for Identifying Prostate Cancer Severity Levels using Machine Learning Methods","year":2023,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Prostate Cancer Canada; University of Alberta; University of Calgary","funders":"","keywords":"Prostate cancer; Naive Bayes classifier; Random forest; Artificial intelligence; Support vector machine; Logistic regression; Machine learning; Decision tree; Prostate biopsy; Computer science; Prostate; Medicine; Cancer; Internal medicine","score_opus":0.678177979157786,"score_gpt":0.5320585504956288,"score_spread":0.1461194286621572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387951364","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031107036,0.00010522753,0.96686435,0.00025529703,0.00035138987,0.0003345867,0.00010035913,0.00087258633,0.0000091655465],"genre_scores_gemma":[0.020281587,0.00081901375,0.978368,0.00006786571,0.00007637037,0.00009651497,0.00010140392,0.00001997176,0.00016931104],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99804115,0.00027557084,0.00042103895,0.00079465634,0.00017846253,0.0002890929],"domain_scores_gemma":[0.99815536,0.0004525738,0.00017968238,0.0010445517,0.00008314291,0.00008466868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034031826,0.0001314621,0.00021495738,0.00012690586,0.00031098287,0.0002482531,0.0009897167,0.000053127635,0.000005220108],"category_scores_gemma":[0.00056650565,0.00011861754,0.000031603497,0.0004156814,0.00004345295,0.002571152,0.0022937509,0.00020637878,0.0000027368333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018603392,0.00003128917,0.013399923,0.00012493393,0.00003483401,0.0000051163956,0.0005121454,0.00009512368,0.4557826,0.0007336205,0.00061859604,0.5286432],"study_design_scores_gemma":[0.00024055035,0.000017369324,0.0079611,0.0000649179,0.000009585036,0.0000039259116,0.000041586514,0.8183184,0.16759056,0.0006881736,0.0048732352,0.00019059618],"about_ca_topic_score_codex":0.00011240171,"about_ca_topic_score_gemma":0.000010648425,"teacher_disagreement_score":0.8182233,"about_ca_system_score_codex":0.000037075275,"about_ca_system_score_gemma":0.000060710245,"threshold_uncertainty_score":0.48370832},"labels":[],"label_agreement":null},{"id":"W4388097990","doi":"10.5267/j.ijdns.2023.9.009","title":"Efficient credit card fraud detection using evolutionary hybrid feature selection and random weight networks","year":2023,"lang":"en","type":"article","venue":"International Journal of Data and Network Science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Credit card fraud; Computer science; Credit card; Feature selection; Machine learning; Artificial intelligence; Feature (linguistics); Cornerstone; Process (computing); Data mining; Payment","score_opus":0.02124885327068184,"score_gpt":0.2923868420032908,"score_spread":0.27113798873260897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388097990","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07362548,0.0005070567,0.92286664,0.00080785074,0.0019708048,0.00008831274,0.000030184674,0.00007977298,0.000023863042],"genre_scores_gemma":[0.946538,0.0006928955,0.051568657,0.000108679225,0.0010486266,0.000001789374,0.000023352404,0.0000058994215,0.000012105844],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981809,0.00006668388,0.0003090129,0.0004000655,0.00079403614,0.00024930175],"domain_scores_gemma":[0.9985316,0.00015440545,0.0003523911,0.00032637763,0.00051911565,0.00011614976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018417726,0.00011078938,0.00014926601,0.00037735395,0.0003561538,0.0003738129,0.0017534838,0.00004551276,0.0000018009135],"category_scores_gemma":[0.00016768902,0.00009629511,0.000026903004,0.0010487711,0.0002080166,0.0016345474,0.0009280547,0.00025683382,0.0000014293552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055264094,0.00017065773,0.01478853,0.000026274545,0.00027211502,0.00021133784,0.0003955478,0.3553174,0.03055184,0.0068947086,0.065638565,0.5251804],"study_design_scores_gemma":[0.0003534693,0.000042700533,0.009748859,0.000063810425,0.0000103791135,0.0007495497,0.000008948804,0.9823398,0.00063941197,0.00072703155,0.0052145133,0.00010150729],"about_ca_topic_score_codex":0.000009974043,"about_ca_topic_score_gemma":0.0000035076903,"teacher_disagreement_score":0.8729125,"about_ca_system_score_codex":0.000114822884,"about_ca_system_score_gemma":0.00016057109,"threshold_uncertainty_score":0.39268005},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.06262470066207466,"score_gpt":0.33965272587246653,"score_spread":0.2770280252103919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388099759","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.7854823e-9,0.5021304,0.49014142,0.000012252416,0.0001715709,0.006587726,0.000021878288,0.0009206858,0.000014055375],"genre_scores_gemma":[0.000004407521,0.9468744,0.0056660366,0.00013137079,0.00035733086,0.046615742,0.00014682114,0.00010720115,0.000096736876],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9954456,0.0005521597,0.0017841707,0.0011564316,0.00056509767,0.0004965472],"domain_scores_gemma":[0.9940347,0.00030317836,0.00188336,0.0033661944,0.0002739551,0.00013863151],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007831998,0.00067171245,0.0026697258,0.00047415972,0.00044133668,0.00036436773,0.002342365,0.00036515517,0.0000011303116],"category_scores_gemma":[0.00011366639,0.00050114276,0.00037523304,0.0038374157,0.000074185824,0.00044957394,0.0002602875,0.0004767544,0.00012682666],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.5471776e-7,0.000044745295,7.554577e-8,0.948245,0.00012872824,0.0000073667616,0.000031786767,0.000046130543,7.5647483e-7,0.00852731,0.0016064442,0.041361097],"study_design_scores_gemma":[0.000068832065,0.000038478775,1.1142324e-7,0.5887665,0.00062270364,0.0004669471,0.000010573622,0.03622296,8.2634534e-7,0.000056842382,0.37284306,0.00090218807],"about_ca_topic_score_codex":0.0000797837,"about_ca_topic_score_gemma":0.000009468493,"teacher_disagreement_score":0.4844754,"about_ca_system_score_codex":0.00036438784,"about_ca_system_score_gemma":0.00027647574,"threshold_uncertainty_score":0.999744},"labels":[],"label_agreement":null},{"id":"W4388212504","doi":"10.1093/oso/9780198527978.003.0018","title":"Detecting credit card fraud using expert systems","year":2004,"lang":"en","type":"book-chapter","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Credit card; Card security code; Credit card fraud; Business; Counterfeit; Financial institution; Chargeback; Receipt; Computer security; Limiting; Internet privacy; ATM card; Credit card interest; Payment; Accounting; Computer science; Finance; Political science; Engineering; Law","score_opus":0.05963687090208311,"score_gpt":0.2785865778759485,"score_spread":0.21894970697386537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388212504","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000015888401,0.0004696569,0.71019536,0.00005623762,0.0009304599,0.0002934378,0.000015651245,0.0012176536,0.28681996],"genre_scores_gemma":[0.015152708,0.00031539396,0.7183339,0.0007577634,0.0020755674,0.00008923314,0.000077894234,0.00023348791,0.26296404],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977711,0.000020138537,0.00052510464,0.0008129796,0.00054785307,0.00032281157],"domain_scores_gemma":[0.9974766,0.00006482135,0.00039808857,0.0017446995,0.00020685329,0.00010896786],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025511888,0.00038880578,0.00042782348,0.00028400944,0.00016903505,0.00039708265,0.0015382427,0.00045413154,0.000058276884],"category_scores_gemma":[0.000031645228,0.00037846333,0.00012919807,0.00007207867,0.00006256324,0.00052439247,0.0004816975,0.00040773035,0.00013586332],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010977244,0.0000061966452,9.636083e-7,0.000049155253,0.00003538365,0.000031290238,0.00014906035,0.00007496638,0.0014491233,0.9857858,0.0029034568,0.009513516],"study_design_scores_gemma":[0.00047564256,0.00016732862,0.000006338139,0.0022640773,0.000046049463,0.00037438297,0.00007481035,0.068360806,0.020510476,0.058921862,0.84587425,0.0029239664],"about_ca_topic_score_codex":0.00031659188,"about_ca_topic_score_gemma":0.000006328642,"teacher_disagreement_score":0.9268639,"about_ca_system_score_codex":0.00058049505,"about_ca_system_score_gemma":0.0002491771,"threshold_uncertainty_score":0.9998667},"labels":[],"label_agreement":null},{"id":"W4388585148","doi":"10.18280/ijsse.130509","title":"Detection of Health Insurance Fraud using Bayesian Optimized XGBoost","year":2023,"lang":"en","type":"article","venue":"International Journal of Safety and Security Engineering","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Bayesian probability; Environmental health; Computer science; Health insurance; Actuarial science; Computer security; Business; Risk analysis (engineering); Medicine; Artificial intelligence; Economics; Health care","score_opus":0.014302643126892448,"score_gpt":0.2661878477067442,"score_spread":0.25188520457985175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388585148","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03380137,0.0001609915,0.9647642,0.0006324503,0.000506071,0.00004209626,0.000014904387,0.00006429021,0.0000136187355],"genre_scores_gemma":[0.95309865,0.00067665795,0.04611962,0.00003533039,0.00005965081,5.732698e-7,0.0000027513865,0.0000052061223,0.0000015334759],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989957,0.000030251267,0.0004866956,0.00009500284,0.00029225458,0.00010004831],"domain_scores_gemma":[0.99921584,0.000074048316,0.0003482782,0.00010767492,0.00020869327,0.00004543525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065510365,0.000069391084,0.00017207477,0.00031902216,0.000036283836,0.000038924933,0.0004076132,0.0000356254,0.000001490386],"category_scores_gemma":[0.000104133345,0.00007086587,0.000047103644,0.00025789673,0.000016819164,0.00054994505,0.000089772395,0.00014988102,4.8018103e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042894454,0.00027082255,0.0036253806,0.0004397517,0.0006599792,0.00014948047,0.009735913,0.25105867,0.24653104,0.06274112,0.00020480028,0.4241541],"study_design_scores_gemma":[0.0006399903,0.000070217284,0.019357173,0.00027160827,0.000002396029,0.00019734609,0.000044614884,0.9587121,0.017789291,0.0012748856,0.0015116297,0.00012873039],"about_ca_topic_score_codex":0.000014510812,"about_ca_topic_score_gemma":8.5568087e-7,"teacher_disagreement_score":0.9192973,"about_ca_system_score_codex":0.00007992076,"about_ca_system_score_gemma":0.00004731994,"threshold_uncertainty_score":0.28898263},"labels":[],"label_agreement":null},{"id":"W4388736371","doi":"10.1016/j.ejor.2023.11.016","title":"Column generation-based prototype learning for optimizing area under the receiver operating characteristic curve","year":2023,"lang":"en","type":"article","venue":"European Journal of Operational Research","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Overfitting; Ranking (information retrieval); Computer science; Maximization; Receiver operating characteristic; Artificial intelligence; Machine learning; Feature selection; Binary classification; Support vector machine; Metric (unit); Pattern recognition (psychology); Mathematics; Mathematical optimization; Artificial neural network","score_opus":0.21545877449864434,"score_gpt":0.3905772167184525,"score_spread":0.17511844221980818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388736371","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0139646055,0.000036555084,0.9740354,0.0102414545,0.00019662632,0.0007900828,0.000009104098,0.00008445701,0.00064171344],"genre_scores_gemma":[0.9004883,0.00004253932,0.09703312,0.00047403996,0.00063495967,0.00012311913,0.000095839736,0.00003753903,0.0010705345],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963243,0.00164311,0.0005350103,0.00026463676,0.00091934716,0.00031356633],"domain_scores_gemma":[0.9962502,0.0009654693,0.00020699823,0.000333215,0.0021535861,0.00009049768],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.010727248,0.00010861552,0.00013589823,0.00031299,0.0011255905,0.0010654862,0.0012075729,0.00002446079,0.000042979773],"category_scores_gemma":[0.0020775336,0.00008009896,0.000068170455,0.000773628,0.000103027545,0.0006841703,0.0001761543,0.0006210825,0.0000836352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023500356,0.00028750164,0.0010750813,0.00009657764,0.00017129064,0.00020863133,0.0027859975,0.36426628,0.3933236,0.079970084,0.100851566,0.056728397],"study_design_scores_gemma":[0.0005484652,0.000666395,0.006561258,0.000095331656,0.000003908813,0.00003797048,0.00016014339,0.96019715,0.0075000417,0.00015513143,0.023910372,0.00016380382],"about_ca_topic_score_codex":0.0000018796848,"about_ca_topic_score_gemma":0.0000010110405,"teacher_disagreement_score":0.8865237,"about_ca_system_score_codex":0.00011794094,"about_ca_system_score_gemma":0.00059238373,"threshold_uncertainty_score":0.9999715},"labels":[],"label_agreement":null},{"id":"W4388874216","doi":"10.1145/3625156.3625169","title":"Handling Data Imbalance In Linear Modelling of Fatality Rate of Auto Collision","year":2023,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Toronto Metropolitan University","funders":"","keywords":"Collision; Computer science; Data modeling; Data mining; Machine learning; Predictive modelling; Artificial intelligence; Computer security; Database","score_opus":0.15393158973517101,"score_gpt":0.338425445121476,"score_spread":0.18449385538630497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388874216","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031816315,0.000018502093,0.9671527,0.00022676458,0.00007636802,0.00014139901,0.00008902659,0.0002630844,0.00021584459],"genre_scores_gemma":[0.728554,0.000113532486,0.27104545,0.00002809663,0.000008043327,0.000005529628,0.00012709382,0.0000051477386,0.000113074624],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987353,0.00006863318,0.00045934514,0.00039211512,0.00018497436,0.00015962038],"domain_scores_gemma":[0.9977954,0.0001589138,0.00018081917,0.0017359264,0.00010243552,0.000026474498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014465458,0.000078010016,0.0002015378,0.0001763508,0.000024467092,0.000019299676,0.001741463,0.000050781055,0.000002490843],"category_scores_gemma":[0.00013172989,0.00007267145,0.000018550047,0.0011551316,0.000043226777,0.00071433577,0.00089620013,0.00008260265,0.000010922765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011947931,0.0007173745,0.027763816,0.00096059864,0.00006251029,0.000035361965,0.0023670888,0.33927998,0.2795106,0.304343,0.014738786,0.030101448],"study_design_scores_gemma":[0.00011625919,0.000012165251,0.0018588782,0.00005534759,9.1276786e-7,2.7570098e-7,0.0000138015685,0.89419687,0.10119705,0.0021429465,0.00033975567,0.000065723325],"about_ca_topic_score_codex":0.00021509676,"about_ca_topic_score_gemma":0.000014285091,"teacher_disagreement_score":0.6967377,"about_ca_system_score_codex":0.00001860077,"about_ca_system_score_gemma":0.00007262058,"threshold_uncertainty_score":0.32361007},"labels":[],"label_agreement":null},{"id":"W4389322561","doi":"10.21203/rs.3.rs-3688727/v1","title":"OSK: Optimal Subsampling Method Based on K-means Clustering for Imbalanced Big Data","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Cluster analysis; Computer science; Categorical variable; Artificial intelligence; Class (philosophy); Big data; Pattern recognition (psychology); Data mining; Machine learning","score_opus":0.4267506895785027,"score_gpt":0.4980191244722518,"score_spread":0.07126843489374907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389322561","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000040738887,0.000032460925,0.9880055,0.003896675,0.00085986085,0.0025643099,0.0025304565,0.0017533534,0.00031665288],"genre_scores_gemma":[0.012898333,0.0000813007,0.9792166,0.00013505758,0.00069175346,0.0018555311,0.004439249,0.00013661748,0.00054556906],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9925967,0.0008376511,0.0006607416,0.0027661864,0.0018558743,0.0012828886],"domain_scores_gemma":[0.98592633,0.0035724924,0.00026524905,0.009068296,0.0009066999,0.0002609161],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.010027109,0.00044424896,0.00057550624,0.0012522052,0.00049333327,0.0011667827,0.010317818,0.00047403478,0.000008074716],"category_scores_gemma":[0.003112125,0.00045256404,0.00017836438,0.0012120078,0.00011960557,0.00039394188,0.011869045,0.0019240347,0.00009245146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000574888,0.0007971134,0.0006906514,0.008700204,0.0002632715,0.00014825544,0.0010365198,0.36748707,0.0055409847,0.019687256,0.13874131,0.45633247],"study_design_scores_gemma":[0.0003704256,0.00018257074,0.0006754538,0.00096527336,0.0000065367476,0.00000157298,0.00004463824,0.97419304,0.0023612473,0.002700147,0.018057097,0.00044202394],"about_ca_topic_score_codex":0.00016302933,"about_ca_topic_score_gemma":0.000061600666,"teacher_disagreement_score":0.60670596,"about_ca_system_score_codex":0.00049162237,"about_ca_system_score_gemma":0.0009909186,"threshold_uncertainty_score":0.9998701},"labels":[],"label_agreement":null},{"id":"W4390586102","doi":"10.1007/s10489-023-05223-x","title":"An augmented AI-based hybrid fraud detection framework for invoicing platforms","year":2024,"lang":"en","type":"article","venue":"Applied Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Prioritization; Process (computing); Set (abstract data type); Feature (linguistics); Identification (biology); Cluster analysis; Computer security; Artificial intelligence; Machine learning; Data mining; Process management","score_opus":0.027068444332485286,"score_gpt":0.32239187101027444,"score_spread":0.29532342667778916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390586102","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011667418,0.00006050214,0.9952233,0.00026552373,0.00047696667,0.0006302363,0.000019122013,0.0019557902,0.00020182003],"genre_scores_gemma":[0.68918663,0.0000108164595,0.30939013,0.0008926172,0.000084210405,0.00036889932,0.000034369397,0.000021779497,0.000010554384],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982443,0.00001131987,0.00036785204,0.000749789,0.00027458358,0.00035219901],"domain_scores_gemma":[0.99839073,0.00032114523,0.00008530495,0.0010107576,0.00009013021,0.0001019546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043958233,0.00021056194,0.00016053737,0.0002473981,0.00018610463,0.0004659324,0.001164809,0.00011988032,0.000019391957],"category_scores_gemma":[0.000069669586,0.0001977435,0.00006458899,0.0006643437,0.00006998594,0.0007435486,0.000083101186,0.0003436976,0.00013324802],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014616107,0.0000369614,0.0000043895116,0.00005476623,0.000009477035,0.0000021121368,0.00014623626,0.00035268732,0.026385311,0.57406515,0.0002829423,0.39864537],"study_design_scores_gemma":[0.000017161012,0.00007045689,0.000008640961,0.00004658046,0.0000034905447,0.0000022986153,0.000019801451,0.3198848,0.49437186,0.1827783,0.002655305,0.00014131436],"about_ca_topic_score_codex":0.00001121267,"about_ca_topic_score_gemma":0.0000043484415,"teacher_disagreement_score":0.6880199,"about_ca_system_score_codex":0.0001495216,"about_ca_system_score_gemma":0.000095930336,"threshold_uncertainty_score":0.8063746},"labels":[],"label_agreement":null},{"id":"W4390598906","doi":"10.2139/ssrn.4684590","title":"Handling the Imbalanced Problem in Agro-Food Data Analysis","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Conestoga College","funders":"","keywords":"Computer science","score_opus":0.02818498612118853,"score_gpt":0.2915145119743127,"score_spread":0.2633295258531242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390598906","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018723616,0.010043555,0.97898686,0.0071531525,0.00042607918,0.0004789864,0.00008913316,0.0003637267,0.00058611756],"genre_scores_gemma":[0.95481074,0.009274544,0.034493286,0.00017124094,0.0003732317,0.00009127016,0.0002721782,0.000044912525,0.00046862123],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9948216,0.00031715306,0.00084105605,0.0012269112,0.00065789995,0.0021353478],"domain_scores_gemma":[0.99529964,0.00011921727,0.0005708604,0.0038052704,0.00013271364,0.00007232781],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006837512,0.00037643468,0.0005302781,0.00084705965,0.00019558215,0.0011662372,0.009666715,0.00025516815,0.0000047669487],"category_scores_gemma":[0.00011360002,0.00027097407,0.00024268475,0.0020238713,0.00006892629,0.00046192572,0.0063641644,0.008902153,0.000029576988],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017023389,0.00013883853,0.0010140811,0.00009932965,0.0035712642,0.000022906373,0.0007922228,0.002206457,0.00034214446,0.9065852,0.0015100876,0.0837004],"study_design_scores_gemma":[0.00016241879,0.00007288231,0.00042895455,0.00014376314,0.00029741062,0.00011319749,0.00013393535,0.09213964,0.00017385317,0.90471274,0.0012459848,0.00037524203],"about_ca_topic_score_codex":0.000114816365,"about_ca_topic_score_gemma":0.0023320199,"teacher_disagreement_score":0.9529384,"about_ca_system_score_codex":0.0014719585,"about_ca_system_score_gemma":0.0049241483,"threshold_uncertainty_score":0.99997425},"labels":[],"label_agreement":null},{"id":"W4390738572","doi":"10.1109/tbdata.2024.3352978","title":"GAT-COBO: Cost-Sensitive Graph Neural Network for Telecom Fraud Detection","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Natural Science Foundation of China","keywords":"Computer science; Graph; Artificial intelligence; Machine learning; Classifier (UML); Theoretical computer science","score_opus":0.08922606455742202,"score_gpt":0.3055968200315244,"score_spread":0.21637075547410237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390738572","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013984472,0.00007453575,0.99083674,0.0010334967,0.0040587783,0.00072403136,0.0016905622,0.0013709664,0.000071025424],"genre_scores_gemma":[0.93236893,0.00015852267,0.06554344,0.0005824468,0.0004305242,0.0003317015,0.00034065603,0.0000419979,0.0002018037],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980821,0.000083485196,0.0002994683,0.00091206364,0.00024485966,0.00037805055],"domain_scores_gemma":[0.99739546,0.00036165555,0.0000631058,0.0019892994,0.00009511315,0.00009535787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039150164,0.00021436614,0.00017531682,0.00026460807,0.00034903933,0.00038562992,0.0013082653,0.00012674142,0.0000064620567],"category_scores_gemma":[0.000014480257,0.00021307981,0.00009437205,0.0010131405,0.000072558876,0.001173625,0.000016261678,0.00037337997,0.00007310741],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002979533,0.0000626462,8.7725334e-7,0.000027846661,0.000051297375,0.000007832376,0.000055504494,0.0013364337,0.0038180992,0.0007271854,0.015238149,0.9786443],"study_design_scores_gemma":[0.00030000083,0.00023207901,0.00014031724,0.000095305455,0.000058983678,0.00006940705,0.000015156913,0.74925333,0.14018454,0.00229992,0.10689627,0.0004546994],"about_ca_topic_score_codex":0.000046164198,"about_ca_topic_score_gemma":0.00021348729,"teacher_disagreement_score":0.97818965,"about_ca_system_score_codex":0.00008280561,"about_ca_system_score_gemma":0.00007886802,"threshold_uncertainty_score":0.86891425},"labels":[],"label_agreement":null},{"id":"W4390880298","doi":"10.1145/3638285","title":"Arabic Sentiment Analysis for ChatGPT Using Machine Learning Classification Algorithms: A Hyperparameter Optimization Technique","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Hyperparameter; Arabic; Computer science; Sentiment analysis; Artificial intelligence; Machine learning; Algorithm; Natural language processing","score_opus":0.015791467211840795,"score_gpt":0.27409165186836254,"score_spread":0.25830018465652177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390880298","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041604,0.00018527145,0.99690825,0.0007390804,0.00004375333,0.00059500907,0.00004895138,0.0008990866,0.00016453394],"genre_scores_gemma":[0.44950816,0.000020994521,0.54944927,0.0002801624,0.000024311263,0.00026753615,0.00030282408,0.00002000047,0.00012673634],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855614,0.00007220641,0.00049371447,0.00036318955,0.00027546237,0.00023929462],"domain_scores_gemma":[0.9990209,0.000093248615,0.00021091591,0.00047746114,0.000116126546,0.00008135384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048650702,0.0002171669,0.00021598497,0.0011299326,0.00044611047,0.0010282424,0.00038201132,0.00013956828,0.000022939292],"category_scores_gemma":[0.000065887085,0.00020746245,0.00012414165,0.0015077898,0.000049317157,0.002705916,0.000019757761,0.00028935962,0.000006712129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017899061,0.000053784715,0.00001778587,0.0003108402,0.0001245259,0.0000015720227,0.0069418265,0.04083479,0.0024682733,0.00027723625,0.000013048943,0.9489384],"study_design_scores_gemma":[0.00016742948,0.000044884175,0.00004076368,0.00014922206,0.00013024743,0.000025412275,0.0009370808,0.98401535,0.011187241,0.000060796054,0.003006093,0.00023547858],"about_ca_topic_score_codex":0.000013286393,"about_ca_topic_score_gemma":0.0000020957225,"teacher_disagreement_score":0.94870293,"about_ca_system_score_codex":0.00014002937,"about_ca_system_score_gemma":0.000064574284,"threshold_uncertainty_score":0.9915365},"labels":[],"label_agreement":null},{"id":"W4390906071","doi":"10.1007/s10994-023-06414-w","title":"Understanding imbalanced data: XAI & interpretable ML framework","year":2024,"lang":"en","type":"article","venue":"Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Class (philosophy); Deep learning; Focus (optics); Key (lock); Outlier; Set (abstract data type); Data mining","score_opus":0.13825777887594604,"score_gpt":0.34134489256745015,"score_spread":0.20308711369150412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390906071","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012048605,0.0007508159,0.98861897,0.0021495542,0.00059775496,0.000116666146,0.000023943203,0.0027396309,0.004882169],"genre_scores_gemma":[0.7488422,0.00011034758,0.24874432,0.00031201108,0.00013204264,0.000015349011,0.00024377866,0.00003440879,0.0015655779],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981203,0.00013696177,0.00027430075,0.00080330746,0.00030338022,0.0003617276],"domain_scores_gemma":[0.9978846,0.00036529676,0.00008102619,0.001566554,0.00002491175,0.000077666446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082355534,0.00019066769,0.00019319839,0.00021231074,0.00023278703,0.000984968,0.0019915842,0.00010400311,0.00010836559],"category_scores_gemma":[0.0004777203,0.00017882432,0.000044515516,0.0007616716,0.00004892865,0.0014871377,0.0012353543,0.00085869286,0.0002820563],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011997179,0.000048312853,0.00474761,0.00018780034,0.00010072462,0.00005380204,0.0021209035,0.00077160954,0.005558932,0.9098765,0.030439511,0.046082254],"study_design_scores_gemma":[0.000062707266,0.000027714656,0.0001446939,0.0002786042,0.000008681578,0.000026989921,0.000028506012,0.6696479,0.00027210845,0.031692836,0.29753992,0.00026939905],"about_ca_topic_score_codex":0.0000364906,"about_ca_topic_score_gemma":0.000014545294,"teacher_disagreement_score":0.8781837,"about_ca_system_score_codex":0.00019607985,"about_ca_system_score_gemma":0.0000627634,"threshold_uncertainty_score":0.9498069},"labels":[],"label_agreement":null},{"id":"W4391123134","doi":"10.1016/j.engappai.2024.107934","title":"An improved generative adversarial network to oversample imbalanced datasets","year":2024,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Key Research and Development Program of China; National University's Basic Research Foundation of China; Fundamental Research Funds for the Central Universities; Ministry of Science and Technology of the People's Republic of China; National Natural Science Foundation of China","keywords":"Discriminator; Computer science; Oversampling; Benchmark (surveying); Residual; Artificial intelligence; Pattern recognition (psychology); Constraint (computer-aided design); Sampling (signal processing); Algorithm; Data mining; Machine learning; Detector; Mathematics","score_opus":0.01907279863279813,"score_gpt":0.29987895030655387,"score_spread":0.2808061516737557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391123134","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014400651,0.0000840592,0.99748766,0.00034153063,0.00031359607,0.0005456599,0.00024788422,0.00079948374,0.000036140813],"genre_scores_gemma":[0.37136224,0.000013208551,0.62760305,0.000075566575,0.0003132257,0.0004064762,0.00019880713,0.000018494131,0.00000896095],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850625,0.000021711008,0.00042878857,0.0005770016,0.00018610833,0.000280126],"domain_scores_gemma":[0.99833065,0.00014266603,0.000060324655,0.0012377708,0.00009570379,0.00013290979],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033350408,0.00016652387,0.00016393916,0.00018865391,0.00008596922,0.00021225896,0.0012728831,0.000068683716,0.000015439682],"category_scores_gemma":[0.00006536821,0.0001817561,0.00004625614,0.0012939796,0.000036701917,0.0005811702,0.00016870705,0.00015735021,0.00008331538],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000065022646,0.00005990107,0.0000026478697,0.00002845027,0.000020743373,0.0000010530077,0.0003037263,0.07187807,0.1356448,0.6466141,0.0016659505,0.14377412],"study_design_scores_gemma":[0.000007564594,0.00006840516,0.00002178016,0.000025664373,0.000005719519,0.0000017729024,0.000017888517,0.7747689,0.19048232,0.0075754435,0.026826931,0.00019762108],"about_ca_topic_score_codex":0.000045725305,"about_ca_topic_score_gemma":0.000007715642,"teacher_disagreement_score":0.7028908,"about_ca_system_score_codex":0.00007223797,"about_ca_system_score_gemma":0.00008031874,"threshold_uncertainty_score":0.7411799},"labels":[],"label_agreement":null},{"id":"W4391127911","doi":"10.1007/s10994-023-06497-5","title":"Empirical analysis of performance assessment for imbalanced classification","year":2024,"lang":"en","type":"article","venue":"Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Machine learning; Computer science","score_opus":0.0385424843247923,"score_gpt":0.3639158091002024,"score_spread":0.3253733247754101,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391127911","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011922346,0.00009733842,0.9847929,0.001092578,0.00009992925,0.00016567751,0.000017173643,0.00057984225,0.0012321967],"genre_scores_gemma":[0.8673596,0.00003926843,0.13195364,0.000056456545,0.000022567843,0.00008065172,0.00018188504,0.000009805745,0.0002961593],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987916,0.00007597259,0.0003221052,0.00040273066,0.00023450129,0.00017308648],"domain_scores_gemma":[0.99905354,0.00023412077,0.00012558923,0.00045416437,0.00009603596,0.00003652575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006608437,0.00010982012,0.00022526411,0.000476814,0.00009858361,0.0001301749,0.0005084097,0.000054643853,0.000017745631],"category_scores_gemma":[0.00007636415,0.00009833213,0.00012772673,0.001575593,0.000030184667,0.00037982367,0.00009610483,0.00019652191,0.000005518411],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002011132,0.00014203586,0.36502075,0.00036865342,0.0007687629,0.0000024307085,0.00097072095,0.0071099363,0.046565462,0.1615127,0.0015208917,0.41599753],"study_design_scores_gemma":[0.000061674225,0.00007099031,0.12883644,0.00001801263,0.00007347651,8.2698557e-7,0.0000069576513,0.8422994,0.0016335867,0.0001761679,0.026729718,0.00009273946],"about_ca_topic_score_codex":0.000005158606,"about_ca_topic_score_gemma":0.0000024044139,"teacher_disagreement_score":0.8554372,"about_ca_system_score_codex":0.000085259126,"about_ca_system_score_gemma":0.00006897278,"threshold_uncertainty_score":0.4009868},"labels":[],"label_agreement":null},{"id":"W4391249640","doi":"10.1109/la-cci58595.2023.10409456","title":"Automatic classification of categories for Great Hobbies Inc. based on Vendor Information","year":2023,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health PEI; University of Prince Edward Island","funders":"","keywords":"Vendor; Computer science; Artificial intelligence; Information retrieval; Business","score_opus":0.03292497885457999,"score_gpt":0.28186931243349733,"score_spread":0.24894433357891735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391249640","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036821773,0.000001529983,0.9904197,0.0018996025,0.00013019539,0.00050713384,0.0000549748,0.0014834428,0.001821251],"genre_scores_gemma":[0.897554,0.0000050898866,0.101119295,0.00028278536,0.00001367082,0.0003996932,0.00050221,0.000007052809,0.000116208],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990876,0.000028916009,0.00033716625,0.00015142176,0.00024708043,0.00014782939],"domain_scores_gemma":[0.9986619,0.0002524228,0.00020869738,0.0006461625,0.00020233313,0.000028512999],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034945188,0.00009406138,0.00012418295,0.00037756012,0.000082397484,0.000090922294,0.00052770297,0.000055637953,0.000012919044],"category_scores_gemma":[0.00022017586,0.00008191597,0.000035402805,0.0006521613,0.000045628905,0.0011101684,0.00005375724,0.00004096762,0.000113960705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001609392,0.000050147224,0.0004440357,0.00026489366,0.000009909593,2.3604977e-7,0.00054770394,0.00015757502,0.004148639,0.72724247,0.043508753,0.22360957],"study_design_scores_gemma":[0.00022356784,0.00011380732,0.02051145,0.00001856712,0.0000031793998,3.8156963e-7,0.000049650822,0.92301106,0.041922387,0.005243834,0.008798273,0.0001038528],"about_ca_topic_score_codex":0.00001335225,"about_ca_topic_score_gemma":0.0000027264514,"teacher_disagreement_score":0.92285347,"about_ca_system_score_codex":0.000055213655,"about_ca_system_score_gemma":0.000082515944,"threshold_uncertainty_score":0.33404362},"labels":[],"label_agreement":null},{"id":"W4391540853","doi":"10.1007/s43681-023-00415-0","title":"Evaluating trustworthiness of decision tree learning algorithms based on equivalence checking","year":2024,"lang":"en","type":"article","venue":"AI and Ethics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"New York Institute of Technology; Bishop's University; Université du Québec à Montréal; Université de Sherbrooke; Université du Québec en Outaouais","funders":"","keywords":"Decision tree; Trustworthiness; Equivalence (formal languages); Computer science; ID3 algorithm; Decision tree learning; Algorithm; Incremental decision tree; Theoretical computer science; Machine learning; Artificial intelligence; Mathematics; Discrete mathematics; Computer security","score_opus":0.1207564725191268,"score_gpt":0.43073131984773705,"score_spread":0.30997484732861025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391540853","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033611844,0.00019783483,0.9932258,0.0022001371,0.00020085256,0.00007477262,0.0000021847925,0.00029193723,0.00044528925],"genre_scores_gemma":[0.8130567,0.00009354475,0.18624349,0.0004994174,0.000029486459,0.000009418494,0.0000051635757,0.000008742133,0.000054007945],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865025,0.0001299294,0.00022265948,0.0003525676,0.0005056791,0.00013893537],"domain_scores_gemma":[0.99796987,0.001421483,0.00006892784,0.00035984535,0.00014359542,0.00003625996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025957394,0.000095758856,0.00011645652,0.00013281846,0.00014050194,0.00016829425,0.0003719705,0.00013332738,0.0000056561144],"category_scores_gemma":[0.0011218813,0.0000830646,0.00003174833,0.0004176126,0.000065423046,0.00034867154,0.00014064423,0.00076485507,0.0000052219634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005208812,0.000012683778,0.00017133821,0.00011450772,0.0000033023837,0.000006392847,0.0010036347,0.0013338475,0.0021410726,0.03174688,0.00008075018,0.9633804],"study_design_scores_gemma":[0.00008327306,0.00013246713,0.00080554036,0.0006017534,0.000004711936,0.0000037199961,0.000016226832,0.98204017,0.0073344884,0.008116451,0.00076351763,0.00009768409],"about_ca_topic_score_codex":0.000010408902,"about_ca_topic_score_gemma":0.000001803372,"teacher_disagreement_score":0.98070633,"about_ca_system_score_codex":0.000024060144,"about_ca_system_score_gemma":0.00014966456,"threshold_uncertainty_score":0.33872762},"labels":[],"label_agreement":null},{"id":"W4391978582","doi":"10.22214/ijraset.2024.58477","title":"Credit Card Fraud Detection using Machine Learning (Logistic Regression)","year":2024,"lang":"en","type":"article","venue":"International Journal for Research in Applied Science and Engineering Technology","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Logistic regression; Credit card fraud; Credit card; Computer science; Artificial intelligence; Machine learning; Statistics; Mathematics; World Wide Web; Payment","score_opus":0.09986082079832441,"score_gpt":0.41776989105398776,"score_spread":0.31790907025566334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391978582","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018613907,0.0003602573,0.9770629,0.0021930353,0.0010750745,0.00017706252,0.0000039742304,0.00040652967,0.00010726706],"genre_scores_gemma":[0.9317719,0.00016001347,0.06786603,0.000010429938,0.00011404287,0.000051552088,0.0000013098193,0.000009215476,0.00001552424],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998228,0.000014556187,0.00022182743,0.0003751088,0.0007650419,0.00039547833],"domain_scores_gemma":[0.999143,0.00017751128,0.000038083203,0.00018821818,0.00037968025,0.00007348971],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031195402,0.000091078844,0.00009869013,0.0030689337,0.00027818276,0.00064263446,0.0014501265,0.000094670795,0.0000013392314],"category_scores_gemma":[0.000872446,0.00007966108,0.000019160372,0.0018127587,0.00028092376,0.00049314613,0.0004760184,0.00095452636,0.0000036801953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001351665,0.000017425902,0.00012969055,0.0000305521,0.000014877516,0.00007930254,0.00009755547,0.0019447095,0.52489483,0.2600992,0.00006939749,0.21260892],"study_design_scores_gemma":[0.000110060224,0.00005256525,0.00006215417,0.00012248567,9.4706974e-7,0.000345746,0.000034049957,0.91104126,0.04104071,0.027771704,0.0193252,0.00009311595],"about_ca_topic_score_codex":0.000013063742,"about_ca_topic_score_gemma":0.0000032178195,"teacher_disagreement_score":0.913158,"about_ca_system_score_codex":0.0005307849,"about_ca_system_score_gemma":0.00020231341,"threshold_uncertainty_score":0.6196939},"labels":[],"label_agreement":null},{"id":"W4391987539","doi":"10.48550/arxiv.2402.11742","title":"Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; McKnight Foundation; Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Alfred P. Sloan Foundation; National Science Foundation","keywords":"Class (philosophy); Spectral line; Mathematics; Artificial intelligence; Computer science; Physics","score_opus":0.0663146756179159,"score_gpt":0.21139657268802883,"score_spread":0.14508189707011293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391987539","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03745685,0.00046598006,0.94486314,0.0011748649,0.0010671671,0.0009293305,0.0006629191,0.0037158497,0.009663913],"genre_scores_gemma":[0.9671031,0.0006691242,0.028882386,0.000222154,0.00027731908,0.000009501743,0.00057447725,0.0000795159,0.0021824054],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945903,0.00016796333,0.00049206876,0.0034675715,0.00033124763,0.00095088873],"domain_scores_gemma":[0.9923684,0.00016336922,0.0004779695,0.0064933365,0.00022075017,0.00027617524],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0004850561,0.0008140522,0.0008117735,0.00045001722,0.00023222074,0.0007426463,0.0077969963,0.00045102555,0.000024499597],"category_scores_gemma":[0.000053905675,0.00083206774,0.00018085986,0.0013254348,0.00041559478,0.0011808041,0.0072114477,0.0019170138,0.00020823342],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013104221,0.00021495754,0.0068294997,0.00066834025,0.0003979201,0.0013886249,0.00018308764,0.012981979,0.0007514934,0.96484494,0.01095158,0.00065653963],"study_design_scores_gemma":[0.0007980674,0.00014784941,0.005374326,0.0007763985,0.00018439685,0.000058388305,0.00008037007,0.8231796,0.0032741264,0.16093065,0.0033650787,0.0018307397],"about_ca_topic_score_codex":0.0002030161,"about_ca_topic_score_gemma":0.00018643527,"teacher_disagreement_score":0.92964625,"about_ca_system_score_codex":0.00059525226,"about_ca_system_score_gemma":0.0006980488,"threshold_uncertainty_score":0.999413},"labels":[],"label_agreement":null},{"id":"W4392100598","doi":"10.51594/farj.v6i2.821","title":"DEVELOPING A MEASUREMENT INSTRUMENT FOR TECHNICAL AND ANALYTICAL SKILLS IN AUDITING FOR ENHANCED FRAUD DETECTION","year":2024,"lang":"en","type":"article","venue":"Finance & Accounting Research Journal","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nipissing University","funders":"","keywords":"Audit; Accounting; Business; Computer science","score_opus":0.09504806700650219,"score_gpt":0.39322240759463034,"score_spread":0.29817434058812814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392100598","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025004746,0.00031516628,0.97008514,0.0035194291,0.00021606684,0.000668559,0.000005454123,0.00012916229,0.0000562624],"genre_scores_gemma":[0.7715413,0.00020015457,0.22761025,0.000059627524,0.00018521854,0.00036660442,0.0000015667916,0.000015048737,0.000020235617],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972619,0.00008784621,0.0005452042,0.000546534,0.00085930125,0.00069923006],"domain_scores_gemma":[0.9981473,0.00058559934,0.00012351139,0.00026505115,0.00081901625,0.000059511356],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0094260955,0.00013969616,0.00020127374,0.0006787898,0.00049357093,0.0011537633,0.0006559761,0.00011401822,0.0000013808437],"category_scores_gemma":[0.0033546488,0.00013082975,0.000065103784,0.0009781641,0.00008748751,0.0013151187,0.00026104634,0.0007651449,0.0000033733734],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003174622,0.00005724145,0.0002410664,0.00021061715,0.000015777387,0.0000110701185,0.00018973507,0.000018139763,0.057214566,0.05999201,0.0013492107,0.8806688],"study_design_scores_gemma":[0.0018105775,0.00076624524,0.03326512,0.0058543803,0.000015338517,0.0003643532,0.00016147849,0.34864935,0.33019367,0.1533793,0.12461419,0.00092597125],"about_ca_topic_score_codex":0.000006102176,"about_ca_topic_score_gemma":0.000025224283,"teacher_disagreement_score":0.87974286,"about_ca_system_score_codex":0.0011119618,"about_ca_system_score_gemma":0.0006088645,"threshold_uncertainty_score":0.9998831},"labels":[],"label_agreement":null},{"id":"W4392174247","doi":"10.1007/978-981-97-0523-8_166","title":"Addressing Credit Fraud Threat: Detected Through Supervised Machine Learning Model","year":2024,"lang":"en","type":"book-chapter","venue":"Applied economics and policy studies","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Machine learning; Computer science; Artificial intelligence; Business","score_opus":0.10920659951861404,"score_gpt":0.31604332168910093,"score_spread":0.20683672217048688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392174247","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000097089105,0.007155296,0.051880118,0.0044663926,0.00030787344,0.0038202559,0.0005289839,0.0017949484,0.92994905],"genre_scores_gemma":[0.050367042,0.18179917,0.28475016,0.0070435167,0.0044841757,0.008051534,0.00075037515,0.0009581884,0.46179584],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982162,0.000006539206,0.0004938745,0.0008612483,0.00009023029,0.00033188492],"domain_scores_gemma":[0.99879164,0.00012908717,0.00026893005,0.00068290177,0.000057900732,0.00006952489],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015944394,0.0005023752,0.0006360281,0.00025783776,0.00033286,0.00030711511,0.00060185423,0.00026913735,0.0000060651682],"category_scores_gemma":[0.000018172545,0.00048595044,0.000094339295,0.000056376182,0.0002074673,0.000253209,0.0011631867,0.00053956744,0.000069032336],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000059254426,0.0000037501084,0.0000010099209,0.00009875136,0.00019866553,0.0000012460237,0.0010196011,0.00028233003,0.000032313907,0.97961897,0.00158945,0.017148014],"study_design_scores_gemma":[0.00024053059,0.000032294374,0.000004869668,0.000101133795,0.00004732625,0.0000074175236,0.000033790693,0.074342564,0.00036661868,0.7642483,0.1599868,0.00058832526],"about_ca_topic_score_codex":0.00003983416,"about_ca_topic_score_gemma":0.00004336238,"teacher_disagreement_score":0.4681532,"about_ca_system_score_codex":0.00018016029,"about_ca_system_score_gemma":0.00011357807,"threshold_uncertainty_score":0.9997592},"labels":[],"label_agreement":null},{"id":"W4392387002","doi":"10.18280/ria.380113","title":"Proposed Convolutional Neural Network Model for Finger Vein Image Classification","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Artificial intelligence; Computer science; Image (mathematics); Pattern recognition (psychology)","score_opus":0.07373430512394175,"score_gpt":0.31465812390580683,"score_spread":0.24092381878186508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392387002","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002936144,0.00029354825,0.9918397,0.0043358095,0.00058089796,0.0006656161,0.000038579074,0.0009250433,0.0010271788],"genre_scores_gemma":[0.70735514,0.000049350172,0.2877921,0.00027242218,0.00026916928,0.00027461047,0.00010782529,0.000031055028,0.0038483306],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980181,0.000049506896,0.00051714573,0.0007574285,0.00021796886,0.00043985507],"domain_scores_gemma":[0.99845016,0.00026130854,0.00010774436,0.0008582782,0.00023569918,0.00008679804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006541642,0.00019323731,0.00017338876,0.00013227828,0.00023820791,0.00044994577,0.0009836719,0.00010839229,0.00003316535],"category_scores_gemma":[0.00013079323,0.0001916021,0.00013036068,0.0006589287,0.00012922182,0.0009056573,0.00014284145,0.00021410744,0.00030466382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013024196,0.00008317988,0.000011959899,0.00013021173,0.000014802212,0.000004322745,0.00051216024,0.058789704,0.04336456,0.80901676,0.031653732,0.056405574],"study_design_scores_gemma":[0.000019261683,0.00004570264,0.000020415902,0.000069009555,0.0000070069286,0.000011420331,0.00002385867,0.9270458,0.027962267,0.032892294,0.011688806,0.00021410968],"about_ca_topic_score_codex":0.0000028944453,"about_ca_topic_score_gemma":0.0000021510125,"teacher_disagreement_score":0.86825615,"about_ca_system_score_codex":0.00012783575,"about_ca_system_score_gemma":0.00016126697,"threshold_uncertainty_score":0.7813307},"labels":[],"label_agreement":null},{"id":"W4392401953","doi":"10.1007/s10462-024-10724-3","title":"Resampling strategies for imbalanced regression: a survey and empirical analysis","year":2024,"lang":"en","type":"article","venue":"Artificial Intelligence Review","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Fundação de Amparo à Ciência e Tecnologia do Estado de Pernambuco; Conselho Nacional de Desenvolvimento Científico e Tecnológico; École de technologie supérieure","keywords":"Resampling; Computer science; Regression; Regression analysis; Statistics; Machine learning; Artificial intelligence; Econometrics; Mathematics","score_opus":0.2207092403690384,"score_gpt":0.4567738095203853,"score_spread":0.2360645691513469,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392401953","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013965185,0.045531474,0.9506298,0.002584207,0.000146265,0.00044814014,0.000035803485,0.00038756194,0.000097151256],"genre_scores_gemma":[0.6116623,0.1294052,0.25538516,0.0022261622,0.00020856944,0.0006893437,0.00026264114,0.000045715722,0.0001148997],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803674,0.00017713419,0.0006100533,0.0006927018,0.00021610533,0.00026726598],"domain_scores_gemma":[0.9981327,0.00076457334,0.00010594684,0.00071859616,0.00018903987,0.00008916243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018733485,0.0001806226,0.0004238994,0.00020204294,0.00012879058,0.00060738804,0.00064651633,0.00006890229,0.000023724117],"category_scores_gemma":[0.00046470723,0.0001390574,0.00015691845,0.0022246004,0.00008936986,0.0006572227,0.00014653958,0.00014634406,0.00003937116],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006178026,0.000027675995,0.0002897538,0.0010379379,0.0001048733,0.0000056839112,0.00017033842,0.0000137259285,0.0002938242,0.36362383,0.0030310433,0.6313951],"study_design_scores_gemma":[0.000026642298,0.00025403057,0.002922574,0.0062803132,0.00051156204,0.000032798984,0.00016339008,0.4896026,0.009760795,0.39761835,0.09158839,0.0012385525],"about_ca_topic_score_codex":0.000029250648,"about_ca_topic_score_gemma":0.00007204912,"teacher_disagreement_score":0.69524455,"about_ca_system_score_codex":0.000037155565,"about_ca_system_score_gemma":0.00016239856,"threshold_uncertainty_score":0.5857057},"labels":[],"label_agreement":null},{"id":"W4393023621","doi":"10.48550/arxiv.2403.11032","title":"FH-TabNet: Multi-Class Familial Hypercholesterolemia Detection via a Multi-Stage Tabular Deep Learning","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Class (philosophy); Familial hypercholesterolemia; Artificial intelligence; Stage (stratigraphy); Computer science; Deep learning; Medicine; Internal medicine; Biology; Cholesterol","score_opus":0.0866161824988796,"score_gpt":0.22742070545231172,"score_spread":0.1408045229534321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393023621","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0929791,0.00011611339,0.9029989,0.00005043969,0.00088655984,0.00056283816,0.000039538183,0.0021473188,0.00021919202],"genre_scores_gemma":[0.97298354,0.000206155,0.02322549,0.00009750062,0.00010225956,0.000013142506,0.00007759985,0.0000700851,0.0032242488],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961714,0.00036943206,0.0004262152,0.0022245406,0.00020902885,0.00059934676],"domain_scores_gemma":[0.997023,0.00008899822,0.00040177954,0.0020057207,0.00024670587,0.00023380951],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0004923682,0.0006015683,0.0004812671,0.0006834181,0.00030542267,0.00039558476,0.0025970084,0.0007203538,0.000017133601],"category_scores_gemma":[0.00009052775,0.0007291256,0.00029645255,0.0009386616,0.00017972277,0.00063444907,0.004159487,0.0023924438,0.00047786982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032228985,0.0018934616,0.011106732,0.0025926116,0.0012087554,0.0042256303,0.005898465,0.5746633,0.17055412,0.05590807,0.00036961565,0.17125696],"study_design_scores_gemma":[0.0005885049,0.00006740632,0.0016040878,0.00012820489,0.00007195494,0.000009415479,0.00010311541,0.98408896,0.007121071,0.0017035148,0.0037784541,0.00073531165],"about_ca_topic_score_codex":0.00034064797,"about_ca_topic_score_gemma":0.0003600246,"teacher_disagreement_score":0.8800044,"about_ca_system_score_codex":0.000762692,"about_ca_system_score_gemma":0.0001576179,"threshold_uncertainty_score":0.9999091},"labels":[],"label_agreement":null},{"id":"W4393857732","doi":"10.1016/j.rpth.2024.102403","title":"Machine learning analysis of bleeding status in venous thromboembolism patients","year":2024,"lang":"en","type":"article","venue":"Research and Practice in Thrombosis and Haemostasis","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Ottawa Hospital","funders":"Alliance de recherche numérique du Canada","keywords":"Venous thromboembolism; Medicine; Intensive care medicine; Internal medicine; Thrombosis","score_opus":0.1276848708195365,"score_gpt":0.43255716905114255,"score_spread":0.30487229823160605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393857732","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95418024,0.016701605,0.01130252,0.0077124634,0.00016159547,0.0009881847,0.0002095987,0.00025758767,0.0084861955],"genre_scores_gemma":[0.9627809,0.030004127,0.0070909965,0.00003608328,0.000007747138,0.000023945011,0.000037230246,0.000009327527,0.000009654843],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9977096,0.00052118755,0.00034637377,0.0004900018,0.000514658,0.00041818453],"domain_scores_gemma":[0.9965016,0.0028234844,0.00008156191,0.00029532998,0.00019878395,0.00009919017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029944838,0.000112731024,0.00036675273,0.0015287511,0.00012167489,0.00038874373,0.00027235202,0.0000794293,0.00001577169],"category_scores_gemma":[0.0014757599,0.000104613355,0.000030446176,0.0036774345,0.00014662574,0.0014746697,0.0003750743,0.0005834591,0.0000025388006],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000104242165,0.0012760395,0.17153491,0.0003916413,0.0008446229,0.000043961398,0.01800221,0.00006622534,0.0019850498,0.079193056,0.00048644285,0.7260716],"study_design_scores_gemma":[0.0010170089,0.0013000871,0.8076552,0.00054163014,0.00025938742,0.000008063768,0.0026113957,0.14386156,0.0026126087,0.008475367,0.031100795,0.0005568855],"about_ca_topic_score_codex":0.0020817162,"about_ca_topic_score_gemma":0.0001856534,"teacher_disagreement_score":0.7255147,"about_ca_system_score_codex":0.00009239438,"about_ca_system_score_gemma":0.00008384571,"threshold_uncertainty_score":0.42660087},"labels":[],"label_agreement":null},{"id":"W4394213566","doi":"10.6084/m9.figshare.21666869","title":"Getting the ROC into Sync","year":2023,"lang":"en","type":"dataset","venue":"Figshare","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"sync; Computer science; Telecommunications","score_opus":0.044908805711612904,"score_gpt":0.2995676492698444,"score_spread":0.25465884355823154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394213566","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.3525064e-9,0.00009031075,0.0003403618,0.00085181504,0.00021645485,0.0002820195,0.99726063,0.0008888508,0.000069577705],"genre_scores_gemma":[3.8794835e-7,0.00001693107,0.0013278206,0.0009362342,0.00023865925,0.0007101932,0.9964948,0.000019557128,0.00025540058],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983789,0.00007894164,0.00027171857,0.00056030013,0.00041817172,0.0002920105],"domain_scores_gemma":[0.9965616,0.00039324124,0.00030001858,0.0025655902,0.00012331171,0.000056251563],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00015771066,0.00023312573,0.00018293985,0.0001330427,0.00024207112,0.00048981304,0.0053599863,0.00023020746,0.0046111266],"category_scores_gemma":[0.00202927,0.00017491863,0.0000779074,0.00059073913,0.000009523333,0.00031663143,0.0020688956,0.00054795446,0.057002135],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.514659e-7,0.000004875456,3.3346232e-8,0.00011314151,0.000007404428,0.000014095057,0.000013975954,5.1778403e-7,0.000002197206,0.0000311237,0.997162,0.0026505191],"study_design_scores_gemma":[0.000021581642,0.000011938976,0.000031237363,0.00081903726,0.0000032097973,0.000006109595,0.0000034108552,0.00032533886,0.00007993821,0.00031962412,0.99815166,0.00022691466],"about_ca_topic_score_codex":0.00004880246,"about_ca_topic_score_gemma":0.000038999104,"teacher_disagreement_score":0.05239101,"about_ca_system_score_codex":0.00007982188,"about_ca_system_score_gemma":0.00014704054,"threshold_uncertainty_score":0.9962988},"labels":[],"label_agreement":null},{"id":"W4394853018","doi":"10.1080/2573234x.2024.2342773","title":"Predicting fraud in MD&A sections using deep learning","year":2024,"lang":"en","type":"article","venue":"Journal of Business Analytics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Deep learning; Computer science; Artificial intelligence; Convolutional neural network; Transformer; F1 score; Machine learning; Artificial neural network; Engineering","score_opus":0.04788753852339553,"score_gpt":0.3088563643410194,"score_spread":0.2609688258176238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394853018","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033331756,0.00063168677,0.9647752,0.0004280501,0.00049868773,0.000034184053,9.964962e-7,0.00010542974,0.00019400424],"genre_scores_gemma":[0.8709901,0.00038281985,0.12821557,0.000042133084,0.00027090678,8.836591e-7,0.00000179783,0.000014963179,0.000080856385],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987495,0.000055130167,0.0005396617,0.00016386098,0.00031777166,0.00017405263],"domain_scores_gemma":[0.99887645,0.00012155227,0.00028510112,0.00022860506,0.00043669934,0.000051576368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068955927,0.00010045258,0.00019466048,0.000747348,0.00008874601,0.00038258298,0.00046661583,0.000068532456,0.000008398485],"category_scores_gemma":[0.00036190214,0.000091403934,0.00006730853,0.0022572726,0.000028608827,0.0011999715,0.000110125606,0.00050449144,0.000005593388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026287556,0.00038840555,0.09509625,0.00057207345,0.00031656757,0.0007742376,0.003649982,0.6908972,0.039757743,0.024438063,0.0021005422,0.1419826],"study_design_scores_gemma":[0.000097561584,0.000019637815,0.008923451,0.0003813226,0.000029362565,0.00035995911,0.000069880545,0.97712207,0.00048663642,0.0014348129,0.010948333,0.00012695782],"about_ca_topic_score_codex":0.000028619668,"about_ca_topic_score_gemma":0.000024091762,"teacher_disagreement_score":0.8376583,"about_ca_system_score_codex":0.0002061732,"about_ca_system_score_gemma":0.00019317139,"threshold_uncertainty_score":0.37273443},"labels":[],"label_agreement":null},{"id":"W4394866268","doi":"10.1016/j.caeai.2024.100222","title":"Enhancing algorithmic assessment in education: Equi-fused-data-based SMOTE for balanced learning","year":2024,"lang":"en","type":"article","venue":"Computers and Education Artificial Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université TÉLUQ","funders":"American University in Cairo; Foundation for Psychocultural Research","keywords":"Computer science; Robustness (evolution); Machine learning; Artificial intelligence; Data mining; F1 score","score_opus":0.060133128276284954,"score_gpt":0.38031635467911146,"score_spread":0.3201832264028265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394866268","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001819805,0.00060163374,0.98944366,0.0042360364,0.0028851833,0.00052445155,0.000008669319,0.00036532633,0.00011526247],"genre_scores_gemma":[0.46309564,0.000093596514,0.53521466,0.00067202485,0.00034976855,0.00023451848,0.00021301539,0.000018152663,0.000108638764],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808896,0.00008552235,0.00051984336,0.000834137,0.00018781063,0.0002837344],"domain_scores_gemma":[0.9985382,0.0003693448,0.00011530562,0.0007118011,0.00016497492,0.00010039518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080942037,0.00018308302,0.00018153754,0.000379158,0.00017873557,0.0008027436,0.0009413422,0.00007595912,0.0000096737285],"category_scores_gemma":[0.00010720282,0.00019564251,0.00003811691,0.0006798414,0.00006655262,0.00087971863,0.0002097048,0.00027311823,0.000021395259],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028178952,0.00013638409,0.000056196845,0.000090894784,0.000004544342,5.618103e-7,0.00038413127,0.00026484582,0.0011118144,0.13035563,0.0014819067,0.86611027],"study_design_scores_gemma":[0.00002079612,0.00006815517,0.0002904932,0.00032697304,0.000005808608,0.000004985114,0.00032497058,0.94179636,0.010027282,0.025304189,0.021582631,0.00024735447],"about_ca_topic_score_codex":0.00005767799,"about_ca_topic_score_gemma":0.000021442414,"teacher_disagreement_score":0.94153154,"about_ca_system_score_codex":0.00019875559,"about_ca_system_score_gemma":0.0017074525,"threshold_uncertainty_score":0.79780704},"labels":[],"label_agreement":null},{"id":"W4395018386","doi":"10.1109/icosst60641.2023.10505068","title":"Overcoming Imbalanced Datasets and Feature Complexity in Fraud Transaction Detection Through Down-Sampling and Dimension Reduction","year":2023,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bishop's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Database transaction; Reduction (mathematics); Dimension (graph theory); Dimensionality reduction; Feature (linguistics); Data mining; Sampling (signal processing); Pattern recognition (psychology); Artificial intelligence; Mathematics; Database; Detector","score_opus":0.06048644076122597,"score_gpt":0.31336278785691407,"score_spread":0.2528763470956881,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395018386","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19378768,0.000046556524,0.80364233,0.0011996838,0.00020623708,0.00028597206,0.000036013676,0.00072377187,0.00007176845],"genre_scores_gemma":[0.906718,0.00027488504,0.092676744,0.00007930295,0.000026151965,0.000024579414,0.0001683662,0.000008254515,0.000023680419],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988529,0.00006692048,0.00018957719,0.00052057573,0.0001659359,0.00020410812],"domain_scores_gemma":[0.999398,0.00006081439,0.00007795119,0.00039769878,0.000025880307,0.00003967146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033711136,0.00013146494,0.00014732723,0.00017508704,0.00018836709,0.00013232407,0.00015879063,0.00011000854,0.0000025212307],"category_scores_gemma":[0.00002856202,0.00012832922,0.000014920095,0.00066638255,0.00006445558,0.0015358865,0.00010676,0.00021263659,0.00000505797],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006786137,0.000064026055,0.0011113246,0.0001047473,0.000014481821,0.0000065715503,0.0015741002,0.00012425793,0.8083485,0.012715201,0.0017748015,0.17409417],"study_design_scores_gemma":[0.001482047,0.00016625135,0.30652443,0.00017969216,0.000014846546,0.00019493536,0.00047515187,0.27477753,0.372893,0.036104653,0.006421392,0.0007660585],"about_ca_topic_score_codex":0.00020618769,"about_ca_topic_score_gemma":0.00011631903,"teacher_disagreement_score":0.7129303,"about_ca_system_score_codex":0.000067074216,"about_ca_system_score_gemma":0.000010512624,"threshold_uncertainty_score":0.5233114},"labels":[],"label_agreement":null},{"id":"W4395069916","doi":"10.1109/iatmsi60426.2024.10503258","title":"Leveraging Artificial Intelligence for Enhanced Data Generation in Addressing Imbalance in Binary Classification System","year":2024,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Binary classification; Binary number; Machine learning; Support vector machine; Mathematics","score_opus":0.2661857283743112,"score_gpt":0.3807205949571857,"score_spread":0.11453486658287448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395069916","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052537713,0.00020204646,0.9910463,0.00118763,0.00047708742,0.00058828713,0.00002415747,0.00066307856,0.00055765576],"genre_scores_gemma":[0.8428771,0.00002872348,0.15633817,0.00005236414,0.00012067372,0.00021533479,0.00031970214,0.000013649867,0.00003431511],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976845,0.000101739184,0.00067266054,0.0010229067,0.0002217504,0.00029647406],"domain_scores_gemma":[0.9982945,0.0001693904,0.00009858092,0.0013311142,0.00006952405,0.000036896963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013238085,0.0001567824,0.00017924489,0.0004561249,0.00007775025,0.0005597922,0.0014319238,0.00009750592,0.0000037526545],"category_scores_gemma":[0.00012342438,0.00015852609,0.000024167293,0.0010542391,0.000033274275,0.0020746565,0.00028603416,0.00018238036,0.00002706977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009311375,0.00006334653,0.00006474224,0.00025347824,0.0000044747394,0.000008384151,0.0005825615,0.00049152045,0.31155744,0.473949,0.0011484367,0.2118673],"study_design_scores_gemma":[0.000033892564,0.000015695985,0.00048075436,0.00026724098,0.0000017038219,0.000003743942,0.00022828241,0.88380796,0.11259552,0.002043904,0.00035410252,0.00016721874],"about_ca_topic_score_codex":0.000037056903,"about_ca_topic_score_gemma":0.000076241085,"teacher_disagreement_score":0.8833164,"about_ca_system_score_codex":0.0003573002,"about_ca_system_score_gemma":0.00016448175,"threshold_uncertainty_score":0.64645064},"labels":[],"label_agreement":null},{"id":"W4396494566","doi":"10.18280/ts.410224","title":"Enhancing Financial Fraud Detection Through Chimp-Optimized Long Short-Term Memory Networks","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Term (time); Business; Computer science; Finance","score_opus":0.0170689799068116,"score_gpt":0.25808946308656666,"score_spread":0.24102048317975505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396494566","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007943674,0.0003404091,0.9880467,0.00022571908,0.0008978506,0.00043938548,0.000008012384,0.0014700217,0.00062821247],"genre_scores_gemma":[0.9484504,0.00006341816,0.050200727,0.00034690992,0.0006155196,0.00017309276,0.000036615613,0.00002613063,0.00008722154],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99786925,0.00009613708,0.00050433574,0.00068464543,0.00041078107,0.0004348498],"domain_scores_gemma":[0.99916387,0.000109351284,0.000078062316,0.00050580426,0.000063643645,0.00007924536],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005571625,0.00025698816,0.00023255574,0.00014482562,0.00021807078,0.0004608304,0.00073961826,0.00014106216,0.00013811156],"category_scores_gemma":[0.000020768617,0.0002494283,0.00013083957,0.0005286817,0.000049681137,0.0013244651,0.00018514117,0.00034858496,0.00004180024],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010313435,0.0003015772,0.00022647822,0.0002401402,0.00014591675,0.00022914345,0.0026720816,0.003613133,0.15451017,0.022487171,0.006344508,0.80912656],"study_design_scores_gemma":[0.00051143556,0.0002415865,0.003936943,0.00027263793,0.000044291715,0.000056599198,0.000022263283,0.63072526,0.35868567,0.0020858909,0.0027404071,0.00067700754],"about_ca_topic_score_codex":0.000010050254,"about_ca_topic_score_gemma":0.000023741644,"teacher_disagreement_score":0.9405067,"about_ca_system_score_codex":0.00017135605,"about_ca_system_score_gemma":0.00009929307,"threshold_uncertainty_score":0.99999577},"labels":[],"label_agreement":null},{"id":"W4396982566","doi":"10.2139/ssrn.4830898","title":"Neural Network Characterization and Entropy Regulated Data Balancing Through Principal Component Analysis","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Principal component analysis; Computer science; Artificial neural network; Artificial intelligence; Data mining; Pattern recognition (psychology)","score_opus":0.022549329986122454,"score_gpt":0.27862960222059957,"score_spread":0.2560802722344771,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396982566","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044850882,0.0028014504,0.9478644,0.0027080195,0.0008184601,0.0003344487,0.00010007304,0.0004925902,0.000029677685],"genre_scores_gemma":[0.9641803,0.009653639,0.021563506,0.00021397951,0.0009005079,0.000022958626,0.0031226182,0.000051753414,0.00029071936],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99519134,0.0003071031,0.0008041255,0.0012325819,0.00057263864,0.0018921898],"domain_scores_gemma":[0.9966678,0.000052057556,0.00076504116,0.0022550712,0.00015235093,0.00010770156],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0023637556,0.00041536667,0.0005948551,0.00033157115,0.0002733401,0.0011028008,0.0030871811,0.00026703108,0.000006363054],"category_scores_gemma":[0.000045725636,0.00038693135,0.00015783451,0.0010256658,0.00006748323,0.00079809985,0.005507541,0.0042786375,0.000009506416],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007134689,0.00015839223,0.004505315,0.00019333336,0.0063074064,0.00006532058,0.0007778067,0.0056488914,0.007636965,0.88505125,0.0009664763,0.08861749],"study_design_scores_gemma":[0.0002038749,0.00007072653,0.008006249,0.00013106705,0.0006798812,0.0003185203,0.000024572597,0.784241,0.00014426975,0.20261137,0.0030283195,0.00054010213],"about_ca_topic_score_codex":0.000057096087,"about_ca_topic_score_gemma":0.000102018275,"teacher_disagreement_score":0.9263009,"about_ca_system_score_codex":0.0009563956,"about_ca_system_score_gemma":0.0014381992,"threshold_uncertainty_score":0.99993414},"labels":[],"label_agreement":null},{"id":"W4399356382","doi":"10.1016/j.ins.2024.120835","title":"CPS-3WS: A critical pattern supported three-way sampling method for classifying class-overlapped imbalanced data","year":2024,"lang":"en","type":"article","venue":"Information Sciences","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"National Key Research and Development Program of China; Anhui University; National Natural Science Foundation of China","keywords":"Class (philosophy); Computer science; Sampling (signal processing); Data mining; Artificial intelligence; Pattern recognition (psychology); Computer vision","score_opus":0.16655484710524662,"score_gpt":0.4331206472449304,"score_spread":0.2665658001396838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399356382","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000925364,0.00007392806,0.9887534,0.0063062576,0.0009868772,0.0004923052,0.00040167727,0.0012217171,0.001671325],"genre_scores_gemma":[0.26172236,0.000019746314,0.73588777,0.0016906736,0.00012260559,0.00015623028,0.00036558442,0.000010568553,0.000024479585],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970094,0.00006875796,0.00082681014,0.00070433767,0.0008295805,0.00056111027],"domain_scores_gemma":[0.9967718,0.0013180802,0.00020404039,0.001302993,0.00027371754,0.00012936616],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0034366082,0.00022634515,0.0002462319,0.0004902906,0.0005057394,0.0029711798,0.0034994688,0.00012725567,0.000030458546],"category_scores_gemma":[0.0011329349,0.00019229404,0.00007497304,0.0013521595,0.00025390048,0.015160658,0.0007548372,0.00023059254,0.00014593938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061343794,0.000026267247,0.00028319907,0.00023008551,0.000020377083,0.0000018335697,0.0008296927,0.0000531941,0.0026248135,0.22341497,0.01539527,0.7571142],"study_design_scores_gemma":[0.00013457389,0.00006478913,0.00095844496,0.00010313413,0.000009496224,0.000024902109,0.00014459962,0.87830234,0.0015285828,0.013925243,0.10453866,0.0002652643],"about_ca_topic_score_codex":0.000046448407,"about_ca_topic_score_gemma":0.000024358982,"teacher_disagreement_score":0.8782491,"about_ca_system_score_codex":0.000094736315,"about_ca_system_score_gemma":0.0004140354,"threshold_uncertainty_score":0.9986138},"labels":[],"label_agreement":null},{"id":"W4399390176","doi":"10.1016/j.jbi.2024.104666","title":"Understanding random resampling techniques for class imbalance correction and their consequences on calibration and discrimination of clinical risk prediction models","year":2024,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Medical Research Council; Lotto New Zealand; All-India Institute of Medical Sciences; KU Leuven; Natural Sciences and Engineering Research Council of Canada; Stroke Association; European Commission; Fonds Wetenschappelijk Onderzoek; National Heart Foundation of Australia","keywords":"Undersampling; Resampling; Computer science; Estimator; Artificial intelligence; Calibration; Oversampling; Random forest; Machine learning; Brier score; Statistics; Data mining; Mathematics","score_opus":0.1356301825345485,"score_gpt":0.3526789340283135,"score_spread":0.217048751493765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399390176","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003290815,0.000116101226,0.9947367,0.0007489674,0.00065461075,0.00022950709,0.00005680876,0.00008733958,0.000079186575],"genre_scores_gemma":[0.900941,0.0021705043,0.09666092,0.000073329145,0.00011869494,0.000008934919,0.000016715583,0.000005357698,0.0000045428933],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981642,0.0000865174,0.0012583452,0.00010019986,0.00028606775,0.000104722305],"domain_scores_gemma":[0.9976585,0.0011725342,0.00081202015,0.00012766139,0.00014426422,0.00008501159],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029143356,0.000096407224,0.00026505438,0.0003203817,0.00008896012,0.0001688303,0.00017537519,0.00014298083,3.7627234e-7],"category_scores_gemma":[0.00064557913,0.00006547768,0.00006391681,0.00021559818,0.00029358504,0.001641634,0.000043742642,0.00024937815,4.6739903e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007619318,0.0002925306,0.0007005487,0.0017396027,0.0002955573,0.000004262658,0.011366326,0.0005653345,0.005503535,0.24605432,0.02540832,0.70730776],"study_design_scores_gemma":[0.00037666873,0.00067358714,0.00006762973,0.00068680017,0.00002052384,0.000052385778,0.0006019755,0.94242555,0.0043019042,0.049928717,0.0008018293,0.000062456376],"about_ca_topic_score_codex":0.0000022201618,"about_ca_topic_score_gemma":0.0000010789859,"teacher_disagreement_score":0.9418602,"about_ca_system_score_codex":0.00007951932,"about_ca_system_score_gemma":0.00013425456,"threshold_uncertainty_score":0.26701024},"labels":[],"label_agreement":null},{"id":"W4399433522","doi":"10.1080/00207543.2024.2361434","title":"Supply chain fraud prediction with machine learning and artificial intelligence","year":2024,"lang":"en","type":"article","venue":"International Journal of Production Research","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Roads University","funders":"","keywords":"Artificial intelligence; Supply chain; Computer science; Machine learning; Engineering; Business","score_opus":0.07692584221330417,"score_gpt":0.3965441986824003,"score_spread":0.31961835646909614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399433522","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011082566,0.0008558579,0.9518741,0.034122724,0.0015007813,0.00016307223,0.000009130771,0.0001538655,0.00023791533],"genre_scores_gemma":[0.96973556,0.0008620188,0.028039288,0.0000175729,0.00083955197,0.00001090504,0.000007863759,0.000010050284,0.00047716804],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978646,0.00018390719,0.0003398005,0.00028797833,0.0011757658,0.00014797006],"domain_scores_gemma":[0.99823976,0.0001356184,0.000102945065,0.00014898805,0.0013092193,0.00006348226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026884812,0.000074151445,0.00008349259,0.000875366,0.0001072192,0.0005928575,0.00059500465,0.00003939175,0.000034068613],"category_scores_gemma":[0.0005435214,0.000057911573,0.00002560125,0.00056178134,0.00013979903,0.0012421,0.00015066282,0.0007496552,0.000016738928],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016461013,0.00013126279,0.0022398287,0.000039196682,0.00013478061,0.00014574215,0.0012471149,0.0003994909,0.032771625,0.15895686,0.0033610433,0.8004084],"study_design_scores_gemma":[0.00023856506,0.0021009478,0.0048581865,0.0011907946,0.000020249863,0.005571939,0.0008528688,0.2731344,0.3677867,0.11709366,0.22671236,0.00043930794],"about_ca_topic_score_codex":0.000014961371,"about_ca_topic_score_gemma":0.0000040142336,"teacher_disagreement_score":0.95865303,"about_ca_system_score_codex":0.00014604516,"about_ca_system_score_gemma":0.00016517067,"threshold_uncertainty_score":0.57169384},"labels":[],"label_agreement":null},{"id":"W4399448134","doi":"10.1007/s00500-024-09931-5","title":"Methods for class-imbalanced learning with support vector machines: a review and an empirical evaluation","year":2024,"lang":"en","type":"review","venue":"Soft Computing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor; Toronto Metropolitan University","funders":"","keywords":"Machine learning; Support vector machine; Computer science; Artificial intelligence; Benchmark (surveying); Class (philosophy); Categorization; Empirical research; Data mining; Inefficiency; Mathematics","score_opus":0.12126035373795162,"score_gpt":0.5094392597996527,"score_spread":0.388178906061701,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399448134","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.904455e-8,0.5060087,0.4916602,0.00013446544,0.00012236158,0.0014050935,0.0000091955535,0.0005831011,0.00007678822],"genre_scores_gemma":[0.0000025984439,0.5562093,0.44264144,0.00024054838,0.00014024055,0.0003215396,0.00032695362,0.00005914901,0.000058206515],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.995496,0.001295988,0.0009295386,0.0014364804,0.0003930224,0.0004490035],"domain_scores_gemma":[0.9968696,0.00088990154,0.0007406638,0.0010058025,0.00034456063,0.00014946908],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0054612583,0.0005821347,0.0017389206,0.00026609097,0.0002418015,0.0004452963,0.0011055229,0.00023694405,0.000007906874],"category_scores_gemma":[0.00082123984,0.00042713317,0.0002257842,0.000972139,0.00007112498,0.00041285716,0.0004963332,0.000804664,0.000016984071],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.981096e-7,0.000015550897,0.0000032664932,0.024403203,0.00006181729,0.0000017276319,0.000093375245,0.0000020237815,7.872053e-7,0.0008068548,0.0013509588,0.9732595],"study_design_scores_gemma":[0.0001157707,0.00023493811,0.0000040290793,0.016524622,0.0012693721,0.00013149963,0.0000037298612,0.16528136,0.0000010929543,0.00040719545,0.81551653,0.0005098408],"about_ca_topic_score_codex":0.0000020912075,"about_ca_topic_score_gemma":9.4951565e-7,"teacher_disagreement_score":0.9727497,"about_ca_system_score_codex":0.00022896803,"about_ca_system_score_gemma":0.0007478681,"threshold_uncertainty_score":0.999818},"labels":[],"label_agreement":null},{"id":"W4399474324","doi":"10.55041/ijsrem35598","title":"Analysis of Patient Condition Classification Methods Utilizing Drug Reviews","year":2024,"lang":"en","type":"article","venue":"INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Categorization; Bridging (networking); The Internet; Medicine; Computer science; Psychology; Artificial intelligence; World Wide Web","score_opus":0.09627384327420858,"score_gpt":0.4368319493970003,"score_spread":0.34055810612279175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399474324","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0143350065,0.0028846986,0.9808228,0.0007303461,0.00068599015,0.00022492881,0.0000064121705,0.000030551044,0.0002792483],"genre_scores_gemma":[0.869087,0.0014453789,0.12933868,0.0000061803044,0.000013554436,0.000021921123,0.000010243643,0.0000040455893,0.00007303188],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980922,0.00022649598,0.0006626708,0.00026356676,0.00059601216,0.00015908988],"domain_scores_gemma":[0.9990443,0.0002423393,0.0001299183,0.00027498786,0.00025563166,0.000052819007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007909511,0.00007238307,0.00020229627,0.003913318,0.000048259444,0.00035571973,0.00046815502,0.000020756575,0.0000070459546],"category_scores_gemma":[0.000091056994,0.00006135567,0.000103891,0.00301899,0.0000872121,0.0006119552,0.00016310302,0.00023020947,0.0000024536284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011393671,0.00013172819,0.00012428123,0.0009338943,0.00040353186,0.000045541477,0.0010556815,0.0025908914,0.030925492,0.41019556,0.00409392,0.54948807],"study_design_scores_gemma":[0.00014265018,0.00006694801,0.00761219,0.0021934144,0.000078096906,0.00002098707,0.0002734047,0.8681825,0.006147699,0.0037752576,0.11136129,0.00014559302],"about_ca_topic_score_codex":0.0000026696166,"about_ca_topic_score_gemma":8.05407e-7,"teacher_disagreement_score":0.8655916,"about_ca_system_score_codex":0.00011504686,"about_ca_system_score_gemma":0.000024859088,"threshold_uncertainty_score":0.3491813},"labels":[],"label_agreement":null},{"id":"W4399785296","doi":"10.1016/j.ipm.2024.103809","title":"Are LLMs good at structured outputs? A benchmark for evaluating structured output capabilities in LLMs","year":2024,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China","keywords":"Benchmark (surveying); Geography","score_opus":0.026997922937062133,"score_gpt":0.30205991012994654,"score_spread":0.2750619871928844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399785296","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010268375,0.00036532874,0.9797121,0.0012762366,0.0007277673,0.0019363053,0.00008951528,0.0013037121,0.004320611],"genre_scores_gemma":[0.8460637,0.000011039968,0.15166526,0.0006331027,0.00004166251,0.0006831901,0.00022387561,0.000017905497,0.0006602959],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99765605,0.00004570781,0.0008284398,0.00043993734,0.0006283591,0.0004015173],"domain_scores_gemma":[0.9985792,0.000066928325,0.00046488387,0.0006155752,0.00021496281,0.000058458783],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008874912,0.00026434683,0.00022853167,0.0006159737,0.000251345,0.0013245697,0.00086845807,0.00010260916,0.000016215618],"category_scores_gemma":[0.00012868104,0.0002470134,0.00006971702,0.00074069534,0.000054738066,0.0044475673,0.0004117508,0.0001638491,0.000026309852],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002415075,0.0000210811,0.0003846017,0.003164658,0.000038263242,0.0000037947589,0.007656362,0.0012201043,0.00011943052,0.084719226,0.004162819,0.8984855],"study_design_scores_gemma":[0.0012242295,0.000110083245,0.035837036,0.0012154515,0.000051481096,0.00001859442,0.0023374727,0.78424096,0.0039760214,0.069890715,0.100152105,0.0009458198],"about_ca_topic_score_codex":0.000008096347,"about_ca_topic_score_gemma":0.00001868702,"teacher_disagreement_score":0.8975397,"about_ca_system_score_codex":0.0005676851,"about_ca_system_score_gemma":0.00008577896,"threshold_uncertainty_score":0.9999982},"labels":[],"label_agreement":null},{"id":"W4399922780","doi":"10.1002/adts.202400234","title":"Distribution Enhancement for Imbalanced Data with Generative Adversarial Network","year":2024,"lang":"en","type":"article","venue":"Advanced Theory and Simulations","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Adversarial system; Generative grammar; Generative adversarial network; Artificial intelligence; Computer science; Distribution (mathematics); Pattern recognition (psychology); Machine learning; Mathematics; Deep learning","score_opus":0.02011919984567702,"score_gpt":0.3072258978439821,"score_spread":0.28710669799830507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399922780","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008604187,0.000316026,0.9965751,0.00040928426,0.00024359365,0.00050468754,0.0006520601,0.0003189107,0.000119891476],"genre_scores_gemma":[0.78968334,0.000047875707,0.20738865,0.0001215455,0.0001427329,0.000098014614,0.0023066986,0.000009689322,0.00020142381],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892604,0.00007844091,0.00017474563,0.00051730825,0.00010595087,0.00019750115],"domain_scores_gemma":[0.9983962,0.0006820662,0.000054602086,0.00074491446,0.000077248755,0.000044970184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039602493,0.00012344228,0.00011490204,0.000029598157,0.00028909527,0.00015756898,0.0004090173,0.000039362407,0.000007693037],"category_scores_gemma":[0.00009456851,0.00010161769,0.000016981556,0.00028252692,0.000070031645,0.001282401,0.0001619017,0.000079671685,0.0000031384154],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006916584,0.000016851083,0.000015402355,0.0000128845895,0.000029489458,8.9676803e-7,0.00010112786,0.008367676,0.0012134602,0.95658123,0.0005632732,0.033028517],"study_design_scores_gemma":[0.00047328026,0.00014651529,0.00013241755,0.00007166791,0.000028424769,0.0000031709067,0.000019855233,0.6268808,0.004460703,0.29637954,0.07117285,0.00023073662],"about_ca_topic_score_codex":4.449705e-7,"about_ca_topic_score_gemma":0.000003962054,"teacher_disagreement_score":0.7891865,"about_ca_system_score_codex":0.0000395299,"about_ca_system_score_gemma":0.00006195482,"threshold_uncertainty_score":0.4143849},"labels":[],"label_agreement":null},{"id":"W4400349968","doi":"10.3390/math12132118","title":"Joint Statistical Inference for the Area under the ROC Curve and Youden Index under a Density Ratio Model","year":2024,"lang":"en","type":"article","venue":"Mathematics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Higher Education Discipline Innovation Project; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Receiver operating characteristic; Youden's J statistic; Biomarker; Estimator; Statistics; Area under the curve; Inference; Mathematics; Normality; Medicine; Computer science; Internal medicine; Artificial intelligence; Biology","score_opus":0.08902763889821706,"score_gpt":0.3242592254334621,"score_spread":0.235231586535245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400349968","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00058632804,0.000072878676,0.9941767,0.0042604594,0.00006360371,0.0004393301,0.000040813327,0.0002227405,0.0001371516],"genre_scores_gemma":[0.7780038,0.000030464873,0.2210533,0.0005235011,0.00002169771,0.00012530742,0.000007123378,0.000012504202,0.00022230131],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990565,0.000031013016,0.00024169864,0.00025558207,0.00024596052,0.00016920574],"domain_scores_gemma":[0.9977954,0.0012978007,0.00006346784,0.0007155885,0.00008998288,0.000037767863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005779945,0.00012523335,0.0001321386,0.000036841066,0.00019225365,0.0005864862,0.00055460964,0.00005432725,0.0000051696084],"category_scores_gemma":[0.00018215126,0.000068213456,0.00003068695,0.00015022724,0.00013608717,0.00022733913,0.00029185024,0.00016901123,0.000011413883],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.149274e-7,0.000020158559,0.000008127063,0.000056980876,0.000017479939,5.214936e-7,0.0009297924,0.0005641178,0.0001584798,0.9934837,0.0032447353,0.0015150983],"study_design_scores_gemma":[0.00003022378,0.000008624221,0.0002809305,0.00002236007,0.000011070407,0.000007091085,0.00010902739,0.5956545,0.00028376377,0.4034394,0.00009422894,0.000058786514],"about_ca_topic_score_codex":0.000005706663,"about_ca_topic_score_gemma":0.000018503117,"teacher_disagreement_score":0.7774175,"about_ca_system_score_codex":0.000045947134,"about_ca_system_score_gemma":0.00011565601,"threshold_uncertainty_score":0.56554997},"labels":[],"label_agreement":null},{"id":"W4400676406","doi":"10.1007/978-3-031-65112-0_6","title":"A Preliminary Study to Examining Per-class Performance Bias via Robustness Distributions","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Robustness (evolution); Computer science; Class (philosophy); Algorithm; Artificial intelligence","score_opus":0.04316998529932985,"score_gpt":0.2785133695285633,"score_spread":0.23534338422923345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400676406","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001931222,0.00014566757,0.99207634,0.00083829084,0.0016168001,0.0012681261,0.000036615667,0.0008848428,0.0012021253],"genre_scores_gemma":[0.69403183,0.000013886142,0.3043465,0.00038076015,0.00029248005,0.000119851,0.000029211165,0.00005451426,0.0007309714],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99451554,0.000055724777,0.0007885526,0.0025136082,0.0012960283,0.0008305458],"domain_scores_gemma":[0.99579895,0.00042702333,0.00026865426,0.002859924,0.00038166938,0.0002637811],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.001457216,0.0007099869,0.00060700806,0.0013913873,0.000446769,0.0010752195,0.005502158,0.0002455192,0.000017329827],"category_scores_gemma":[0.00012315644,0.00066242425,0.000094855226,0.0015976959,0.00046968178,0.0010589587,0.0039150603,0.0011680613,0.00020107489],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002377071,0.00035466798,0.00056892785,0.00018194556,0.000042301996,0.00024214873,0.0038924715,0.049306154,0.0003564246,0.014893371,0.00028353295,0.9298543],"study_design_scores_gemma":[0.0002049921,0.0017918984,0.0027080725,0.0009178537,0.000030521103,0.00017921883,0.0000024346255,0.97660613,0.0022941919,0.011365598,0.0025360964,0.001363016],"about_ca_topic_score_codex":0.000014764047,"about_ca_topic_score_gemma":0.000031328582,"teacher_disagreement_score":0.9284913,"about_ca_system_score_codex":0.0007356129,"about_ca_system_score_gemma":0.0005186526,"threshold_uncertainty_score":0.99996173},"labels":[],"label_agreement":null},{"id":"W4400697361","doi":"10.47836/pjst.32.4.10","title":"Borderline-DEMNET: A Workflow for Detecting Alzheimer’s and Dementia Stage by Solving Class Imbalance Problem","year":2024,"lang":"en","type":"article","venue":"Pertanika journal of science & technology","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; F. Hoffmann-La Roche; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Dementia; Class (philosophy); Workflow; Stage (stratigraphy); Medicine; Computer science; Psychology; Artificial intelligence; Disease; Internal medicine; Biology; Database","score_opus":0.018669834107116152,"score_gpt":0.29135872930114715,"score_spread":0.272688895194031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400697361","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010900828,0.017052678,0.9639837,0.006648665,0.0004052348,0.0003440801,0.000011058579,0.00051247305,0.00014125701],"genre_scores_gemma":[0.6812649,0.00029222196,0.31818596,0.00013373682,0.000038011673,0.00003072872,5.272559e-7,0.000015202745,0.000038748898],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99762344,0.000025021047,0.00065673504,0.0006302276,0.00045938598,0.0006051976],"domain_scores_gemma":[0.99835336,0.00016757425,0.00041689814,0.0004943971,0.00044618503,0.00012159155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019950364,0.00020692615,0.00029689976,0.0011601438,0.00045933627,0.00059802004,0.0022878116,0.00015048808,0.0000053267495],"category_scores_gemma":[0.0004046417,0.00017776496,0.00006428582,0.002545638,0.0009468368,0.0019365756,0.00039469113,0.00047916968,0.0000026888483],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001147722,0.000053506916,0.0009270188,0.000058891488,0.000093398085,0.000025383397,0.000417467,0.000020435491,0.6413124,0.05608746,0.0029333227,0.2980592],"study_design_scores_gemma":[0.000814724,0.0013560576,0.00024001292,0.00072569004,0.00015182578,0.0012497086,0.00065562193,0.2961415,0.4733508,0.05374453,0.1706611,0.0009084204],"about_ca_topic_score_codex":0.0000041287403,"about_ca_topic_score_gemma":0.0000058047585,"teacher_disagreement_score":0.670364,"about_ca_system_score_codex":0.00012033099,"about_ca_system_score_gemma":0.00038978193,"threshold_uncertainty_score":0.7249045},"labels":[],"label_agreement":null},{"id":"W4400836543","doi":"10.20944/preprints202407.1257.v1","title":"A Closest Resemblance Classifier with Feature Interval Learning and Outranking Measures for Improved Performance","year":2024,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Overfitting; Artificial intelligence; Computer science; Machine learning; Random forest; Support vector machine; Classifier (UML); Pattern recognition (psychology); Feature (linguistics); Robustness (evolution); Random subspace method; Pairwise comparison; Artificial neural network; Data mining","score_opus":0.09348759723230013,"score_gpt":0.342511839297815,"score_spread":0.24902424206551485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400836543","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.454318,0.0014037557,0.5203366,0.008257281,0.0014642684,0.003989132,0.000113211936,0.004041615,0.0060761143],"genre_scores_gemma":[0.9534082,0.0004572127,0.04228503,0.00013633848,0.00019380901,0.0009059573,0.00005736934,0.000076198136,0.0024798813],"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9965595,0.0001325671,0.00045399976,0.0019342002,0.0003865937,0.0005331095],"domain_scores_gemma":[0.99730647,0.00013794944,0.00039869375,0.0016636818,0.00036103756,0.00013217141],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0012194501,0.0005244303,0.00055004365,0.0002835867,0.00023367882,0.00037003672,0.0017764941,0.00044521398,0.0000068986537],"category_scores_gemma":[0.0002616315,0.00045947096,0.00013711717,0.00028805935,0.00016897691,0.00039380035,0.003878248,0.0023296895,0.00005124762],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001306763,0.00043998283,0.48263198,0.01058908,0.0014534122,0.00006599629,0.010017872,0.00050906406,0.19517317,0.02782024,0.0032712938,0.26672116],"study_design_scores_gemma":[0.00204965,0.00068175944,0.19385113,0.007411948,0.0003216305,0.0002084537,0.00022925234,0.26719958,0.3234738,0.021060707,0.1796484,0.003863673],"about_ca_topic_score_codex":0.000020721189,"about_ca_topic_score_gemma":0.000021033626,"teacher_disagreement_score":0.49909022,"about_ca_system_score_codex":0.0001822079,"about_ca_system_score_gemma":0.00027806978,"threshold_uncertainty_score":0.999972},"labels":[],"label_agreement":null},{"id":"W4400911009","doi":"10.1109/ic3se62002.2024.10593528","title":"Fraud Identification in Financial Transactions: Machine Learning-Based Anomaly Detection Method","year":2024,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Anomaly detection; Computer science; Identification (biology); Artificial intelligence; Anomaly (physics); Machine learning; Finance; Business","score_opus":0.01233980567521107,"score_gpt":0.28123410472366117,"score_spread":0.2688942990484501,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400911009","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040696454,0.0001294088,0.9964138,0.0009223107,0.00029575042,0.0001933479,0.0000058653245,0.0013989123,0.00023362329],"genre_scores_gemma":[0.82990086,0.000017402263,0.16914855,0.00012180745,0.000022391217,0.00012379755,0.000016955824,0.0000101395835,0.000638124],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987115,0.00016165902,0.0003117595,0.00046892377,0.00018852986,0.00015759359],"domain_scores_gemma":[0.9993462,0.00012892002,0.00005164428,0.0003909516,0.00004974048,0.000032527554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077945186,0.00010935779,0.000101963466,0.0004740733,0.00008829244,0.0002675632,0.00038997913,0.0000954179,0.00005897273],"category_scores_gemma":[0.00008587825,0.000108568915,0.000053916563,0.0011867525,0.000018144961,0.0008382199,0.000014950241,0.00030639733,0.00009587485],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010723337,0.000093221104,0.00010478267,0.000061491,0.000005992426,0.000017244618,0.0001721615,0.0023230014,0.06277967,0.012452538,0.00014056305,0.9218386],"study_design_scores_gemma":[0.000084046085,0.00003431322,0.0030675502,0.00001684373,0.0000030776814,0.000008283982,0.000003526758,0.78398573,0.20004037,0.0019049443,0.01073897,0.00011234668],"about_ca_topic_score_codex":0.00017657662,"about_ca_topic_score_gemma":0.00027747464,"teacher_disagreement_score":0.9217263,"about_ca_system_score_codex":0.0001291366,"about_ca_system_score_gemma":0.000098769495,"threshold_uncertainty_score":0.44273117},"labels":[],"label_agreement":null},{"id":"W4400976257","doi":"10.1109/accai61061.2024.10601786","title":"Machine Learning-Based Fraud Detection System for Insurance Claims in IoT Environment","year":2024,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Internet of Things; Computer science; Computer security","score_opus":0.012675870675331172,"score_gpt":0.23248951384812339,"score_spread":0.21981364317279223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400976257","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017090448,0.00018350306,0.9956867,0.00043257198,0.00020151878,0.0003614551,0.000013608895,0.0011821981,0.000229418],"genre_scores_gemma":[0.94012296,0.000011124906,0.059266116,0.000063024745,0.000023633467,0.00025970375,0.000013437632,0.000011676337,0.00022829963],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899125,0.000055790875,0.00022158277,0.0004055239,0.00015797654,0.00016785924],"domain_scores_gemma":[0.99942297,0.00010993167,0.000042457064,0.00037983418,0.000013016545,0.000031804248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003722294,0.0001004448,0.00010543329,0.00017483589,0.00005987362,0.00012188555,0.00036289752,0.000065754844,0.0000072065613],"category_scores_gemma":[0.000013648333,0.000093890776,0.000040689552,0.00026349,0.00001863793,0.00018704846,0.000053309806,0.00015903996,0.00007201689],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050822917,0.00019254452,0.0038974185,0.0010189153,0.000027175312,0.000028611787,0.00031258597,0.013929746,0.09168631,0.10223264,0.00060180895,0.7860214],"study_design_scores_gemma":[0.0001528423,0.00008257002,0.0018611387,0.00005618851,0.0000012302913,0.000003401662,0.000006152504,0.84574395,0.12558815,0.00046145305,0.025925027,0.000117911484],"about_ca_topic_score_codex":0.000030761992,"about_ca_topic_score_gemma":0.000016143214,"teacher_disagreement_score":0.9384139,"about_ca_system_score_codex":0.0002430835,"about_ca_system_score_gemma":0.000026260037,"threshold_uncertainty_score":0.38287547},"labels":[],"label_agreement":null},{"id":"W4401011377","doi":"10.1016/b978-0-443-24010-2.00002-0","title":"Machine learning","year":2024,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Artificial intelligence; Psychology","score_opus":0.01856283733271414,"score_gpt":0.24885705177948172,"score_spread":0.2302942144467676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401011377","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.6085948e-8,0.0021742107,0.0084460825,0.00028801616,0.00044352803,0.00027031486,0.000031708,0.0016849098,0.9866612],"genre_scores_gemma":[0.00008275399,0.0002282473,0.014559706,0.00029667353,0.0001748066,0.00003931691,0.00006160924,0.00007993686,0.9844769],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99819565,0.00001917708,0.0003866911,0.0007599214,0.00038352807,0.00025503684],"domain_scores_gemma":[0.99834144,0.000051379076,0.00020000637,0.0012327656,0.00007960342,0.000094774645],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002781238,0.00037394877,0.0003458628,0.00027461178,0.00010169519,0.00028084175,0.0013854323,0.00027405613,0.00009786539],"category_scores_gemma":[0.000016572261,0.00035088666,0.00017061377,0.000027470507,0.000080834434,0.0001284993,0.0007489673,0.0010164676,0.0020883782],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.0670983e-7,0.0000010423652,3.0781393e-7,0.000030556028,0.000017654165,0.000024564115,0.00003993551,1.2599162e-7,0.000022710816,0.41063946,0.0003294137,0.58889383],"study_design_scores_gemma":[0.000034941055,0.000030499516,7.7613447e-7,0.00022764977,0.000018285435,0.000026573298,3.4175468e-7,0.0009166134,0.00017294593,0.14635558,0.8518978,0.00031802477],"about_ca_topic_score_codex":2.9576194e-7,"about_ca_topic_score_gemma":0.0000024321405,"teacher_disagreement_score":0.85156834,"about_ca_system_score_codex":0.000112496615,"about_ca_system_score_gemma":0.00009047764,"threshold_uncertainty_score":0.9998943},"labels":[],"label_agreement":null},{"id":"W4401455142","doi":"10.18357/bigr52202421689","title":"Customs Laboratories and the Prevention and Detection of Customs Fraud: Two Case Studies","year":2024,"lang":"en","type":"article","venue":"Borders in Globalization Review","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Business; Computer security; Computer science","score_opus":0.016377057915347222,"score_gpt":0.358904514955055,"score_spread":0.3425274570397078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401455142","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008001108,0.47579864,0.5204308,0.001581084,0.00018931761,0.00080438855,0.000009858131,0.00018673998,0.00019908477],"genre_scores_gemma":[0.63719755,0.35623288,0.0058192974,0.0005182481,0.000018874058,0.00016498534,0.000009590211,0.000008937649,0.000029640585],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989452,0.00023983183,0.00034628785,0.00024939424,0.00013769737,0.00008160759],"domain_scores_gemma":[0.99931026,0.00009547523,0.00012688086,0.0002888311,0.00016113042,0.000017450011],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008963775,0.00009849239,0.00021580482,0.0000752851,0.00006721025,0.000079969024,0.00014008429,0.000031519234,0.0000014217068],"category_scores_gemma":[0.00034603072,0.0000697444,0.000021736272,0.0011811433,0.00018741003,0.0004665096,0.00008638701,0.000063468506,0.0000011498761],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000557307,0.0000190609,0.00017364054,0.0036375732,0.000040588697,0.000024731413,0.00051567383,0.000007578196,0.000072471485,0.56547165,0.0023522144,0.42767924],"study_design_scores_gemma":[0.0036537433,0.00032664175,0.00065115956,0.025038412,0.0005597583,0.0017446891,0.0018615054,0.079295404,0.007327131,0.16465369,0.71350443,0.0013834273],"about_ca_topic_score_codex":0.00003700948,"about_ca_topic_score_gemma":0.00010337749,"teacher_disagreement_score":0.71115226,"about_ca_system_score_codex":0.000039937306,"about_ca_system_score_gemma":0.000043143264,"threshold_uncertainty_score":0.28440937},"labels":[],"label_agreement":null},{"id":"W4401522263","doi":"10.1080/23270012.2024.2377168","title":"Handling highly imbalanced data for classifying fatality of auto collisions using machine learning techniques","year":2024,"lang":"en","type":"article","venue":"Journal of Management Analytics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Toronto Metropolitan University","funders":"","keywords":"Machine learning; Computer science; Artificial intelligence; Risk analysis (engineering); Data mining; Medicine","score_opus":0.09543007381265481,"score_gpt":0.35827034273818315,"score_spread":0.26284026892552836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401522263","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007105991,0.0005934963,0.9969203,0.0008100796,0.0002510105,0.00024557993,0.00006966694,0.00019169702,0.00020757377],"genre_scores_gemma":[0.20129283,0.00057663926,0.79768586,0.000076981174,0.00010721366,0.0000037061222,0.000050327646,0.000019807312,0.00018663291],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980083,0.000065936394,0.00088596507,0.00033262107,0.00048874243,0.0002184293],"domain_scores_gemma":[0.99785644,0.00021593987,0.0006748139,0.00091054966,0.0002792806,0.000062991494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021697443,0.00015739769,0.0003554191,0.0006048384,0.00013206064,0.00031899408,0.0019290042,0.00006421229,0.0000038773105],"category_scores_gemma":[0.00019159012,0.00013729984,0.00013344195,0.00077741244,0.00005170323,0.0012491231,0.00083186483,0.0002849544,8.1435087e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024502908,0.0009656135,0.0058995336,0.0061033187,0.003852649,0.00051197916,0.0012069254,0.008872193,0.12392419,0.5355315,0.024631971,0.2882551],"study_design_scores_gemma":[0.0001857219,0.00010288624,0.00014585187,0.0005608661,0.00018997896,0.000017722981,0.000051438783,0.91925174,0.014743773,0.0021090498,0.06248531,0.00015565522],"about_ca_topic_score_codex":0.0000071098534,"about_ca_topic_score_gemma":0.0000016307571,"teacher_disagreement_score":0.9103795,"about_ca_system_score_codex":0.00015524073,"about_ca_system_score_gemma":0.000096466014,"threshold_uncertainty_score":0.55989254},"labels":[],"label_agreement":null},{"id":"W4401752135","doi":"10.1109/aim55361.2024.10637111","title":"Transfer Learning in CNC Milling Machines for Chatter Detection using LSTM-AutoEncoders","year":2024,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Transfer of learning; Speech recognition","score_opus":0.032745869226933386,"score_gpt":0.2942524537386038,"score_spread":0.2615065845116704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401752135","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016042618,0.00008556534,0.9814639,0.0008288013,0.00025258385,0.00021567615,0.0000019301374,0.00089238986,0.00021649699],"genre_scores_gemma":[0.8100368,0.000012979166,0.18934923,0.0002704588,0.00004900988,0.00005263503,0.0000052474816,0.000015443435,0.00020822967],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999085,0.000035895286,0.00020191786,0.0003668162,0.00011064341,0.00019973004],"domain_scores_gemma":[0.9996485,0.000088460045,0.000012816443,0.00019605279,0.000029676328,0.000024464678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032963083,0.000102998536,0.0000962353,0.00027627565,0.00008264463,0.00021851335,0.00026903415,0.000060633945,0.0000102913355],"category_scores_gemma":[0.000021355969,0.00009386072,0.000049880633,0.0004037933,0.000016761489,0.0009826558,0.00003257688,0.00016427189,0.000008539629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001158076,0.000032439468,0.00045978403,0.00021763092,0.000020710622,0.0000089279865,0.0014921649,0.010433446,0.5264345,0.042141333,0.00014654247,0.41860095],"study_design_scores_gemma":[0.00007238831,0.000027417153,0.000098592755,0.000047496174,0.0000025715756,0.000007098214,0.000020044517,0.89924824,0.09444756,0.0019532691,0.003958856,0.000116472256],"about_ca_topic_score_codex":0.000065696164,"about_ca_topic_score_gemma":0.000039032628,"teacher_disagreement_score":0.8888148,"about_ca_system_score_codex":0.00007800334,"about_ca_system_score_gemma":0.0000309431,"threshold_uncertainty_score":0.38275293},"labels":[],"label_agreement":null},{"id":"W4402095110","doi":"10.23977/jeis.2024.090307","title":"Research on medical insurance fraud identification method based on multi-source datasets","year":2024,"lang":"en","type":"article","venue":"Journal of Electronics and Information Science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Identification (biology); Medical insurance; Insurance fraud; Computer science; Business; Data science; Data mining; Actuarial science","score_opus":0.045168190876206736,"score_gpt":0.4145474269694186,"score_spread":0.3693792360932119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402095110","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018106878,0.00014177714,0.99356806,0.0036660174,0.00020957802,0.000103638406,0.00001712393,0.000052373594,0.00043072275],"genre_scores_gemma":[0.9484698,0.00055641937,0.049555734,0.0013268309,0.0000447713,0.000008499499,0.000015246327,0.000004518013,0.000018137362],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99656737,0.00013587935,0.00058325386,0.00021127112,0.002208817,0.00029342528],"domain_scores_gemma":[0.9980604,0.00043461611,0.00026083944,0.00048485651,0.00059669244,0.00016258254],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01292582,0.00008712833,0.0001119171,0.0013238149,0.00029205516,0.0011063305,0.0015256536,0.000065290005,0.000007688516],"category_scores_gemma":[0.0012466877,0.0000666559,0.00003043819,0.0021967937,0.00019058514,0.007834822,0.00011707328,0.00071412034,0.000037218655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030388226,0.000099082914,0.000035453675,0.000050719107,0.000005672003,0.000005085276,0.00047188494,0.0014165781,0.0039234986,0.41116428,0.0076558236,0.57514155],"study_design_scores_gemma":[0.00016821652,0.00029786452,0.0023553444,0.000123861,0.0000011623056,0.000045122997,0.000024845976,0.85380197,0.0155707,0.0007303029,0.12680067,0.00007995057],"about_ca_topic_score_codex":0.0000021508968,"about_ca_topic_score_gemma":5.5771955e-7,"teacher_disagreement_score":0.94665915,"about_ca_system_score_codex":0.000224047,"about_ca_system_score_gemma":0.001192813,"threshold_uncertainty_score":0.9999306},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Finance; Artificial intelligence; Machine learning; Business","score_opus":0.12398321975984171,"score_gpt":0.38355762344557265,"score_spread":0.2595744036857309,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402194596","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.6728816e-8,0.95025474,0.045065697,0.0010754954,0.000050416857,0.0008021038,0.00005989171,0.00028059483,0.0024110281],"genre_scores_gemma":[0.000027628439,0.9893951,0.009021038,0.00045204323,0.00007181805,0.00075866043,0.00012135572,0.000012633891,0.00013971669],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99808943,0.00049360056,0.0005880588,0.00037350878,0.00028220526,0.00017321206],"domain_scores_gemma":[0.99788034,0.00025853337,0.0006048627,0.0011000015,0.00014770342,0.000008548915],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00094319246,0.00023815373,0.0005858264,0.00014887666,0.0018758641,0.0004234981,0.0033752983,0.00017884684,0.0000019525685],"category_scores_gemma":[0.0000866442,0.00015813945,0.00020931872,0.0014107259,0.0010863018,0.00051396346,0.0011909965,0.00080192275,0.0000062235913],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.424869e-8,0.000010632847,5.7241444e-8,0.0042776586,0.000007312949,9.278716e-8,0.0009886494,6.1525367e-9,7.065495e-7,0.4129029,0.0005824445,0.5812295],"study_design_scores_gemma":[0.000008746456,0.000032442542,3.923366e-7,0.008192733,0.00012955331,0.000013507356,0.000055703662,0.00019178401,0.0000026993644,0.007892928,0.9833202,0.00015932704],"about_ca_topic_score_codex":0.00008243975,"about_ca_topic_score_gemma":0.00011299178,"teacher_disagreement_score":0.9827377,"about_ca_system_score_codex":0.000069452166,"about_ca_system_score_gemma":0.00017875373,"threshold_uncertainty_score":0.99942356},"labels":[],"label_agreement":null},{"id":"W4402464093","doi":"10.11159/mvml24.109","title":"Dataset-augmenting training procedure in class-imbalanced learning","year":2024,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Training (meteorology); Artificial intelligence; Class (philosophy); Machine learning; Training set","score_opus":0.011239886609611074,"score_gpt":0.23287292477117905,"score_spread":0.22163303816156799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402464093","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.761825,0.007928554,0.20466352,0.0059623844,0.009786083,0.0033392413,0.000058191035,0.003467458,0.0029695388],"genre_scores_gemma":[0.9967868,0.00002695424,0.0028992374,0.000039958548,0.00006582387,0.000028719032,8.6376184e-7,0.000008157506,0.00014352678],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984836,0.0000076009023,0.00027746803,0.000541808,0.00035101775,0.00033851803],"domain_scores_gemma":[0.99951893,0.00011055729,0.00008883706,0.00014022995,0.0000648135,0.00007662827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078512245,0.0001505974,0.00020702193,0.00045972897,0.00014092025,0.00075233093,0.0008174469,0.000034132165,1.2364823e-7],"category_scores_gemma":[0.0000845555,0.00011092281,0.00002003773,0.0019103383,0.00010309383,0.00064773747,0.00030771267,0.00037257068,3.7930226e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009126541,0.000046777113,0.0029859315,0.00083576783,0.000024637617,0.0000075016587,0.00085851277,0.0036355346,0.035817157,0.8830292,0.002075494,0.07067435],"study_design_scores_gemma":[0.000084778796,0.000054148724,0.001834036,0.0007364543,0.000002416207,0.000036759393,0.000010992089,0.9899348,0.002436791,0.000080646656,0.004647798,0.00014034733],"about_ca_topic_score_codex":0.00000595664,"about_ca_topic_score_gemma":5.08081e-7,"teacher_disagreement_score":0.9862993,"about_ca_system_score_codex":0.00005392032,"about_ca_system_score_gemma":0.00005448754,"threshold_uncertainty_score":0.7254744},"labels":[],"label_agreement":null},{"id":"W4402509619","doi":"10.1016/j.jobe.2024.110613","title":"Explainable domain adaptation for imbalanced occupancy estimation","year":2024,"lang":"en","type":"article","venue":"Journal of Building Engineering","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Concordia University","keywords":"Occupancy; Domain adaptation; Estimation; Adaptation (eye); Computer science; Domain (mathematical analysis); Artificial intelligence; Statistics; Pattern recognition (psychology); Mathematics; Engineering; Psychology; Architectural engineering","score_opus":0.014525283201267636,"score_gpt":0.2699169583688019,"score_spread":0.2553916751675343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402509619","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042718644,0.00037560123,0.9939414,0.00034660212,0.00066964544,0.00010405173,0.0000027712701,0.00026758714,0.000020470039],"genre_scores_gemma":[0.41337934,0.0000137138095,0.58647966,0.00000987907,0.000087094326,0.000011473704,0.000001369709,0.000008736125,0.000008715986],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921393,0.000008787475,0.00032217635,0.00012731778,0.00017815584,0.0001496552],"domain_scores_gemma":[0.9994083,0.00014790302,0.00012237359,0.0001675142,0.000111266854,0.000042616724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055767345,0.000086713095,0.00012763371,0.00030961868,0.000037422633,0.00021749981,0.00035177259,0.00003990871,7.9607e-7],"category_scores_gemma":[0.00016461458,0.00008181459,0.000069502974,0.00030380118,0.0000046726086,0.0012845297,0.000029040504,0.00012435905,0.0000011947457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001463041,0.000027287191,0.00002987935,0.00042349982,0.00006091148,0.00003512697,0.0009286287,0.18506034,0.22325116,0.51366794,0.0026895455,0.07381102],"study_design_scores_gemma":[0.00012421465,0.000059240952,0.00015319813,0.00027322324,0.000005849709,0.000072792995,0.000013727549,0.9576497,0.024989821,0.008804262,0.007758352,0.000095616975],"about_ca_topic_score_codex":6.289111e-7,"about_ca_topic_score_gemma":5.3339498e-8,"teacher_disagreement_score":0.7725894,"about_ca_system_score_codex":0.0001408846,"about_ca_system_score_gemma":0.000062362604,"threshold_uncertainty_score":0.33363023},"labels":[],"label_agreement":null},{"id":"W4402891761","doi":"10.1109/access.2024.3468993","title":"Machine Learning Based Method for Insurance Fraud Detection on Class Imbalance Datasets With Missing Values","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ontario Ministry of Research and Innovation; National Natural Science Foundation of China; Prince Sattam bin Abdulaziz University","keywords":"Computer science; Class (philosophy); Machine learning; Artificial intelligence; Data mining","score_opus":0.035227580994497645,"score_gpt":0.3528297738485358,"score_spread":0.3176021928540382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402891761","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000654514,0.00014788384,0.9958207,0.00093056704,0.00045046827,0.00036748828,0.0002593592,0.0012119575,0.00015707996],"genre_scores_gemma":[0.76962924,0.000018692297,0.22916417,0.0006319123,0.00011564752,0.00018313149,0.00016342172,0.000034424836,0.0000593474],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99822676,0.000160864,0.00024269335,0.0007579066,0.00032139322,0.00029036865],"domain_scores_gemma":[0.998331,0.000588313,0.00013903518,0.0007853419,0.00008824337,0.00006803693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006719337,0.00021273711,0.0001969844,0.00023086226,0.00025830782,0.0009705404,0.0012453878,0.00008216547,0.0000039358133],"category_scores_gemma":[0.00012355823,0.00017686794,0.000048158905,0.00071042887,0.0000413806,0.0016310144,0.00007867559,0.00033538576,0.00001304816],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022100065,0.0001510822,0.001663584,0.00059993356,0.00007446689,0.00004860177,0.00014665198,0.010934426,0.066174954,0.0043508215,0.006264796,0.9093697],"study_design_scores_gemma":[0.00020144894,0.00013749987,0.0010468333,0.00017921755,0.000007327816,0.00000886759,0.0000013627694,0.67370504,0.29899952,0.001223395,0.02428379,0.00020568962],"about_ca_topic_score_codex":0.000045633977,"about_ca_topic_score_gemma":0.000014649601,"teacher_disagreement_score":0.909164,"about_ca_system_score_codex":0.000098216784,"about_ca_system_score_gemma":0.000084499625,"threshold_uncertainty_score":0.9358943},"labels":[],"label_agreement":null},{"id":"W4402951643","doi":"10.11648/j.acm.20241305.15","title":"Pseudo Oversampling Based on Feature Transformation and Fuzzy Membership Functions for Imbalanced and Overlapping Data","year":2024,"lang":"en","type":"article","venue":"Applied and Computational Mathematics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Oversampling; Feature (linguistics); Transformation (genetics); Fuzzy logic; Artificial intelligence; Mathematics; Pattern recognition (psychology); Computer science; Biology; Linguistics","score_opus":0.041881921210263184,"score_gpt":0.2859209444016908,"score_spread":0.24403902319142762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402951643","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013978016,0.00007470169,0.99474174,0.001725591,0.0000564957,0.00040496222,0.00015175926,0.000269075,0.0011778619],"genre_scores_gemma":[0.5394675,0.000015663349,0.45977446,0.00028958634,0.000033705124,0.00005757,0.00033189103,0.000010576632,0.00001901076],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991229,0.000008824044,0.00018378539,0.00037605833,0.00018508612,0.00012331002],"domain_scores_gemma":[0.99889416,0.00067413575,0.000058125675,0.0002852509,0.000037735237,0.000050613555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028708775,0.00013356247,0.00013510494,0.000114187,0.00017862505,0.00037714036,0.00019766728,0.000062392115,0.0000012505735],"category_scores_gemma":[0.000023860643,0.00012330497,0.000015437477,0.00016798596,0.00004480318,0.00039355902,0.000074166695,0.00010616589,0.0000022286958],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000818628,0.000027266766,0.000005423112,0.0004623927,0.00001884378,3.494237e-7,0.0006335115,0.0007723107,0.0004772271,0.9797822,0.0010036202,0.016808629],"study_design_scores_gemma":[0.00023319841,0.000025398906,0.00025754,0.00009511875,0.00001583934,0.000010344271,0.0001093709,0.81726253,0.000052260177,0.18061168,0.001204526,0.00012221374],"about_ca_topic_score_codex":6.135016e-7,"about_ca_topic_score_gemma":4.8891434e-7,"teacher_disagreement_score":0.8164902,"about_ca_system_score_codex":0.000019733954,"about_ca_system_score_gemma":0.000041579067,"threshold_uncertainty_score":0.50282305},"labels":[],"label_agreement":null},{"id":"W4403209789","doi":"10.11591/ijai.v13.i4.pp4054-4061","title":"Enhancing interpretability in random forest: Leveraging inTrees for association rule extraction insights","year":2024,"lang":"en","type":"article","venue":"IAES International Journal of Artificial Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ontario Council on Graduate Studies, Council of Ontario Universities","keywords":"Interpretability; Random forest; Unemployment; Decision tree; Association rule learning; Computer science; Set (abstract data type); Government (linguistics); Machine learning; Data mining; Economics; Economic growth","score_opus":0.02988994069230209,"score_gpt":0.34204617072206933,"score_spread":0.3121562300297672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403209789","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033519667,0.00030405767,0.9600267,0.002023332,0.0036842553,0.00018798109,0.0000070753154,0.00009293495,0.00015401277],"genre_scores_gemma":[0.95183533,0.000102541766,0.047460414,0.00009839834,0.00042710183,0.00002373442,0.000006397308,0.000010485645,0.000035594192],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99768835,0.00011072655,0.0011135908,0.00030489717,0.0005882262,0.00019418854],"domain_scores_gemma":[0.9973128,0.0011694119,0.00047231777,0.00020237731,0.00079201395,0.000051123054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017332162,0.00013963472,0.00022167772,0.00063332956,0.00005283617,0.00060317124,0.0010933279,0.000096311436,0.000019414425],"category_scores_gemma":[0.0016496521,0.0001296579,0.00016727405,0.00034215857,0.000036748646,0.0022150348,0.00009154885,0.00034790608,0.00001806483],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037582248,0.00032192553,0.001864735,0.00006549982,0.00019631193,0.00007948896,0.0073483842,0.0031023999,0.07023827,0.21761483,0.0005363157,0.698256],"study_design_scores_gemma":[0.00013577097,0.00012290676,0.000958699,0.0005508549,0.000015666601,0.00006167836,0.0004138851,0.28474957,0.4299163,0.27713245,0.005697054,0.0002451654],"about_ca_topic_score_codex":0.00003189869,"about_ca_topic_score_gemma":0.00016609363,"teacher_disagreement_score":0.91831565,"about_ca_system_score_codex":0.0008394854,"about_ca_system_score_gemma":0.00022344233,"threshold_uncertainty_score":0.5816394},"labels":[],"label_agreement":null},{"id":"W4403299049","doi":"10.22214/ijraset.2024.64502","title":"Integrating Autoencoders with Local Outlier Factor and Isolation Forest for Effective Fraud Detection in Imbalanced Datasets","year":2024,"lang":"en","type":"article","venue":"International Journal for Research in Applied Science and Engineering Technology","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Local outlier factor; Anomaly detection; Outlier; Isolation (microbiology); Artificial intelligence; Computer science; Factor (programming language); Pattern recognition (psychology); Machine learning; Biology; Bioinformatics","score_opus":0.024734224468441212,"score_gpt":0.3589017047016991,"score_spread":0.3341674802332579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403299049","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026938783,0.000058283164,0.9707468,0.0013674026,0.0001934939,0.0005417444,0.000020168214,0.000116964395,0.000016358666],"genre_scores_gemma":[0.9077285,0.000044492892,0.09180021,0.000011544472,0.000027949482,0.0003723921,0.00000550048,0.00000775476,0.000001633895],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866694,0.000009987553,0.00019705431,0.00039357247,0.0003982765,0.0003341592],"domain_scores_gemma":[0.999248,0.0003074927,0.000035427307,0.00014157975,0.00021504884,0.000052446238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017551116,0.00009421873,0.000103558974,0.0021372274,0.00012901184,0.00044185127,0.00069526565,0.00008214806,2.1213498e-7],"category_scores_gemma":[0.00037378355,0.00007867856,0.000009944734,0.001122954,0.0002829313,0.0006789535,0.00018717552,0.00049095124,4.423995e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000777213,0.00002629956,0.00043345598,0.00005657264,0.000016556263,0.000017493157,0.00034578564,0.0020139732,0.09218485,0.2076382,0.00005390239,0.6971352],"study_design_scores_gemma":[0.00037698672,0.00017810919,0.0013974522,0.00014657514,7.447911e-7,0.00008633993,0.00013763017,0.9611115,0.014378669,0.019466655,0.0026198898,0.00009947967],"about_ca_topic_score_codex":0.000010705389,"about_ca_topic_score_gemma":0.000059484184,"teacher_disagreement_score":0.9590975,"about_ca_system_score_codex":0.00044731447,"about_ca_system_score_gemma":0.00014091987,"threshold_uncertainty_score":0.4260782},"labels":[],"label_agreement":null},{"id":"W4403344783","doi":"10.4230/lipics.forc.2024.8","title":"Score Design for Multi-Criteria Incentivization","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Science Foundation","keywords":"Computer science; Process engineering; Engineering","score_opus":0.24406661648319683,"score_gpt":0.25632064095610857,"score_spread":0.01225402447291174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403344783","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014817455,0.000057887923,0.99516314,0.00013805275,0.0008355141,0.0009455315,0.00010509454,0.0011185551,0.00015449456],"genre_scores_gemma":[0.7540629,0.000097412725,0.24399507,0.00007595742,0.00006169417,0.000015243823,0.00013784089,0.000028380147,0.0015255233],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99812657,0.00011987909,0.00020720309,0.0012071986,0.00006929776,0.00026982694],"domain_scores_gemma":[0.9981047,0.000084942454,0.0001990815,0.001288493,0.00023952733,0.00008327026],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035055145,0.00026634688,0.00023389151,0.00032789636,0.00011405446,0.00030253315,0.001851271,0.00027327644,0.000009220739],"category_scores_gemma":[0.00006346784,0.00031479547,0.00013638406,0.0005446976,0.000073705814,0.00039999015,0.0021400584,0.0003362176,0.00008288299],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004401465,0.00022248257,0.00023303316,0.00057409826,0.000115386996,0.00008978364,0.0003389938,0.015773382,0.0016529643,0.9611303,0.015298356,0.0045271716],"study_design_scores_gemma":[0.00020559126,0.000029021345,0.00013871695,0.00014869834,0.00003630335,0.0000013378817,0.000008253137,0.87872565,0.0039150864,0.11533199,0.0011450029,0.00031434308],"about_ca_topic_score_codex":0.000016506185,"about_ca_topic_score_gemma":0.000004293878,"teacher_disagreement_score":0.8629523,"about_ca_system_score_codex":0.00027664186,"about_ca_system_score_gemma":0.00024035806,"threshold_uncertainty_score":0.99993044},"labels":[],"label_agreement":null},{"id":"W4403484215","doi":"10.3390/foods13203300","title":"Handling the Imbalanced Problem in Agri-Food Data Analysis","year":2024,"lang":"en","type":"review","venue":"Foods","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Conestoga College","funders":"McGill University","keywords":"Machine learning; Computer science; Bottleneck; Artificial intelligence; Support vector machine; Robustness (evolution); Data mining","score_opus":0.14925905577220794,"score_gpt":0.39432743280974103,"score_spread":0.2450683770375331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403484215","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.1300864e-8,0.77969885,0.21788579,0.00020509938,0.00017853106,0.0006026761,0.00033997357,0.00039654702,0.0006925172],"genre_scores_gemma":[0.000017378392,0.9386528,0.05954239,0.000047112128,0.00010597113,0.000306589,0.0010864852,0.000029693796,0.00021157096],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99681646,0.0002834376,0.0008263767,0.0013147878,0.00038210014,0.00037682758],"domain_scores_gemma":[0.9938147,0.00020727614,0.00036863473,0.0055145454,0.000041409527,0.000053443007],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0013604746,0.00039537152,0.001200439,0.0006942988,0.000082971346,0.0006026304,0.008140388,0.00023398423,0.0000067935566],"category_scores_gemma":[0.00008485159,0.00023889812,0.0003133233,0.0054510557,0.00005616921,0.00046584423,0.002690233,0.0007432832,0.00012609191],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.0319254e-7,0.000028167096,0.0000028564866,0.0025491503,0.00060470577,0.0000075071266,0.00007431263,0.000002644219,3.3389662e-7,0.015155192,0.0049707983,0.97660404],"study_design_scores_gemma":[0.00003250207,0.000029664247,0.000007970503,0.002387591,0.0010928235,0.000009140381,0.0000031840602,0.005595739,0.0000019056612,0.0014730265,0.98906046,0.0003059826],"about_ca_topic_score_codex":0.000018520905,"about_ca_topic_score_gemma":0.00008893631,"teacher_disagreement_score":0.9840897,"about_ca_system_score_codex":0.00013769363,"about_ca_system_score_gemma":0.00033551376,"threshold_uncertainty_score":0.99722606},"labels":[],"label_agreement":null},{"id":"W4403847593","doi":"10.1111/jedm.12420","title":"Algorithmic Bias in BERT for Response Accuracy Prediction: A Case Study for Investigating Population Validity","year":2024,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University of Edmonton; University of Alberta","funders":"","keywords":"Item response theory; Population; Psychology; Test validity; Predictive validity; Statistics; Computer science; Econometrics; Psychometrics; Mathematics; Clinical psychology; Demography","score_opus":0.3090948321123259,"score_gpt":0.41355177989540626,"score_spread":0.10445694778308035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403847593","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46102875,0.0002685058,0.52169424,0.013272935,0.0019231833,0.001709633,0.000044014734,0.000052212563,0.000006516774],"genre_scores_gemma":[0.87060624,0.0000028700356,0.12853085,0.000065882195,0.00041687893,0.00033978393,0.000008872392,0.000009769979,0.000018864945],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978583,0.0002880432,0.0008091516,0.00025162313,0.0006480083,0.00014487834],"domain_scores_gemma":[0.99676025,0.0015887332,0.00037418545,0.0002554495,0.0009385707,0.00008279008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0075259707,0.00011332205,0.00016112425,0.00043350304,0.00012850674,0.00022138843,0.00033551382,0.000040418206,0.0000040247633],"category_scores_gemma":[0.0057875016,0.00010348855,0.00008798638,0.0004082581,0.000014250218,0.00096632,0.000031223943,0.00015190682,0.0000010073475],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019495047,0.013389576,0.32565123,0.001999299,0.0012088675,0.00042804328,0.047735557,0.0031496189,0.06710986,0.06462865,0.14980842,0.32294136],"study_design_scores_gemma":[0.0048801005,0.005222192,0.68252695,0.0022946848,0.00026274464,0.0059610163,0.0034375633,0.15110584,0.009784258,0.11055002,0.022953892,0.0010207568],"about_ca_topic_score_codex":0.00004275144,"about_ca_topic_score_gemma":0.00003149608,"teacher_disagreement_score":0.4095775,"about_ca_system_score_codex":0.00085948623,"about_ca_system_score_gemma":0.001116206,"threshold_uncertainty_score":0.69285977},"labels":[],"label_agreement":null},{"id":"W4403905936","doi":"10.59934/jaiea.v4i1.644","title":"Application of the KARP RABIN Algorithm for Plagiarism Detection System in Thesis Proposal Submission in the Department of Informatics Engineering STMIK Kaputama","year":2024,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Informatics; Health informatics; Plagiarism detection; Software engineering; Engineering; Medicine; Information retrieval; Electrical engineering; Nursing","score_opus":0.01300149316848713,"score_gpt":0.24890497788113794,"score_spread":0.23590348471265082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403905936","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067341346,0.00018038708,0.9920623,0.00019042738,0.000093704635,0.0006869186,0.000011146093,0.000036316476,0.0000046787886],"genre_scores_gemma":[0.8890802,0.000047145633,0.11058979,0.0000049485134,0.000044950266,0.00022207983,0.0000025722197,0.000007513128,8.083599e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870497,0.00002366717,0.0008155182,0.00010911978,0.00022620858,0.000120540615],"domain_scores_gemma":[0.99906784,0.00024028282,0.00025469807,0.000297552,0.00011443319,0.00002517675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010593843,0.000100795136,0.00016389666,0.00030852886,0.000039748113,0.00006835323,0.0005271007,0.00008070777,1.5005149e-7],"category_scores_gemma":[0.00005156088,0.00006923405,0.00006353921,0.000815461,0.0000272119,0.00028544758,0.00004588679,0.00022829442,5.952666e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008340471,0.000099586854,0.00003778414,0.00051309814,0.000021841402,6.4687606e-7,0.0016256935,0.03803246,0.046708092,0.0861245,0.000014885701,0.82681304],"study_design_scores_gemma":[0.000021523983,0.000043524433,0.0003709134,0.00017145413,0.000011013276,0.000021779346,0.00030279974,0.81916136,0.17765638,0.0009813603,0.0011960393,0.00006183932],"about_ca_topic_score_codex":0.0000126148125,"about_ca_topic_score_gemma":0.0000042255233,"teacher_disagreement_score":0.88234603,"about_ca_system_score_codex":0.00010415119,"about_ca_system_score_gemma":0.0000575551,"threshold_uncertainty_score":0.28232825},"labels":[],"label_agreement":null},{"id":"W4403913051","doi":"10.1016/j.mlwa.2024.100597","title":"Enhancing SMOTE for imbalanced data with abnormal minority instances","year":2024,"lang":"en","type":"article","venue":"Machine Learning with Applications","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data mining; Artificial intelligence","score_opus":0.01791840181232909,"score_gpt":0.2855672153657165,"score_spread":0.26764881355338743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403913051","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034072113,0.0004010842,0.9935885,0.0016398516,0.00003372865,0.0008039764,0.00013237227,0.0016346897,0.0014250423],"genre_scores_gemma":[0.38084775,0.000041149226,0.61626625,0.000121569945,0.00011411729,0.0010833177,0.00081306876,0.000027463973,0.0006853325],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99830955,0.000038512513,0.00023967028,0.0008561003,0.00025198807,0.00030417598],"domain_scores_gemma":[0.997938,0.00022588241,0.00012435963,0.0015202047,0.00011280507,0.00007877646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004304302,0.00019496947,0.00017449613,0.00013249603,0.00037266553,0.0004082784,0.0016089819,0.000051190527,0.0000061503597],"category_scores_gemma":[0.000038521597,0.00014846199,0.000022527372,0.00081283564,0.00008461382,0.000996245,0.00026123607,0.00035817063,0.000027472115],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010506956,0.0002241849,0.017726287,0.0008084594,0.00021265696,0.000015351578,0.00084282877,0.000950209,0.00983092,0.57425374,0.00318435,0.39184594],"study_design_scores_gemma":[0.00038388357,0.00023878958,0.0030226647,0.0001291903,0.00004234345,0.000055693647,0.000032927324,0.39037067,0.005341982,0.0015167359,0.598392,0.000473081],"about_ca_topic_score_codex":0.000059061535,"about_ca_topic_score_gemma":0.00018278579,"teacher_disagreement_score":0.5952077,"about_ca_system_score_codex":0.000052972402,"about_ca_system_score_gemma":0.0001848976,"threshold_uncertainty_score":0.6054104},"labels":[],"label_agreement":null},{"id":"W4404200974","doi":"10.1007/978-3-031-71452-8_5","title":"Prevalence Threshold, Screening Curves and Screening Probability Square Plane S","year":2024,"lang":"en","type":"book-chapter","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital","funders":"","keywords":"Square (algebra); Statistics; Plane (geometry); Mathematics; Statistical physics; Physics; Geometry","score_opus":0.047911527214017126,"score_gpt":0.26692009487166435,"score_spread":0.21900856765764723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404200974","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000023096172,0.00801188,0.6752562,0.0017485315,0.00012482665,0.0009381343,0.00017076393,0.002072952,0.3116744],"genre_scores_gemma":[0.0016042338,0.0045096003,0.43242332,0.0009240088,0.00016800956,0.00012232222,0.00021626298,0.00009883794,0.55993336],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997098,0.00002043729,0.00053752656,0.0014100908,0.00060734747,0.00032659833],"domain_scores_gemma":[0.99761426,0.00014180595,0.00022659759,0.0017237607,0.00015113124,0.00014246581],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006191543,0.00047418883,0.00040909837,0.000212032,0.00013023037,0.0003881166,0.0014184504,0.00030210937,0.00016877273],"category_scores_gemma":[0.000045684854,0.00042561383,0.0001024897,0.0000921442,0.00023872315,0.0007468783,0.0012787158,0.00067320024,0.000081665225],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040381447,0.000007780407,0.00018397861,0.002018192,0.00003525595,0.000020328507,0.00003961956,0.0000013214251,0.00001872572,0.95860875,0.0114375595,0.027624434],"study_design_scores_gemma":[0.00032340805,0.00034347532,0.0017174584,0.017244106,0.00018130527,0.00026620814,0.000010571704,0.016902536,0.0010274813,0.67775226,0.28154296,0.002688209],"about_ca_topic_score_codex":0.000012040036,"about_ca_topic_score_gemma":0.0000091885395,"teacher_disagreement_score":0.2808565,"about_ca_system_score_codex":0.00004853852,"about_ca_system_score_gemma":0.00006564866,"threshold_uncertainty_score":0.9998196},"labels":[],"label_agreement":null},{"id":"W4404716839","doi":"10.1007/s44163-024-00199-0","title":"The effect of resampling techniques on the performances of machine learning clinical risk prediction models in the setting of severe class imbalance: development and internal validation in a retrospective cohort","year":2024,"lang":"en","type":"article","venue":"Discover Artificial Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Mount Sinai Hospital; University of British Columbia; Carleton University; Providence Health Care; St. Paul's Hospital; University of Toronto; Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Nova Scotia Health Authority; Dalhousie University; Providence Health Care","keywords":"Resampling; Oversampling; Random forest; Machine learning; Artificial intelligence; Logistic regression; Boosting (machine learning); Computer science; Jackknife resampling; Algorithm; Data mining; Statistics; Mathematics; Bandwidth (computing)","score_opus":0.031637490919592906,"score_gpt":0.32662512621877005,"score_spread":0.29498763529917715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404716839","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64901996,0.000106126114,0.34991142,0.00015750647,0.00009162219,0.00046242384,0.000015778804,0.000036937236,0.00019821737],"genre_scores_gemma":[0.9977924,0.00041510342,0.0016674803,0.000007981775,0.00002194967,0.000078466845,0.000006528637,0.000005793975,0.000004252764],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777454,0.00055204646,0.0008506921,0.00030369795,0.00038131158,0.00013773651],"domain_scores_gemma":[0.9976659,0.0015804751,0.00034970985,0.00032601025,0.00006699748,0.000010908769],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006528873,0.00011723326,0.0002061588,0.00012238527,0.00011742022,0.000108149696,0.0006044624,0.000059343103,8.541048e-7],"category_scores_gemma":[0.00061992987,0.000061951745,0.000048380578,0.00053005636,0.00019360291,0.0004068573,0.0001541839,0.0005406842,5.573212e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019163152,0.000075151715,0.6421362,0.00011309357,0.00004643762,0.00000141868,0.0073214183,0.005873651,0.0013801858,0.088613935,0.000024810244,0.25422204],"study_design_scores_gemma":[0.000021363187,0.00032706978,0.07161967,0.00050424517,0.0000085455595,0.0000023843263,0.00034595956,0.6889395,0.22752689,0.010595565,0.000032026677,0.00007678719],"about_ca_topic_score_codex":0.00016549237,"about_ca_topic_score_gemma":0.000102518854,"teacher_disagreement_score":0.68306583,"about_ca_system_score_codex":0.000073031355,"about_ca_system_score_gemma":0.000056933855,"threshold_uncertainty_score":0.2526319},"labels":[],"label_agreement":null},{"id":"W4404983478","doi":"10.21203/rs.3.rs-5147684/v1","title":"Optimized Feature Selection and Enhanced Recurrent Neural Network for Financial Fraud Detection","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Computer science; Database transaction; Feature selection; Credit card fraud; Financial fraud; Financial statement; Selection (genetic algorithm); Financial transaction; Artificial neural network; Artificial intelligence; Feature (linguistics); Machine learning; Credit card; Finance; Data mining; Business; Accounting; Payment; Database","score_opus":0.045942765539957686,"score_gpt":0.37850445536293564,"score_spread":0.33256168982297796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404983478","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041489983,0.0015872305,0.98617107,0.0022798658,0.0016193322,0.002937187,0.00013564031,0.00097553036,0.00014513607],"genre_scores_gemma":[0.6139143,0.0013207678,0.3750694,0.00009061566,0.0025724191,0.0056810877,0.00041259988,0.000092383954,0.0008463872],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996625,0.0004021112,0.00030250326,0.001296786,0.0006851412,0.0006884529],"domain_scores_gemma":[0.9977803,0.00034637042,0.0001350377,0.000826694,0.00077286805,0.00013871385],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00175783,0.0002872947,0.00033318577,0.00043750278,0.00043348072,0.0008682265,0.0008783634,0.00057449454,0.000004756738],"category_scores_gemma":[0.0006686669,0.00027873213,0.00013977363,0.0009815764,0.000077391924,0.00022333616,0.0020707985,0.0024448768,0.000012681619],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038408296,0.0001163436,0.00002077178,0.002854211,0.00006359662,0.000008292545,0.0006034385,0.0028488005,0.006956549,0.02304415,0.102793284,0.8603065],"study_design_scores_gemma":[0.00057884946,0.00074946217,0.0013839834,0.0012111457,0.000022517985,0.000014672108,0.000019499314,0.8113044,0.0392567,0.12359599,0.021188948,0.00067384774],"about_ca_topic_score_codex":0.000027418944,"about_ca_topic_score_gemma":0.00005442775,"teacher_disagreement_score":0.8596326,"about_ca_system_score_codex":0.00038095223,"about_ca_system_score_gemma":0.00040457852,"threshold_uncertainty_score":0.9999665},"labels":[],"label_agreement":null},{"id":"W4405045292","doi":"10.1016/j.eswa.2024.126033","title":"Stacked fuzzy envelope consistency imbalanced ensemble classification method","year":2024,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Chongqing Municipal Education Commission; Natural Science Foundation of Chongqing; National Natural Science Foundation of China","keywords":"Computer science; Consistency (knowledge bases); Artificial intelligence; Pattern recognition (psychology); Ensemble learning; Envelope (radar); Fuzzy logic; Machine learning; Data mining","score_opus":0.031137723218206563,"score_gpt":0.31543773548748494,"score_spread":0.28430001226927837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405045292","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000019190571,0.0024043943,0.9740732,0.002518516,0.00026588817,0.0016396474,0.000040615738,0.002646025,0.016392533],"genre_scores_gemma":[0.43708345,0.00022681989,0.54987615,0.00028479507,0.00024273024,0.00997812,0.00017615747,0.000057383786,0.0020743932],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972776,0.00017196698,0.00060107943,0.0010808688,0.00047859628,0.00038985146],"domain_scores_gemma":[0.9969432,0.0002831521,0.00020324031,0.0020886874,0.00031109506,0.00017067793],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00056388834,0.00029669562,0.00030959034,0.00028265378,0.0003218266,0.00069882325,0.0012150864,0.00014595766,0.000009294963],"category_scores_gemma":[0.000026279624,0.0002455763,0.000066683555,0.0013829848,0.00010252292,0.0008224874,0.00012125217,0.00022863655,0.00045305063],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004226569,0.00006128821,0.000050541188,0.00008204364,0.000044541248,0.0000045175752,0.0005914163,0.000012503019,0.036575057,0.91194284,0.018062148,0.03256886],"study_design_scores_gemma":[0.00028478858,0.00008087815,0.00084259606,0.00022447317,0.000018981236,0.00019709549,0.0005115201,0.064798295,0.012234061,0.0050918204,0.9150082,0.00070728693],"about_ca_topic_score_codex":0.00007474698,"about_ca_topic_score_gemma":0.0000063272614,"teacher_disagreement_score":0.90685105,"about_ca_system_score_codex":0.0002452276,"about_ca_system_score_gemma":0.00036708667,"threshold_uncertainty_score":0.99999964},"labels":[],"label_agreement":null},{"id":"W4405411700","doi":"10.21203/rs.3.rs-5635767/v1","title":"Harnessing Exploratory Data Analysis for Robust Financial Fraud Detection and Model Enhancement","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Roads University","funders":"","keywords":"Business; Exploratory analysis; Finance; Computer science; Data science","score_opus":0.22604347339254985,"score_gpt":0.4210172000216969,"score_spread":0.19497372662914705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405411700","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010956851,0.0011208524,0.994856,0.0006254594,0.00019816171,0.001037122,0.0005895989,0.0003603008,0.00011681925],"genre_scores_gemma":[0.6133345,0.00064664165,0.38244653,0.000042041804,0.00025353688,0.001868815,0.0009856875,0.000041489468,0.00038079446],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961457,0.00023899728,0.0003972268,0.0018021126,0.00091849,0.000497431],"domain_scores_gemma":[0.9955206,0.00021085347,0.00013294964,0.0033906496,0.00061518763,0.00012976358],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.003044848,0.00023927682,0.0003517013,0.0011821399,0.00040561234,0.0012755025,0.0025167253,0.0003035305,0.000003866809],"category_scores_gemma":[0.00049361074,0.00024024807,0.00010254322,0.0013621938,0.00013210878,0.0006084276,0.01017843,0.0011300577,0.000011654758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001564637,0.0006129454,0.00026998404,0.010403176,0.0011325105,0.00004942305,0.0042475923,0.03316188,0.023632078,0.04940425,0.03870865,0.8382211],"study_design_scores_gemma":[0.00007369065,0.000044946086,0.00014971978,0.0002532755,0.00005752129,5.1909825e-7,0.000042216092,0.9586031,0.009356992,0.029901799,0.0012835723,0.00023268556],"about_ca_topic_score_codex":0.000047446825,"about_ca_topic_score_gemma":0.0000932781,"teacher_disagreement_score":0.9254412,"about_ca_system_score_codex":0.00032275595,"about_ca_system_score_gemma":0.00085627224,"threshold_uncertainty_score":0.9997613},"labels":[],"label_agreement":null},{"id":"W4405485983","doi":"10.24124/2024/59588","title":"GANS-based data augmentation in credit card fraud detection","year":2024,"lang":"en","type":"dissertation","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Credit card fraud; Credit card; Computer science; Computer security; Data science; Business; World Wide Web; Payment","score_opus":0.038456914627293996,"score_gpt":0.3332041983942003,"score_spread":0.2947472837669063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405485983","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013427155,0.00021846278,0.9840439,0.00039190738,0.0028917668,0.0006904439,0.00017729602,0.0015987002,0.008644788],"genre_scores_gemma":[0.6831413,0.00026774537,0.21755517,0.0008167986,0.000632416,0.0009258043,0.0806415,0.00018370809,0.015835565],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99770355,0.00007327266,0.00046873107,0.0010496419,0.00048494167,0.00021987231],"domain_scores_gemma":[0.9974947,0.0000712735,0.00018470176,0.0020953778,0.000105717045,0.000048238187],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043490742,0.00025142264,0.00022226838,0.00065755483,0.000055679124,0.0003795264,0.0020578695,0.000303564,0.00003891645],"category_scores_gemma":[0.00008310381,0.0002591347,0.00004541546,0.0008750168,0.000014507029,0.0010308383,0.00014768138,0.00041834178,0.00022495653],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011747899,0.0003213416,0.00014397595,0.0015072331,0.00010337113,0.00008395018,0.0019954785,0.000136162,0.05842925,0.023509372,0.12513374,0.78851867],"study_design_scores_gemma":[0.00057248,0.00014369878,0.005945897,0.00060195004,0.00007003973,0.0000050657445,0.00048222672,0.5758557,0.3605185,0.0070955274,0.047551025,0.0011579428],"about_ca_topic_score_codex":0.00047049616,"about_ca_topic_score_gemma":0.0036172085,"teacher_disagreement_score":0.7873607,"about_ca_system_score_codex":0.00024808972,"about_ca_system_score_gemma":0.0002862221,"threshold_uncertainty_score":0.9999861},"labels":[],"label_agreement":null},{"id":"W4405614982","doi":"10.3390/jrfm17120573","title":"Forensic Accounting and Risk Management: Exploring the Impact of Generalized Audit Software and Whistleblowing Systems on Fraud Detection in Indonesia","year":2024,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Universitas Diponegoro","keywords":"Accounting; Audit; Forensic accounting; Business; Risk management; Audit risk; Software; Computer science; Finance","score_opus":0.01456780403506407,"score_gpt":0.2399761249423511,"score_spread":0.22540832090728702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405614982","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57616454,0.001191239,0.42219174,0.0000146457,0.00023453195,0.00015520863,0.0000039194897,0.000022562883,0.0000215728],"genre_scores_gemma":[0.981159,0.010242945,0.008485261,0.000007318595,0.000074170566,0.000018213756,3.8902607e-7,0.000007465232,0.0000052376336],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990162,0.00007537703,0.00037075355,0.00019616577,0.00020440864,0.00013704546],"domain_scores_gemma":[0.9993743,0.00008797363,0.00028505898,0.00018658952,0.000037407004,0.000028715482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009463996,0.00011725692,0.00019466325,0.00044096983,0.00012887988,0.00023712101,0.00019811899,0.00003139258,2.2818398e-7],"category_scores_gemma":[0.000041932664,0.0000810923,0.000051253104,0.00037881327,0.00003323148,0.0005887486,0.00017423066,0.00021844693,3.1220594e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032928674,0.00001608231,0.016792133,0.00017200167,0.00004538365,0.000041116757,0.0005435285,0.00030880695,0.000027302567,0.007047661,0.00010360677,0.97486943],"study_design_scores_gemma":[0.00072446844,0.00023855497,0.9715536,0.00092908053,0.000102922626,0.00004445927,0.00022935083,0.016961617,0.00024167192,0.006334998,0.002452171,0.00018708299],"about_ca_topic_score_codex":0.00011912631,"about_ca_topic_score_gemma":0.000011284561,"teacher_disagreement_score":0.9746824,"about_ca_system_score_codex":0.00007580702,"about_ca_system_score_gemma":0.000010276435,"threshold_uncertainty_score":0.3306848},"labels":[],"label_agreement":null},{"id":"W4405631556","doi":"10.47899/ijss.1591168","title":"Sağlık Sektöründe Karar Destek Araçları: İş Zekâsı, Makine Öğrenmesi, Derin Öğrenme ve Yapay Zeka Uygulamaları","year":2024,"lang":"tr","type":"article","venue":"İzmir Sosyal Bilimler Dergisi","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics","score_opus":0.02524931241039707,"score_gpt":0.2834740808280565,"score_spread":0.2582247684176594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405631556","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1303178,0.04271939,0.6758733,0.0531078,0.026847817,0.009036491,0.0029011117,0.021674775,0.03752155],"genre_scores_gemma":[0.89868563,0.0018681531,0.07980195,0.0021814732,0.0017181777,0.0005821722,0.00043651418,0.00045918606,0.014266759],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9870094,0.00069751055,0.0025670184,0.0045533343,0.0023817595,0.0027909998],"domain_scores_gemma":[0.9917752,0.0007391696,0.00070821965,0.0050404896,0.00073663646,0.001000274],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.0020349692,0.0019698339,0.0016426945,0.0014724293,0.00075855246,0.0038840813,0.0049811597,0.001260095,0.00094220444],"category_scores_gemma":[0.00045057412,0.0019547765,0.00094632286,0.0040630763,0.00095826935,0.0031082926,0.0023724728,0.0022765868,0.0054562152],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045133493,0.002398271,0.0049283444,0.0032381818,0.0016902812,0.0036711046,0.007298541,0.0003170322,0.083899856,0.24243282,0.3732572,0.27641705],"study_design_scores_gemma":[0.0018640435,0.0010269148,0.029970286,0.002433329,0.00046975695,0.000806427,0.00045837148,0.06760643,0.07916064,0.016141413,0.7954451,0.0046172854],"about_ca_topic_score_codex":0.00018231398,"about_ca_topic_score_gemma":0.00012167157,"teacher_disagreement_score":0.7683678,"about_ca_system_score_codex":0.0010015587,"about_ca_system_score_gemma":0.0013867336,"threshold_uncertainty_score":0.9999711},"labels":[],"label_agreement":null},{"id":"W4405633240","doi":"10.1109/icdabi63787.2024.10800738","title":"Machine Learning for Detecting Financial Statement Fraud: A Bibliometric Analysis","year":2024,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Financial statement; Computer science; Statement (logic); Financial statement analysis; Accounting; Data science; Artificial intelligence; Financial analysis; Business; Political science","score_opus":0.03248137288188185,"score_gpt":0.32059494638824376,"score_spread":0.2881135735063619,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405633240","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00087769434,0.0004821394,0.99610513,0.00040185623,0.00012497787,0.00018568031,0.000012421325,0.0012626561,0.00054745056],"genre_scores_gemma":[0.680861,0.00008351745,0.31793642,0.00011391794,0.000036567195,0.00010453114,0.000031395317,0.000008475903,0.0008241661],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987726,0.00003592061,0.00028592395,0.0004350813,0.00023703765,0.00023343848],"domain_scores_gemma":[0.99916995,0.00026939117,0.00006610023,0.00035420258,0.00009274593,0.000047590143],"candidate_categories":["bibliometrics"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.00086075993,0.00010156189,0.00014454662,0.041789833,0.00013636755,0.00051433797,0.0005098724,0.000041621664,0.000051624127],"category_scores_gemma":[0.00037136758,0.00008762251,0.00011872995,0.13536423,0.000010610008,0.0005466641,0.00016944547,0.00013876698,0.000034280456],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002988028,0.000026509217,0.0014438091,0.00005701039,0.00012873687,0.0000047797676,0.00014002321,0.00033344066,0.0014198666,0.046185795,0.002871654,0.9473854],"study_design_scores_gemma":[0.00006791637,0.00007963761,0.0027915465,0.000009792168,0.00004433062,0.000001181879,0.0000054458574,0.8943286,0.009399238,0.002084208,0.09104623,0.00014187157],"about_ca_topic_score_codex":0.000057039866,"about_ca_topic_score_gemma":0.00001644976,"teacher_disagreement_score":0.9472435,"about_ca_system_score_codex":0.00007529418,"about_ca_system_score_gemma":0.000060454757,"threshold_uncertainty_score":0.9690707},"labels":[{"model":"gemma","categories":["bibliometrics"],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["bibliometrics"],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4405791979","doi":"10.18280/isi.290620","title":"Unveiling Financial Fraud: A Comprehensive Review of Machine Learning and Data Mining Techniques","year":2024,"lang":"en","type":"review","venue":"Ingénierie des systèmes d information","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Data science; Computer science; Business; Finance; Data mining","score_opus":0.056533209819596274,"score_gpt":0.3408913100692309,"score_spread":0.28435810024963465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405791979","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.4270008e-7,0.85837114,0.13897333,0.000021189797,0.0001439656,0.00084323966,0.00029244157,0.00065198314,0.0007025006],"genre_scores_gemma":[0.000004758634,0.8966017,0.1008584,0.00012728022,0.00004759788,0.00013846575,0.002175743,0.00002290184,0.000023161641],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99694085,0.00022235117,0.0017209423,0.0004701533,0.00037833332,0.00026739502],"domain_scores_gemma":[0.9966084,0.00022126998,0.0015014556,0.0012663954,0.0003361443,0.00006637626],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011324928,0.0004440091,0.0013849956,0.00062551047,0.0001578163,0.00033828165,0.0016971844,0.00028238853,0.000007706041],"category_scores_gemma":[0.0010680147,0.00037964788,0.00014062409,0.0011235065,0.00015326933,0.0035337482,0.0017958737,0.0005684831,0.000038195965],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.290918e-7,0.0000037605255,6.2648394e-7,0.18483792,0.000025096753,0.0000018178828,0.00019050179,3.725182e-8,5.893194e-7,0.0011918998,0.002296349,0.8114509],"study_design_scores_gemma":[0.000026792733,0.000043343865,8.760497e-7,0.1586403,0.00016520747,0.000105330306,0.000014176974,0.002201818,0.0000152584735,0.00019015213,0.83830357,0.00029317266],"about_ca_topic_score_codex":0.000018699313,"about_ca_topic_score_gemma":8.5442593e-7,"teacher_disagreement_score":0.83600724,"about_ca_system_score_codex":0.00019434564,"about_ca_system_score_gemma":0.00044007818,"threshold_uncertainty_score":0.99986553},"labels":[],"label_agreement":null},{"id":"W4406203384","doi":"10.61091/jcmcc123-24","title":"Deep Learning Model Based Research on Anomaly Detection and Financial Fraud Identification in Corporate Financial Reporting Statements","year":2024,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Financial statement; Anomaly detection; Audit; Artificial neural network; Autoencoder; Accounting; Artificial intelligence; Computer science; Financial ratio; Anomaly (physics); Identification (biology); F1 score; Machine learning; Finance; Data mining; Business","score_opus":0.08164214882031957,"score_gpt":0.35736388435227084,"score_spread":0.2757217355319513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406203384","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40898374,0.000121228615,0.5871869,0.00010290637,0.003192766,0.00024858746,8.02344e-7,0.000083598774,0.00007949312],"genre_scores_gemma":[0.98355746,0.000036159665,0.016002253,0.000016336991,0.00034814142,0.000009055519,0.0000018437473,0.000022916985,0.0000058409955],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99596936,0.00027744716,0.0020109455,0.00044911704,0.00092651864,0.00036662174],"domain_scores_gemma":[0.99619216,0.00061807357,0.0021188722,0.0003076692,0.00064088235,0.00012235076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008662095,0.0002264486,0.00048206918,0.0008520704,0.00038372978,0.00086802826,0.00048093576,0.00019200996,7.469809e-7],"category_scores_gemma":[0.0031237795,0.00022211499,0.00007783066,0.0010162472,0.00008519908,0.0008250467,0.00025284258,0.0011657943,0.0000016369082],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000085103275,0.0004123066,0.0002624668,0.00039373816,0.00001798929,0.00011852808,0.001660576,0.0025716512,0.008111841,0.9416048,0.00008282379,0.044678155],"study_design_scores_gemma":[0.0007028776,0.00040076632,0.0005889179,0.00043663866,0.000008310319,0.000021432685,0.000042774736,0.6067991,0.0031837155,0.38759306,0.000073412535,0.00014897894],"about_ca_topic_score_codex":0.000008579627,"about_ca_topic_score_gemma":0.000001482698,"teacher_disagreement_score":0.6042274,"about_ca_system_score_codex":0.00024482567,"about_ca_system_score_gemma":0.00036417996,"threshold_uncertainty_score":0.9057587},"labels":[],"label_agreement":null},{"id":"W4406271657","doi":"10.48550/arxiv.2501.04903","title":"Analyzing decision tree bias towards the minority class","year":2025,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Decision tree; Computer science; Psychology; Artificial intelligence","score_opus":0.1373005555953687,"score_gpt":0.23467947601991754,"score_spread":0.09737892042454885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406271657","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012034994,0.000075776356,0.9718179,0.00067068706,0.0005945495,0.00035321954,0.000059601716,0.00063158973,0.013761643],"genre_scores_gemma":[0.9756793,0.0004927471,0.020048002,0.00022676644,0.00007246066,0.0000036276956,0.000037644862,0.000008743456,0.003430705],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976135,0.00026656533,0.00030570722,0.0013114415,0.00016173649,0.00034107154],"domain_scores_gemma":[0.9954346,0.00037624038,0.00035489758,0.003450171,0.00028062135,0.000103505154],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0007062095,0.00033286642,0.00034589597,0.00042061007,0.0002882838,0.00028932153,0.0055165114,0.00034900254,0.000014287147],"category_scores_gemma":[0.00021929164,0.00029591194,0.00026840976,0.001355039,0.00015687491,0.0004516265,0.004746747,0.0008138973,0.000047777532],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041941854,0.0001546897,0.006865968,0.00010462873,0.00015564208,0.0001196864,0.0001990981,0.010902237,0.00005722564,0.85260653,0.018516973,0.11027537],"study_design_scores_gemma":[0.00043421175,0.000043528864,0.01911725,0.00025523666,0.0001419386,0.0000043619675,0.00005674824,0.7830676,0.0016107224,0.17288344,0.021574467,0.0008105119],"about_ca_topic_score_codex":0.000276755,"about_ca_topic_score_gemma":0.00014157283,"teacher_disagreement_score":0.9636443,"about_ca_system_score_codex":0.00038773494,"about_ca_system_score_gemma":0.0004390422,"threshold_uncertainty_score":0.9999493},"labels":[],"label_agreement":null},{"id":"W4406458801","doi":"10.1109/bigdata62323.2024.10825957","title":"Big data analytic of US Medicare Claims of healthcare service informatics and billing fraud","year":2024,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Big data; Health informatics; Informatics; Health care; Healthcare service; Computer science; Data science; Data mining; Engineering","score_opus":0.08696358680796142,"score_gpt":0.3216540670007815,"score_spread":0.23469048019282007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406458801","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055078752,0.00053416006,0.9885015,0.0042342125,0.00017497313,0.00014439513,0.00017448897,0.00028094708,0.0004474824],"genre_scores_gemma":[0.80146056,0.00035168705,0.19733639,0.0006694038,0.000027566286,0.0000034443399,0.00012576394,0.0000062891504,0.000018881452],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988631,0.000024751163,0.00048391634,0.00020571915,0.00030190762,0.000120585835],"domain_scores_gemma":[0.99811107,0.00012490478,0.00012843698,0.0014049388,0.00016788267,0.00006274631],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004561621,0.00008171362,0.00017474109,0.00019635432,0.000027421731,0.000059982918,0.0012838836,0.000063901665,0.0000051982242],"category_scores_gemma":[0.00003991381,0.00006402085,0.000014246629,0.0008815866,0.00005492491,0.0006519802,0.0007745487,0.00011462383,0.000004330457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053613253,0.00005727986,0.004214081,0.0071892045,0.000111522364,0.0000065084305,0.0065742377,0.00003158451,0.0017366239,0.19058469,0.009282913,0.78020597],"study_design_scores_gemma":[0.000094916046,0.000059919654,0.0013838989,0.00043893827,0.00001620661,0.000012622423,0.0005262939,0.97099715,0.007399943,0.002677384,0.016246628,0.00014608422],"about_ca_topic_score_codex":0.00043915218,"about_ca_topic_score_gemma":0.00016667908,"teacher_disagreement_score":0.97096556,"about_ca_system_score_codex":0.000016767204,"about_ca_system_score_gemma":0.00018144926,"threshold_uncertainty_score":0.26106945},"labels":[],"label_agreement":null},{"id":"W4406597461","doi":"10.47363/jaicc/2022(1)419","title":"Artificial Intelligence-Powered Credit Card Fraud Detection: Feature Engineering and Machine Learning Approach’s","year":2022,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence & Cloud Computing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Tellabs (Canada)","funders":"","keywords":"Credit card fraud; Feature engineering; Credit card; Feature (linguistics); Computer science; Artificial intelligence; Computer security; Deep learning; World Wide Web; Payment","score_opus":0.03934615702084595,"score_gpt":0.26667608717306435,"score_spread":0.2273299301522184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406597461","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02014735,0.000623826,0.9757168,0.0006695425,0.0022436494,0.00021924751,0.000007960797,0.00028186836,0.00008972283],"genre_scores_gemma":[0.8848863,0.000047966558,0.1138501,0.00009393585,0.0010577511,0.000008038436,0.000006643245,0.00003211796,0.00001714554],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99627966,0.00031852024,0.0013451474,0.0005940912,0.00092056295,0.00054202025],"domain_scores_gemma":[0.99749416,0.00036137094,0.0010668671,0.0004979717,0.00036454955,0.00021509251],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0024479602,0.00034895103,0.0005253946,0.0005778139,0.00091429846,0.0004971801,0.0015919608,0.00013205892,0.000025178786],"category_scores_gemma":[0.0005318013,0.0003650573,0.0002109814,0.0013234382,0.00010860706,0.00052926684,0.0009304486,0.0020977613,0.0000072906655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000087969864,0.00020528161,0.00008997306,0.000040473056,0.00007863317,0.00008201624,0.0032738536,0.20952374,0.0146600045,0.03797254,0.00013677178,0.73384875],"study_design_scores_gemma":[0.000020705083,0.00050737656,0.00004601204,0.00004348832,0.000022725484,0.0006950758,0.0012018831,0.9197237,0.06568174,0.0073903864,0.0042798864,0.0003870148],"about_ca_topic_score_codex":0.000031484353,"about_ca_topic_score_gemma":0.0000047985704,"teacher_disagreement_score":0.86473894,"about_ca_system_score_codex":0.00028461046,"about_ca_system_score_gemma":0.00013521404,"threshold_uncertainty_score":0.99988014},"labels":[],"label_agreement":null},{"id":"W4406844097","doi":"10.1007/978-3-031-78980-9_8","title":"ITERADE - ITERative Anomaly Detection Ensemble for Credit Card Fraud Detection","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Credit card fraud; Anomaly detection; Credit card; Anomaly (physics); Artificial intelligence; World Wide Web; Physics","score_opus":0.016502409019085135,"score_gpt":0.25954134134901335,"score_spread":0.2430389323299282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406844097","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025665224,0.00017934048,0.99316394,0.0004657129,0.0027449345,0.0010958757,0.000051232582,0.00056165963,0.0017116596],"genre_scores_gemma":[0.300717,0.00004410109,0.6955657,0.0013645145,0.0008380849,0.00021358536,0.00004305356,0.000046601966,0.0011673416],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99600416,0.00005488602,0.00065257034,0.001951,0.0007088042,0.00062856695],"domain_scores_gemma":[0.9964771,0.00066285284,0.0004396173,0.0017212043,0.0005787213,0.0001204987],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00077266904,0.0005817168,0.00055594573,0.0014192711,0.00047895225,0.00086886494,0.0026232565,0.0005184784,0.0000045047254],"category_scores_gemma":[0.00024717834,0.00058778684,0.00019086667,0.0009058808,0.00036514614,0.0012444236,0.0007601424,0.0007568081,0.000014515948],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015620451,0.000019100682,0.000006205275,0.000062451545,0.000015030391,0.0000083704435,0.000337269,0.00077960035,0.008913154,0.0073745684,0.00010024987,0.98236835],"study_design_scores_gemma":[0.00033683787,0.00042238354,0.000099901226,0.00037523857,0.000018220004,0.000043959768,2.4242445e-7,0.5657411,0.29496804,0.11974732,0.017427836,0.0008188918],"about_ca_topic_score_codex":0.000031649553,"about_ca_topic_score_gemma":0.0001971286,"teacher_disagreement_score":0.9815495,"about_ca_system_score_codex":0.00075045606,"about_ca_system_score_gemma":0.00045579736,"threshold_uncertainty_score":0.99965733},"labels":[],"label_agreement":null},{"id":"W4406911682","doi":"10.3390/math13030434","title":"Bi-Partitioned Feature-Weighted K-Means Clustering for Detecting Insurance Fraud Claim Patterns","year":2025,"lang":"en","type":"article","venue":"Mathematics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Feature (linguistics); Insurance fraud; k-means clustering; Computer science; Pattern recognition (psychology); Data mining; Artificial intelligence; Business; Actuarial science","score_opus":0.0228842605894272,"score_gpt":0.28191660962032333,"score_spread":0.2590323490308961,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406911682","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048885434,0.000025068839,0.9914597,0.0011180944,0.0002465547,0.00049181876,0.000044068314,0.00072269596,0.0010034529],"genre_scores_gemma":[0.33202618,0.00001021548,0.66688097,0.00035607122,0.0000352011,0.00021568204,0.000015802687,0.000014679912,0.000445161],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885035,0.000028376866,0.00034195583,0.00033369396,0.00017336382,0.00027227815],"domain_scores_gemma":[0.99848765,0.0002658225,0.000188357,0.000882597,0.00013621677,0.000039363767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003225264,0.00016156067,0.00021611627,0.00016388543,0.00022293958,0.00021075919,0.00082187244,0.00010353309,0.0000044142967],"category_scores_gemma":[0.00017821832,0.00015590675,0.00006960611,0.0004297142,0.000025174633,0.00034080536,0.00021591707,0.00014517317,0.000014028566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046535908,0.0011231109,0.006538827,0.005991715,0.0002974785,0.000018299066,0.009945759,0.00032127977,0.054714456,0.6935774,0.03099917,0.19642593],"study_design_scores_gemma":[0.0006342601,0.00006441421,0.0025328621,0.00066725345,0.000019183854,0.000012229711,0.00016320287,0.7886003,0.11269261,0.086144954,0.008017372,0.00045135253],"about_ca_topic_score_codex":0.00000292023,"about_ca_topic_score_gemma":0.000016850574,"teacher_disagreement_score":0.788279,"about_ca_system_score_codex":0.00007547418,"about_ca_system_score_gemma":0.00003653905,"threshold_uncertainty_score":0.63576925},"labels":[],"label_agreement":null},{"id":"W4407128969","doi":"10.1109/icit63607.2024.10859521","title":"Machine learning based fraudulent detection system for financial transactions","year":2024,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.014598905146765413,"score_gpt":0.24411352268375186,"score_spread":0.22951461753698646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407128969","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002618168,0.00006485147,0.9953637,0.00050908275,0.0005324508,0.00025172884,0.000018523207,0.0028447232,0.00038877485],"genre_scores_gemma":[0.8541167,0.0000038823828,0.14502594,0.00006365999,0.00004473679,0.00022342784,0.00001235745,0.000009349015,0.0004999738],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926615,0.000031899566,0.00015716226,0.00029181165,0.00011778603,0.00013522043],"domain_scores_gemma":[0.9995552,0.00009170752,0.00002598914,0.00024414898,0.000049405753,0.000033568464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024255566,0.00008148068,0.00007570973,0.00014564749,0.00016426465,0.00017707085,0.00024948822,0.00005673663,0.000014420214],"category_scores_gemma":[0.000024053688,0.00007353325,0.00006887959,0.00031251585,0.000010374892,0.0003437454,0.0000094924135,0.00013225562,0.000033843473],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017895869,0.000062061285,0.000010484026,0.0005473385,0.000018417182,0.0000064512515,0.00016516539,0.0018496029,0.047348674,0.14103632,0.0009773277,0.8079603],"study_design_scores_gemma":[0.000070724745,0.000055687244,0.000025144596,0.000030345513,0.0000044035082,0.000004985217,0.000004761847,0.7665124,0.17571355,0.0002115033,0.05729053,0.000075971446],"about_ca_topic_score_codex":0.000022882597,"about_ca_topic_score_gemma":0.00001706824,"teacher_disagreement_score":0.8540905,"about_ca_system_score_codex":0.000117434116,"about_ca_system_score_gemma":0.000066840585,"threshold_uncertainty_score":0.29985988},"labels":[],"label_agreement":null},{"id":"W4407129200","doi":"10.1109/icitr64794.2024.10857748","title":"Improving Class Imbalance in the Classification of Multi-Dimensional Data: Interpretable Model Design and Evaluation","year":2024,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"International Development Research Centre","keywords":"Class (philosophy); Computer science; Artificial intelligence; Data modeling; Machine learning; Data mining; Database","score_opus":0.1265287147301302,"score_gpt":0.35352046972844653,"score_spread":0.22699175499831634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407129200","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001926191,0.00038067353,0.99575293,0.0009810291,0.00007283666,0.00051574537,0.000014911767,0.00014667338,0.00020903243],"genre_scores_gemma":[0.67370963,0.000017076583,0.32601887,0.000104011415,0.000006551316,0.000065817156,0.000036767018,0.000004698131,0.000036594214],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99840903,0.00022686177,0.0003156687,0.000525403,0.00038522642,0.00013782045],"domain_scores_gemma":[0.9983376,0.0002961516,0.00008713204,0.0011481885,0.00011075584,0.000020143074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032625813,0.000099983205,0.00010589672,0.00014374548,0.000043162752,0.00019070166,0.0011535751,0.000057089743,0.0000029151045],"category_scores_gemma":[0.00015169826,0.00007083974,0.0000137244515,0.00039744456,0.00006087872,0.0015589544,0.0003214935,0.00014754763,0.000004684058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021979055,0.00023933947,0.00027963036,0.00016690846,0.00002524437,0.0000032436708,0.0016394781,0.013809652,0.44028568,0.30434132,0.009948713,0.22923881],"study_design_scores_gemma":[0.00011421842,0.000017067652,0.0016256714,0.000043198095,0.0000075187763,0.000006147043,0.000030892283,0.99218976,0.002850746,0.0029493154,0.00008469182,0.00008074408],"about_ca_topic_score_codex":0.000030285319,"about_ca_topic_score_gemma":0.000012239273,"teacher_disagreement_score":0.97838014,"about_ca_system_score_codex":0.00006268546,"about_ca_system_score_gemma":0.00020845416,"threshold_uncertainty_score":0.2888761},"labels":[],"label_agreement":null},{"id":"W4407217313","doi":"10.1016/j.neucom.2025.129528","title":"Multi-level analyzation of imbalance to resolve non-IID-ness in federated learning","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Institute for Information and Communications Technology Promotion; Seoul National University; Ministry of Health and Welfare; National Research Foundation of Korea; Ministry of Food and Drug Safety; Ministry of Trade, Industry and Energy","keywords":"Computer science; Federated learning; Artificial intelligence","score_opus":0.028048570370535254,"score_gpt":0.3093686405149193,"score_spread":0.28132007014438404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407217313","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056584623,0.00000941027,0.94183415,0.00042317837,0.00012836566,0.00028491486,0.0000016173055,0.0002445123,0.000489218],"genre_scores_gemma":[0.748415,0.000002476833,0.25111276,0.00032023864,0.0000113568185,0.000014078746,0.0000060544808,0.0000071205777,0.00011091216],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984443,0.00012868205,0.0004737186,0.0005132358,0.00018048646,0.0002595361],"domain_scores_gemma":[0.9990079,0.00016155098,0.00019968733,0.00039934035,0.00019177559,0.00003976753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044432102,0.00013470123,0.00022693019,0.00045190228,0.00012904106,0.00011505342,0.0007436202,0.00006272931,8.17799e-7],"category_scores_gemma":[0.00035314882,0.00015160022,0.0000322207,0.0019895001,0.00002011924,0.00025199036,0.0004278041,0.00025156612,0.0000068999448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038835457,0.00036005088,0.12617883,0.00022384991,0.00002308875,0.000028206707,0.0018288123,0.050377175,0.5295727,0.0076216385,0.0012183888,0.28252837],"study_design_scores_gemma":[0.00028059533,0.000027956674,0.2845511,0.00015654968,0.0000013809442,0.0000012300248,0.000021795951,0.66468084,0.049674947,0.000056796438,0.00043181228,0.00011497066],"about_ca_topic_score_codex":0.00005144946,"about_ca_topic_score_gemma":0.000021276572,"teacher_disagreement_score":0.6918304,"about_ca_system_score_codex":0.00006385408,"about_ca_system_score_gemma":0.00008205429,"threshold_uncertainty_score":0.61820775},"labels":[],"label_agreement":null},{"id":"W4407421575","doi":"10.62754/joe.v4i2.6377","title":"Advanced Machine Learning Approaches for Credit Card Fraud Detection in the USA: A Comprehensive Analysis","year":2025,"lang":"en","type":"article","venue":"Journal of Ecohumanism","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Credit card fraud; Credit card; Computer science; Computer security; Machine learning; Business; Data science; Artificial intelligence; World Wide Web","score_opus":0.054239590415394764,"score_gpt":0.2987704024424302,"score_spread":0.24453081202703542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407421575","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022893092,0.00020656512,0.97544724,0.00065742695,0.00018407758,0.0002022612,0.000004033311,0.000027361115,0.00037796667],"genre_scores_gemma":[0.9549813,0.000051565385,0.044532795,0.00023592127,0.000056687233,0.000029571123,0.0000055605133,0.0000042751913,0.000102292026],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885404,0.00015790088,0.0004463381,0.00018491497,0.00020849521,0.0001483155],"domain_scores_gemma":[0.998685,0.00030582905,0.00045098737,0.00033660504,0.00019958284,0.00002196877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071381533,0.00010376799,0.0002773364,0.00059727306,0.00016724909,0.00013580766,0.0008785121,0.000056115903,0.0000029566816],"category_scores_gemma":[0.00013826297,0.000076900615,0.00018689728,0.00083444547,0.000031217434,0.00046606452,0.00007520402,0.00035938816,0.0000012283122],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037296108,0.0009544572,0.024579389,0.00029546916,0.0026340764,0.00007506339,0.009512628,0.089145444,0.030132538,0.26152623,0.0029966598,0.5777751],"study_design_scores_gemma":[0.0022458453,0.0009072969,0.22793016,0.00010452451,0.00050106423,0.00006696685,0.00089242344,0.6413352,0.0212174,0.032582827,0.07174232,0.00047396478],"about_ca_topic_score_codex":0.000023205812,"about_ca_topic_score_gemma":0.00025020097,"teacher_disagreement_score":0.93208826,"about_ca_system_score_codex":0.00009856266,"about_ca_system_score_gemma":0.0000471027,"threshold_uncertainty_score":0.3135916},"labels":[],"label_agreement":null},{"id":"W4407421883","doi":"10.1016/j.bar.2025.101560","title":"Reprint of: The use of machine learning algorithms to predict financial statement fraud","year":2025,"lang":"en","type":"article","venue":"The British Accounting Review","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":6,"is_retracted":true,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Roads University","funders":"","keywords":"Reprint; Statement (logic); Financial statement; Computer science; Machine learning; Algorithm; Artificial intelligence; Finance; Accounting; Economics; Political science; Law; Audit","score_opus":0.02836881766134944,"score_gpt":0.28204777033002026,"score_spread":0.2536789526686708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407421883","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006469077,0.0254705,0.95566493,0.0086618,0.0004639599,0.0023286415,0.00007211185,0.00032112,0.0005478269],"genre_scores_gemma":[0.3087733,0.1640258,0.49039397,0.031069044,0.00023794139,0.0009592965,0.00006654954,0.000083485815,0.0043905983],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99844146,0.00017032355,0.00064466597,0.00027576907,0.00030494304,0.00016281614],"domain_scores_gemma":[0.99814636,0.00014552343,0.00043207337,0.001035876,0.00022319237,0.000016974265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015726469,0.00009141338,0.00026521704,0.000031033884,0.0002093969,0.0001909538,0.0015403313,0.000027187192,0.000010941973],"category_scores_gemma":[0.0020585263,0.00006932172,0.000088367946,0.0007383521,0.00006085071,0.0002656096,0.0010255261,0.00020747325,0.0000056112253],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001420515,0.000038599017,0.0027823711,0.000946897,0.000013598222,0.0000011767733,0.00004669218,0.000047210866,0.00025988463,0.00327841,0.030672768,0.96191096],"study_design_scores_gemma":[0.00017186652,0.00003858377,0.068437666,0.02155442,0.000054132564,0.000021334246,0.0000043749537,0.009278743,0.004988113,0.001468909,0.8937555,0.00022634039],"about_ca_topic_score_codex":0.00058433425,"about_ca_topic_score_gemma":0.000027840779,"teacher_disagreement_score":0.96168464,"about_ca_system_score_codex":0.000039009334,"about_ca_system_score_gemma":0.00010891048,"threshold_uncertainty_score":0.28623444},"labels":[],"label_agreement":null},{"id":"W4407549728","doi":"10.2139/ssrn.5068697","title":"Enhancing Credit Card Fraud Detection: A Comprehensive Study of Machine Learning Algorithms and Performance Evaluation","year":2025,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wycliffe College","funders":"","keywords":"Credit card fraud; Credit card; Computer science; Machine learning; Artificial intelligence; Algorithm; World Wide Web; Payment","score_opus":0.014703629527065797,"score_gpt":0.28151028985377674,"score_spread":0.26680666032671096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407549728","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43927598,0.0011457087,0.5589925,0.00008094737,0.00014098464,0.00022969513,4.6215214e-7,0.00006373884,0.00006995962],"genre_scores_gemma":[0.99628425,0.0010344177,0.0024798485,0.000021285763,0.000050467224,0.000023743838,0.0000020974016,0.00000606786,0.00009784066],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99816734,0.0002458281,0.0003469117,0.00026256684,0.00040263662,0.0005747399],"domain_scores_gemma":[0.99895,0.0000723485,0.00026136514,0.00027277056,0.0004135403,0.000029941388],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015827708,0.000119961376,0.00018715559,0.00026754543,0.000321896,0.00007731494,0.00040094645,0.00004822842,0.0000018846616],"category_scores_gemma":[0.000090839276,0.00011467542,0.000030021374,0.00047583057,0.00002938828,0.00048153818,0.0001367571,0.0011177646,0.0000012889609],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000383808,0.0001355259,0.004610602,0.0000221441,0.0001687092,9.364721e-7,0.0010638176,0.00033969592,0.014066612,0.004150955,0.000009739093,0.9753929],"study_design_scores_gemma":[0.0035770067,0.0049833553,0.0618665,0.00017833605,0.00017134871,0.00039084884,0.0060447003,0.82763624,0.07044842,0.023055773,0.0011282396,0.0005192502],"about_ca_topic_score_codex":0.00007221292,"about_ca_topic_score_gemma":0.00025761,"teacher_disagreement_score":0.9748736,"about_ca_system_score_codex":0.00047727115,"about_ca_system_score_gemma":0.0006838947,"threshold_uncertainty_score":0.4856193},"labels":[],"label_agreement":null},{"id":"W4407592061","doi":"10.71070/oaml.v5i1.76","title":"MDD-based Domain Adaptation Algorithm for Improving the Applicability of the Artificial Neural Network in Vehicle Insurance Claim Fraud Detection","year":2025,"lang":"en","type":"article","venue":"Optimizations in Applied Machine Learning","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Artificial neural network; Computer science; Adaptation (eye); Domain adaptation; Domain (mathematical analysis); Insurance fraud; Artificial intelligence; Machine learning; Business; Finance; Psychology; Mathematics; Neuroscience","score_opus":0.009857638806303607,"score_gpt":0.24129989383251746,"score_spread":0.23144225502621385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407592061","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035892874,0.000027797467,0.9940688,0.0007150089,0.00010901377,0.0011516932,0.000008817676,0.00012651148,0.00020308832],"genre_scores_gemma":[0.67594665,0.0000017762451,0.3233763,0.00011680052,0.000017983946,0.0005087074,0.00001671646,0.000007739971,0.000007315597],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857765,0.00020042766,0.0004735093,0.000370544,0.00015701237,0.0002208476],"domain_scores_gemma":[0.998673,0.0004038342,0.00027026364,0.0005692123,0.000069800466,0.0000138628975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00099929,0.00012705213,0.00015995282,0.00013843058,0.00038802088,0.00007670152,0.00066054217,0.000089145535,0.0000012212262],"category_scores_gemma":[0.00015855009,0.00010166626,0.00004793775,0.0018580264,0.000095000665,0.00013101356,0.00015318138,0.00042859057,3.9296106e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013062868,0.00003789985,0.001640542,0.000012312233,0.0000016340912,3.5508425e-8,0.000111411675,0.73923177,0.0017482969,0.012244884,0.0000023217344,0.24495584],"study_design_scores_gemma":[0.0003370562,0.00001493078,0.008911888,0.000015405047,0.0000032553958,1.6385245e-7,0.00005911149,0.9801443,0.004277267,0.0059730527,0.0001749645,0.00008859532],"about_ca_topic_score_codex":0.00008471395,"about_ca_topic_score_gemma":0.00023802741,"teacher_disagreement_score":0.6723574,"about_ca_system_score_codex":0.0001208394,"about_ca_system_score_gemma":0.00008648419,"threshold_uncertainty_score":0.41458297},"labels":[],"label_agreement":null},{"id":"W4407614550","doi":"10.21203/rs.3.rs-6026136/v1","title":"Real-Time Financial Fraud Detection Using Adaptive Graph Neural Networks and Federated Learning","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Financial fraud; Artificial neural network; Adaptive learning; Graph; Artificial intelligence; Machine learning; Business; Accounting; Theoretical computer science","score_opus":0.05770605325976844,"score_gpt":0.3612099117997352,"score_spread":0.30350385853996675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407614550","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028369416,0.00024331166,0.96842766,0.00017267634,0.0002494384,0.0010212634,0.000033036664,0.0008490869,0.0006340961],"genre_scores_gemma":[0.97476405,0.00062931987,0.023627445,0.000024849323,0.00022904511,0.00020488084,0.000104868,0.000027366692,0.00038819484],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958606,0.001272273,0.00036467426,0.001116898,0.0007189257,0.0006666487],"domain_scores_gemma":[0.9975573,0.000422056,0.00019534721,0.00079603004,0.00088780007,0.00014146288],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0016695246,0.00028831663,0.00035544782,0.0008076712,0.000968543,0.00089677394,0.0009320383,0.0005478742,0.0000074703253],"category_scores_gemma":[0.0005618915,0.000310213,0.00008873968,0.0013537118,0.00018927202,0.0004100523,0.0030141105,0.0027895316,0.000005361433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005915817,0.00043075587,0.0038372148,0.0017760101,0.0002579768,0.00027754533,0.0020783348,0.17068362,0.036230005,0.021954734,0.0052230647,0.75665915],"study_design_scores_gemma":[0.00012983919,0.00015373236,0.0036913313,0.00040277292,0.0000054111797,0.0000059382983,0.0000307507,0.9900584,0.0023381657,0.0027203953,0.00019450695,0.00026874954],"about_ca_topic_score_codex":0.00080175325,"about_ca_topic_score_gemma":0.00004506392,"teacher_disagreement_score":0.9463946,"about_ca_system_score_codex":0.00035315918,"about_ca_system_score_gemma":0.00046898573,"threshold_uncertainty_score":0.999935},"labels":[],"label_agreement":null},{"id":"W4407626533","doi":"10.1016/j.mlwa.2025.100630","title":"Predicting classification errors using NLP-based machine learning algorithms and expert opinions","year":2025,"lang":"en","type":"article","venue":"Machine Learning with Applications","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; Western University","funders":"","keywords":"Artificial intelligence; Computer science; Machine learning; Natural language processing","score_opus":0.02403382708901836,"score_gpt":0.3024235520663833,"score_spread":0.27838972497736497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407626533","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014734126,0.00040704876,0.99144393,0.0034469278,0.00004617346,0.00072579697,0.000020557607,0.0015034233,0.0009327297],"genre_scores_gemma":[0.58244276,0.000055495988,0.41539982,0.00032488685,0.00005179716,0.0008125415,0.00047594353,0.000038170077,0.00039856322],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99783975,0.00021371203,0.00043191106,0.0008512286,0.0003022584,0.00036115682],"domain_scores_gemma":[0.99818474,0.0002872014,0.00035291296,0.0008640808,0.00018688358,0.00012417737],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00048522753,0.00028942563,0.00025699695,0.00043825182,0.0012122501,0.00028034535,0.00075769064,0.00012242963,0.000007949267],"category_scores_gemma":[0.00015826679,0.00027459065,0.00004655947,0.0013879843,0.00016258347,0.00043430162,0.00024818748,0.0007621329,0.00000873493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005618697,0.0005429441,0.48969924,0.00022133296,0.0001629521,0.00000480424,0.0012342987,0.022630684,0.022623323,0.17076239,0.00035830654,0.29170352],"study_design_scores_gemma":[0.00042420314,0.00006717618,0.010721056,0.00008437423,0.000020056446,0.000012307894,0.00007497886,0.93198705,0.0013471572,0.00033033558,0.05465633,0.0002749976],"about_ca_topic_score_codex":0.00029024278,"about_ca_topic_score_gemma":0.000043713302,"teacher_disagreement_score":0.90935636,"about_ca_system_score_codex":0.00014137753,"about_ca_system_score_gemma":0.0001825319,"threshold_uncertainty_score":0.9999706},"labels":[],"label_agreement":null},{"id":"W4408328303","doi":"10.1016/j.neucom.2025.129896","title":"Improving GBDT performance on imbalanced datasets: An empirical study of class-balanced loss functions","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Fields Institute for Research in Mathematical Sciences","funders":"","keywords":"Computer science; Class (philosophy); Artificial intelligence; Machine learning","score_opus":0.023983889575710293,"score_gpt":0.3180405051427695,"score_spread":0.2940566155670592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408328303","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7101345,0.000006459167,0.28730628,0.00022886391,0.00042208703,0.00055797765,0.00003064947,0.0007193486,0.00059384067],"genre_scores_gemma":[0.9896443,0.0000031576399,0.009377777,0.000733894,0.000063863714,0.000048625414,0.00006488258,0.000016015598,0.00004751317],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973773,0.00021034965,0.0006425804,0.00095715316,0.00040374752,0.0004088811],"domain_scores_gemma":[0.99730307,0.00023566866,0.0003476246,0.0018916824,0.00013702067,0.00008496273],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004322447,0.00025910747,0.00033790772,0.00034729688,0.00035610638,0.00015679134,0.0017236553,0.00008334823,0.000002513884],"category_scores_gemma":[0.00013577993,0.00025586458,0.000049058945,0.0012003533,0.00006496031,0.0007354541,0.00066063105,0.0004412338,0.000014078748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024075198,0.0068930727,0.23924573,0.00035284643,0.00010261149,0.00005136612,0.001646852,0.0074262414,0.057119723,0.0058982316,0.009773106,0.67124945],"study_design_scores_gemma":[0.0018833491,0.0024158247,0.2836084,0.00014463768,0.000024977142,0.000014693222,0.00022745538,0.68895245,0.017183509,0.00012777185,0.004906269,0.0005106755],"about_ca_topic_score_codex":0.000022204184,"about_ca_topic_score_gemma":0.0000059912263,"teacher_disagreement_score":0.6815262,"about_ca_system_score_codex":0.00008399267,"about_ca_system_score_gemma":0.00011468682,"threshold_uncertainty_score":0.99998933},"labels":[],"label_agreement":null},{"id":"W4408830429","doi":"10.3390/math13071059","title":"Optimizing Accuracy, Recall, Specificity, and Precision Using ILP","year":2025,"lang":"en","type":"article","venue":"Mathematics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Recall; Computer science; Precision and recall; Artificial intelligence; Machine learning; Psychology; Cognitive psychology","score_opus":0.04936020873309961,"score_gpt":0.3233243585947993,"score_spread":0.2739641498616997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408830429","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0077523263,0.00007902413,0.9876275,0.0003829003,0.00010234153,0.00019552174,0.0000025185295,0.00027928074,0.003578551],"genre_scores_gemma":[0.03581821,0.00006782108,0.9637156,0.000120885365,0.000014210116,0.000007950782,0.0000016015339,0.000006810103,0.0002468918],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991149,0.000028745622,0.00028314904,0.0002584961,0.00016591146,0.00014880169],"domain_scores_gemma":[0.9987058,0.0003161165,0.00012227324,0.0007535753,0.000068908346,0.000033320186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037974442,0.000105786145,0.00015572987,0.00013376563,0.000116156945,0.0002772424,0.00065891974,0.000063206135,0.000005871119],"category_scores_gemma":[0.00024633823,0.00009684212,0.00002316588,0.00033736884,0.00004027919,0.00044116608,0.0005988836,0.00010138496,0.000009535609],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003591889,0.00019368937,0.00010173796,0.00025594071,0.000022052498,0.000005819114,0.001792634,0.000066805726,0.039006237,0.8517173,0.0053929975,0.10144118],"study_design_scores_gemma":[0.00019549365,0.00002217739,0.00021289448,0.00041466972,0.000013470294,0.000022714314,0.0001191811,0.7237224,0.07297717,0.19487238,0.007167315,0.00026014546],"about_ca_topic_score_codex":0.0000021414057,"about_ca_topic_score_gemma":6.0384656e-7,"teacher_disagreement_score":0.7236556,"about_ca_system_score_codex":0.000053326043,"about_ca_system_score_gemma":0.000037762686,"threshold_uncertainty_score":0.39491072},"labels":[],"label_agreement":null},{"id":"W4408879004","doi":"10.18280/ijsse.150214","title":"Hybrid Machine Learning for Fraud Detection: Balancing Accuracy and Security in Digital Transactions","year":2025,"lang":"en","type":"article","venue":"International Journal of Safety and Security Engineering","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Computer security","score_opus":0.0050949619406903115,"score_gpt":0.23487007327550796,"score_spread":0.22977511133481765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408879004","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021483418,0.00035897622,0.9766816,0.00092202815,0.00035526507,0.00007583697,0.000027166569,0.000046736724,0.00004900264],"genre_scores_gemma":[0.9944506,0.0005003131,0.0049338024,0.00004425607,0.000048476,0.000003988721,0.000005524522,0.000004256427,0.000008761876],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99925274,0.000010631088,0.00035089962,0.00013623005,0.00014652986,0.00010296234],"domain_scores_gemma":[0.9993176,0.0002843073,0.000118315555,0.00007269515,0.00016567958,0.000041404594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031121544,0.00008952923,0.00014256635,0.0003034846,0.000058331305,0.00017866494,0.00028743735,0.0000381158,0.0000018230412],"category_scores_gemma":[0.0002899121,0.00009411493,0.000045440902,0.00011556347,0.00001668719,0.0011356513,0.0000498101,0.00032226706,1.3240368e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007731671,0.0004235796,0.00645065,0.0005051213,0.00065813976,0.00015680974,0.0065538776,0.02589767,0.0137130255,0.10397297,0.00011853166,0.84077644],"study_design_scores_gemma":[0.0010731736,0.00006948507,0.003288082,0.00025088497,0.000009032208,0.000301965,0.00005538298,0.9524377,0.009200628,0.009926534,0.023211736,0.00017541758],"about_ca_topic_score_codex":0.000008081437,"about_ca_topic_score_gemma":0.000007104676,"teacher_disagreement_score":0.9729672,"about_ca_system_score_codex":0.000086011416,"about_ca_system_score_gemma":0.000030512243,"threshold_uncertainty_score":0.38378954},"labels":[],"label_agreement":null},{"id":"W4408933702","doi":"10.36227/techrxiv.174320129.94245631/v1","title":"PRACH Preamble Detection as a Multi-Class Classification Problem: A Machine Learning Approach Using SVM","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nokia (Canada)","funders":"","keywords":"Preamble; Support vector machine; Class (philosophy); Artificial intelligence; Computer science; Machine learning; Pattern recognition (psychology); Telecommunications","score_opus":0.07256493185181481,"score_gpt":0.32500472805525754,"score_spread":0.2524397962034427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408933702","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029140347,0.00012863518,0.97547954,0.00036246618,0.0003151085,0.0020444763,0.0000298907,0.0030928636,0.018255632],"genre_scores_gemma":[0.16288257,0.000085004074,0.82861346,0.0001523226,0.00006905849,0.00089429267,0.00038324166,0.000040969324,0.0068790903],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952652,0.0006694255,0.00089989736,0.0019985528,0.00063641224,0.0005305319],"domain_scores_gemma":[0.99590105,0.00012567484,0.0010038705,0.0023152174,0.0005198483,0.00013435128],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014666811,0.00059122936,0.00054265157,0.00075329636,0.0004293001,0.0008363847,0.0023658276,0.0007572608,0.000012364442],"category_scores_gemma":[0.00036304857,0.0005979055,0.00018543436,0.0010004817,0.0000868051,0.0008940185,0.002747388,0.0018718876,0.000040371706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012249527,0.0032416706,0.001891587,0.003944163,0.0005836554,0.000014274855,0.003053962,0.052761175,0.13072604,0.16496429,0.0010959686,0.6376007],"study_design_scores_gemma":[0.00029066575,0.000056938417,0.00018412225,0.00016373539,0.000042834607,0.000030626943,0.000039834,0.9751598,0.015782358,0.0027431985,0.004932679,0.0005732074],"about_ca_topic_score_codex":0.0012107582,"about_ca_topic_score_gemma":0.000059156948,"teacher_disagreement_score":0.9223986,"about_ca_system_score_codex":0.0007365451,"about_ca_system_score_gemma":0.00072520424,"threshold_uncertainty_score":0.99964726},"labels":[],"label_agreement":null},{"id":"W4408940825","doi":"10.3390/jrfm18040179","title":"Secure and Transparent Banking: Explainable AI-Driven Federated Learning Model for Financial Fraud Detection","year":2025,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Business; Computer science; Accounting","score_opus":0.01214165787277058,"score_gpt":0.24623514024161122,"score_spread":0.23409348236884064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408940825","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010058112,0.00024583895,0.9888654,0.00026340818,0.0001856471,0.00024344995,0.000005325002,0.00004203765,0.00009082619],"genre_scores_gemma":[0.94361526,0.0009242033,0.055046212,0.00023224718,0.00004867671,0.00002851413,0.0000016505039,0.0000051791812,0.00009807646],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990946,0.000040368166,0.00033583798,0.00021507521,0.00014333309,0.00017076002],"domain_scores_gemma":[0.9994233,0.0000382095,0.00023939357,0.00011138908,0.00014750515,0.00004015474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041788773,0.0001164014,0.00020116243,0.0002563458,0.00039632578,0.0001731251,0.00021476155,0.0000748077,5.2490515e-7],"category_scores_gemma":[0.00009016058,0.0001097467,0.000052570813,0.00024449517,0.000025561194,0.00042105565,0.00009026604,0.00024901686,1.87473e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016479111,0.00007778318,0.0009415765,0.0001590129,0.000020188296,0.000012190735,0.0008697296,0.0049384446,0.00030489327,0.07384549,0.0017692529,0.91689664],"study_design_scores_gemma":[0.0017803404,0.00039011246,0.01847098,0.00023848935,0.00009514446,0.00001031156,0.000099250814,0.8117398,0.0021201447,0.06482868,0.09995081,0.00027594887],"about_ca_topic_score_codex":0.000006171152,"about_ca_topic_score_gemma":0.000024304898,"teacher_disagreement_score":0.9338191,"about_ca_system_score_codex":0.00005681654,"about_ca_system_score_gemma":0.00005591854,"threshold_uncertainty_score":0.44753405},"labels":[],"label_agreement":null},{"id":"W4409363516","doi":"10.1609/aaai.v39i19.34200","title":"Leveraging Group Classification with Descending Soft Labeling for Deep Imbalanced Regression","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Regression; Group (periodic table); Computer science; Pattern recognition (psychology); Natural language processing; Statistics; Mathematics; Chemistry","score_opus":0.07752779049181162,"score_gpt":0.3199438742680034,"score_spread":0.24241608377619178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409363516","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00996799,0.000029602312,0.9825762,0.0036533764,0.0002718432,0.00080429425,0.0000040779323,0.0002945426,0.0023980779],"genre_scores_gemma":[0.9079399,0.000035783898,0.09141234,0.00024432404,0.00003137752,0.00017855506,0.000003460889,0.000013745047,0.00014046789],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9979496,0.000020151021,0.00057701126,0.0006943544,0.00038668633,0.0003721954],"domain_scores_gemma":[0.9978183,0.00018702743,0.00056796556,0.00051464734,0.0008572853,0.000054774042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067044405,0.0002536949,0.0002772868,0.00024875026,0.00041285026,0.0003474368,0.0021494783,0.00010998971,0.0000054326847],"category_scores_gemma":[0.00048542937,0.00018010814,0.000083566985,0.0010034874,0.00020370501,0.0006485446,0.00027841565,0.00027465067,0.000007003294],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000076238764,0.000068142646,0.00036099902,0.000069021604,0.000010913028,7.443377e-8,0.00030353773,0.000014737972,0.18573654,0.68687385,0.00012418834,0.12636176],"study_design_scores_gemma":[0.000062502506,0.00011274087,0.00049838977,0.0009161977,0.000015611526,0.0000017718103,0.00048442069,0.22729757,0.6488579,0.121275835,0.00025636228,0.00022069392],"about_ca_topic_score_codex":0.000008727158,"about_ca_topic_score_gemma":0.0000046035093,"teacher_disagreement_score":0.8979719,"about_ca_system_score_codex":0.00013081786,"about_ca_system_score_gemma":0.00011020117,"threshold_uncertainty_score":0.7344597},"labels":[],"label_agreement":null},{"id":"W4409376371","doi":"10.5430/ijhe.v14n2p35","title":"Academic Fraud in the Use of Generative Artificial Intelligence (GenAI) for Faculty Promotion and Tenure","year":2025,"lang":"en","type":"article","venue":"International Journal of Higher Education","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Promotion (chess); Generative grammar; Psychology; Artificial intelligence; Political science; Computer science; Law","score_opus":0.1308052673445225,"score_gpt":0.4205395865578941,"score_spread":0.28973431921337156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409376371","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037602298,0.00020810809,0.9165989,0.043726202,0.0014648079,0.00030965902,0.000020301237,0.0000112400185,0.00005846226],"genre_scores_gemma":[0.92831296,0.0000689885,0.070534475,0.0006595427,0.00018102842,0.000036630026,0.000021317242,0.0000027400072,0.0001823422],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99902457,0.00007436301,0.00045956692,0.00012233766,0.00025574054,0.00006344222],"domain_scores_gemma":[0.9985603,0.00016627094,0.00039998873,0.00013385764,0.00072424655,0.000015345075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038705097,0.000064861706,0.000090608715,0.00028510182,0.000028478422,0.00009967916,0.00056390336,0.000058680034,0.0000036467989],"category_scores_gemma":[0.00018720169,0.000047706533,0.00003462192,0.00022984193,0.000043915832,0.0007676866,0.000044228258,0.00016977642,4.8815696e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047954694,0.00034175083,0.0022992943,0.000019877703,0.0000399649,8.9506307e-7,0.0015873263,0.00009484081,0.010148995,0.7460949,0.01246664,0.22685759],"study_design_scores_gemma":[0.00034447666,0.00030315694,0.24974036,0.0005875371,0.00003861162,0.00007272543,0.0003928262,0.010223713,0.12309558,0.54529,0.069650955,0.0002600709],"about_ca_topic_score_codex":0.0000089627665,"about_ca_topic_score_gemma":0.0000024315787,"teacher_disagreement_score":0.89071065,"about_ca_system_score_codex":0.00008660491,"about_ca_system_score_gemma":0.0002182053,"threshold_uncertainty_score":0.1945416},"labels":[],"label_agreement":null},{"id":"W4409418782","doi":"10.70389/pjai.100014","title":"Enhancing Banking Fraud Detection: Role of Machine Learning and Deep Learning Methods","year":2025,"lang":"en","type":"article","venue":"Premier Journal of Artificial Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Machine learning; Business","score_opus":0.02079107149305121,"score_gpt":0.33615785568314827,"score_spread":0.31536678419009706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409418782","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005318516,0.0024000017,0.99125725,0.000111171794,0.00024341121,0.00007402715,2.6786097e-7,0.00006640362,0.00052893045],"genre_scores_gemma":[0.6645164,0.00028474498,0.33510274,0.000021165444,0.000038653365,0.0000022775894,2.465562e-7,0.0000056509543,0.000028137447],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99803424,0.0003916718,0.0008810744,0.00024449208,0.00024947384,0.00019902652],"domain_scores_gemma":[0.9980006,0.0005944552,0.0007049323,0.00021766598,0.0004206997,0.00006164082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023710732,0.00013434612,0.0002916235,0.00040657585,0.00020942563,0.00013790959,0.00061890756,0.00008646561,0.000024298804],"category_scores_gemma":[0.0013371784,0.00012985502,0.000079963684,0.00066663005,0.00008857531,0.0005955826,0.00026150953,0.00070195267,0.000002076799],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001514679,0.000017875554,0.00053472276,0.000017971828,0.000018618639,0.0000014163211,0.0008499308,0.0003449261,0.30894783,0.0087198345,4.7343534e-7,0.68053126],"study_design_scores_gemma":[0.000017240434,0.0000993595,0.00013542784,0.0001245019,0.000014589008,0.000029347353,0.00035736075,0.14880274,0.81281185,0.035538416,0.0019791499,0.00009000511],"about_ca_topic_score_codex":0.000018319051,"about_ca_topic_score_gemma":0.000015565709,"teacher_disagreement_score":0.68044126,"about_ca_system_score_codex":0.00007622391,"about_ca_system_score_gemma":0.0000640662,"threshold_uncertainty_score":0.5295334},"labels":[],"label_agreement":null},{"id":"W4409486158","doi":"10.5006/c2022-17833","title":"Applying Machine Learning Techniques to Identify and Predict Behavior of Rectifier and Groundbed State Change","year":2022,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Rectifier (neural networks); State (computer science); Machine learning; Artificial intelligence; Artificial neural network; Programming language","score_opus":0.042716741800823924,"score_gpt":0.3111382263006084,"score_spread":0.2684214844997845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409486158","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13686898,0.00021748355,0.85738,0.00087135995,0.00012266835,0.0024847235,0.00007177015,0.0015039955,0.0004790725],"genre_scores_gemma":[0.8411218,0.000101766396,0.15437923,0.00036072906,0.000013670279,0.0034852298,0.00002298974,0.000015830698,0.0004987364],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99895126,0.000097890894,0.00020819595,0.00035516065,0.00023880799,0.00014871682],"domain_scores_gemma":[0.99940664,0.000044156383,0.00010718591,0.00033690385,0.00004482,0.000060326267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005867216,0.000095816256,0.00013684254,0.0002240002,0.00019627402,0.000092649316,0.00037890847,0.000021626998,0.000024652572],"category_scores_gemma":[0.000028448345,0.000097006494,0.000014241228,0.00035030156,0.00003497059,0.00046178684,0.0010583678,0.00018388199,7.341105e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017221462,0.00009166093,0.025105363,0.00004784484,0.00001152858,0.000010385068,0.0019852025,8.1569846e-7,0.19951496,0.006247148,0.0005755978,0.7663923],"study_design_scores_gemma":[0.00079032365,0.0020142912,0.20884912,0.00010038942,0.00005104175,0.0002855171,0.0006597327,0.016564166,0.5771625,0.005358602,0.18685116,0.0013131303],"about_ca_topic_score_codex":0.00028539103,"about_ca_topic_score_gemma":0.000015106928,"teacher_disagreement_score":0.76507914,"about_ca_system_score_codex":0.000038577462,"about_ca_system_score_gemma":0.00001090062,"threshold_uncertainty_score":0.395581},"labels":[],"label_agreement":null},{"id":"W4409603844","doi":"10.61091/jcmcc127b-162","title":"Research on Audit Data Anomaly Detection and Risk Assessment Method Based on Data Mining Technology","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Yunnan University; Tianjin University; Tianjin University of Technology","keywords":"Anomaly detection; Audit; Data mining; Anomaly (physics); Data science; Computer science; Business; Accounting","score_opus":0.06909951381157049,"score_gpt":0.4040861612218774,"score_spread":0.3349866474103069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409603844","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03525255,0.000094079885,0.95594716,0.0012844212,0.005820499,0.0003964269,0.00002430301,0.0001396816,0.0010408541],"genre_scores_gemma":[0.70309895,0.000053916992,0.2964997,0.00003624052,0.00028159568,0.0000034991926,0.0000071390173,0.000015687741,0.000003281469],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962682,0.0006460508,0.0009952855,0.0007368438,0.0009808416,0.00037279338],"domain_scores_gemma":[0.991984,0.0035633522,0.0010571977,0.0025450122,0.0007330248,0.0001174261],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011392867,0.0002621184,0.0006118993,0.0012132964,0.00064988213,0.0006420708,0.0035339247,0.0002487679,0.000001053926],"category_scores_gemma":[0.002487833,0.0002372914,0.00004008917,0.0013692855,0.00013913648,0.00061422685,0.0029065693,0.0012678535,0.0000011492524],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000078941426,0.00068316224,0.00039379302,0.00013010448,0.00010747791,0.000018142971,0.00008569568,0.00005357107,0.00050475245,0.9095399,0.0014236828,0.0869808],"study_design_scores_gemma":[0.0021801319,0.0011744548,0.00047934536,0.0005898045,0.00005903565,0.000023809067,0.00016901665,0.6915972,0.0015755851,0.2994338,0.0025016095,0.00021620521],"about_ca_topic_score_codex":0.000012324875,"about_ca_topic_score_gemma":0.0000010357595,"teacher_disagreement_score":0.69154364,"about_ca_system_score_codex":0.00017419702,"about_ca_system_score_gemma":0.00042503464,"threshold_uncertainty_score":0.96764624},"labels":[],"label_agreement":null},{"id":"W4409791323","doi":"10.61091/jcmcc127a-400","title":"Deep reinforcement learning-based heterogeneous graph neural networks for multi-task financial fraud detection: a new framework incorporating variational self-encoders","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Computer science; Encoder; Task (project management); Artificial intelligence; Graph; Artificial neural network; Machine learning; Theoretical computer science; Management","score_opus":0.014118360666004817,"score_gpt":0.2610091801802655,"score_spread":0.24689081951426067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409791323","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015059964,0.00015938336,0.98691034,0.00027039705,0.010367706,0.0005621215,5.1713084e-7,0.00020476617,0.000018793222],"genre_scores_gemma":[0.7070073,0.0000075682497,0.2920541,0.00013067985,0.00076001836,0.000013241882,0.000004276836,0.00001961876,0.0000032102969],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969766,0.00016328559,0.0014559143,0.00039571375,0.0005930792,0.00041539824],"domain_scores_gemma":[0.9957847,0.0010655671,0.0018485483,0.000404911,0.000697344,0.00019895234],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015089759,0.00036601952,0.0006702509,0.00039137623,0.0007014597,0.0005690509,0.0009688158,0.00033319046,0.0000011103912],"category_scores_gemma":[0.0014700688,0.00036857426,0.00026463636,0.00079556037,0.00006130295,0.00040922398,0.00030005933,0.0008292134,3.534663e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013464395,0.0004905681,0.00009749186,0.00017286607,0.00014554188,0.000009966915,0.0005938976,0.18635301,0.00010205193,0.80485636,0.00019428668,0.0068493015],"study_design_scores_gemma":[0.002478457,0.00057949475,0.000027192491,0.00018162305,0.000053107444,0.00001693303,0.000018860683,0.71680546,0.00055337383,0.27877682,0.00027568045,0.00023297236],"about_ca_topic_score_codex":0.0000065916993,"about_ca_topic_score_gemma":8.7512643e-7,"teacher_disagreement_score":0.7055013,"about_ca_system_score_codex":0.00021012372,"about_ca_system_score_gemma":0.0004963848,"threshold_uncertainty_score":0.9998766},"labels":[],"label_agreement":null},{"id":"W4409791783","doi":"10.61091/jcmcc127a-469","title":"Financial fraud identification model construction based on topological data analysis","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Identification (biology); Topological data analysis; Business; Computer science; Topology (electrical circuits); Data mining; Data science; Mathematics; Algorithm","score_opus":0.027016920589702263,"score_gpt":0.29851136506711784,"score_spread":0.27149444447741555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409791783","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016760468,0.000043853244,0.9766702,0.0006298542,0.0051144664,0.0001871578,0.000009664231,0.000093964685,0.00049037184],"genre_scores_gemma":[0.82583064,0.000013133334,0.17383268,0.00009073248,0.000209308,0.0000021484461,0.00000968118,0.000006858549,0.0000048442375],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973473,0.000142011,0.001202896,0.0004381306,0.00063785183,0.00023179622],"domain_scores_gemma":[0.9963466,0.0006176615,0.001178194,0.0012075236,0.0005676543,0.00008236274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023053878,0.0002245185,0.00063239376,0.00067741045,0.00030207637,0.00043940853,0.0018789534,0.0002007123,0.000002044564],"category_scores_gemma":[0.0013578844,0.00020381593,0.00014861603,0.0013124454,0.00011699891,0.00051540614,0.0005503386,0.00044600104,0.0000011919673],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031393585,0.00034175607,0.00013448393,0.000038844355,0.00007914708,0.0000033288622,0.000065090884,0.0012240413,0.00022346861,0.9934557,0.00050897896,0.0038937875],"study_design_scores_gemma":[0.0007185361,0.00010216145,0.00021244382,0.00006079968,0.00011983601,0.000003733642,0.000013883808,0.54528606,0.00062964816,0.45260188,0.00013979708,0.00011125428],"about_ca_topic_score_codex":0.0000026041496,"about_ca_topic_score_gemma":2.0355108e-7,"teacher_disagreement_score":0.80907017,"about_ca_system_score_codex":0.00011036437,"about_ca_system_score_gemma":0.00034474386,"threshold_uncertainty_score":0.83113724},"labels":[],"label_agreement":null},{"id":"W4410253327","doi":"10.1016/j.procs.2025.04.266","title":"Enhancing Model Performance in Hybrid Class Imbalance Techniques","year":2025,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Class (philosophy); Artificial intelligence","score_opus":0.00991858894615224,"score_gpt":0.25582980037837383,"score_spread":0.24591121143222158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410253327","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017781226,0.000048584883,0.97642004,0.00095059903,0.00034889617,0.00041477135,0.000002220027,0.0010983152,0.0029353136],"genre_scores_gemma":[0.58130556,0.000044429515,0.41749668,0.0009351554,0.000028978222,0.00010806243,0.0000012994932,0.000005638313,0.00007415747],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99692744,0.000029996781,0.00053614326,0.0011947977,0.00058615755,0.00072548626],"domain_scores_gemma":[0.9979911,0.00007429364,0.00016321105,0.0013237789,0.0003394219,0.00010823057],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014140591,0.0002583483,0.00027559896,0.0009238,0.0002800757,0.0004615603,0.004419664,0.00006451095,8.475592e-7],"category_scores_gemma":[0.00010737034,0.00025895663,0.000040632956,0.0031032786,0.00037909992,0.0030388935,0.0014226799,0.0003387193,0.000018793222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020943671,0.0004051628,0.022211537,0.00041836014,0.000009861312,0.000022057966,0.0009982294,0.0027409587,0.11753351,0.3313085,0.003087728,0.52124316],"study_design_scores_gemma":[0.000089537876,0.000029361985,0.0042886003,0.00014284883,8.737072e-7,0.000010012445,0.0000015115302,0.69020563,0.2999567,0.004479464,0.00058842154,0.00020702858],"about_ca_topic_score_codex":0.0000050813733,"about_ca_topic_score_gemma":0.000005085136,"teacher_disagreement_score":0.68746465,"about_ca_system_score_codex":0.00033777088,"about_ca_system_score_gemma":0.0009979373,"threshold_uncertainty_score":0.9999863},"labels":[],"label_agreement":null},{"id":"W4410283059","doi":"10.18280/ijsse.150303","title":"Click Fraud Detection in Online Advertising: A Comparative Study of Machine Learning Models","year":2025,"lang":"en","type":"article","venue":"International Journal of Safety and Security Engineering","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Online advertising; Machine learning; Online learning; Artificial intelligence; Computer security; World Wide Web; The Internet","score_opus":0.018766626515969553,"score_gpt":0.2841086789529371,"score_spread":0.26534205243696757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410283059","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3194704,0.00016895094,0.67990774,0.00016099235,0.00016022558,0.000059437232,0.0000040812606,0.000020715803,0.000047459038],"genre_scores_gemma":[0.9941831,0.00018473827,0.005586552,0.000015930951,0.000019148381,0.000001098425,0.0000023614464,0.0000023067241,0.000004761952],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910235,0.00004086831,0.00046841163,0.00010420911,0.00021869264,0.000065479595],"domain_scores_gemma":[0.9993844,0.00010030513,0.00019502654,0.00008232359,0.00021561941,0.000022315526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000299435,0.00007295967,0.00018400868,0.0004174017,0.00002062669,0.000029511768,0.0003833264,0.000032736287,8.1151626e-7],"category_scores_gemma":[0.000068659596,0.00007275088,0.000028158418,0.0002253049,0.000011128555,0.0005527257,0.0001202031,0.00031188058,7.066309e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078889646,0.0024334453,0.008557308,0.00011684748,0.00062897685,0.000096027856,0.032754626,0.76070166,0.022831913,0.06751927,0.000021284282,0.103549734],"study_design_scores_gemma":[0.00079812336,0.00013760952,0.012420153,0.00015897819,0.000004897785,0.000022235181,0.00034594396,0.98042834,0.0038267872,0.0014116697,0.00037899837,0.000066295506],"about_ca_topic_score_codex":0.000045649293,"about_ca_topic_score_gemma":0.00005808021,"teacher_disagreement_score":0.6747127,"about_ca_system_score_codex":0.00008056896,"about_ca_system_score_gemma":0.000022590983,"threshold_uncertainty_score":0.29666948},"labels":[],"label_agreement":null},{"id":"W4410381392","doi":"10.48175/ijarsct-11978t","title":"Unsupervised Deep Learning for Credit Card Fraud Detection: An Autoencoder-Driven Framework with Real-Time Dash Visualization Using Tensorflow 2.X","year":2023,"lang":"en","type":"article","venue":"International Journal of Advanced Research in Science Communication and Technology","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"ASTER","funders":"","keywords":"Autoencoder; Credit card fraud; Dash; Credit card; Deep learning; Computer science; Artificial intelligence; Visualization; Machine learning; Operating system; World Wide Web","score_opus":0.07077762657174014,"score_gpt":0.4364017754089402,"score_spread":0.36562414883720007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410381392","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20068224,0.000078865654,0.7947913,0.0036002945,0.00014639854,0.00032995545,0.000003105507,0.0002851469,0.00008268883],"genre_scores_gemma":[0.69093937,0.0010064917,0.3079376,0.00001843054,0.000030338326,0.00003697465,0.000008462782,0.000010471809,0.000011883145],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99756724,0.00024193758,0.00046378264,0.0003681569,0.0010057833,0.000353088],"domain_scores_gemma":[0.99495864,0.00052542466,0.00034787704,0.00071752456,0.0033507675,0.0000997807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030459573,0.00011038681,0.0001921402,0.003069317,0.0005151597,0.000303059,0.0034355698,0.00013686052,0.0000028644213],"category_scores_gemma":[0.0016716459,0.00010092465,0.000024045275,0.0042566103,0.0009433991,0.0021726205,0.0006668249,0.0006756465,0.0000029390008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022056056,0.00023619631,0.005912848,0.000024945,0.000045676716,0.000038737136,0.0021938756,0.03615761,0.41502625,0.116303265,0.000029431167,0.4238106],"study_design_scores_gemma":[0.00067669386,0.00053592003,0.0030283362,0.00024231704,0.0000026801654,0.00011973634,0.0011797579,0.9369163,0.017916564,0.037907504,0.001318734,0.00015546776],"about_ca_topic_score_codex":0.000014726172,"about_ca_topic_score_gemma":0.000019833915,"teacher_disagreement_score":0.9007587,"about_ca_system_score_codex":0.00034525097,"about_ca_system_score_gemma":0.0003068935,"threshold_uncertainty_score":0.63842005},"labels":[],"label_agreement":null},{"id":"W4410491803","doi":"10.1109/jstsp.2025.3558652","title":"R-Bench: Are Your Large Multimodal Model Robust to Real-World Corruptions?","year":2025,"lang":"en","type":"article","venue":"IEEE Journal of Selected Topics in Signal Processing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Computer vision","score_opus":0.04899085643834207,"score_gpt":0.33231877452336195,"score_spread":0.2833279180850199,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410491803","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013550958,0.00009868684,0.9823399,0.00240062,0.0001858427,0.00015001357,0.000005630989,0.00010790758,0.0011603937],"genre_scores_gemma":[0.73895365,0.000035517078,0.25950754,0.00057727157,0.00013004632,0.000009292622,0.0000017811789,0.000009664502,0.000775239],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981051,0.00007962409,0.00076391164,0.00030022205,0.00039456968,0.00035656808],"domain_scores_gemma":[0.9979955,0.000050218958,0.00050603144,0.00028230742,0.0010633493,0.00010261022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005683632,0.00017299535,0.00031726324,0.0009648846,0.00016852713,0.0002572036,0.001098236,0.00010421182,0.000005084862],"category_scores_gemma":[0.00012575275,0.00016812743,0.000053030508,0.0025353676,0.000027195214,0.0009928339,0.00010713084,0.0006132442,0.000002408148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034470105,0.0025795707,0.0585973,0.00073860283,0.00015105419,0.00029918773,0.0054852855,0.33831105,0.14555712,0.04725592,0.042406306,0.3582739],"study_design_scores_gemma":[0.0006391781,0.000073466595,0.012906177,0.00074408064,0.00001511214,0.000023677529,0.00006930951,0.9606959,0.015553318,0.007826787,0.001173612,0.00027937855],"about_ca_topic_score_codex":0.000017144703,"about_ca_topic_score_gemma":0.00009468114,"teacher_disagreement_score":0.7254027,"about_ca_system_score_codex":0.00033433634,"about_ca_system_score_gemma":0.0006902778,"threshold_uncertainty_score":0.68560374},"labels":[],"label_agreement":null},{"id":"W4410734606","doi":"10.1002/for.3284","title":"Default Prediction Framework With Optimal Feature Set and Matching Ratio","year":2025,"lang":"en","type":"article","venue":"Journal of Forecasting","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China","keywords":"Feature (linguistics); Matching (statistics); Computer science; Set (abstract data type); Pattern recognition (psychology); Artificial intelligence; Econometrics; Mathematics; Statistics","score_opus":0.01887874567049567,"score_gpt":0.2666547613807316,"score_spread":0.24777601571023591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410734606","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0408996,0.00010544633,0.9572275,0.0012223396,0.00014704496,0.000060915307,0.000003393226,0.000056076253,0.00027764874],"genre_scores_gemma":[0.43769103,0.00001052506,0.562067,0.000118410004,0.00006183758,0.0000016690807,0.0000010840047,0.0000032785424,0.000045219847],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999304,0.000032574975,0.00023340668,0.00012568214,0.00018946984,0.00011485794],"domain_scores_gemma":[0.99914384,0.0001428421,0.00032230344,0.0001704642,0.00018092294,0.00003965778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042173953,0.00007978655,0.00012699873,0.00015255087,0.00013211303,0.00020866425,0.00029872273,0.00006727083,9.190893e-7],"category_scores_gemma":[0.00017448621,0.000060375798,0.000023286371,0.00030267856,0.000025820998,0.00083656394,0.000081052975,0.0003767909,2.3806258e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042803067,0.00019697336,0.051546205,0.00047104745,0.00045295007,0.00029772214,0.01150678,0.015596425,0.019555137,0.22986603,0.038413715,0.631669],"study_design_scores_gemma":[0.0019563583,0.0012277791,0.052606907,0.0056217276,0.00011709931,0.004175908,0.0011880745,0.8312175,0.029352581,0.06178568,0.010108472,0.00064187276],"about_ca_topic_score_codex":0.0000014625051,"about_ca_topic_score_gemma":7.333048e-7,"teacher_disagreement_score":0.81562114,"about_ca_system_score_codex":0.000044958444,"about_ca_system_score_gemma":0.00008044873,"threshold_uncertainty_score":0.24620534},"labels":[],"label_agreement":null},{"id":"W4410755212","doi":"10.1007/978-981-96-6403-0_13","title":"Credit Card Fraud Detection with Deep Multilayer Perceptrons","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Credit card fraud; Computer science; Perceptron; Artificial intelligence; Pattern recognition (psychology); Credit card; World Wide Web; Artificial neural network","score_opus":0.024203241766438035,"score_gpt":0.2779501540965774,"score_spread":0.2537469123301394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410755212","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008837164,0.00011144688,0.8507563,0.0005403141,0.00018549895,0.00042209102,0.000020714911,0.00026259827,0.14769223],"genre_scores_gemma":[0.09023021,0.0027784968,0.90117776,0.0017573115,0.00006387948,0.00019543705,0.00018339897,0.000018993196,0.0035944849],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981448,0.000036389756,0.00062270113,0.00041781107,0.00051854295,0.0002597569],"domain_scores_gemma":[0.99531,0.00018366694,0.0003541103,0.0034167103,0.00063914165,0.00009637507],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00071262376,0.0002707146,0.00026825172,0.0013924416,0.0005962783,0.00072320347,0.0040301937,0.00017707008,0.000006526879],"category_scores_gemma":[0.000050088976,0.00025546964,0.000041644118,0.0006741353,0.0008979049,0.007711813,0.002175189,0.00058502436,0.00004445492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038673866,0.000016911918,0.000031982792,0.000030690342,0.000008288445,3.418348e-7,0.0011368444,0.00011891975,0.000024390314,0.34962407,0.0005277798,0.64847594],"study_design_scores_gemma":[0.00032563327,0.000098007644,0.002070275,0.00026793854,0.000011266339,0.000029706063,0.000032933473,0.65899354,0.00019551718,0.0032683597,0.33421108,0.000495754],"about_ca_topic_score_codex":0.000023853474,"about_ca_topic_score_gemma":0.000057006986,"teacher_disagreement_score":0.6588746,"about_ca_system_score_codex":0.0002987038,"about_ca_system_score_gemma":0.00037170536,"threshold_uncertainty_score":0.99998975},"labels":[],"label_agreement":null},{"id":"W4411247987","doi":"10.3390/jrfm18060323","title":"AI and Financial Fraud Prevention: Mapping the Trends and Challenges Through a Bibliometric Lens","year":2025,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Business; Data science; Through-the-lens metering; Lens (geology); Computer science; Finance; Engineering","score_opus":0.04284091819857188,"score_gpt":0.2805251681321447,"score_spread":0.2376842499335728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411247987","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031313805,0.021361567,0.96509886,0.008586837,0.00028361322,0.00012851557,0.0000043269074,0.000028834447,0.0013760957],"genre_scores_gemma":[0.62649673,0.32005277,0.051506877,0.0013509623,0.00021082464,0.000022930484,9.3450547e-7,0.0000071495756,0.00035080587],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990395,0.000068862726,0.00032895207,0.00021368764,0.00020220327,0.00014684077],"domain_scores_gemma":[0.999321,0.00006921792,0.00026238852,0.00024030104,0.00007984876,0.00002727443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073483784,0.000111882066,0.00019461713,0.0038907449,0.00023868371,0.00018025073,0.0003491702,0.00005607004,0.0000013875019],"category_scores_gemma":[0.000094957046,0.00008147217,0.00004547394,0.0060686073,0.00007573567,0.00064894435,0.000353026,0.00020879097,3.934323e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000842685,0.000031540974,0.00052664534,0.0000473027,0.000009762836,0.000008023552,0.00039147103,6.384173e-7,0.0000022773474,0.14404926,0.0036638924,0.8512608],"study_design_scores_gemma":[0.00045893472,0.0001286463,0.44051462,0.00013042802,0.00003497888,0.000018192184,0.00007548934,0.00017835919,0.000025340907,0.048742082,0.5095989,0.00009400597],"about_ca_topic_score_codex":0.0000055743203,"about_ca_topic_score_gemma":0.000006584538,"teacher_disagreement_score":0.913592,"about_ca_system_score_codex":0.000020154917,"about_ca_system_score_gemma":0.00002879033,"threshold_uncertainty_score":0.3471671},"labels":[],"label_agreement":null},{"id":"W4411406627","doi":"10.1109/access.2025.3580738","title":"Separated and Independent Contrastive Semi-Supervised Learning for Imbalanced Datasets","year":2025,"lang":"en","type":"article","venue":"IEEE Access","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Hallym University","keywords":"Computer science; Artificial intelligence; Machine learning; Natural language processing; Pattern recognition (psychology)","score_opus":0.024917631523983512,"score_gpt":0.3386380374540611,"score_spread":0.3137204059300776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411406627","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01614675,0.00007232042,0.9814296,0.00049480627,0.00025927558,0.0005598451,0.00014063573,0.00039258748,0.0005042007],"genre_scores_gemma":[0.99055374,0.00004711189,0.007923656,0.0007201754,0.000026436579,0.00023087961,0.00025646674,0.000008299605,0.00023326057],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988107,0.00006543141,0.00023348397,0.000504725,0.00013974105,0.00024592195],"domain_scores_gemma":[0.99898213,0.00022929802,0.000110351604,0.000489386,0.00013251897,0.000056298657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027159447,0.00014233653,0.00019582013,0.00013868244,0.00017774546,0.00045923132,0.0011875697,0.000083937826,0.0000039252022],"category_scores_gemma":[0.00013348588,0.00013894831,0.000024464394,0.0004019332,0.00005027361,0.0011538697,0.00029249504,0.00016345513,0.0000045919696],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048214116,0.00053725526,0.0749076,0.0006229194,0.00048380578,0.000045073964,0.001193208,0.0014609786,0.26961064,0.09489941,0.2782584,0.27749854],"study_design_scores_gemma":[0.0032676242,0.0001508033,0.07335829,0.00019827178,0.00004169123,0.000010589273,0.00005005301,0.45912012,0.40805715,0.0102754,0.04474679,0.00072322757],"about_ca_topic_score_codex":0.000024908039,"about_ca_topic_score_gemma":0.000008299477,"teacher_disagreement_score":0.97440696,"about_ca_system_score_codex":0.000047951864,"about_ca_system_score_gemma":0.00008817057,"threshold_uncertainty_score":0.56661475},"labels":[],"label_agreement":null},{"id":"W4411429323","doi":"10.21203/rs.3.rs-6895500/v1","title":"Introducing DART: A Novel Deep Adaptive Upsampling Technique for Handling Class Imbalance","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Roads University","funders":"","keywords":"Undersampling; Resampling; Machine learning; Artificial intelligence; Oversampling; Computer science; Random forest; Multinomial logistic regression; Generalizability theory; Jackknife resampling; Data mining; Statistics; Mathematics; Bandwidth (computing)","score_opus":0.09381332995188661,"score_gpt":0.40685344103207816,"score_spread":0.31304011108019153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411429323","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000026627536,0.00055265974,0.9888501,0.0021270725,0.0004581228,0.005077908,0.00060133456,0.0009643692,0.001341769],"genre_scores_gemma":[0.05650545,0.00023462648,0.93305963,0.00012046257,0.0005270791,0.008605055,0.00034491724,0.00005485116,0.0005479347],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99387044,0.00037038713,0.00078761956,0.002401675,0.0012693242,0.0013005721],"domain_scores_gemma":[0.9910307,0.0017034588,0.0003598119,0.003730102,0.0029701006,0.0002058283],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0056338497,0.0005018156,0.0007021429,0.0013426364,0.00071220164,0.000872193,0.0047426205,0.00069881266,0.000006331024],"category_scores_gemma":[0.0028127886,0.00053280534,0.00023327576,0.0015565233,0.00022940658,0.0005094591,0.006172329,0.002782352,0.000014961506],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031167662,0.00084086164,0.00039005,0.0070866914,0.0003293838,0.000027585189,0.0025002765,0.016392857,0.09362892,0.81488675,0.018163841,0.045441117],"study_design_scores_gemma":[0.00065557926,0.00033000245,0.00022895107,0.0049809297,0.000018752107,0.000012523694,0.00023931648,0.7847859,0.12441288,0.059041146,0.024205552,0.0010884715],"about_ca_topic_score_codex":0.00012564531,"about_ca_topic_score_gemma":0.000040663785,"teacher_disagreement_score":0.76839304,"about_ca_system_score_codex":0.0010519748,"about_ca_system_score_gemma":0.0016918692,"threshold_uncertainty_score":0.99971235},"labels":[],"label_agreement":null},{"id":"W4411436346","doi":"10.1007/978-3-031-87496-3_12","title":"Is Expert-Labeled Data Worth the Cost? Exploring Active and Semi-supervised Learning Across Imbalance Scenarios in Financial Crime Detection","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Supervised learning; Finance; Labeled data; Data science; Artificial neural network; Economics","score_opus":0.058980587540579874,"score_gpt":0.3038318852418694,"score_spread":0.2448512977012895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411436346","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009825273,0.00044761554,0.9954799,0.000955042,0.00084272755,0.0007938006,0.000033573066,0.00026733888,0.00019748569],"genre_scores_gemma":[0.8142642,0.0015034887,0.17841488,0.0044958442,0.00056026434,0.0002892817,0.00006667433,0.00006576004,0.00033963745],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955584,0.00010515022,0.0005862812,0.0022415784,0.00075173524,0.0007568746],"domain_scores_gemma":[0.99596626,0.00070630724,0.00033018432,0.0026760914,0.00022408883,0.00009709216],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011825191,0.0005312658,0.00052805914,0.00050734833,0.00062846846,0.00080473773,0.005375485,0.00031743688,0.000004488116],"category_scores_gemma":[0.0005797892,0.0004566247,0.00005407964,0.0011610022,0.0006371358,0.002113952,0.004528206,0.0016847478,0.0000062083664],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019600466,0.00002038783,0.00024011446,0.00002625345,0.000006634834,0.00001942443,0.0038925563,0.0006363085,0.0010869836,0.0007379581,0.00004350365,0.9932703],"study_design_scores_gemma":[0.0006310561,0.000120964745,0.0041630995,0.0011147432,0.0000073463193,0.000035875797,0.000008070558,0.9501751,0.028234083,0.006922337,0.0076259174,0.00096141704],"about_ca_topic_score_codex":0.00010866028,"about_ca_topic_score_gemma":0.00034776295,"teacher_disagreement_score":0.99230886,"about_ca_system_score_codex":0.0004292613,"about_ca_system_score_gemma":0.00053404114,"threshold_uncertainty_score":0.9997885},"labels":[],"label_agreement":null},{"id":"W4411565097","doi":"10.1007/978-981-96-6579-2_24","title":"Data Augmentation with Variational Autoencoder for Imbalanced Dataset","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Autoencoder; Computer science; Artificial intelligence; Machine learning; Pattern recognition (psychology); Data mining; Artificial neural network","score_opus":0.03483581431491785,"score_gpt":0.30480724813344284,"score_spread":0.269971433818525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411565097","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.774583e-7,0.000054191023,0.9911843,0.0018382133,0.00063813146,0.0009049909,0.00443676,0.0002571978,0.0006860625],"genre_scores_gemma":[0.000342526,0.000021901398,0.98830074,0.0020292462,0.00018546352,0.000066714296,0.008695273,0.000020238764,0.0003379109],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996082,0.000026601027,0.0005097714,0.0020727322,0.0008571144,0.0004517566],"domain_scores_gemma":[0.9947515,0.0006388219,0.00040597309,0.0037829059,0.0003332084,0.000087573666],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00097040617,0.00041758857,0.0003923249,0.00064857735,0.00026334374,0.00060126855,0.0068282126,0.0002135905,0.000013842076],"category_scores_gemma":[0.00015345281,0.00037031996,0.000035084653,0.00056601857,0.0003732283,0.0016975242,0.0019456027,0.0003954426,0.000010871195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048946324,0.000086881046,0.000052057312,0.00015851235,0.000055225002,0.000019172749,0.00017522268,0.01392658,0.00017852872,0.2578194,0.017595828,0.70988363],"study_design_scores_gemma":[0.00041236964,0.00010658066,0.00014144563,0.00023340108,0.000014776366,0.000015398447,6.739677e-8,0.8883804,0.0004590865,0.082712285,0.027068125,0.0004560396],"about_ca_topic_score_codex":0.000015076438,"about_ca_topic_score_gemma":0.00008900764,"teacher_disagreement_score":0.87445384,"about_ca_system_score_codex":0.00031728842,"about_ca_system_score_gemma":0.0013564782,"threshold_uncertainty_score":0.9998749},"labels":[],"label_agreement":null},{"id":"W4411632752","doi":"10.18280/ijsse.150504","title":"Comparative Analysis of Machine Learning Models for Credit Card Fraud Detection Using SMOTE for Class Imbalance","year":2025,"lang":"en","type":"article","venue":"International Journal of Safety and Security Engineering","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Credit card fraud; Class (philosophy); Computer science; Credit card; Machine learning; Artificial intelligence; Computer security; World Wide Web","score_opus":0.022310455638140828,"score_gpt":0.29058474027150377,"score_spread":0.26827428463336295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411632752","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015133672,0.00025395898,0.983824,0.00020562808,0.000335598,0.000102875216,0.00009142272,0.000025480005,0.000027352318],"genre_scores_gemma":[0.93608844,0.00012358237,0.063685045,0.00002183758,0.000051793824,0.0000037486952,0.000016731809,0.0000030438014,0.000005755096],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913687,0.00001860985,0.00043580687,0.00013122728,0.00018567873,0.00009180006],"domain_scores_gemma":[0.9986685,0.00026323347,0.00031953672,0.00009382525,0.00062617054,0.000028713412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004199665,0.000087989814,0.00030227803,0.0005306717,0.000051909403,0.000050221206,0.00037735334,0.00005104289,4.6585686e-7],"category_scores_gemma":[0.0001127354,0.0000900868,0.00014274904,0.00030956295,0.00001841236,0.00049867184,0.00006527328,0.00015213685,1.6795589e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020722684,0.00003601967,0.00024013879,0.000057071953,0.0013583897,0.0000011309398,0.0007817142,0.92505556,0.019345982,0.049493607,0.0000132419955,0.0034099305],"study_design_scores_gemma":[0.0003568921,0.00004677481,0.00059830927,0.00006989952,0.00009839539,0.000005761669,0.000025322683,0.98114157,0.013620106,0.0020133066,0.001954129,0.0000695565],"about_ca_topic_score_codex":0.00001607761,"about_ca_topic_score_gemma":0.000008418559,"teacher_disagreement_score":0.92095476,"about_ca_system_score_codex":0.00010857221,"about_ca_system_score_gemma":0.00003637467,"threshold_uncertainty_score":0.3673633},"labels":[],"label_agreement":null},{"id":"W4411811345","doi":"10.1007/978-981-96-8889-0_33","title":"DistResampleR-Lite: Light Distributed Resampler for Imbalanced Regression Problems","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Regression; Artificial intelligence; Statistics; Mathematics","score_opus":0.022373347818347072,"score_gpt":0.2778266701672654,"score_spread":0.2554533223489184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411811345","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000024755257,0.00036701176,0.9902472,0.0037770185,0.0013898155,0.0015958956,0.00046730984,0.0007219622,0.0014313301],"genre_scores_gemma":[0.009878148,0.00015640809,0.9850598,0.0013429642,0.00045093868,0.0003110929,0.0008031055,0.00006446168,0.0019330542],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99439585,0.00005234549,0.00097116793,0.0025744794,0.0010230665,0.0009830993],"domain_scores_gemma":[0.9942341,0.00091913954,0.00065629504,0.0033051092,0.0006792899,0.00020605892],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0009960112,0.00079381175,0.0008201916,0.00092138926,0.00046842717,0.00082441,0.005822541,0.00057136785,0.000014328518],"category_scores_gemma":[0.0005336054,0.0006768824,0.00022237009,0.0011386973,0.00054167124,0.00084528583,0.0019376863,0.0008276018,0.0000132766945],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038669827,0.00010375104,0.00011974446,0.0003841645,0.00003191778,0.000022841434,0.00033566804,0.0015905139,0.0020669235,0.17347273,0.007981766,0.8138513],"study_design_scores_gemma":[0.0008672118,0.00030420467,0.0003361232,0.002878349,0.000023471412,0.000028122424,2.1023351e-7,0.27864382,0.018431287,0.49143687,0.20537607,0.0016742713],"about_ca_topic_score_codex":0.000016993925,"about_ca_topic_score_gemma":0.00004742646,"teacher_disagreement_score":0.81217706,"about_ca_system_score_codex":0.0006479466,"about_ca_system_score_gemma":0.0008101065,"threshold_uncertainty_score":0.9995682},"labels":[],"label_agreement":null},{"id":"W4411969915","doi":"10.1101/2025.06.26.661884","title":"Novel binning-based methods for model fitting and data splitting improved machine learning imbalanced data","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Data mining; Algorithm","score_opus":0.06597440103141576,"score_gpt":0.3401000506503915,"score_spread":0.27412564961897573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411969915","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00042423926,0.000949869,0.9897088,0.0007220069,0.00051119074,0.0014232036,0.004335215,0.0019205268,0.0000049484165],"genre_scores_gemma":[0.058103625,0.00010381659,0.9406679,0.0004534949,0.00015574107,0.00032742214,0.00007593944,0.00010017957,0.00001184745],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9936645,0.00028993498,0.0010883032,0.0037850447,0.0003376326,0.00083456264],"domain_scores_gemma":[0.9864429,0.0008913253,0.0012512362,0.010533885,0.0006445989,0.00023603822],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0060402034,0.00078704866,0.00091374916,0.0005038694,0.00051850535,0.0010611409,0.009206825,0.0005822407,0.0000013535301],"category_scores_gemma":[0.00437558,0.0008858205,0.000087193206,0.0008040873,0.0001373842,0.0012159863,0.01444646,0.0014015941,0.0000013287287],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034485427,0.00015889599,0.0008991056,0.0016000507,0.00017780652,0.0000027392903,0.000015376703,0.0013862242,0.98962003,0.004880301,0.0003307691,0.00089421705],"study_design_scores_gemma":[0.00066935754,0.000026775117,0.00056658883,0.00048077168,0.000094805146,1.872988e-8,0.0000010329031,0.92056924,0.07345794,0.000016774718,0.003307925,0.00080874254],"about_ca_topic_score_codex":0.00007467616,"about_ca_topic_score_gemma":0.0000024668605,"teacher_disagreement_score":0.919183,"about_ca_system_score_codex":0.00020814076,"about_ca_system_score_gemma":0.0014786159,"threshold_uncertainty_score":0.99997586},"labels":[],"label_agreement":null},{"id":"W4412049267","doi":"10.1016/j.eswa.2025.128920","title":"A comprehensive review on data-level methods for imbalanced data classification","year":2025,"lang":"en","type":"review","venue":"Expert Systems with Applications","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Artificial intelligence; Data classification; Data mining; Pattern recognition (psychology); Machine learning","score_opus":0.3769644452128858,"score_gpt":0.5124121553384758,"score_spread":0.13544771012559004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412049267","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.2821921e-11,0.4927626,0.49455333,0.00034287848,0.0001493441,0.008144401,0.0033028647,0.00043941577,0.00030517517],"genre_scores_gemma":[1.834335e-8,0.5567122,0.38888863,0.00041219773,0.00015273657,0.028960608,0.024462756,0.00004517368,0.0003657118],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99344534,0.0008141714,0.0016507063,0.0031438926,0.00046275035,0.00048314745],"domain_scores_gemma":[0.9734556,0.0024178638,0.0016995185,0.021642227,0.0006183637,0.00016643188],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0014809697,0.0008062026,0.0024727674,0.00039828607,0.00040226895,0.00035920116,0.014444005,0.00036299523,0.0000028896457],"category_scores_gemma":[0.00032354426,0.00061270257,0.0001644228,0.0019111373,0.00011912238,0.0007890381,0.0018103711,0.0004428024,0.0000955862],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018006127,0.0000796461,3.4523673e-8,0.037769143,0.00011230265,2.5500736e-7,0.000007934185,1.6506e-7,0.0000025477855,0.033903185,0.13449,0.793633],"study_design_scores_gemma":[0.00014353824,0.00003698685,5.7086334e-7,0.041610938,0.00024713756,0.000030021445,0.000011206018,0.004378712,0.0000021831854,0.000068615554,0.95287037,0.00059974013],"about_ca_topic_score_codex":0.000024115163,"about_ca_topic_score_gemma":0.0000015129609,"teacher_disagreement_score":0.81838036,"about_ca_system_score_codex":0.00029883676,"about_ca_system_score_gemma":0.001259588,"threshold_uncertainty_score":0.9996324},"labels":[],"label_agreement":null},{"id":"W4412357334","doi":"10.63471/amlid25001","title":"Big Data Analytics and Its Usage on Financial Fraud Detection in the USA","year":2025,"lang":"en","type":"article","venue":"Advances in Machine Learning IoT and Data Security","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wycliffe College","funders":"","keywords":"Big data; Analytics; Business; Data science; Financial fraud; Finance; Computer science; Accounting; Data mining","score_opus":0.044957051012980476,"score_gpt":0.3383120534359343,"score_spread":0.2933550024229538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412357334","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15182231,0.010722489,0.8285761,0.004051116,0.0008940349,0.0008701782,0.0006466052,0.00029682877,0.002120362],"genre_scores_gemma":[0.99277896,0.0031914131,0.003237336,0.00045305624,0.000050558265,0.000007943889,0.0002595963,0.0000036597564,0.000017499959],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998501,0.00024626928,0.00022745978,0.00067709474,0.00017036115,0.00017780022],"domain_scores_gemma":[0.9980666,0.00037685674,0.000096642194,0.0014205673,0.000017475126,0.000021861126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013970229,0.00012723984,0.00015229915,0.0001957119,0.00016811311,0.00014519675,0.0019727398,0.000064724256,0.0000012385951],"category_scores_gemma":[0.0012900353,0.00010257733,0.000006486771,0.000701187,0.00006318726,0.0010522788,0.0015463786,0.00064259884,0.0000019752526],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045262874,0.0001366989,0.08229364,0.000097663826,0.0000057854913,0.0000186899,0.0004982313,0.00013870269,0.0001561926,0.039837066,0.00027890122,0.87649316],"study_design_scores_gemma":[0.00041393415,0.00008845575,0.098314695,0.00008542406,0.0000075205944,0.0000065016643,0.000027668728,0.6973231,0.00028256583,0.013528485,0.18971662,0.00020503633],"about_ca_topic_score_codex":0.00015685857,"about_ca_topic_score_gemma":0.0043730545,"teacher_disagreement_score":0.8762881,"about_ca_system_score_codex":0.000019783884,"about_ca_system_score_gemma":0.000033801534,"threshold_uncertainty_score":0.4182982},"labels":[],"label_agreement":null},{"id":"W4412387458","doi":"10.1145/3733567.3735571","title":"Mitigating Class Imbalance in Fact-Checking Datasets Through LLM-Based Synthetic Data Generation","year":2025,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Class (philosophy); Synthetic data; Data mining; Artificial intelligence","score_opus":0.07088414799895912,"score_gpt":0.3394362157914215,"score_spread":0.26855206779246243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412387458","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012579865,0.0000744175,0.99021024,0.0031741161,0.00020177338,0.0002922772,0.00026207458,0.00047752657,0.004049583],"genre_scores_gemma":[0.6733354,0.000016044314,0.3225268,0.00205213,0.000025765623,0.00004481724,0.0019221603,0.000007786771,0.00006913343],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997848,0.00014199724,0.00046594098,0.000964326,0.00026584155,0.0003139288],"domain_scores_gemma":[0.9961437,0.00018761004,0.00014597745,0.003431073,0.00005866837,0.00003299465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067884626,0.000177473,0.00019775906,0.00015978009,0.00013532204,0.00034762733,0.0027931717,0.00009236385,0.000017562952],"category_scores_gemma":[0.00038992998,0.00017610905,0.000021514634,0.00079005177,0.00006420424,0.0021062412,0.00083188136,0.00020635438,0.000025466908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012347283,0.00062563946,0.008722381,0.00020827376,0.000039608636,0.000037033868,0.0002962364,0.00084678904,0.18901353,0.48978236,0.21933651,0.09107931],"study_design_scores_gemma":[0.00025172217,0.000012805284,0.0014079771,0.00011717801,0.0000039113015,0.0000016842567,0.000017616885,0.84455407,0.13559437,0.0017722792,0.016054362,0.00021202111],"about_ca_topic_score_codex":0.00013647549,"about_ca_topic_score_gemma":0.00014604128,"teacher_disagreement_score":0.84370726,"about_ca_system_score_codex":0.00012456578,"about_ca_system_score_gemma":0.0002012036,"threshold_uncertainty_score":0.71815187},"labels":[],"label_agreement":null},{"id":"W4412477681","doi":"10.1007/978-981-96-9914-8_32","title":"Fraud Detection Based on Dynamic Graph Neural Networks","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Graph; Artificial neural network; Artificial intelligence; Theoretical computer science","score_opus":0.009428327176739066,"score_gpt":0.24062829625491056,"score_spread":0.2311999690781715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412477681","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004098442,0.00011120826,0.9939624,0.00074557087,0.0021941722,0.00049612985,0.0000095993255,0.0006910268,0.0017857935],"genre_scores_gemma":[0.57624406,0.00004544176,0.41627195,0.0067255027,0.00025654671,0.000055640623,0.000038428752,0.0000484947,0.00031396726],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961037,0.00006139208,0.0005184053,0.001830997,0.00086837757,0.00061709905],"domain_scores_gemma":[0.99628484,0.0005674694,0.0003291599,0.0024671694,0.00022911192,0.00012225068],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006867957,0.0005608334,0.00044344066,0.0016824831,0.00031839818,0.0005669217,0.0039658146,0.00046351214,0.000009094326],"category_scores_gemma":[0.00010584778,0.00054040365,0.00015477106,0.0013205883,0.00050292845,0.0005192737,0.00075394695,0.0012526921,0.000012486238],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007212644,0.000021048898,0.000009835485,0.0000178353,0.0000035432715,0.0000185262,0.0000206561,0.14490053,0.000081036385,0.0056490027,0.000041508636,0.8492293],"study_design_scores_gemma":[0.00015157115,0.00016974058,0.00016184765,0.00024458626,0.000004907611,0.000009041066,1.9180249e-8,0.95144224,0.001004514,0.045758534,0.0005793851,0.0004736331],"about_ca_topic_score_codex":0.000011293769,"about_ca_topic_score_gemma":0.000063716856,"teacher_disagreement_score":0.8487556,"about_ca_system_score_codex":0.00048755118,"about_ca_system_score_gemma":0.00029510685,"threshold_uncertainty_score":0.9997048},"labels":[],"label_agreement":null},{"id":"W4412477765","doi":"10.1007/s42979-025-04198-5","title":"Dynamic Focal Loss for Imbalanced Learning","year":2025,"lang":"en","type":"article","venue":"SN Computer Science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Artificial intelligence; Psychology","score_opus":0.00862036241531885,"score_gpt":0.2908034358957149,"score_spread":0.28218307348039606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412477765","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016176484,0.000031825155,0.9931984,0.0020322232,0.0010349052,0.00035096874,0.0000034881168,0.00083907007,0.00089147134],"genre_scores_gemma":[0.447926,0.000007175303,0.55101514,0.000645156,0.000024656712,0.000059632286,0.0000045028014,0.00000487647,0.00031284033],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978311,0.000040939056,0.00028946638,0.0009241578,0.00037273183,0.00054157356],"domain_scores_gemma":[0.99826306,0.00017411512,0.000118511074,0.0010294729,0.0003216297,0.000093197596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009537839,0.00016709797,0.00019009651,0.00040238438,0.0005612664,0.0005658757,0.0034895441,0.000057757497,0.0000016190982],"category_scores_gemma":[0.0001250619,0.00016246215,0.00006648288,0.0019440207,0.00042139657,0.0011574074,0.0009821024,0.00018769446,0.00002179651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008078436,0.00007124788,0.0011727009,0.000041663086,0.000009296999,0.0000043443642,0.0002189599,0.0006701362,0.011899166,0.5069533,0.0026503087,0.47630078],"study_design_scores_gemma":[0.00027453923,0.00009732981,0.006779768,0.000046322337,0.000002274797,0.00000813822,0.0000038447706,0.948916,0.0113360835,0.018351194,0.013971723,0.00021276364],"about_ca_topic_score_codex":0.000003662316,"about_ca_topic_score_gemma":0.000001793102,"teacher_disagreement_score":0.9482459,"about_ca_system_score_codex":0.00018277901,"about_ca_system_score_gemma":0.00040071394,"threshold_uncertainty_score":0.6625014},"labels":[],"label_agreement":null},{"id":"W4412927804","doi":"10.18280/ijsse.150614","title":"A Hybrid Oversampling Approach for Fraud Detection: Integrating SMOTE-ENN and ADASYN","year":2025,"lang":"en","type":"article","venue":"International Journal of Safety and Security Engineering","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Oversampling; Computer science; Artificial intelligence; Computer network","score_opus":0.006881669786136047,"score_gpt":0.238778308328132,"score_spread":0.23189663854199594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412927804","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003306742,0.00031542292,0.9951215,0.0005964838,0.00038363767,0.00007453499,0.000011959538,0.0000467254,0.00014303841],"genre_scores_gemma":[0.7970495,0.0001919743,0.20255841,0.00008699239,0.0000951047,0.000003557098,0.0000036801769,0.0000037817852,0.000006966261],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992775,0.000010748528,0.00031944204,0.00014225597,0.0001573914,0.00009271225],"domain_scores_gemma":[0.9993207,0.00016969568,0.00013843538,0.000092829854,0.00023834055,0.000040011037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040896537,0.000087878994,0.00013523287,0.0002231137,0.00006184437,0.00016599397,0.00036552185,0.00003815537,6.235157e-7],"category_scores_gemma":[0.00024702703,0.000085629115,0.000045894936,0.000083609775,0.000018344484,0.00059790513,0.00012113211,0.00020687847,5.263634e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032303878,0.00015575072,0.0004605576,0.00033196446,0.0005973098,0.000028190565,0.0022938328,0.00695982,0.022364276,0.6147038,0.00037188552,0.35140958],"study_design_scores_gemma":[0.000601018,0.00005492668,0.0007773264,0.00019361051,0.000011569196,0.00022161692,0.00008478347,0.9647696,0.012724924,0.006386666,0.014034569,0.00013936652],"about_ca_topic_score_codex":0.000005172895,"about_ca_topic_score_gemma":6.984775e-7,"teacher_disagreement_score":0.9578098,"about_ca_system_score_codex":0.00007206828,"about_ca_system_score_gemma":0.000030219646,"threshold_uncertainty_score":0.34918538},"labels":[],"label_agreement":null},{"id":"W4412945576","doi":"10.18653/v1/2025.acl-long.407","title":"Data Laundering: Artificially Boosting Benchmark Results through Knowledge Distillation","year":2025,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Boosting (machine learning); Benchmark (surveying); Computer science; Data mining; Machine learning; Artificial intelligence; Geology","score_opus":0.10788426963403835,"score_gpt":0.37254498024136695,"score_spread":0.2646607106073286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412945576","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008466121,0.000055693807,0.78913623,0.0017710078,0.0003066727,0.00015664482,0.000048632886,0.00076208176,0.20767835],"genre_scores_gemma":[0.5352206,0.000027989225,0.45977622,0.00036188107,0.00007707713,0.000015895741,0.00060265034,0.000008220803,0.003909444],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983954,0.0000628212,0.00044382922,0.0007178102,0.00015738483,0.00022274994],"domain_scores_gemma":[0.9968474,0.00027831335,0.00012708032,0.0025902397,0.00012534823,0.000031603104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005978548,0.00012691622,0.00013055421,0.0000947288,0.000198783,0.00029166168,0.00217576,0.00007005417,0.000007714037],"category_scores_gemma":[0.00069520815,0.00012136881,0.00002070076,0.0007347414,0.00004920207,0.0014094674,0.0014616797,0.000118319105,0.00005742397],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007761564,0.000059043574,0.00007660801,0.000021011489,0.000010968949,0.0000013224235,0.0003478124,0.00001059286,0.0020156314,0.83655626,0.098573074,0.062319916],"study_design_scores_gemma":[0.0003438406,0.000030587453,0.0041703368,0.00013101216,0.000011068223,0.0000032081953,0.00010590105,0.3208291,0.022019211,0.059988793,0.5919725,0.00039449055],"about_ca_topic_score_codex":0.000024647221,"about_ca_topic_score_gemma":0.0000734592,"teacher_disagreement_score":0.77656746,"about_ca_system_score_codex":0.00006849166,"about_ca_system_score_gemma":0.00017081744,"threshold_uncertainty_score":0.49492764},"labels":[],"label_agreement":null},{"id":"W4412958808","doi":"10.4018/979-8-3373-1250-7.ch005","title":"Generative AI in Fraud Prevention","year":2025,"lang":"en","type":"book-chapter","venue":"Advances in computational intelligence and robotics book series","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Generative grammar; Computer science; Psychology; Artificial intelligence","score_opus":0.023821309389189152,"score_gpt":0.3153316160945524,"score_spread":0.29151030670536326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412958808","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.0475784e-7,0.008476592,0.94813335,0.0018596132,0.0002475748,0.00033886742,0.00001555327,0.000089424095,0.04083885],"genre_scores_gemma":[0.0009450366,0.044993587,0.8081419,0.0020702663,0.00008473627,0.0000855201,0.00026172094,0.000030214233,0.14338703],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998213,0.00003896532,0.0006406073,0.0006320021,0.00027854677,0.00019687234],"domain_scores_gemma":[0.99894524,0.00024829677,0.00023708561,0.00033161594,0.00019878623,0.000038960476],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00017517467,0.00030029603,0.0003540231,0.00045862506,0.00008831283,0.000121836245,0.0005601294,0.00020239988,0.000015254424],"category_scores_gemma":[0.000036681264,0.00032034345,0.000049673694,0.00015819319,0.00023612818,0.0024160247,0.00029553365,0.00042991177,0.0000130243925],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006995666,0.000018714118,0.000021177675,0.000050133996,0.000007426304,0.000010360152,0.00009770173,0.13408741,0.0000010233232,0.82750124,0.00021704515,0.037980743],"study_design_scores_gemma":[0.000051315626,0.00008672533,0.000055205004,0.000544709,0.0000046137675,0.000009422081,0.000013276019,0.06683135,0.00018204497,0.8815131,0.0503973,0.00031089367],"about_ca_topic_score_codex":0.0000029296602,"about_ca_topic_score_gemma":0.00009165567,"teacher_disagreement_score":0.13999143,"about_ca_system_score_codex":0.00013445168,"about_ca_system_score_gemma":0.00023121796,"threshold_uncertainty_score":0.99992484},"labels":[],"label_agreement":null},{"id":"W4412984931","doi":"10.1109/access.2025.3596060","title":"AI Driven Fraud Detection Models in Financial Networks: A Comprehensive Systematic Review","year":2025,"lang":"en","type":"article","venue":"IEEE Access","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Computer science; Computer security","score_opus":0.027556133119273744,"score_gpt":0.3215991415299487,"score_spread":0.29404300841067493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412984931","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001889954,0.0032562227,0.9937178,0.00072226743,0.0004292364,0.0011913454,0.0000025747265,0.00028828956,0.00020329095],"genre_scores_gemma":[0.9769592,0.0028802308,0.0046106763,0.014376732,0.000050193437,0.0010346132,0.000007636574,0.000011738854,0.00006896353],"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850374,0.00018898307,0.00051770173,0.0003921297,0.00018302246,0.00021444414],"domain_scores_gemma":[0.9985322,0.00011628052,0.00019898951,0.00092933344,0.00019229736,0.000030921277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024604448,0.0001449538,0.00043147363,0.00021966382,0.00007459842,0.00020723644,0.0017321539,0.00009212984,0.000001329814],"category_scores_gemma":[0.00009517157,0.00013675213,0.000057234083,0.0013127994,0.000027379423,0.0015010651,0.0002489789,0.00022502903,0.000009959251],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006340593,0.0008069866,0.0007482738,0.51263183,0.00020598227,0.00014080078,0.0007669636,0.06904603,0.0030461352,0.22711892,0.12538508,0.060039572],"study_design_scores_gemma":[0.00023905165,0.000021757229,0.00075147266,0.048923954,0.000036101083,0.000006174431,0.0000030841134,0.9277406,0.0029081313,0.018809052,0.0002786382,0.00028201967],"about_ca_topic_score_codex":0.00004480041,"about_ca_topic_score_gemma":0.000055582987,"teacher_disagreement_score":0.9891071,"about_ca_system_score_codex":0.00012594898,"about_ca_system_score_gemma":0.000085385764,"threshold_uncertainty_score":0.55765903},"labels":[],"label_agreement":null},{"id":"W4413096310","doi":"10.1109/iccsp64183.2025.11088608","title":"Talent Tracer – AI Driven Interview Preparation Engine for Job Seekers using LLMs","year":2025,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Seekers; TRACER; Computer science; Applied psychology; Psychology; Political science","score_opus":0.03626295179460489,"score_gpt":0.3521951140334841,"score_spread":0.3159321622388792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413096310","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007470559,0.000056972134,0.99386066,0.0029991153,0.0002135989,0.0005196967,0.0000070910737,0.00041744765,0.0011783852],"genre_scores_gemma":[0.3025649,0.000025301619,0.6927872,0.0019021899,0.000029828325,0.000179503,0.000022338212,0.000008456439,0.00248032],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991757,0.000037040492,0.000235985,0.0003067661,0.00009833374,0.00014616988],"domain_scores_gemma":[0.99921995,0.00004341955,0.00006178217,0.00053134264,0.00011592396,0.000027604869],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024369481,0.00009431551,0.00011622032,0.00012223252,0.00006910258,0.00012836771,0.00051706634,0.00005066979,0.00001488153],"category_scores_gemma":[0.000032751883,0.00008745565,0.000055418495,0.00028347076,0.000020140134,0.0006317129,0.00013215888,0.00005662503,0.000008153135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023657283,0.00021592336,0.00049120164,0.00033325888,0.000101501326,0.0000014879994,0.0007797601,0.0012725403,0.05944834,0.5542274,0.120422706,0.2626822],"study_design_scores_gemma":[0.00021181286,0.00005167755,0.00062831905,0.00008308039,0.000010978416,0.000002210014,0.0000148224335,0.88150775,0.060583938,0.003006798,0.053753246,0.00014537039],"about_ca_topic_score_codex":0.000009690038,"about_ca_topic_score_gemma":0.0000108005015,"teacher_disagreement_score":0.8802352,"about_ca_system_score_codex":0.0001047197,"about_ca_system_score_gemma":0.000070794886,"threshold_uncertainty_score":0.3566338},"labels":[],"label_agreement":null},{"id":"W4413111174","doi":"10.1002/sim.70227","title":"A Framework for Generating Realistic Synthetic Tabular Data in a Randomized Controlled Trial Setting","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Randomized controlled trial; Synthetic data; Copula (linguistics); Artificial intelligence; Machine learning; Data mining; Econometrics; Medicine; Mathematics","score_opus":0.03481874690734359,"score_gpt":0.3819513484906666,"score_spread":0.347132601583323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413111174","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005461434,0.00030268123,0.99125093,0.0030634906,0.00064124836,0.0041508414,0.00016356142,0.00009466779,0.000277956],"genre_scores_gemma":[0.026929254,0.00010327529,0.9702732,0.00074566493,0.00014939894,0.0013801223,0.00033141693,0.000011014639,0.00007663276],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99686974,0.0006077505,0.0013253465,0.0005877721,0.0003119198,0.0002974451],"domain_scores_gemma":[0.9827983,0.015193054,0.00038861248,0.0014521301,0.00012750147,0.00004041482],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008428017,0.00017516117,0.0013378435,0.00040744446,0.00007466012,0.00006272776,0.0013280041,0.00010048161,0.000009525116],"category_scores_gemma":[0.080666825,0.00013846085,0.000032754,0.00054110767,0.00018465825,0.00012047697,0.00027458408,0.00029975266,8.853417e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.05648784,0.000051720734,0.000009756437,0.00007892392,0.00002852018,0.000014140232,0.00024711242,0.0000349771,0.000078678975,0.928783,0.0038471932,0.010338138],"study_design_scores_gemma":[0.34623167,0.00003691098,0.0000042573297,0.000412759,0.000030972427,4.6535402e-7,0.000027841375,0.43612418,0.000014211543,0.21688378,0.00016305062,0.00006991584],"about_ca_topic_score_codex":0.0000976849,"about_ca_topic_score_gemma":0.000067209854,"teacher_disagreement_score":0.7118992,"about_ca_system_score_codex":0.00009263944,"about_ca_system_score_gemma":0.00022178331,"threshold_uncertainty_score":0.9270771},"labels":[],"label_agreement":null},{"id":"W4413135014","doi":"10.1002/isaf.70014","title":"Introducing DART: A Novel Deep Adaptive Upsampling Technique for Handling Class Imbalance","year":2025,"lang":"en","type":"article","venue":"Intelligent systems in accounting, finance and management/Intelligent systems in accounting, finance & management","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Roads University","funders":"","keywords":"Dart; Upsampling; Class (philosophy); Computer science; Artificial intelligence; Parallel computing; Algorithm; Programming language","score_opus":0.018667170096489768,"score_gpt":0.2759751859412146,"score_spread":0.25730801584472485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413135014","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019311513,0.008245665,0.9684946,0.00028838977,0.003955289,0.011073021,0.000039425046,0.0005896965,0.00538277],"genre_scores_gemma":[0.8424251,0.014467485,0.12302269,0.0005633851,0.0003931977,0.014922822,0.000079005484,0.00017548079,0.003950842],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9892156,0.00019999617,0.0037290698,0.0035898967,0.0010903297,0.0021751162],"domain_scores_gemma":[0.99387026,0.00039898435,0.002137701,0.0029683376,0.0005384661,0.000086235625],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0060608718,0.0013382301,0.001729216,0.0030663842,0.0006297689,0.0017655774,0.00391631,0.00050767616,0.0000035168325],"category_scores_gemma":[0.00019891714,0.0014964817,0.00028171457,0.0034600005,0.00024279914,0.0021427076,0.0022152918,0.0008794232,0.000046837864],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014006409,0.0006501294,0.004732298,0.0062538176,0.00027914823,0.00011895307,0.000694198,0.06454468,0.0006638467,0.88311195,0.00405219,0.034758706],"study_design_scores_gemma":[0.0018835459,0.0001888206,0.002436102,0.017001716,0.00013141628,0.000052868985,0.0026799738,0.5152907,0.0035876224,0.0050018863,0.4492773,0.0024680952],"about_ca_topic_score_codex":0.0010011428,"about_ca_topic_score_gemma":0.00026460347,"teacher_disagreement_score":0.8781101,"about_ca_system_score_codex":0.0015358633,"about_ca_system_score_gemma":0.000107588115,"threshold_uncertainty_score":0.9999369},"labels":[],"label_agreement":null},{"id":"W4413215614","doi":"10.1145/3712255.3726544","title":"Resampling Framework Based on Swarm Intelligence Optimization for Imbalanced Data Classification","year":2025,"lang":"en","type":"article","venue":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Swarm intelligence; Resampling; Artificial intelligence; Machine learning; Data mining; Particle swarm optimization","score_opus":0.06434208009306372,"score_gpt":0.3166632246331814,"score_spread":0.25232114454011767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413215614","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029416112,0.00006225385,0.99220717,0.003292228,0.00027235906,0.0007055496,0.0000347683,0.00015771309,0.00032637492],"genre_scores_gemma":[0.5621735,0.000032594588,0.43750167,0.00015472368,0.000018925832,0.0000445848,0.000057367033,0.0000046985833,0.000011951099],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984363,0.000027772285,0.00045964983,0.0006177328,0.00028135988,0.0001772336],"domain_scores_gemma":[0.9979222,0.00033591618,0.00039682354,0.00049975776,0.0008051255,0.000040175135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003589284,0.00016545474,0.00018594922,0.00020263091,0.00032077776,0.00015540027,0.0015029274,0.00010546699,0.0000021848066],"category_scores_gemma":[0.00041486198,0.00014717982,0.000037639733,0.0006499528,0.0001427564,0.0004087974,0.00040671916,0.0001441343,9.541361e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010577123,0.00022306753,0.0065931696,0.00032997134,0.000027736358,3.9016964e-8,0.00020827644,0.25896844,0.0019219639,0.6723497,0.003972025,0.055299852],"study_design_scores_gemma":[0.00014186381,0.00005300718,0.03161119,0.00029325433,0.000013378445,0.0000010429427,0.000058027905,0.88257474,0.001918904,0.08301331,0.00019879904,0.0001224992],"about_ca_topic_score_codex":0.0000037263053,"about_ca_topic_score_gemma":2.64532e-7,"teacher_disagreement_score":0.62360626,"about_ca_system_score_codex":0.00007792388,"about_ca_system_score_gemma":0.00017772813,"threshold_uncertainty_score":0.6001819},"labels":[],"label_agreement":null},{"id":"W4413274834","doi":"10.1016/j.bspc.2025.108347","title":"Supervised sequential contrastive regression: Improving performance on imbalanced rehabilitation exercises","year":2025,"lang":"en","type":"article","venue":"Biomedical Signal Processing and Control","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Toronto Rehabilitation Institute; University Health Network","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Regression; Rehabilitation; Artificial intelligence; Machine learning; Regression analysis; Linear regression; Pattern recognition (psychology); Physical medicine and rehabilitation; Statistics; Mathematics; Physical therapy; Medicine","score_opus":0.008597259272130895,"score_gpt":0.25468399584053886,"score_spread":0.24608673656840796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413274834","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015622043,0.00039601684,0.9789089,0.0037735137,0.00013948591,0.00034865615,0.000011612808,0.000415321,0.0003844818],"genre_scores_gemma":[0.98812866,0.000019919606,0.0106553575,0.0008771631,0.00007543841,0.00012550544,0.000013824997,0.000006806075,0.00009734243],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99831444,0.00010208676,0.00035987826,0.0005483172,0.00037725785,0.00029803396],"domain_scores_gemma":[0.9989862,0.00031313288,0.0001422808,0.0002636179,0.00017359441,0.00012116949],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048738735,0.00019121244,0.00027428448,0.00019049124,0.0003412189,0.00022916142,0.00045359792,0.00013903744,0.000008682357],"category_scores_gemma":[0.00018873248,0.0001452558,0.000042289277,0.00043420505,0.0002983291,0.0005122659,0.00008471981,0.00021715695,0.000004685861],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018458394,0.000105222585,0.0004458182,0.00016091089,0.000010216559,0.0000029433036,0.00012699509,0.0000017410384,0.04202682,0.0020893698,0.0005057689,0.9543396],"study_design_scores_gemma":[0.0063277255,0.0014089516,0.022876939,0.001967092,0.00006550519,0.00001159644,0.00016888308,0.9274005,0.029870987,0.0046901708,0.0045345686,0.000677073],"about_ca_topic_score_codex":0.000007551925,"about_ca_topic_score_gemma":2.6085016e-7,"teacher_disagreement_score":0.9725066,"about_ca_system_score_codex":0.000074131385,"about_ca_system_score_gemma":0.0002338342,"threshold_uncertainty_score":0.592336},"labels":[],"label_agreement":null},{"id":"W4413363767","doi":"10.1016/j.procs.2025.07.152","title":"Towards effective and robust bank fraud detection thanks to machine learning","year":2025,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Computer security","score_opus":0.008544032707416823,"score_gpt":0.24758545687467567,"score_spread":0.23904142416725885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413363767","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008815176,0.00008042513,0.9875624,0.00090509583,0.0006811435,0.000523706,0.0000016170007,0.00071726786,0.0007131629],"genre_scores_gemma":[0.668104,0.0000128719175,0.33093193,0.0007476306,0.00004910646,0.00010341257,9.666729e-7,0.0000051105167,0.000044942433],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979676,0.000058136364,0.0002116522,0.0009690065,0.00040270734,0.00039087058],"domain_scores_gemma":[0.9988025,0.000113229326,0.000085531436,0.0005462139,0.00029870548,0.00015384579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009719642,0.00018464295,0.00017768246,0.0005913353,0.00047972947,0.0006325275,0.0015392011,0.000059763282,0.0000013201374],"category_scores_gemma":[0.00030609683,0.0001727115,0.000026273376,0.0026433442,0.0002052916,0.0012278134,0.0014372967,0.00027792575,0.000018142278],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060894545,0.00002887081,0.0014421357,0.00003635558,0.000004938843,0.0000020009763,0.0007456438,0.00048989116,0.009497138,0.01218632,0.00015647501,0.97540414],"study_design_scores_gemma":[0.00018912868,0.00023418228,0.039554596,0.00007188329,0.000004176443,0.000020814174,0.000007002706,0.81484073,0.13977668,0.0024910802,0.0025330805,0.0002766634],"about_ca_topic_score_codex":0.000033051612,"about_ca_topic_score_gemma":0.0000101534015,"teacher_disagreement_score":0.97512746,"about_ca_system_score_codex":0.00014586448,"about_ca_system_score_gemma":0.000186047,"threshold_uncertainty_score":0.70429707},"labels":[],"label_agreement":null},{"id":"W4413393717","doi":"10.23919/indiacom66777.2025.11115819","title":"A Comprehensive Review of Machine Learning Techniques in Fraud Detection","year":2025,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence","score_opus":0.015245209603024942,"score_gpt":0.2933885586018869,"score_spread":0.27814334899886195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413393717","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009681664,0.0045781727,0.98711586,0.00089732313,0.00003324211,0.00029335695,0.000001030912,0.0005182466,0.006465975],"genre_scores_gemma":[0.32280025,0.038462985,0.6322792,0.005224521,0.000012681691,0.00024846935,0.000021064216,0.000012594318,0.0009382051],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99918246,0.000101426034,0.00030208132,0.00021161184,0.00010833551,0.000094070114],"domain_scores_gemma":[0.99925405,0.00007683599,0.0001063176,0.00041904062,0.00013146595,0.0000123085465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002622176,0.0000745483,0.00017947792,0.0002464537,0.000026157031,0.0000147783585,0.00045167643,0.000042848264,0.000012096178],"category_scores_gemma":[0.00012126522,0.000068312955,0.000031570977,0.00089175144,0.000026207928,0.00022320889,0.00018693242,0.00016452296,0.000004100506],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000052460646,0.000081005455,0.0014987566,0.003365072,0.000010169048,0.000002315051,0.00004742057,0.0000013404763,0.09333169,0.052606262,0.001575014,0.8474757],"study_design_scores_gemma":[0.00009482806,0.000059770395,0.0029511927,0.002934394,0.0000031265827,0.0000032871599,0.0000070102815,0.00786712,0.83769214,0.002865528,0.14539988,0.00012171981],"about_ca_topic_score_codex":0.00009316163,"about_ca_topic_score_gemma":0.000011142082,"teacher_disagreement_score":0.847354,"about_ca_system_score_codex":0.000045542285,"about_ca_system_score_gemma":0.000030560434,"threshold_uncertainty_score":0.27857214},"labels":[],"label_agreement":null},{"id":"W4413394506","doi":"10.1109/iaecst64597.2024.11117868","title":"Telecom Fraud Detection Based on Deep Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Telecommunications; Computer science; Deep learning; Computer security; Artificial intelligence","score_opus":0.010057991933525159,"score_gpt":0.24772989619507157,"score_spread":0.2376719042615464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413394506","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017865666,0.000023500263,0.980465,0.0007353917,0.00021954397,0.0000710138,3.6171747e-7,0.0027767622,0.015529797],"genre_scores_gemma":[0.9088756,0.000005062135,0.08989314,0.00043384562,0.000037139387,0.000026668324,0.000004161895,0.00000831992,0.00071609014],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924546,0.000044367713,0.00010537273,0.00030957666,0.00016570199,0.000129535],"domain_scores_gemma":[0.99943495,0.00011393089,0.000019402336,0.0003724162,0.000026589572,0.00003269262],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020145063,0.00007415061,0.000052668853,0.00017558766,0.000080200225,0.00027466659,0.0003514256,0.00004680661,0.00006827493],"category_scores_gemma":[0.00005179233,0.0000643956,0.000030746956,0.00043688813,0.00001223452,0.00033834451,0.000046958798,0.0002010288,0.000427865],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018085015,0.000018570969,0.000051943392,0.000013298345,0.000003140771,0.0000063565312,0.000042719294,0.00036933753,0.009757008,0.045406137,0.0012041425,0.94312555],"study_design_scores_gemma":[0.000028010256,0.00007151673,0.00051203184,0.0000135013215,8.811843e-7,0.0000022598863,0.0000030269887,0.8392748,0.09755477,0.0010578142,0.061400928,0.000080430014],"about_ca_topic_score_codex":0.0000073400124,"about_ca_topic_score_gemma":0.0000047311873,"teacher_disagreement_score":0.9430451,"about_ca_system_score_codex":0.000062725645,"about_ca_system_score_gemma":0.000022228767,"threshold_uncertainty_score":0.54994816},"labels":[],"label_agreement":null},{"id":"W4413912380","doi":"10.5267/j.ijdns.2025.7.003","title":"EFC-Tomek: An effective undersampling technique for credit card fraud detection","year":2025,"lang":"en","type":"article","venue":"International Journal of Data and Network Science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Undersampling; Credit card fraud; Credit card; Computer science; Business; Artificial intelligence; Finance; Payment","score_opus":0.03184383700583517,"score_gpt":0.36447503392579556,"score_spread":0.3326311969199604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413912380","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016215787,0.00010418913,0.99586964,0.0006318694,0.0013160388,0.00025105398,0.00004171001,0.000042831394,0.00012108006],"genre_scores_gemma":[0.71182305,0.000088380686,0.2874409,0.0002540826,0.00034596177,0.00002006028,0.000015446716,0.0000034287439,0.000008683315],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863017,0.00004751637,0.00031886203,0.00037703765,0.0004421627,0.00018425351],"domain_scores_gemma":[0.9980549,0.00029825215,0.00029678887,0.0005483321,0.00072692696,0.00007476272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026195655,0.000090911475,0.00013633555,0.00036825097,0.00022164665,0.00044019808,0.0038435915,0.000048173108,7.812326e-7],"category_scores_gemma":[0.00036075505,0.00008094948,0.000028558577,0.00060039223,0.00020417523,0.0036479763,0.00071756844,0.00016655118,3.8646309e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013199523,0.00010515956,0.0012256729,0.000019536186,0.00009748309,0.000009239517,0.0001704744,0.000523296,0.09612465,0.06393467,0.004315601,0.83334225],"study_design_scores_gemma":[0.0015634865,0.0009770247,0.021701522,0.0007431306,0.00006573364,0.00043271,0.00015915626,0.46366337,0.25767833,0.1868153,0.06557188,0.0006283354],"about_ca_topic_score_codex":0.000009232602,"about_ca_topic_score_gemma":0.000010205144,"teacher_disagreement_score":0.8327139,"about_ca_system_score_codex":0.00013202244,"about_ca_system_score_gemma":0.00020542137,"threshold_uncertainty_score":0.7142413},"labels":[],"label_agreement":null},{"id":"W4414166064","doi":"10.1109/tmm.2025.3607712","title":"Oversampling With GAN via Meta-Learning for Imbalanced Data","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Oversampling; Discriminator; Generator (circuit theory); Consistency (knowledge bases); Mode (computer interface); Pattern recognition (psychology); Contrast (vision); Bayesian probability","score_opus":0.061232010547466464,"score_gpt":0.31698107717266627,"score_spread":0.2557490666251998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414166064","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000044863275,0.00003085523,0.9971856,0.0007742013,0.0003503749,0.00053206226,0.00010021652,0.00075534434,0.00022650842],"genre_scores_gemma":[0.41811526,0.000028965076,0.58052945,0.00030742135,0.000021362139,0.00031540045,0.0000711605,0.00001798389,0.0005930087],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99843746,0.000057826514,0.00026427108,0.0007200157,0.00022776783,0.00029263424],"domain_scores_gemma":[0.9975522,0.00054270326,0.000109903405,0.0015957331,0.00012854996,0.0000709153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000335144,0.00020792203,0.00028347707,0.0002472357,0.00029249754,0.00012520091,0.0014078972,0.00008891647,0.000021226402],"category_scores_gemma":[0.000033978624,0.00017625789,0.000086360145,0.0005478192,0.00006681449,0.00075029855,0.00000866016,0.00031171978,0.000020195179],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003410921,0.00080714765,0.000111687055,0.00018305342,0.0025631147,0.000009079457,0.0008360415,0.038622938,0.05240256,0.00221508,0.0047523035,0.8971559],"study_design_scores_gemma":[0.0008509209,0.000118871685,0.00014368835,0.0000377451,0.0003021145,0.000003788718,0.00002626964,0.8511928,0.13310342,0.0003003078,0.013641411,0.00027866536],"about_ca_topic_score_codex":0.00003003101,"about_ca_topic_score_gemma":0.00003136908,"teacher_disagreement_score":0.8968772,"about_ca_system_score_codex":0.00006662571,"about_ca_system_score_gemma":0.00010721474,"threshold_uncertainty_score":0.7187588},"labels":[],"label_agreement":null},{"id":"W4414231415","doi":"10.1109/amlds63918.2025.11159446","title":"Enhanced Pre-Trained Graph Neural Networks with Applications in Financial Fraud Detection","year":2025,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Robustness (evolution); Modular design; Financial fraud; Artificial neural network; Flexibility (engineering); Task (project management); Context (archaeology); Graph; Domain (mathematical analysis)","score_opus":0.005432626123870248,"score_gpt":0.23971507617126317,"score_spread":0.23428245004739293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414231415","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045997975,0.000017227228,0.99196047,0.00031584344,0.000067873756,0.0005285738,0.0000013356835,0.00059217226,0.0019167078],"genre_scores_gemma":[0.9476847,0.000007814213,0.05110026,0.00037319487,0.000019834506,0.00056156423,0.000010599255,0.000004361024,0.00023767415],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990516,0.000036045778,0.00021208459,0.000389278,0.000107493055,0.00020355014],"domain_scores_gemma":[0.9991512,0.000059784124,0.00006718878,0.000622176,0.000070050366,0.00002964287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012278387,0.00011368088,0.000116175426,0.00023074355,0.00010166157,0.00008041687,0.00060565636,0.000082098864,0.0000034803716],"category_scores_gemma":[0.000023155311,0.00009674928,0.00002508452,0.001653941,0.00004741671,0.0003859546,0.00009003529,0.00016945897,0.0000017504806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000067147754,0.00027849522,0.002275154,0.00003294517,0.000014427483,0.0000020056812,0.00026744496,0.0047582053,0.020195149,0.47386828,0.0010298084,0.49721095],"study_design_scores_gemma":[0.0008443924,0.00017061266,0.19138522,0.000047015186,0.000008792922,0.0000031794334,0.0000309387,0.6112679,0.17478122,0.018485235,0.0024931869,0.00048228708],"about_ca_topic_score_codex":0.000041029354,"about_ca_topic_score_gemma":0.00037772505,"teacher_disagreement_score":0.9430849,"about_ca_system_score_codex":0.0000499598,"about_ca_system_score_gemma":0.00005246899,"threshold_uncertainty_score":0.39453214},"labels":[],"label_agreement":null},{"id":"W4414231693","doi":"10.1109/amlds63918.2025.11159335","title":"Attention-Driven Dual-Level Cost-Sensitive Stacking for Financial Statement Fraud Detection","year":2025,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Financial statement; Weighting; Benchmark (surveying); Transparency (behavior); Anomaly detection; Feature (linguistics); Financial ratio; Range (aeronautics)","score_opus":0.037164629859092024,"score_gpt":0.3128963654068623,"score_spread":0.27573173554777025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414231693","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011766761,0.000004421342,0.9946669,0.0012934479,0.00042973214,0.00086497056,0.00006953285,0.00042986407,0.0010644814],"genre_scores_gemma":[0.6299471,0.000012587803,0.3668626,0.0009634596,0.000048105376,0.00042242615,0.000058714948,0.000008053442,0.0016769153],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99888176,0.000036326317,0.00027193234,0.00040942396,0.00016755583,0.00023300132],"domain_scores_gemma":[0.998969,0.000115483126,0.00012217626,0.00044002122,0.000319275,0.00003401985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030406757,0.00011733655,0.0001273587,0.0001733732,0.00021924835,0.0001420516,0.0002913882,0.00006693887,0.0000060992575],"category_scores_gemma":[0.00014231994,0.000117751675,0.00005771274,0.0003293183,0.00002977695,0.0005277031,0.00017793223,0.000085691034,0.000021686885],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029564777,0.000104517465,0.00025473983,0.00004684269,0.000034718618,0.0000030261692,0.00016576677,0.000038110866,0.05632575,0.51384735,0.026571652,0.402578],"study_design_scores_gemma":[0.0013177089,0.00021137425,0.046098832,0.00011468428,0.000023749191,0.000004255483,0.00012462167,0.15161188,0.66380906,0.025151974,0.110999495,0.0005323339],"about_ca_topic_score_codex":0.000024446696,"about_ca_topic_score_gemma":0.000073576055,"teacher_disagreement_score":0.6287705,"about_ca_system_score_codex":0.0001992969,"about_ca_system_score_gemma":0.00012781726,"threshold_uncertainty_score":0.4801774},"labels":[],"label_agreement":null},{"id":"W4414706630","doi":"10.1016/j.icte.2025.09.011","title":"Imbalanced classification with label noise: A systematic review and comparative analysis","year":2025,"lang":"en","type":"article","venue":"ICT Express","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus","funders":"Directorate for Computer and Information Science and Engineering; Directorate for STEM Education; National Science Foundation","keywords":"Resampling; Class (philosophy); Identification (biology); Noise (video); Empirical research; Ensemble learning; Domain (mathematical analysis); Multi-label classification","score_opus":0.03347594150859454,"score_gpt":0.313325711634043,"score_spread":0.2798497701254484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414706630","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00036634854,0.006696311,0.9862686,0.0013350033,0.000024079018,0.0012577438,0.00002133132,0.00039177143,0.0036388556],"genre_scores_gemma":[0.9116329,0.0012891687,0.08269082,0.001730302,0.000007294682,0.0012700685,0.0000611613,0.0000064738188,0.0013118095],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986223,0.00017932669,0.00037847707,0.0004527748,0.00020776146,0.00015938334],"domain_scores_gemma":[0.9980606,0.00014027586,0.0002755352,0.0012636471,0.00021036455,0.000049600058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003043861,0.00016078404,0.0006461251,0.00022837015,0.00009979993,0.00016125961,0.0007851808,0.00004456814,0.0000030425563],"category_scores_gemma":[0.000054185944,0.00012128864,0.00003896468,0.0016435812,0.00007110467,0.0004496094,0.00013492574,0.00009984546,0.000009022851],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037754377,0.0005128661,0.0037039148,0.1697081,0.0028167933,0.00000952532,0.0019083597,0.000025935211,0.022785166,0.7812716,0.016234135,0.0009858451],"study_design_scores_gemma":[0.005875794,0.00073304784,0.13659395,0.22071907,0.024227967,0.000073428666,0.0013521089,0.51859105,0.06905949,0.0067623258,0.01087947,0.005132254],"about_ca_topic_score_codex":0.00000875223,"about_ca_topic_score_gemma":0.0000052655914,"teacher_disagreement_score":0.91126657,"about_ca_system_score_codex":0.000050318224,"about_ca_system_score_gemma":0.000042922544,"threshold_uncertainty_score":0.49460074},"labels":[],"label_agreement":null},{"id":"W4414890836","doi":"10.1007/978-981-96-6938-7_39","title":"Addressing Overfitting in an Imbalanced Dataset for MS Progression Prediction","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Overfitting; Oversampling; Bootstrap aggregating; Generalization; Resampling; Stability (learning theory); Principal component analysis; Perceptron; Ensemble learning; Interpretability","score_opus":0.04537730595900261,"score_gpt":0.3195773059497233,"score_spread":0.27419999999072064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414890836","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010923771,0.0033734515,0.9921672,0.000087869696,0.0008623995,0.001389712,0.00080449384,0.00017217295,0.0011318288],"genre_scores_gemma":[0.8005345,0.0027911628,0.13409494,0.0013547859,0.004817073,0.0023799744,0.050858624,0.0002998162,0.0028691667],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978718,0.000083181374,0.0006488475,0.000848097,0.00021939626,0.00032865713],"domain_scores_gemma":[0.9982297,0.00038064417,0.00040661797,0.0008494042,0.000076675984,0.00005695502],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007269683,0.0003271041,0.00050040137,0.00028870214,0.00011965945,0.0003946339,0.000573702,0.0006493171,0.0000011364546],"category_scores_gemma":[0.00008722841,0.0002946058,0.000037071688,0.00014168705,0.00004714871,0.0004138494,0.00020382943,0.00055419997,2.4980014e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019162198,0.00012120006,0.005396558,0.0022074722,0.000071314345,0.000053139614,0.00051574106,0.03867437,0.00036577354,0.10514083,0.017512297,0.8297497],"study_design_scores_gemma":[0.00041542386,0.000108986875,0.00024357435,0.0047652656,0.000010443725,0.000010145748,0.0000020289467,0.96878713,0.00004279598,0.004291196,0.020982692,0.0003402926],"about_ca_topic_score_codex":0.000024286193,"about_ca_topic_score_gemma":0.00012650776,"teacher_disagreement_score":0.9301128,"about_ca_system_score_codex":0.00013715848,"about_ca_system_score_gemma":0.000065477056,"threshold_uncertainty_score":0.9999506},"labels":[],"label_agreement":null},{"id":"W4415127930","doi":"10.3390/risks13100198","title":"Application of Standard Machine Learning Models for Medicare Fraud Detection with Imbalanced Data","year":2025,"lang":"en","type":"article","venue":"Risks","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Columbia College","funders":"","keywords":"Interpretability; Random forest; AdaBoost; Decision tree; Feature selection; Resampling; Preprocessor; Feature (linguistics); Ensemble learning","score_opus":0.04827192005258184,"score_gpt":0.32589928921471273,"score_spread":0.2776273691621309,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415127930","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00030452543,0.000121866455,0.99801224,0.00028618582,0.000040254323,0.00042752744,0.00015550746,0.0003060489,0.0003458097],"genre_scores_gemma":[0.80568963,0.00004988403,0.19381459,0.00004585806,0.000012535166,0.0001200213,0.00022402192,0.0000064306887,0.00003702423],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902964,0.000037442504,0.00020720951,0.00039588904,0.00020584653,0.00012397178],"domain_scores_gemma":[0.9983293,0.00009284671,0.0001848058,0.0011818092,0.00018532366,0.000025932746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040313962,0.00008675153,0.00015209953,0.000105713625,0.00009940589,0.00003407883,0.0010356519,0.00006252272,9.0048854e-7],"category_scores_gemma":[0.00008791656,0.000074955235,0.000016940561,0.00037318192,0.000042074902,0.00045145358,0.00023060612,0.00013081526,7.595351e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013117553,0.000045486817,0.0016466734,0.00014029627,0.000046952493,3.003461e-7,0.00017907952,0.0017473417,0.015300153,0.042523377,0.00085480744,0.93738437],"study_design_scores_gemma":[0.0003760008,0.00009648426,0.00061206525,0.00003739777,0.000012765517,8.278001e-7,0.000019104904,0.92147344,0.057697777,0.007931235,0.011657059,0.00008582502],"about_ca_topic_score_codex":0.00009179469,"about_ca_topic_score_gemma":0.000049848495,"teacher_disagreement_score":0.93729854,"about_ca_system_score_codex":0.000048498285,"about_ca_system_score_gemma":0.00007706361,"threshold_uncertainty_score":0.30565858},"labels":[],"label_agreement":null},{"id":"W4415185471","doi":"10.1016/j.patcog.2025.112610","title":"Calibrated mixup for imbalanced regression on tabular data","year":2025,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Information Technology Research Centre; Military Institute of Science and Technology; Ministry of Science and ICT, South Korea; National Research Foundation of Korea; Ministry of Education","keywords":"Smoothing; Consistency (knowledge bases); Regression; Calibration; Synthetic data; Fidelity; k-nearest neighbors algorithm; Key (lock)","score_opus":0.07969439146022948,"score_gpt":0.3383243437362332,"score_spread":0.2586299522760037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415185471","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029985157,0.000026522252,0.9917928,0.0024029568,0.0004243548,0.00053920073,0.0004742347,0.00057309004,0.0007683417],"genre_scores_gemma":[0.81930393,0.00014203887,0.15965228,0.0075927903,0.00020549794,0.00069354253,0.011748223,0.000040995666,0.0006206809],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99862987,0.00008023501,0.00026268652,0.00065218186,0.00016239271,0.00021262451],"domain_scores_gemma":[0.99807715,0.00015601101,0.00013942215,0.0014560702,0.00013143198,0.00003991669],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003117051,0.00014523586,0.00014965638,0.00017321075,0.000121740995,0.00014784263,0.0012424357,0.00009823593,0.000016856762],"category_scores_gemma":[0.00015892327,0.00013101217,0.00003224029,0.00033903032,0.000023175548,0.00067688304,0.00029449558,0.000115748255,0.000082885985],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027076034,0.00013216093,0.0006900973,0.00006349091,0.000016558726,0.0000024195808,0.000021141172,6.052829e-7,0.0069978014,0.00076061895,0.064142905,0.9271451],"study_design_scores_gemma":[0.0028987012,0.00029719263,0.010679491,0.001489331,0.000046040823,0.0000055970763,0.00003342153,0.31115118,0.56203604,0.041209057,0.06929419,0.00085976825],"about_ca_topic_score_codex":0.000013887414,"about_ca_topic_score_gemma":0.0000071898053,"teacher_disagreement_score":0.9262854,"about_ca_system_score_codex":0.000047590955,"about_ca_system_score_gemma":0.00004732984,"threshold_uncertainty_score":0.53425217},"labels":[],"label_agreement":null},{"id":"W4415551573","doi":"10.70891/jair.2025.080018","title":"Blockchain Fraud Detection Using Ensemble Graph Neural Networks","year":2025,"lang":"","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Graph; Database transaction; Anonymity; Modular design; Cryptocurrency; Blockchain; Convolutional neural network; Artificial neural network","score_opus":0.1673559395360158,"score_gpt":0.43175027877153277,"score_spread":0.264394339235517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415551573","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03792794,0.0019006061,0.95434004,0.0019266739,0.0030566696,0.00053792546,0.000003856817,0.00005811314,0.00024819918],"genre_scores_gemma":[0.9806112,0.00083294144,0.017362118,0.00012554538,0.00088947004,0.000010212368,7.048861e-7,0.000028150655,0.00013964022],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99099904,0.0020051172,0.002665035,0.00079150626,0.0021168427,0.0014224539],"domain_scores_gemma":[0.99113744,0.0013050709,0.0010629436,0.0012991236,0.004809898,0.00038554522],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.012375265,0.00039193686,0.000688276,0.0034629798,0.0012494486,0.0014761486,0.003379049,0.00050768675,0.00006790055],"category_scores_gemma":[0.0021085073,0.00039062503,0.0004208053,0.007990291,0.0009464568,0.0009949462,0.00091634155,0.0036382545,0.000027964752],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031425507,0.0004051279,0.00008273429,0.000062495965,0.00009618626,0.00010057275,0.0005139499,0.05217779,0.06457905,0.022269284,0.00038764416,0.85901093],"study_design_scores_gemma":[0.000036358575,0.0004834433,0.000053077514,0.00032539028,0.000024557394,0.000087530505,0.00056581217,0.69261163,0.25762814,0.047662426,0.0003186475,0.00020299166],"about_ca_topic_score_codex":0.00021026123,"about_ca_topic_score_gemma":0.00009291821,"teacher_disagreement_score":0.9426833,"about_ca_system_score_codex":0.00080288417,"about_ca_system_score_gemma":0.0010928491,"threshold_uncertainty_score":0.99985456},"labels":[],"label_agreement":null},{"id":"W4415599542","doi":"10.2139/ssrn.5669479","title":"ETU-SAM: Efficient and Transparent Uncertainty Estimation for Segment Anything Model in Ultrasound Segmentation","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Segmentation; Estimator; Key (lock); Bayesian inference; Bayesian probability; Inference; Uncertainty quantification; Software deployment; Reliability (semiconductor)","score_opus":0.026282060940178736,"score_gpt":0.31138575960819054,"score_spread":0.2851036986680118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415599542","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01711251,0.0018771196,0.97580016,0.0017399209,0.00054006017,0.002573472,0.00017148159,0.00012593565,0.00005936108],"genre_scores_gemma":[0.82217205,0.0148587655,0.1614598,0.00020386271,0.000098028955,0.00056645385,0.00030224974,0.00003896607,0.00029982167],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99239594,0.00040163202,0.0018242473,0.0014972675,0.0008770629,0.0030038345],"domain_scores_gemma":[0.99684405,0.00047537687,0.0012031763,0.0008639119,0.00043265024,0.00018083505],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0069673574,0.00074246316,0.0007695965,0.0008763222,0.00067139755,0.0008221888,0.0015057725,0.00046234304,0.0000035469309],"category_scores_gemma":[0.00025174028,0.0007970438,0.00025397964,0.00057988113,0.00013808977,0.0006992483,0.00032860233,0.0039182217,0.000001828235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00012767056,0.00027036507,0.000080649064,0.00024979017,0.000121864636,8.475732e-7,0.002699921,0.76086146,0.0017198191,0.10435762,0.000028314955,0.12948167],"study_design_scores_gemma":[0.0013423942,0.00023448332,0.00014486506,0.00063542847,0.00010200843,0.00008495038,0.0007085538,0.77558345,0.0019559406,0.21865463,0.000026341948,0.000526972],"about_ca_topic_score_codex":0.00014827974,"about_ca_topic_score_gemma":0.00049816084,"teacher_disagreement_score":0.81434035,"about_ca_system_score_codex":0.008837774,"about_ca_system_score_gemma":0.008070705,"threshold_uncertainty_score":0.99944806},"labels":[],"label_agreement":null},{"id":"W4415649477","doi":"10.3390/jrfm18110605","title":"Using Machine Learning to Detect Financial Statement Fraud: A Cross-Country Analysis Applied to Wirecard AG","year":2025,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Financial statement; Vendor; Pipeline (software); Boosting (machine learning); Gradient boosting; Statement (logic); Ensemble learning","score_opus":0.010471847398814259,"score_gpt":0.2840781956072661,"score_spread":0.27360634820845187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415649477","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06413889,0.00014795906,0.93474036,0.000121341785,0.00023527342,0.00027358608,0.000017556778,0.000045488,0.00027954875],"genre_scores_gemma":[0.6821275,0.00032805037,0.31654173,0.0007732035,0.000081699145,0.000020981593,0.000003104527,0.000007855995,0.000115883864],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982474,0.000058252463,0.00067072944,0.00035331788,0.00038925192,0.00028106177],"domain_scores_gemma":[0.9989269,0.00004310936,0.00039613657,0.0003607023,0.00015757691,0.000115593764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011551853,0.0001782806,0.00039569402,0.0010829085,0.00029350515,0.00030054012,0.0006444705,0.00005901806,0.0000042824217],"category_scores_gemma":[0.00017135021,0.00016737122,0.00011000617,0.0020065533,0.000025964751,0.0002552241,0.0005417525,0.00027412997,0.000004372235],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027995033,0.00009455085,0.019673852,0.00007565628,0.00021531651,0.00006552383,0.00093591184,0.030314796,0.0006455452,0.025126176,0.0017206614,0.92085207],"study_design_scores_gemma":[0.0017243343,0.00057484495,0.45592093,0.00023579616,0.00084384554,0.0000088584575,0.00011577046,0.020067386,0.003622331,0.012060738,0.5040402,0.0007849612],"about_ca_topic_score_codex":0.00008043149,"about_ca_topic_score_gemma":0.000057843867,"teacher_disagreement_score":0.9200671,"about_ca_system_score_codex":0.00020108708,"about_ca_system_score_gemma":0.000081520615,"threshold_uncertainty_score":0.68252003},"labels":[],"label_agreement":null},{"id":"W4415722142","doi":"10.3390/jrfm18110612","title":"A Systematic Review of Artificial Intelligence Applied to Compliance: Fraud Detection in Cryptocurrency Transactions","year":2025,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Agencia Estatal de Investigación; European Commission; Ministerio de Ciencia, Innovación y Universidades","keywords":"Cryptocurrency; Transparency (behavior); Bridging (networking); Key (lock); Quality (philosophy); Applications of artificial intelligence","score_opus":0.01751035328781938,"score_gpt":0.2810347906765492,"score_spread":0.2635244373887298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415722142","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017440796,0.0019607753,0.9967938,0.00013826064,0.00018169566,0.0005893499,0.000003658297,0.000013002865,0.00014501358],"genre_scores_gemma":[0.86664855,0.021818832,0.11094497,0.00040899284,0.000024115034,0.00013347981,5.6527836e-7,0.000004578261,0.000015918746],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9987266,0.000054422206,0.0008119025,0.00013601272,0.00017839579,0.000092640454],"domain_scores_gemma":[0.9991878,0.000051207277,0.00038353927,0.00024226759,0.00010677067,0.000028412138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007863799,0.00007818665,0.0003363426,0.00039750175,0.00004963643,0.000027970596,0.0003868061,0.000028064622,0.000001798246],"category_scores_gemma":[0.000113335875,0.0000695143,0.000052381518,0.000925377,0.000019675652,0.00014046284,0.000042285785,0.00014430702,0.0000022288418],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000232655,0.00012540129,0.000010847682,0.048488986,0.000012852744,0.0000037198104,0.00024858053,0.000042827185,0.0000956682,0.074300006,0.000076434866,0.8765714],"study_design_scores_gemma":[0.0009683651,0.0009845343,0.024925323,0.60038066,0.0009313355,0.00004017544,0.0010208902,0.013575999,0.026172299,0.32363477,0.0061932798,0.0011723288],"about_ca_topic_score_codex":0.0000045340967,"about_ca_topic_score_gemma":0.000010254781,"teacher_disagreement_score":0.8858489,"about_ca_system_score_codex":0.000055212346,"about_ca_system_score_gemma":0.00002708153,"threshold_uncertainty_score":0.2834711},"labels":[],"label_agreement":null},{"id":"W4415974865","doi":"10.1016/j.procs.2025.09.519","title":"Disentangled Deep Smoothed Bootstrap for Fair Imbalanced Regression","year":2025,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Fondation du Risque; CNP Assurances","keywords":"Benchmark (surveying); Representation (politics); Focus (optics); Regression; Deep learning; External Data Representation; Latent variable; Big data","score_opus":0.017933237357502557,"score_gpt":0.308492226226615,"score_spread":0.2905589888691124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415974865","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014799971,0.00008887391,0.9921419,0.0024146137,0.0011677574,0.000808714,0.0000065505797,0.0010249973,0.0008665678],"genre_scores_gemma":[0.42168418,0.000016495387,0.5766392,0.0011339146,0.00009624898,0.0002586786,0.000008389877,0.0000094666775,0.00015345855],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99720395,0.000030513556,0.0004082302,0.0011990924,0.00052233663,0.00063587667],"domain_scores_gemma":[0.99767023,0.00018027908,0.00020424787,0.0013155402,0.00047154888,0.0001581719],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007330981,0.00025624302,0.00026764086,0.00046872662,0.0005148181,0.0005960138,0.0039940025,0.00008014813,0.0000024665069],"category_scores_gemma":[0.00019106184,0.00021711961,0.00008854889,0.00218755,0.00039407203,0.0015993997,0.0008809032,0.00014502204,0.00001425729],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038163675,0.00025105794,0.0025862493,0.00017767228,0.000017417042,0.0000049172972,0.0006967305,0.000058933187,0.0406896,0.41936302,0.011813474,0.5243028],"study_design_scores_gemma":[0.00087109575,0.00014156761,0.01166356,0.00019076388,0.000008698579,0.000011260867,0.000014504015,0.80154717,0.13117948,0.04514138,0.008726074,0.00050441246],"about_ca_topic_score_codex":0.0000024238473,"about_ca_topic_score_gemma":0.0000022605625,"teacher_disagreement_score":0.8014883,"about_ca_system_score_codex":0.00017128265,"about_ca_system_score_gemma":0.0004936566,"threshold_uncertainty_score":0.8853881},"labels":[],"label_agreement":null},{"id":"W4416021517","doi":"10.36948/ijfmr.2025.v07i06.59649","title":"Securing Credit: A Hybrid multi-dimensional model using ensemble machine learning classifier with data sampling to detect and prevent credit card fraud.","year":2025,"lang":"","type":"article","venue":"International Journal For Multidisciplinary Research","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Oversampling; Credit card fraud; Ensemble learning; Credit card; Classifier (UML); k-nearest neighbors algorithm; Ensemble forecasting","score_opus":0.24992989053295928,"score_gpt":0.4748435481249088,"score_spread":0.22491365759194953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416021517","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060246095,0.0011416934,0.92941886,0.0047773644,0.0015976811,0.0015042479,0.0011454748,0.00011168323,0.000056871806],"genre_scores_gemma":[0.437755,0.00038665748,0.55903333,0.00009114945,0.00068088155,0.000115854156,0.0002581533,0.00007755297,0.0016014308],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9917882,0.0006382019,0.0013363025,0.0020333775,0.0028668516,0.0013370755],"domain_scores_gemma":[0.99211234,0.0014077214,0.0005246824,0.0015084932,0.0038080197,0.0006387635],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.006814805,0.0005985949,0.0006303342,0.0021574812,0.0027869274,0.0020537178,0.005265391,0.00022788804,0.000017306043],"category_scores_gemma":[0.0018089312,0.0005594777,0.00017082156,0.0008855851,0.00040177748,0.0024308297,0.010303031,0.0028526648,0.000009293996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006731334,0.0015101738,0.0033038256,0.00060410664,0.0023408919,0.000771082,0.0041967197,0.6056737,0.15623526,0.0024080472,0.008486261,0.20773861],"study_design_scores_gemma":[0.0020025547,0.0005198035,0.0005871535,0.0019233954,0.000061161074,0.0006976373,0.00021673461,0.97439593,0.010736147,0.004689793,0.0036213272,0.000548332],"about_ca_topic_score_codex":0.00015297868,"about_ca_topic_score_gemma":0.0001258917,"teacher_disagreement_score":0.37750888,"about_ca_system_score_codex":0.0012722847,"about_ca_system_score_gemma":0.0020803912,"threshold_uncertainty_score":0.99968565},"labels":[],"label_agreement":null},{"id":"W4416035400","doi":"10.18653/v1/2025.emnlp-main.1637","title":"Not What the Doctor Ordered: Surveying LLM-based De-identification and Quantifying Clinical Information Loss","year":2025,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Arthritis Society; Canadian Institute for Advanced Research; Alberta Health Services","keywords":"Information system; MEDLINE; Data loss; Information loss; Risk assessment","score_opus":0.06983332277345129,"score_gpt":0.37491015020687757,"score_spread":0.3050768274334263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416035400","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013402821,0.000033347125,0.9759025,0.009399263,0.00036395574,0.0002650015,0.0000036373256,0.00035391466,0.0002755859],"genre_scores_gemma":[0.95073074,0.00019474946,0.045063574,0.0037300678,0.000016401753,0.00004848401,0.00003596988,0.000003375174,0.00017663902],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99856883,0.00025849516,0.00056377455,0.00024837157,0.00019037027,0.00017016049],"domain_scores_gemma":[0.9980619,0.0006804932,0.0001975171,0.00082813355,0.00019443851,0.000037497382],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0028817272,0.00009649379,0.000115438655,0.00014043968,0.00024521732,0.001575401,0.0007876128,0.00008527408,0.0000059599124],"category_scores_gemma":[0.0005726728,0.000072768074,0.000036496567,0.00048081798,0.00010522097,0.0034796442,0.00018775645,0.00016213625,0.00003184016],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002020764,0.00007913342,0.025046213,0.000074899675,0.000019461411,6.363381e-7,0.00032324772,0.00003171748,0.0011419094,0.3491075,0.0052949865,0.61886007],"study_design_scores_gemma":[0.00068297196,0.000045608787,0.4600315,0.00014348514,0.000015853473,0.0000050337194,0.00029687744,0.4474853,0.043006077,0.003571849,0.044383537,0.0003319018],"about_ca_topic_score_codex":0.000053298547,"about_ca_topic_score_gemma":0.000026882586,"teacher_disagreement_score":0.9373279,"about_ca_system_score_codex":0.000049560484,"about_ca_system_score_gemma":0.00016037206,"threshold_uncertainty_score":0.99946105},"labels":[],"label_agreement":null},{"id":"W4416799704","doi":"10.1109/snpd65828.2025.11253742","title":"Multivariate Bounded Support Kotz Mixture Model: Addressing Financial Fraud and Network Security Challenges","year":2025,"lang":"","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Algoma University; Concordia University","funders":"","keywords":"Credit card fraud; Credit card; Intrusion detection system; Robustness (evolution); The Internet; Network security; Evasion (ethics); Key (lock)","score_opus":0.04019348780060784,"score_gpt":0.307016282237064,"score_spread":0.2668227944364562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416799704","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00048306785,0.00441938,0.96085376,0.009481219,0.001128889,0.0007979543,0.000070859984,0.0008367316,0.02192817],"genre_scores_gemma":[0.7513876,0.0049312003,0.23733684,0.0033412634,0.00036584138,0.000109259665,0.000043691354,0.00003701854,0.0024472864],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99541384,0.00030931376,0.00092695194,0.0017720191,0.0005011205,0.0010767695],"domain_scores_gemma":[0.9968905,0.00022292594,0.00040517625,0.0018728189,0.000366422,0.00024218924],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001301941,0.0006276979,0.0007514682,0.00025257684,0.0008920841,0.0009505901,0.0016406842,0.0007596581,0.000066686334],"category_scores_gemma":[0.00028909568,0.0006423719,0.00013364734,0.00084261,0.00041491946,0.0015000635,0.0017852022,0.0009090912,0.000018021248],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000061207335,0.00023650851,0.000120694174,0.0003117784,0.00005657601,0.000017673117,0.0023706397,0.00019455732,0.00027227937,0.77973026,0.05115975,0.16546808],"study_design_scores_gemma":[0.00066864316,0.00009025659,0.002726342,0.0004264077,0.000045628178,0.000009341213,0.00003942065,0.7180953,0.0019367137,0.24600756,0.029301027,0.0006533501],"about_ca_topic_score_codex":0.000052227624,"about_ca_topic_score_gemma":0.000112936745,"teacher_disagreement_score":0.7509045,"about_ca_system_score_codex":0.00015922858,"about_ca_system_score_gemma":0.0010891706,"threshold_uncertainty_score":0.99960274},"labels":[],"label_agreement":null},{"id":"W4416873441","doi":"10.1109/inc465408.2025.11256257","title":"GAM Oversampling and GMM Based Resampling Algorithm for Classification of Imbalanced Sensitive Credit Data Sets","year":2025,"lang":"","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Oversampling; Undersampling; Resampling; Robustness (evolution); Jackknife resampling; Boosting (machine learning); Class (philosophy); Pattern recognition (psychology)","score_opus":0.07641591695863235,"score_gpt":0.3548904516408329,"score_spread":0.2784745346822005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416873441","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002305067,0.00020969461,0.9905497,0.0028868918,0.0007072199,0.0016637472,0.0026423973,0.00032768596,0.0007821921],"genre_scores_gemma":[0.17005661,0.00018543922,0.8274318,0.0005575154,0.00009340429,0.000059436014,0.0013433882,0.000027169042,0.0002452534],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995449,0.00019181239,0.0012303465,0.0020254655,0.0004970591,0.00060628477],"domain_scores_gemma":[0.9921305,0.0018529753,0.00083570124,0.0039239614,0.0011106598,0.0001462134],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002045209,0.00045283983,0.0006898112,0.0005484456,0.00039470557,0.00040919258,0.0021297722,0.00034667907,0.000010925129],"category_scores_gemma":[0.0010560454,0.0004971378,0.00009938611,0.0011533871,0.0004058617,0.0014718417,0.0013665321,0.00031882065,0.000003122535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014057584,0.00031958224,0.00035204994,0.0006021857,0.00018354217,0.0000024511705,0.00026954582,0.00006231364,0.057848036,0.055222563,0.013843415,0.8711537],"study_design_scores_gemma":[0.0011446688,0.00012072049,0.0062501975,0.00050423335,0.00009352474,0.0000028371485,0.00021789728,0.9222649,0.06174141,0.0023830708,0.004871696,0.0004048919],"about_ca_topic_score_codex":0.00008005645,"about_ca_topic_score_gemma":0.000013936843,"teacher_disagreement_score":0.9222025,"about_ca_system_score_codex":0.00019145424,"about_ca_system_score_gemma":0.0008071351,"threshold_uncertainty_score":0.99974805},"labels":[],"label_agreement":null},{"id":"W4416873823","doi":"10.1109/inc465408.2025.11256487","title":"Fraudulent Firm Classification in External Financial Audits using Machine Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Optech (Canada)","funders":"","keywords":"C4.5 algorithm; Audit; Big data; Interpretability; Naive Bayes classifier; Feature selection; Particle swarm optimization; Scalability; Feature (linguistics)","score_opus":0.037538219891051834,"score_gpt":0.307735224475259,"score_spread":0.27019700458420715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416873823","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015939707,0.0009807791,0.975639,0.0019017486,0.0011262537,0.00061094813,0.000015703179,0.0003691438,0.0034167548],"genre_scores_gemma":[0.81217206,0.000383372,0.18329671,0.0007211698,0.00011287084,0.000055587814,0.000025165153,0.000019691737,0.0032133663],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958184,0.00042254294,0.0012290892,0.0012724801,0.0005510231,0.0007065147],"domain_scores_gemma":[0.9977018,0.00016870885,0.0005261271,0.0012249068,0.00026376286,0.00011464178],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001186119,0.00042750212,0.00046412015,0.0009277778,0.00041834978,0.0004903657,0.0017268832,0.00036635713,0.00018899575],"category_scores_gemma":[0.00066031003,0.00047389884,0.00012363191,0.0022782527,0.000161791,0.0012177766,0.0008464681,0.0010637536,0.0000865792],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008319941,0.0007281509,0.08210785,0.0002025415,0.000022843953,0.000034749286,0.0006346249,0.0010688333,0.05860213,0.44067204,0.001785798,0.41405722],"study_design_scores_gemma":[0.000550535,0.00006391605,0.13239393,0.0005343203,0.000013678755,0.0000069161097,0.000022936638,0.83535,0.014148045,0.00553482,0.010988532,0.00039241364],"about_ca_topic_score_codex":0.00056551705,"about_ca_topic_score_gemma":0.00018648367,"teacher_disagreement_score":0.83428115,"about_ca_system_score_codex":0.0008164876,"about_ca_system_score_gemma":0.00083739817,"threshold_uncertainty_score":0.9997713},"labels":[],"label_agreement":null},{"id":"W4416888374","doi":"10.1080/10920277.2025.2587884","title":"An Effective Bayesian GLM Approach for IBNR Claim Count Estimation","year":2025,"lang":"en","type":"article","venue":"North American Actuarial Journal","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Bayesian probability; Estimation; Bayes estimator; Stability (learning theory); Equating; Estimation theory","score_opus":0.007622397368888987,"score_gpt":0.28817375599079526,"score_spread":0.2805513586219063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416888374","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004022887,0.000008973617,0.99351394,0.00049573585,0.00040492165,0.00068045675,0.000026250122,0.00027007834,0.00057676405],"genre_scores_gemma":[0.5403187,0.000008102195,0.45877838,0.0005271687,0.00018612848,0.000106081345,0.00005335255,0.000009105533,0.000012956873],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982907,0.00019338612,0.00039861424,0.00043900858,0.00032233726,0.00035594133],"domain_scores_gemma":[0.9982422,0.00018817672,0.00046423826,0.00065320247,0.0002857728,0.00016639775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055909774,0.00020045631,0.00030603405,0.00030237893,0.00040417342,0.0005492314,0.0012447409,0.00005388474,0.0000035499563],"category_scores_gemma":[0.0002061761,0.00018234015,0.00009895141,0.00080390077,0.00015944646,0.0010680638,0.00007408964,0.0003426383,0.000003388033],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012260767,0.00018919657,0.0027038427,0.000015482026,0.000055213226,0.000002668732,0.00027192046,0.0010621306,0.0005183634,0.009602263,0.0044868104,0.9809695],"study_design_scores_gemma":[0.0012701764,0.0010748354,0.0872072,0.000027173252,0.000055838063,0.00007513315,0.000102512175,0.8947757,0.0029146045,0.0047751763,0.0072311093,0.0004905727],"about_ca_topic_score_codex":0.000051196777,"about_ca_topic_score_gemma":0.000019290354,"teacher_disagreement_score":0.98047894,"about_ca_system_score_codex":0.00029453347,"about_ca_system_score_gemma":0.0003130163,"threshold_uncertainty_score":0.74356157},"labels":[],"label_agreement":null},{"id":"W4416940015","doi":"10.1007/s41060-025-00885-x","title":"Sequential Bayesian estimation of the F1 score using the Dirichlet-multinomial model","year":2025,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Manitoba","funders":"","keywords":"Benchmark (surveying); Metric (unit); Bayesian probability; Sample (material); Point estimation; Sample size determination; Bayesian inference; Prior probability; Class (philosophy)","score_opus":0.0841653532904757,"score_gpt":0.3783429684597155,"score_spread":0.2941776151692398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416940015","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0138399955,0.000024728464,0.9815343,0.0040353728,0.0003492076,0.000050135066,0.00004151595,0.00000591308,0.00011885408],"genre_scores_gemma":[0.8990269,0.00003298972,0.100559786,0.0003168555,0.00004137453,2.3131662e-7,0.0000027659823,0.000001403404,0.000017711483],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985131,0.000028690556,0.0003734988,0.00016873486,0.0008238802,0.000092066635],"domain_scores_gemma":[0.9980291,0.000066256725,0.00044990584,0.00061454554,0.00081240915,0.000027763748],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013453262,0.00006034591,0.00008920796,0.00022109848,0.00016398894,0.00029856892,0.005112322,0.000021271599,8.9385946e-7],"category_scores_gemma":[0.000529138,0.000035169913,0.00003052485,0.00061402837,0.00045930292,0.0022790527,0.0012384318,0.00013158971,1.3984605e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057592308,0.0003008887,0.008895353,0.000039093793,0.00025690018,0.000013644049,0.0010318608,0.13590051,0.1141678,0.47871146,0.007291285,0.2533336],"study_design_scores_gemma":[0.00010427342,0.000006354243,0.0009801657,0.0000644358,0.000016923184,0.00002514321,0.000025134766,0.98642063,0.0077484204,0.004370196,0.00020337527,0.000034922312],"about_ca_topic_score_codex":0.000016802594,"about_ca_topic_score_gemma":0.0000034366242,"teacher_disagreement_score":0.8851869,"about_ca_system_score_codex":0.00009048893,"about_ca_system_score_gemma":0.0008571147,"threshold_uncertainty_score":0.9500051},"labels":[],"label_agreement":null},{"id":"W4417070367","doi":"10.1080/00949655.2025.2593990","title":"fkbma: an R package for detecting tailoring variables with free-knot B-splines and Bayesian model averaging","year":2025,"lang":"en","type":"article","venue":"Journal of Statistical Computation and Simulation","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute of Mental Health; Canadian Statistical Sciences Institute; Canadian Institutes of Health Research","keywords":"Bayesian probability; Bayesian inference; Pattern recognition (psychology); R package; Statistical model; Bayes estimator; Feature selection","score_opus":0.025059153773878656,"score_gpt":0.3189249957058873,"score_spread":0.2938658419320086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417070367","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008733327,0.000021718499,0.99068254,0.0002801162,0.00004607852,0.00014246984,0.000012987186,0.000047031237,0.000033740787],"genre_scores_gemma":[0.5274314,0.0000029510788,0.4724745,0.00006153325,0.000015682408,0.0000018914637,0.0000050699336,0.0000033414126,0.0000036035465],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991307,0.000051217412,0.00036584234,0.00018398328,0.00016006474,0.00010814625],"domain_scores_gemma":[0.9984612,0.00075992086,0.00023412726,0.00012033542,0.00035668543,0.00006774757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044096037,0.00009396319,0.00016578435,0.00018971326,0.00018387148,0.0002506174,0.00013893377,0.00003930376,5.1826885e-7],"category_scores_gemma":[0.0003290917,0.00008035249,0.000012578681,0.00015506716,0.000035926132,0.0008183981,0.00004840687,0.00010596377,4.698695e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012242337,0.000052998916,0.0008649019,0.000121138335,0.00002826107,0.0000039566385,0.00051866344,0.6139718,0.001153349,0.2111864,0.000064554966,0.17191154],"study_design_scores_gemma":[0.0006130353,0.00013457488,0.0022632126,0.000060850714,0.00001717899,0.0000075106036,0.000038784867,0.875202,0.00031114553,0.12125624,0.000018884952,0.000076569486],"about_ca_topic_score_codex":0.0000025377149,"about_ca_topic_score_gemma":0.0000022870022,"teacher_disagreement_score":0.5186981,"about_ca_system_score_codex":0.00003322223,"about_ca_system_score_gemma":0.000060543563,"threshold_uncertainty_score":0.32766795},"labels":[],"label_agreement":null},{"id":"W4417249301","doi":"10.1109/icia64617.2025.11277823","title":"Leveraging Multi-Channel Image Representations to Enhance Robustness in Tabular Data Classification","year":2025,"lang":"","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Categorical variable; Robustness (evolution); Convolutional neural network; Pattern recognition (psychology); Contextual image classification; Deep learning; Feature extraction; Artificial neural network","score_opus":0.09378805461599643,"score_gpt":0.3951294245450986,"score_spread":0.30134136992910215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417249301","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005916987,0.00019691745,0.97431886,0.019295897,0.00085517776,0.0017271303,0.00013554738,0.0005461731,0.0023325821],"genre_scores_gemma":[0.44962975,0.00021876766,0.5421051,0.0013155998,0.00005618173,0.00036827778,0.0005157195,0.000030865453,0.0057597905],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99366426,0.00043256424,0.0014826267,0.003036367,0.0005676483,0.0008165214],"domain_scores_gemma":[0.990094,0.00030219805,0.00036909967,0.00844234,0.00058876595,0.00020358934],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0019020997,0.00047468135,0.0005060065,0.0012619498,0.0003994748,0.0010401707,0.006905076,0.0002360822,0.000072703835],"category_scores_gemma":[0.0013169248,0.00056167657,0.0000647291,0.004853432,0.00019592424,0.004072045,0.0040738103,0.000575659,0.00018528943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017299868,0.0055902083,0.004371915,0.00096193934,0.00026376083,0.00013192845,0.008400526,0.026490198,0.17617573,0.097419165,0.2476804,0.43234125],"study_design_scores_gemma":[0.00037418504,0.000018515666,0.017472435,0.00034682467,0.00001911478,0.0000022429244,0.0007671893,0.9316628,0.044907708,0.0005700165,0.0033268603,0.0005321293],"about_ca_topic_score_codex":0.0005556551,"about_ca_topic_score_gemma":0.00036924842,"teacher_disagreement_score":0.9051726,"about_ca_system_score_codex":0.00045423428,"about_ca_system_score_gemma":0.0006267088,"threshold_uncertainty_score":0.99999684},"labels":[],"label_agreement":null},{"id":"W4417485293","doi":"10.55041/ijsrem55331","title":"Credit Card Fraud Detection Using Modern Machine Learning And Deep Learning Approaches","year":2025,"lang":"","type":"article","venue":"INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Credit card fraud; Credit card; Deep learning; Database transaction; Random forest; Payment; Normalization (sociology)","score_opus":0.07193143648019425,"score_gpt":0.3309420949797151,"score_spread":0.2590106584995209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417485293","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054133147,0.004827007,0.93894625,0.00043536324,0.0011275249,0.0002839862,0.0000027658123,0.00003422748,0.00020971875],"genre_scores_gemma":[0.97353935,0.002082451,0.023731058,0.000004424423,0.000088384106,0.0000119692895,0.000003843773,0.000013035691,0.00052546273],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967498,0.00034870434,0.0007573598,0.00059326744,0.0010556636,0.00049517344],"domain_scores_gemma":[0.99875176,0.0002399973,0.0002156388,0.00023199782,0.00042762654,0.00013295798],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0073337373,0.00020657998,0.00030108637,0.0035257365,0.0005350193,0.0014985482,0.0006108247,0.00009357731,0.0000029818505],"category_scores_gemma":[0.00023971629,0.00021185084,0.000077252946,0.0016018538,0.00030669526,0.000897431,0.0008680113,0.0014653808,0.0000010971951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012440581,0.00019193455,0.0017787819,0.0017128916,0.00028299767,0.00013547936,0.0011951809,0.1811522,0.015602762,0.011009639,0.00004163538,0.7867721],"study_design_scores_gemma":[0.00047229556,0.000108959706,0.0021982568,0.001641278,0.000019573696,0.00007377885,0.00026467154,0.98549604,0.0011924966,0.0012200051,0.0071572405,0.00015537569],"about_ca_topic_score_codex":0.000024276527,"about_ca_topic_score_gemma":0.000006549815,"teacher_disagreement_score":0.91940624,"about_ca_system_score_codex":0.00031843194,"about_ca_system_score_gemma":0.00006021762,"threshold_uncertainty_score":0.999538},"labels":[],"label_agreement":null},{"id":"W4417515342","doi":"10.48550/arxiv.2505.07033","title":"Introducing the O-Value: A Universal Standardization for Confusion-Matrix-Based Classification Performance Metrics","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Mitacs","keywords":"Robustness (evolution); Standardization; Metric (unit); Binary classification; Performance metric; One-class classification; Rank (graph theory); Percentile","score_opus":0.04293589265727419,"score_gpt":0.3100160745255524,"score_spread":0.2670801818682782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417515342","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012763975,0.00013007973,0.9776807,0.0056272866,0.0010414389,0.0014678936,0.00020903246,0.00068023027,0.0003993534],"genre_scores_gemma":[0.8301283,0.00031424567,0.16695485,0.00064801093,0.00023961044,0.00041228012,0.00066162256,0.000028208002,0.0006128685],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973778,0.00020223878,0.000571774,0.0010174499,0.0004983457,0.00033235401],"domain_scores_gemma":[0.99533933,0.0005678366,0.0006683899,0.002475919,0.00088771916,0.000060806186],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014246051,0.00032132276,0.00033705457,0.0005179012,0.00049154984,0.00028591615,0.0024823884,0.00031482696,0.000006765633],"category_scores_gemma":[0.00088704657,0.00027513597,0.00014672885,0.0012312655,0.00011907844,0.0004385299,0.00088827295,0.000574766,0.000012640386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039228253,0.00067994074,0.11823456,0.0032739085,0.00045725622,0.0000058603728,0.002633523,0.095954545,0.015143693,0.47964978,0.066914745,0.21665989],"study_design_scores_gemma":[0.0004574652,0.00007373745,0.019768232,0.00025032248,0.00007233998,8.964382e-7,0.000055130182,0.9131753,0.01971051,0.0008835275,0.04513314,0.00041941975],"about_ca_topic_score_codex":0.000025816606,"about_ca_topic_score_gemma":0.0000030820165,"teacher_disagreement_score":0.81736434,"about_ca_system_score_codex":0.00058927,"about_ca_system_score_gemma":0.0011605194,"threshold_uncertainty_score":0.9999701},"labels":[],"label_agreement":null},{"id":"W45025849","doi":"","title":"Unsupervised Identity Application Fraud Detection using Rule-based Decision Tree.","year":2010,"lang":"en","type":"article","venue":"Software Engineering and Data Engineering","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Decision tree; Computer science; Identity (music); Artificial intelligence; Machine learning; Identity theft; Data mining; Pattern recognition (psychology); Computer security","score_opus":0.015521125092752195,"score_gpt":0.2569089143695922,"score_spread":0.24138778927684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W45025849","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08990836,0.00007364827,0.90761673,0.000017508397,0.0004751861,0.00017010256,0.000051114373,0.0016858585,0.0000014662289],"genre_scores_gemma":[0.45829278,0.000007782935,0.54146236,0.000013903562,0.0000773618,0.000021457166,0.00009903748,0.00002445688,8.339876e-7],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984883,0.000008536951,0.0002861176,0.0006498699,0.0002795633,0.00028760917],"domain_scores_gemma":[0.99764085,0.00020717627,0.00006638021,0.0018803675,0.00006833434,0.00013687207],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004606425,0.0002313687,0.00018001872,0.00030256316,0.00011341815,0.0002806728,0.0012767386,0.00015446762,0.000002559206],"category_scores_gemma":[0.0007189574,0.00025955262,0.000030745698,0.00055999897,0.00001727787,0.0020382628,0.0004683536,0.0003849056,0.000007924204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009685257,0.00006902214,0.0021967606,0.00024768495,0.000031287927,0.000008268423,0.00006303661,0.070604876,0.63575125,0.0048779617,0.000058408936,0.28608176],"study_design_scores_gemma":[0.00020820454,0.000010570893,0.007828539,0.000043622655,0.000009296525,0.000017866623,0.0000012428145,0.971262,0.017743237,0.00009116276,0.0024973084,0.0002869733],"about_ca_topic_score_codex":0.000038957653,"about_ca_topic_score_gemma":0.000013440737,"teacher_disagreement_score":0.9006571,"about_ca_system_score_codex":0.000049902694,"about_ca_system_score_gemma":0.000034331868,"threshold_uncertainty_score":0.9999857},"labels":[],"label_agreement":null},{"id":"W634768160","doi":"10.71781/15402","title":"Distributions d'auto-amorçage exactes ponctuelles des courbes ROC et des courbes de coûts","year":2009,"lang":"fr","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Resampling; Confidence interval; Mathematics; Pointwise; Receiver operating characteristic; Statistics; Classifier (UML); Artificial intelligence; Pattern recognition (psychology); Computer science","score_opus":0.014075171721667312,"score_gpt":0.21775165789232015,"score_spread":0.20367648617065284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W634768160","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48174638,0.032960385,0.44965214,0.001987771,0.0011491306,0.001143563,0.0014607752,0.0015067111,0.028393151],"genre_scores_gemma":[0.9214316,0.0054205586,0.043849103,0.0002786828,0.00018957586,0.00009170214,0.0031419643,0.000060374405,0.025536414],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9952535,0.0005405655,0.00080868887,0.0012712966,0.0010243214,0.0011016467],"domain_scores_gemma":[0.9956416,0.00044369086,0.0008239166,0.0011102827,0.0013257246,0.0006547864],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00065773656,0.000894074,0.0007089561,0.0005057872,0.012365728,0.0006180035,0.0019063093,0.000793369,0.00005093795],"category_scores_gemma":[0.00044782052,0.0010612039,0.00045899893,0.0009626996,0.0014593205,0.0024024933,0.00040933592,0.00087129185,0.00010799767],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006389459,0.0016966123,0.032889135,0.00063627755,0.0006691328,0.0032040775,0.08080318,0.0021967571,0.09737999,0.7236098,0.006755616,0.049520507],"study_design_scores_gemma":[0.001467878,0.00053530716,0.71836174,0.0020093184,0.0006561414,0.0018866903,0.023257663,0.021657014,0.12165848,0.02641898,0.0797404,0.0023503716],"about_ca_topic_score_codex":0.02040001,"about_ca_topic_score_gemma":0.013630855,"teacher_disagreement_score":0.6971908,"about_ca_system_score_codex":0.009924115,"about_ca_system_score_gemma":0.0043984572,"threshold_uncertainty_score":0.99918383},"labels":[],"label_agreement":null},{"id":"W6889713305","doi":"10.25921/g555-9q86","title":"Surface underway pH, water temperature, salinity, dissolved oxygen, chlorophyll and discrete analyses of dissolved inorganic carbon and total alkalinity from the underway TSG collected during the RRS Discovery fall 2023 oceanographic survey cruise (EXPOCODE 32V320231006) in the North Atlantic Ocean and Labrador Sea from 2023-10-06 to 2023-10-26 (NCEI Accession 0299020)","year":2024,"lang":"en","type":"dataset","venue":"National Oceanic and Atmospheric Administration (NOAA) National Centers for Environmental Information (NCEI)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Fisheries and Oceans Canada","funders":"","keywords":"Dissolved organic carbon; Alkalinity; Sampling (signal processing); Water column; Chlorophyll a; Plankton; Surface water; Total inorganic carbon; Total organic carbon","score_opus":0.018754977561730342,"score_gpt":0.2656638282757249,"score_spread":0.24690885071399454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6889713305","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66906923,0.00025662908,0.0010880049,0.0012709918,0.00014713718,0.0014078195,0.3267022,0.000043174437,0.000014800957],"genre_scores_gemma":[0.6848578,0.00066152256,0.0004255637,0.00037343756,0.0000737144,0.000053848027,0.31339863,0.00002110509,0.00013441942],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9959051,0.00038614473,0.0012231135,0.000787927,0.0013331044,0.0003645854],"domain_scores_gemma":[0.9973196,0.0012219629,0.00068732013,0.00046767123,0.00015363081,0.00014984446],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00089488033,0.00059684174,0.0004971006,0.00009117438,0.00065252517,0.0010974591,0.0008633517,0.00028872854,0.000047631343],"category_scores_gemma":[0.00023521532,0.00038601234,0.00011929966,0.00080456136,0.00041833305,0.0018722793,0.00059777126,0.00052720075,0.000013209486],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004115404,0.0017717961,0.15633972,0.0014640089,0.0025940365,0.000028370367,0.005313448,0.003635695,0.007615985,0.00092629535,0.8157556,0.00043964418],"study_design_scores_gemma":[0.00211081,0.00039713347,0.9534409,0.00023500004,0.00020827483,0.000025519344,0.0011941043,0.030226618,0.00070200395,0.0008320641,0.009609578,0.0010179986],"about_ca_topic_score_codex":0.00068992993,"about_ca_topic_score_gemma":0.0015083508,"teacher_disagreement_score":0.806146,"about_ca_system_score_codex":0.00029322156,"about_ca_system_score_gemma":0.0002730981,"threshold_uncertainty_score":0.9999395},"labels":[],"label_agreement":null},{"id":"W6889729772","doi":"10.25951/4067","title":"This Language, A River: A History of English, K. Aaron Smith and Susan M. Kim, Peterborough, Ontario: Broadview, 2018, 360 pp.","year":2019,"lang":"en","type":"other","venue":"Wydawnictwo Uniwersytetu Jana Kochanowskiego w Kielcach","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"George (robot); Industrial Revolution; Work (physics); Line drawings","score_opus":0.010525722363454917,"score_gpt":0.2193090866235419,"score_spread":0.20878336426008698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6889729772","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004493725,0.029820126,0.011842316,0.00015233952,0.0041964552,0.0018778087,0.00029837605,0.0017376516,0.95002997],"genre_scores_gemma":[0.0014352023,0.0038600022,0.036135104,0.0004919654,0.000522776,0.00014229868,0.00031112944,0.00059781416,0.9565037],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943675,0.0003563967,0.0010466862,0.0020994535,0.001119877,0.001010129],"domain_scores_gemma":[0.9928058,0.00022378426,0.0015263351,0.00463804,0.00042493897,0.00038110852],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006760849,0.0011797707,0.0016186069,0.0010083622,0.000084695275,0.00013321186,0.0035328965,0.001052873,0.0013164019],"category_scores_gemma":[0.00023950003,0.0012116273,0.00036427865,0.0006126832,0.00062718097,0.00073949125,0.0013462622,0.0011815298,0.0003199282],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003309048,0.00017225018,0.00014074436,0.00043619942,0.00020153463,0.000033026936,0.008112753,4.6854063e-7,0.00041463773,0.011716307,0.9738273,0.0049117054],"study_design_scores_gemma":[0.0010800231,0.00038818634,0.000119656375,0.00081670453,0.00012957164,0.000019399447,0.00014339715,0.0002337694,0.00046610003,0.000120595505,0.99524355,0.0012390583],"about_ca_topic_score_codex":0.033333044,"about_ca_topic_score_gemma":0.007542934,"teacher_disagreement_score":0.025960123,"about_ca_system_score_codex":0.0019123297,"about_ca_system_score_gemma":0.0016712435,"threshold_uncertainty_score":0.99959654},"labels":[],"label_agreement":null},{"id":"W6893099797","doi":"10.5281/zenodo.1469776","title":"permittivitycalc","year":2018,"lang":"en","type":"other","venue":"Figshare","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Toronto","funders":"","keywords":"","score_opus":0.039717582236875056,"score_gpt":0.2821830739703147,"score_spread":0.24246549173343968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6893099797","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.305036e-9,0.00008892582,0.005237566,0.00005685276,0.000091147944,0.00017072065,0.13116094,0.002298385,0.86089545],"genre_scores_gemma":[0.0000038646263,0.000003527967,0.022383362,0.0002706512,0.00043013235,0.00023018614,0.0830591,0.00018608422,0.8934331],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990751,0.000027853112,0.00009607626,0.0004303751,0.00019372127,0.00017684417],"domain_scores_gemma":[0.9983817,0.000028308874,0.00016197252,0.0013260269,0.000047854297,0.00005417242],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000025213825,0.00016544154,0.00014524153,0.00015729383,0.000027237515,0.000116571966,0.0016761029,0.00023617306,0.48824793],"category_scores_gemma":[0.0002535037,0.00015967025,0.000047773046,0.00019846567,0.000008043691,0.00012811655,0.00045757196,0.00010236731,0.0851427],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.232973e-8,0.0000071146487,4.31758e-7,0.000038255348,0.000003873721,0.0000036992355,0.000003956337,1.3170914e-9,0.000003103352,0.00046636662,0.9927042,0.0067689163],"study_design_scores_gemma":[0.000026821135,0.000011476774,0.000026864198,0.0009184514,8.3151417e-7,0.0000038340727,2.097338e-7,0.00012862904,0.00044291944,0.00007127363,0.99817675,0.00019195543],"about_ca_topic_score_codex":0.00000203171,"about_ca_topic_score_gemma":0.0000042130546,"teacher_disagreement_score":0.40310523,"about_ca_system_score_codex":0.000026385924,"about_ca_system_score_gemma":0.000068783964,"threshold_uncertainty_score":0.9155696},"labels":[],"label_agreement":null},{"id":"W6902882126","doi":"10.1016/j.hrmr.2025.101103","title":"Predicting wage theft in organizations","year":2025,"lang":"en","type":"article","venue":"Human Resource Management Review","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council; Social Sciences and Humanities Research Council of Canada; McMaster University","keywords":"Wage; Efficiency wage; Job loss; Unemployment","score_opus":0.01236840459018684,"score_gpt":0.290998016120533,"score_spread":0.27862961153034616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902882126","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020933001,0.015974628,0.4838997,0.0061982856,0.00006840372,0.001905826,0.0000028517716,0.0012722275,0.4904687],"genre_scores_gemma":[0.3822456,0.13481489,0.25503913,0.086964324,0.00024696096,0.0032842176,0.00074780075,0.00021070852,0.1364464],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987349,0.00011645796,0.00039854847,0.0003856338,0.00017469752,0.00018979484],"domain_scores_gemma":[0.99865,0.000029728724,0.000112590096,0.0011435872,0.0000399517,0.00002411687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005992268,0.000118554715,0.00018734082,0.0002585534,0.0001417472,0.0001047606,0.0013115559,0.000025983785,0.000052401865],"category_scores_gemma":[0.000056532943,0.00011348547,0.00003187235,0.001747099,0.000025667188,0.00017560227,0.00072811655,0.00011817921,0.000051113904],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.9609932e-7,0.000053450338,0.0026761708,0.0014599203,0.000015118461,0.000009275846,0.000066324654,0.000005212741,0.000020729258,0.89258516,0.04121422,0.06189424],"study_design_scores_gemma":[0.00017387046,0.0000097879865,0.016619334,0.0051927604,0.000027550774,0.0000011059882,0.000040588173,0.00067832635,0.000080601116,0.0030578137,0.9739369,0.0001813608],"about_ca_topic_score_codex":0.000006766876,"about_ca_topic_score_gemma":0.000007021998,"teacher_disagreement_score":0.9327227,"about_ca_system_score_codex":0.00007714873,"about_ca_system_score_gemma":0.00001126801,"threshold_uncertainty_score":0.4627803},"labels":[],"label_agreement":null},{"id":"W6906578362","doi":"10.17632/hy2rz3k83y.3","title":"Geology, geochemistry and Sr-Nd isotopes of the Rio Branco Suite, Nova Brasilândia belt in southwest of the Amazonian Craton: Evidence of a Rodinia pre-assembly accretionary phase (ca. 1137 and 1106 Ma) during the evolution of the Nova Brasilândia orogeny","year":2020,"lang":"en","type":"dataset","venue":"Data Archiving and Networked Services (DANS)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Amazonian; Rodinia; Nova (rocket); Nova scotia; Geochronology; Phase (matter)","score_opus":0.01903720057499256,"score_gpt":0.2742364996733781,"score_spread":0.2551992990983855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6906578362","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.622542,0.0018763114,0.0008058907,0.0004412499,0.00018166151,0.00089745625,0.37321508,0.000030255344,0.000010083725],"genre_scores_gemma":[0.95832723,0.0011917478,0.00093952654,0.00012861856,0.0000848803,0.000032507494,0.039263904,0.000022764174,0.000008828853],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99638397,0.00061861967,0.0010293466,0.0009979999,0.0005757235,0.00039436104],"domain_scores_gemma":[0.99336946,0.0008627538,0.0016039261,0.0039635357,0.00011794737,0.00008235445],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0010544774,0.00044938843,0.0006684659,0.0001209397,0.00032760363,0.00009895274,0.0068829227,0.00023655606,0.0000056033186],"category_scores_gemma":[0.00019209107,0.00027200623,0.00009932427,0.0010648839,0.0012842047,0.0006080592,0.0066349464,0.00076956546,5.049054e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008800185,0.0007551325,0.76897407,0.014767749,0.0005743964,0.000016026075,0.0079985745,0.00034054683,0.11529907,0.00034134157,0.08389705,0.006156049],"study_design_scores_gemma":[0.0007030521,0.0000907355,0.9737359,0.00390768,0.00015315884,0.00008997335,0.00029070134,0.013969272,0.0046601733,0.00027434103,0.0017518045,0.0003731551],"about_ca_topic_score_codex":0.0049537634,"about_ca_topic_score_gemma":0.011600583,"teacher_disagreement_score":0.3357852,"about_ca_system_score_codex":0.000043267344,"about_ca_system_score_gemma":0.0002909165,"threshold_uncertainty_score":0.99997324},"labels":[],"label_agreement":null},{"id":"W6926382288","doi":"10.24451/arbor.13991","title":"Social Entrepreneurship Research as a Means of Transformation: A Vision for the Year 2028","year":2011,"lang":"en","type":"article","venue":"BFH: ARBOR","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Social entrepreneurship; Entrepreneurship; Entrepreneurship education; Social change; State (computer science); Social innovation","score_opus":0.18398656669866686,"score_gpt":0.3958054560709878,"score_spread":0.21181888937232096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6926382288","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044125947,0.00006036649,0.9653814,0.008125079,0.00015423789,0.0012237971,0.000039037004,0.00025803686,0.02034545],"genre_scores_gemma":[0.9755762,0.000026041496,0.02382423,0.00010096484,0.00006395823,0.00017865654,0.0000059631025,0.00000814409,0.00021580071],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99896085,0.00010559155,0.00019838543,0.00019439362,0.00034826426,0.00019252283],"domain_scores_gemma":[0.99895626,0.00021475638,0.000069051894,0.0005114265,0.00021904225,0.000029486584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001002873,0.000061641724,0.00008539675,0.00008932776,0.00017620831,0.000046226,0.0010029429,0.00005318788,0.000033551933],"category_scores_gemma":[0.00011692859,0.000045607507,0.000057430847,0.00034355625,0.00010767392,0.00033484024,0.000085398126,0.00011326799,0.000044140565],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006229023,0.00010482551,0.00007481922,0.000032088716,0.000013674422,5.7944715e-7,0.010127429,2.3392832e-7,0.004645761,0.9333761,0.011641101,0.03992114],"study_design_scores_gemma":[0.0016611925,0.0010496114,0.02883818,0.0000993776,0.000033826436,0.000008531568,0.0012573054,0.017200442,0.54687387,0.21461898,0.18786827,0.00049040467],"about_ca_topic_score_codex":0.00003178845,"about_ca_topic_score_gemma":0.000007074469,"teacher_disagreement_score":0.97116363,"about_ca_system_score_codex":0.000023884517,"about_ca_system_score_gemma":0.000081117214,"threshold_uncertainty_score":0.18637341},"labels":[],"label_agreement":null},{"id":"W6926692721","doi":"10.25549/wpacards-c8-131961","title":"WPA block face card for household census (block 429) in Los Angeles","year":2014,"lang":"en","type":"dataset","venue":"University of Southern California Digital Library","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Census; Block (permutation group theory); Face (sociological concept); Quarter (Canadian coin); Population","score_opus":0.014562778582147077,"score_gpt":0.1851044748354025,"score_spread":0.1705416962532554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6926692721","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011378818,0.00004659666,0.0058574826,0.00018320409,0.000044312917,0.000419298,0.9927427,0.0003552178,0.00023738267],"genre_scores_gemma":[0.00068970764,0.000031729956,0.004694287,0.00012139536,0.00006322169,0.0000018471194,0.994126,0.000035975583,0.00023582403],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982617,0.000054009604,0.00033153163,0.0006669963,0.0003206806,0.00036509853],"domain_scores_gemma":[0.9980728,0.0001671393,0.00040401623,0.0011620144,0.000047976697,0.00014603845],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00009613494,0.00034632842,0.0004924657,0.00037576398,0.000090301335,0.00020529461,0.0025405334,0.00036117504,0.000004173978],"category_scores_gemma":[0.000042256834,0.000383231,0.00020303803,0.0003427923,0.00018541653,0.00061788294,0.0009333769,0.00029734004,0.0001959939],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035852037,0.00009513541,0.00019357003,0.00016017762,0.000021226704,0.000020306094,0.00001105984,0.000015002986,0.0000049124246,0.00003889947,0.9987614,0.00064241234],"study_design_scores_gemma":[0.00036763586,0.0000423169,0.0000141778855,0.00014184223,0.000018117596,0.0000060187385,0.000115724964,0.0002887194,0.00014169073,0.00034786767,0.99811715,0.00039876252],"about_ca_topic_score_codex":0.000044577962,"about_ca_topic_score_gemma":0.000015064534,"teacher_disagreement_score":0.0016071565,"about_ca_system_score_codex":0.00006590062,"about_ca_system_score_gemma":0.00015245318,"threshold_uncertainty_score":0.99986196},"labels":[],"label_agreement":null},{"id":"W6929882984","doi":"10.5281/zenodo.1087463","title":"Moox And Wox Based Hole-Selective Contacts For Wafer-Based Si Solar Cells","year":2017,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"European Commission","keywords":"Dopant; Absorption (acoustics); Thin film; Thin film solar cell; Silicon; Front (military)","score_opus":0.043639172222672884,"score_gpt":0.2657884475559169,"score_spread":0.22214927533324402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929882984","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022321914,0.000014351088,0.98195285,0.0022420685,0.00009515612,0.00086648465,0.0003008214,0.0011912441,0.011104849],"genre_scores_gemma":[0.9725069,0.0000148224835,0.025675891,0.00052548444,0.0000631934,5.225165e-7,0.0004598603,0.000522746,0.00023057126],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998385,0.00017596873,0.00020520587,0.000588885,0.00028614094,0.0003587616],"domain_scores_gemma":[0.99756044,0.00007029499,0.00022818331,0.0012818136,0.0006921752,0.00016707121],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007447332,0.00015459028,0.00015860655,0.00020039032,0.0027942322,0.0022932831,0.0023723391,0.000076902914,0.00021205614],"category_scores_gemma":[0.00086951844,0.00016394399,0.000043314405,0.00019496262,0.0001952434,0.0007716343,0.0008701254,0.00018918746,0.0005191968],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002796938,0.00054773776,0.000042624277,0.000264083,0.00007568295,0.000023902687,0.0010037248,0.00010285894,0.24740456,0.044112213,0.3103356,0.39580733],"study_design_scores_gemma":[0.0010883693,0.00038029865,0.0011546419,0.000036599977,0.000008944043,0.0000061179885,0.000021536183,0.050183043,0.20045437,0.00055775524,0.74583745,0.00027087267],"about_ca_topic_score_codex":0.000015976482,"about_ca_topic_score_gemma":4.319616e-7,"teacher_disagreement_score":0.97027475,"about_ca_system_score_codex":0.0001218475,"about_ca_system_score_gemma":0.000016142927,"threshold_uncertainty_score":0.99874246},"labels":[],"label_agreement":null},{"id":"W6930380084","doi":"10.5281/zenodo.12563724","title":"Is It Safe To Use ManUp Gummies for Men's Health?","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Conversation; Mental health; Health care; Order (exchange); Product (mathematics); Set (abstract data type); Mood","score_opus":0.08446261642589699,"score_gpt":0.31855277190634396,"score_spread":0.23409015548044698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930380084","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.329318e-7,0.00012044717,0.44329974,0.015442943,0.00020622544,0.0013406012,0.001861455,0.0023094262,0.53541887],"genre_scores_gemma":[0.000108965374,0.00032128696,0.04896753,0.0034215862,0.00022378644,9.067436e-7,0.0018660451,0.00490266,0.9401872],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99748653,0.00018744922,0.00036295093,0.0009914858,0.00047378766,0.0004978222],"domain_scores_gemma":[0.9976218,0.000029688943,0.00021031793,0.0015587802,0.00032545364,0.00025396084],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00063107116,0.00027331474,0.00028255783,0.0007481817,0.00066218426,0.0022772246,0.00302894,0.00014427818,0.016994316],"category_scores_gemma":[0.00037724504,0.0002898734,0.000082349834,0.00073658215,0.00008342248,0.00034357226,0.0024071748,0.0002742522,0.09669855],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006739277,0.00003229587,6.689525e-8,0.00020507659,0.00003459736,0.0000032983673,0.0006087705,3.4414572e-7,0.00009564942,0.023830676,0.9325121,0.04267037],"study_design_scores_gemma":[0.00013345588,0.00019632877,0.000009150996,0.00021451492,0.0000071941004,0.00002019896,0.00005920321,0.00028270704,0.00022233752,0.00065553223,0.99791175,0.00028762422],"about_ca_topic_score_codex":0.00003160895,"about_ca_topic_score_gemma":0.0000010945199,"teacher_disagreement_score":0.40476838,"about_ca_system_score_codex":0.0002644501,"about_ca_system_score_gemma":0.000007740165,"threshold_uncertainty_score":0.99995536},"labels":[],"label_agreement":null},{"id":"W6930784010","doi":"10.5281/zenodo.14674304","title":"Phytobia Lioy 1864","year":2025,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Genus; Holotype; Male genitalia; Taxonomy (biology); Phallus (fungus); Group (periodic table)","score_opus":0.027526933342035296,"score_gpt":0.2614976793455541,"score_spread":0.23397074600351883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930784010","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00033925896,0.000049322778,0.71657205,0.0027062309,0.00013302431,0.00027512579,0.000047520483,0.0029705935,0.27690685],"genre_scores_gemma":[0.9334646,0.00023178094,0.047278356,0.0025532919,0.00019040222,3.156896e-7,0.0014857744,0.0012851577,0.013510351],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985964,0.00019578531,0.00021444637,0.00045776134,0.00025281362,0.00028281094],"domain_scores_gemma":[0.9983304,0.000023218767,0.00007785754,0.0010514602,0.00043367158,0.000083387684],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00052400865,0.000108380205,0.00010776043,0.00032616692,0.0013262437,0.0011541619,0.0028126875,0.000054169668,0.0011344362],"category_scores_gemma":[0.0004183696,0.00011797208,0.00003685846,0.0011888546,0.00010195984,0.00055977143,0.0020164826,0.0002022092,0.0045317616],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060000975,0.000065816384,0.00000222537,0.000022341726,0.000012570425,0.0000034719912,0.00019041482,0.0000035730804,0.0065281224,0.21970043,0.5395537,0.23391134],"study_design_scores_gemma":[0.00017732492,0.000049149476,0.00062062574,0.000024632182,0.0000028387356,0.000017685774,0.000025484936,0.0015387913,0.0061839665,0.0028955003,0.98834735,0.00011662646],"about_ca_topic_score_codex":0.0000059678714,"about_ca_topic_score_gemma":9.0676316e-8,"teacher_disagreement_score":0.9331253,"about_ca_system_score_codex":0.00012998485,"about_ca_system_score_gemma":0.000006461689,"threshold_uncertainty_score":0.9999739},"labels":[],"label_agreement":null},{"id":"W6930844070","doi":"10.5281/zenodo.15218280","title":"Empis (Enoplempis) diokra Sinclair, Brooks & Cumming, 2025, sp. nov.","year":2025,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Food Inspection Agency","funders":"","keywords":"Holotype; Summit; Structural basin; Cache","score_opus":0.032558415095305916,"score_gpt":0.27634239075536504,"score_spread":0.24378397566005913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930844070","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00074620685,0.000108599634,0.7267308,0.0039070924,0.00021029002,0.0005362476,0.00012083781,0.0037993551,0.26384056],"genre_scores_gemma":[0.8998619,0.0004353822,0.057548847,0.003937231,0.00036803234,0.0000010196425,0.003711575,0.0023739378,0.03176208],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99761546,0.0003023335,0.00038898786,0.0007552317,0.00045633636,0.00048167002],"domain_scores_gemma":[0.9974845,0.00004420195,0.00014503895,0.0015376587,0.00063755066,0.00015107094],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00079733913,0.00020277099,0.00019616219,0.00048460191,0.0020022998,0.0016042679,0.0037884992,0.000101826015,0.0020853984],"category_scores_gemma":[0.0005892812,0.0002206316,0.00006662922,0.0013683906,0.0001838203,0.0007726301,0.0033552626,0.00035767464,0.007270688],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013634541,0.00012530184,0.00001143663,0.000050407998,0.000029845245,0.0000102234735,0.0004950863,0.0000060707757,0.009470229,0.14342324,0.6045394,0.24182512],"study_design_scores_gemma":[0.00029899715,0.000096203265,0.0007142106,0.000050155246,0.000007559029,0.000026250065,0.00005118257,0.0018527494,0.007965433,0.0019244713,0.9867937,0.00021907434],"about_ca_topic_score_codex":0.000024057554,"about_ca_topic_score_gemma":6.8077776e-7,"teacher_disagreement_score":0.8991157,"about_ca_system_score_codex":0.0002670862,"about_ca_system_score_gemma":0.000017150147,"threshold_uncertainty_score":0.99943215},"labels":[],"label_agreement":null},{"id":"W6931422066","doi":"10.5281/zenodo.4789509","title":"British Columbia +27'710'158'438 lost love spell caster )௵ Alabama Stop Cheating Spell Love Spell for Love Back, Black Magic in Glasgow","year":2021,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Spell; Witch; MAGIC (telescope); Cheating","score_opus":0.032625324003991395,"score_gpt":0.24388271945652826,"score_spread":0.21125739545253686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931422066","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0079743415,0.00012236353,0.131439,0.0022925811,0.0003101361,0.0015624135,0.0007473495,0.00025756154,0.8552942],"genre_scores_gemma":[0.029001134,0.00043081542,0.057731256,0.0016711396,0.0006465376,3.780799e-9,0.0030248787,0.0025006493,0.9049936],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959665,0.00047227685,0.00072449684,0.0013081639,0.00065444526,0.0008741003],"domain_scores_gemma":[0.9966491,0.000118572156,0.00032539136,0.0014303115,0.0011932835,0.0002833656],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010073195,0.00028609874,0.00039526712,0.0002198321,0.000070128684,0.004503579,0.0023838442,0.00017911821,0.10265492],"category_scores_gemma":[0.00085752894,0.00044346487,0.00012324692,0.0014237256,0.00028565928,0.0011384442,0.002317085,0.00055048376,0.59238833],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028855895,0.00034240106,0.00014108469,0.00020287556,0.000033001328,0.00016045525,0.0017583943,0.000044486602,0.008722182,0.0011128255,0.981819,0.005634486],"study_design_scores_gemma":[0.0012035796,0.00024051043,0.0010916317,0.00018390157,0.000012819865,0.00035003448,0.00056091975,0.0118961735,0.0074332943,0.00087546866,0.97560066,0.00055098126],"about_ca_topic_score_codex":0.00019796428,"about_ca_topic_score_gemma":0.00013838672,"teacher_disagreement_score":0.48973343,"about_ca_system_score_codex":0.0004935379,"about_ca_system_score_gemma":0.00004119182,"threshold_uncertainty_score":0.9998017},"labels":[],"label_agreement":null},{"id":"W6931625459","doi":"10.5281/zenodo.8136577","title":"PFT-Vcmax25 optimization in CLASSIC (v.1.3)","year":2023,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Wilfrid Laurier University; Environment and Climate Change Canada; Université du Québec à Trois-Rivières; Université de Montréal","funders":"","keywords":"Benchmarking; License; Code (set theory); Covariance; Government (linguistics); Source code; Open source; Code of practice","score_opus":0.038577997237844615,"score_gpt":0.25916739595814453,"score_spread":0.22058939872029992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931625459","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.815917e-7,0.000054225708,0.4839918,0.00061823556,0.00017948616,0.000487513,0.00017537274,0.00935504,0.50513774],"genre_scores_gemma":[0.002656394,0.004414535,0.1794944,0.0010250253,0.0011852158,0.0000023839377,0.015439776,0.076964684,0.7188176],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976564,0.00031953747,0.0003407837,0.0007951165,0.00046889362,0.00041925802],"domain_scores_gemma":[0.99806905,0.000027377768,0.00025782673,0.0013215739,0.00020513796,0.00011904204],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00062313065,0.00023630713,0.00023809844,0.0011209563,0.0004738798,0.0009393905,0.0031168703,0.00023116411,0.005646391],"category_scores_gemma":[0.00049457734,0.00026947382,0.000048849157,0.0016575751,0.000116753356,0.00041083264,0.0018813414,0.00039958395,0.01117795],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003284504,0.000058011126,6.8267724e-7,0.00004053327,0.000013508701,0.000014447001,0.00012504066,0.0001646368,0.000055275228,0.016145037,0.9076996,0.075679936],"study_design_scores_gemma":[0.00024333087,0.00005538547,0.000055385914,0.00013007349,0.0000037217956,0.000018714854,0.000019138604,0.01378197,0.000056642217,0.00021636767,0.98514825,0.00027099118],"about_ca_topic_score_codex":0.00004130625,"about_ca_topic_score_gemma":0.0000036784822,"teacher_disagreement_score":0.30449742,"about_ca_system_score_codex":0.0003021419,"about_ca_system_score_gemma":0.000009080272,"threshold_uncertainty_score":0.99997574},"labels":[],"label_agreement":null},{"id":"W6931659773","doi":"10.5683/sp2/y4nrg6","title":"Data for: Gas Transfer Velocities Evaluated Using Carbon Dioxide as a Tracer Show High Streamflow to Be a Major Driver of Total CO2 Evasion Flux for a Headwater Stream","year":2019,"lang":"en","type":"dataset","venue":"Borealis","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"TRACER; Hydrology (agriculture); Schmidt number; Carbon dioxide; Flux (metallurgy); Air water; Stream flow; STREAMS","score_opus":0.07949283351172834,"score_gpt":0.3287971293747112,"score_spread":0.24930429586298283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931659773","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021684493,0.00003954612,0.06353644,0.00063811697,0.0002875058,0.0031805483,0.9299789,0.00015642776,0.000014026839],"genre_scores_gemma":[0.0007980498,0.000029777479,0.034676936,0.00033396168,0.0001545222,0.0005028797,0.9632915,0.00006878382,0.00014358576],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959526,0.00015516554,0.0008488251,0.001494889,0.0008891578,0.00065933826],"domain_scores_gemma":[0.993858,0.0003030831,0.00027488096,0.004828774,0.0005545253,0.00018076523],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007405866,0.0006242502,0.00095418293,0.00045081115,0.00011681249,0.00018420538,0.0030045172,0.0005047288,0.00003261088],"category_scores_gemma":[0.00020855873,0.0005758818,0.0001971888,0.00032890897,0.00011437598,0.0006761353,0.0006707754,0.00024472125,0.000003031385],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025560835,0.00014384693,0.0000015829011,0.00038544385,0.00014649109,0.00000421728,0.00014951812,0.00004708377,0.005799785,0.00026796723,0.991298,0.0015004425],"study_design_scores_gemma":[0.002103475,0.0010733376,0.00012646047,0.00061263953,0.00061006914,0.00002921024,0.00006275384,0.027046623,0.066639744,0.0005903743,0.8998855,0.0012198183],"about_ca_topic_score_codex":0.013295655,"about_ca_topic_score_gemma":0.0033705814,"teacher_disagreement_score":0.09141252,"about_ca_system_score_codex":0.00028015234,"about_ca_system_score_gemma":0.00059267535,"threshold_uncertainty_score":0.99966925},"labels":[],"label_agreement":null},{"id":"W6939096622","doi":"10.60692/k4y8j-qwh13","title":"Leveraging feature selection to detect potential tax fraudsters","year":2020,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Taxpayer; Treasury; Payment; Enforcement; Evasion (ethics); Agency (philosophy); Feature (linguistics); Work (physics)","score_opus":0.02713987545648489,"score_gpt":0.2097561702501647,"score_spread":0.1826162947936798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939096622","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011817881,7.801711e-7,0.9835651,0.0019050345,0.00026867545,0.00041106285,0.000030770883,0.0014255425,0.000575147],"genre_scores_gemma":[0.9320899,4.0692797e-8,0.06547038,0.0022109374,0.00009499035,0.000065156775,0.00001273412,0.000007836068,0.000048007318],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986595,0.000062536725,0.00038003232,0.00026990322,0.00037713532,0.00025089222],"domain_scores_gemma":[0.99899584,0.0000033579586,0.00023201639,0.00040940414,0.00018467792,0.00017470085],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00020097202,0.00017137654,0.00016821806,0.00023423576,0.00016943393,0.0005800427,0.0006667284,0.0001003873,0.000005460842],"category_scores_gemma":[0.000029304912,0.00016008172,0.00005659187,0.0007335678,0.000009133603,0.0019186323,0.00018378075,0.00015039384,0.000939851],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004284781,0.00000934901,0.03794928,0.0022548218,0.00030638214,0.000045096644,0.6929105,0.011189666,0.0052082837,0.007360601,0.13089368,0.11144389],"study_design_scores_gemma":[0.0024923428,0.0005379306,0.07668764,0.00040219224,0.000050607596,0.00035730732,0.009520726,0.7240569,0.1402814,0.000020389443,0.043515142,0.002077453],"about_ca_topic_score_codex":0.0000032713424,"about_ca_topic_score_gemma":4.220612e-8,"teacher_disagreement_score":0.92027205,"about_ca_system_score_codex":0.00014667214,"about_ca_system_score_gemma":0.00003967563,"threshold_uncertainty_score":0.99983805},"labels":[],"label_agreement":null},{"id":"W6950327416","doi":"10.5284/1065031","title":"I. Brampton, Hunts.","year":2008,"lang":"en","type":"article","venue":"Archaeology Data Service","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Process (computing); Identification (biology); Product (mathematics)","score_opus":0.09391917020195592,"score_gpt":0.29457479162415495,"score_spread":0.20065562142219903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6950327416","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010556701,0.00010504578,0.96953106,0.016834484,0.00025041556,0.00018595743,0.00015405373,0.0010545084,0.0013278053],"genre_scores_gemma":[0.4007884,0.00028734174,0.57784885,0.018951593,0.000099500576,0.000039503306,0.0017271547,0.000020071126,0.00023757352],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983498,0.000106623105,0.00024779246,0.0007465272,0.00020180624,0.00034748437],"domain_scores_gemma":[0.99472415,0.00013947806,0.00010169857,0.004816988,0.00012506412,0.00009260871],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00030044554,0.00013765172,0.00016595068,0.000114266244,0.00014813761,0.00001443584,0.0071190824,0.00009634554,0.000047104168],"category_scores_gemma":[0.00009279224,0.00013860414,0.000014930898,0.0005803458,0.00024298922,0.0014895514,0.005491128,0.00020192529,0.0006748014],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003538366,0.0004160689,0.05338738,0.00009605053,0.00012348003,0.00041446692,0.008357023,0.0000146239445,0.009851575,0.6601727,0.20938958,0.057741687],"study_design_scores_gemma":[0.00066106627,0.00009578532,0.09685756,0.0000187764,0.000010360849,0.00132916,0.000035343513,0.061650354,0.009424979,0.0269865,0.8022468,0.00068329397],"about_ca_topic_score_codex":0.0002948851,"about_ca_topic_score_gemma":0.0001888875,"teacher_disagreement_score":0.63318616,"about_ca_system_score_codex":0.000018671697,"about_ca_system_score_gemma":0.00011505445,"threshold_uncertainty_score":0.99825287},"labels":[],"label_agreement":null},{"id":"W6969000033","doi":"10.5281/zenodo.6501987","title":"Practical Difficulties and Applications of GNNs on Financial Data for Fraud Detection","year":2022,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Larus Technologies (Canada)","funders":"","keywords":"Database transaction; Big data; Key (lock); Financial fraud; Transaction data","score_opus":0.06599477865940498,"score_gpt":0.29663712976172696,"score_spread":0.23064235110232198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6969000033","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047848068,0.000013124122,0.9943911,0.0011165609,0.000042767086,0.00064066175,0.0009965051,0.00051598443,0.0018048324],"genre_scores_gemma":[0.9528697,0.000060029328,0.041927796,0.0002908359,0.00014410623,0.0000038777757,0.0040184115,0.0004316698,0.00025353231],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988109,0.00016901224,0.00018213889,0.0004171102,0.0002715519,0.0001493219],"domain_scores_gemma":[0.9985477,0.00007277836,0.00013523104,0.000962691,0.00022889528,0.000052718035],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0006348571,0.00007093732,0.000086361404,0.000158464,0.0017047611,0.00023607475,0.0014811592,0.000027527169,0.00020319509],"category_scores_gemma":[0.00074225024,0.00007816559,0.000016436325,0.00043036023,0.00009103476,0.00031335506,0.002601953,0.00017649,0.00006858431],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000082284496,0.00033832283,0.0000013126379,0.00006541786,0.000016953758,0.0000016854361,0.00045169477,0.000033099725,0.011998934,0.27556062,0.2192943,0.49215537],"study_design_scores_gemma":[0.0002177932,0.00032373704,0.00039344624,0.0000037647226,0.0000051602756,0.00003513066,0.00010228854,0.0069171223,0.0027215604,0.0010483823,0.98813814,0.00009347683],"about_ca_topic_score_codex":0.0000040504137,"about_ca_topic_score_gemma":1.952174e-7,"teacher_disagreement_score":0.95246327,"about_ca_system_score_codex":0.00007048724,"about_ca_system_score_gemma":0.000007390501,"threshold_uncertainty_score":0.99959487},"labels":[],"label_agreement":null},{"id":"W6976652103","doi":"10.60692/zybpg-91c05","title":"Leveraging feature selection to detect potential tax fraudsters","year":2020,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Taxpayer; Treasury; Payment; Enforcement; Evasion (ethics); Agency (philosophy); Feature (linguistics); Work (physics)","score_opus":0.02713987545648489,"score_gpt":0.2097561702501647,"score_spread":0.1826162947936798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6976652103","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011817881,7.801711e-7,0.9835651,0.0019050345,0.00026867545,0.00041106285,0.000030770883,0.0014255425,0.000575147],"genre_scores_gemma":[0.9320899,4.0692797e-8,0.06547038,0.0022109374,0.00009499035,0.000065156775,0.00001273412,0.000007836068,0.000048007318],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986595,0.000062536725,0.00038003232,0.00026990322,0.00037713532,0.00025089222],"domain_scores_gemma":[0.99899584,0.0000033579586,0.00023201639,0.00040940414,0.00018467792,0.00017470085],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00020097202,0.00017137654,0.00016821806,0.00023423576,0.00016943393,0.0005800427,0.0006667284,0.0001003873,0.000005460842],"category_scores_gemma":[0.000029304912,0.00016008172,0.00005659187,0.0007335678,0.000009133603,0.0019186323,0.00018378075,0.00015039384,0.000939851],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004284781,0.00000934901,0.03794928,0.0022548218,0.00030638214,0.000045096644,0.6929105,0.011189666,0.0052082837,0.007360601,0.13089368,0.11144389],"study_design_scores_gemma":[0.0024923428,0.0005379306,0.07668764,0.00040219224,0.000050607596,0.00035730732,0.009520726,0.7240569,0.1402814,0.000020389443,0.043515142,0.002077453],"about_ca_topic_score_codex":0.0000032713424,"about_ca_topic_score_gemma":4.220612e-8,"teacher_disagreement_score":0.92027205,"about_ca_system_score_codex":0.00014667214,"about_ca_system_score_gemma":0.00003967563,"threshold_uncertainty_score":0.99983805},"labels":[],"label_agreement":null},{"id":"W6990011412","doi":"","title":"Classification of Missing Youths Cases using Support Vector Machines","year":2019,"lang":"en","type":"dissertation","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Support vector machine; Set (abstract data type); Missing data; Interface (matter); Service (business); Intervention (counseling); Reduction (mathematics)","score_opus":0.05634667820165147,"score_gpt":0.3369673941658371,"score_spread":0.28062071596418564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6990011412","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038849674,0.00022901013,0.9255674,0.00034544928,0.002508775,0.0012006973,0.00020904798,0.001183775,0.029906165],"genre_scores_gemma":[0.79026836,0.000029336561,0.19974542,0.00011130331,0.00008585322,0.000028817725,0.002833275,0.00006453346,0.0068331184],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9978767,0.00007583473,0.0006827727,0.0006619196,0.0004648068,0.00023794746],"domain_scores_gemma":[0.9970601,0.00018152206,0.0008991233,0.0014064217,0.00039045824,0.00006234612],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027214148,0.00030089336,0.0004420797,0.0003963529,0.000087116096,0.00015659486,0.0012101864,0.00030195378,0.000099023106],"category_scores_gemma":[0.0002258011,0.0002873595,0.00012335682,0.000445795,0.000033286655,0.0006804837,0.000076229,0.0002142977,0.00004653726],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007879471,0.00035799402,0.0019753622,0.0016040546,0.00013099176,0.00003315711,0.0027662935,0.000010936944,0.629319,0.13931352,0.008750321,0.21565959],"study_design_scores_gemma":[0.00079310924,0.00044618177,0.06492866,0.0012069042,0.0002543895,0.00023293133,0.0014251799,0.3079656,0.6090955,0.003819841,0.007046976,0.0027847076],"about_ca_topic_score_codex":0.00017864553,"about_ca_topic_score_gemma":0.000028414024,"teacher_disagreement_score":0.75141865,"about_ca_system_score_codex":0.00011486266,"about_ca_system_score_gemma":0.00048645804,"threshold_uncertainty_score":0.99995786},"labels":[],"label_agreement":null},{"id":"W7011007405","doi":"","title":"Learning to live with false alarms","year":2005,"lang":"en","type":"article","venue":"NPARC","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Classifier (UML); Bayes error rate; Naive Bayes classifier; Anomaly detection; Bayes classifier; Bayes' theorem","score_opus":0.01362786877603317,"score_gpt":0.25123609465508073,"score_spread":0.23760822587904756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7011007405","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025476104,0.000008286713,0.9500909,0.007384723,0.00003172486,0.0001856835,0.0000017300171,0.0008800539,0.015940791],"genre_scores_gemma":[0.548627,0.0000034528277,0.44974536,0.00068895606,0.000034345372,0.000026803875,0.0000019831857,0.0000053182375,0.00086677005],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992584,0.000027815144,0.00009444013,0.00025936947,0.00018411825,0.00017586915],"domain_scores_gemma":[0.9993368,0.000028346494,0.000039449926,0.00045436758,0.000062779574,0.0000782558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014315218,0.0000735243,0.000073275914,0.00006765321,0.000068304435,0.00009192545,0.00059857813,0.000026024369,0.0000619666],"category_scores_gemma":[0.000040257,0.00006115255,0.000012740751,0.00023460842,0.000018562085,0.00038613018,0.00014048378,0.00011833817,0.0006247661],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012550654,0.000077224206,0.0012586465,0.0000063647262,0.000011547383,0.000010452268,0.0059196446,0.00029593921,0.0713058,0.058203127,0.026046133,0.83685255],"study_design_scores_gemma":[0.0004461135,0.00068444543,0.008411722,0.000071074996,0.0000060766893,0.00004788854,0.00043699032,0.03673331,0.20731297,0.0050702607,0.7401271,0.00065203715],"about_ca_topic_score_codex":0.0000029266714,"about_ca_topic_score_gemma":0.000006566794,"teacher_disagreement_score":0.83620054,"about_ca_system_score_codex":0.00004121528,"about_ca_system_score_gemma":0.000027759013,"threshold_uncertainty_score":0.80303127},"labels":[],"label_agreement":null},{"id":"W7030454340","doi":"","title":"Neurobehavior of preterm and fullterm [sic] newborns, its relationship to intelligence at 10 years of age","year":2000,"lang":"en","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Population; MEDLINE; Disease; Affect (linguistics)","score_opus":0.00989365120187108,"score_gpt":0.18611275972854194,"score_spread":0.17621910852667086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7030454340","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010963759,0.0011760645,0.0076052425,0.0014702847,0.00030419507,0.0012846938,0.003088132,0.00011916958,0.9739885],"genre_scores_gemma":[0.53234696,0.0009039537,0.04223276,0.00071247446,0.0000540531,0.000036899957,0.00006271036,0.0001626915,0.4234875],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982797,0.000052855943,0.00032621154,0.0003300224,0.0008473626,0.00016385186],"domain_scores_gemma":[0.9988813,0.000143215,0.00030578335,0.00051244587,6.296495e-7,0.00015661874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000010096646,0.00016651877,0.00027585062,0.0000763912,0.00003295377,0.000016126209,0.0006232206,0.000048247573,0.00007797204],"category_scores_gemma":[0.0000055059395,0.00018419411,0.000020159752,0.000120013574,0.00008549128,0.00019241942,0.00034346132,0.000096948366,1.1033834e-8],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064967404,0.00018836904,0.02444924,0.0022865653,0.00018986642,0.00034366534,0.00091768237,0.000047118825,0.065731585,0.25692487,0.22203995,0.4262314],"study_design_scores_gemma":[0.0002715237,0.0003216217,0.18399169,0.0011479425,0.000051889594,0.000016980637,0.00008441255,0.000740146,0.23729345,0.0008961768,0.5743632,0.0008210073],"about_ca_topic_score_codex":0.0006344073,"about_ca_topic_score_gemma":0.0048753107,"teacher_disagreement_score":0.5505009,"about_ca_system_score_codex":0.0000058710575,"about_ca_system_score_gemma":0.00042616398,"threshold_uncertainty_score":0.7511218},"labels":[],"label_agreement":null},{"id":"W7030454379","doi":"","title":"A Needs Assessment Survey of Division Chiefs at an Academic Children’s Hospital","year":2023,"lang":"en","type":"other","venue":"Dove Medical Press (Taylor and Francis Group)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Division (mathematics); Needs assessment; Preparedness; Survey research; Descriptive statistics; Survey methodology","score_opus":0.03359510402049193,"score_gpt":0.3208697828868731,"score_spread":0.2872746788663812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7030454379","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047691024,0.0012619757,0.98952085,0.00019519187,0.0010223208,0.00076086546,0.0009975778,0.0013624114,0.004401906],"genre_scores_gemma":[0.9634135,0.0005601888,0.022944566,0.00073472696,0.0010900934,0.00047759863,0.005453448,0.0012697111,0.004056213],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99549717,0.00039233707,0.0007924031,0.0010829418,0.0016848472,0.000550323],"domain_scores_gemma":[0.996623,0.0003465068,0.00060572976,0.001801651,0.0000940091,0.000529105],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017222177,0.0005270761,0.0008547893,0.00042281105,0.00011040702,0.000096182936,0.002520841,0.001072402,0.00035540317],"category_scores_gemma":[0.000634135,0.00044784383,0.000118866934,0.00065101706,0.0004491357,0.0003734993,0.0015368433,0.0010837377,0.00007525344],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002352553,0.0005767237,0.07724677,0.00024209502,0.00022387525,0.00001065656,0.00062977476,8.573702e-7,0.00018086917,0.0077272486,0.04170273,0.87143487],"study_design_scores_gemma":[0.0027861632,0.00063787895,0.8533929,0.00019840067,0.0001099507,0.000030501024,0.0000133291605,0.07682456,0.00019765797,0.0012931058,0.06212772,0.002387801],"about_ca_topic_score_codex":0.0025826644,"about_ca_topic_score_gemma":0.00083395117,"teacher_disagreement_score":0.9665763,"about_ca_system_score_codex":0.00007784142,"about_ca_system_score_gemma":0.000008378772,"threshold_uncertainty_score":0.99979734},"labels":[],"label_agreement":null},{"id":"W7039677030","doi":"","title":"Mining impact and Indigenous protected and conserved areas","year":2023,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"Social Sciences and Humanities Research Council of Canada; Mitacs","keywords":"Sustenance; Indigenous; Traditional knowledge; Natural resource; Land use; Resource (disambiguation); Land management","score_opus":0.021781931105159493,"score_gpt":0.23711975745693922,"score_spread":0.21533782635177973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7039677030","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9922805,0.00014770037,0.006003562,0.00020287,0.00008287758,0.00048770773,0.00003915349,0.00042610863,0.0003295309],"genre_scores_gemma":[0.92295545,0.0009461822,0.071634464,0.000033960714,0.000042399235,0.0000074566665,0.0010385358,0.00007539583,0.0032661376],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99903446,0.00006298572,0.00009232972,0.00041092996,0.0002092316,0.00019008451],"domain_scores_gemma":[0.9989626,0.00007625727,0.0003072046,0.00042220738,0.00015033298,0.00008142013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016385074,0.00017764907,0.00027184695,0.00035823995,0.00022483263,0.000078112615,0.00055057585,0.00021137529,0.0000014410525],"category_scores_gemma":[0.00004777286,0.0002222447,0.00004533475,0.0003751387,0.000078232835,0.00034539722,0.00018708209,0.00018049235,0.000008096847],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011864894,0.0006497165,0.47008523,0.0061663543,0.0019465439,0.001275127,0.099826805,0.000019167566,0.06779699,0.0073104324,0.056462407,0.28727475],"study_design_scores_gemma":[0.0003258985,0.0001525272,0.98210096,0.00021921394,0.000036640533,0.000013149571,0.013774394,0.0013206076,0.0011321419,0.00027843544,0.0003374051,0.00030862514],"about_ca_topic_score_codex":0.0016938224,"about_ca_topic_score_gemma":0.052809495,"teacher_disagreement_score":0.5120157,"about_ca_system_score_codex":0.000062430634,"about_ca_system_score_gemma":0.00015034339,"threshold_uncertainty_score":0.96447426},"labels":[],"label_agreement":null},{"id":"W7042806372","doi":"","title":"Prevalence of asthma symptoms among adults aged 20â44 years in Canada","year":2001,"lang":"en","type":"article","venue":"PubMed Central","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Asthma; Epidemiology; MEDLINE; Population; Prevalence","score_opus":0.007340934129597527,"score_gpt":0.19086283389298617,"score_spread":0.18352189976338865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7042806372","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9855428,0.000057024878,0.013223501,0.000121862824,0.00029720837,0.00034020824,0.000024323994,0.00008787545,0.00030522997],"genre_scores_gemma":[0.9971358,0.00008217997,0.002455595,0.000073204465,0.000028976647,0.00008780358,0.0000064499304,0.000006441399,0.00012353067],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981897,0.00006517379,0.00028747937,0.00031691653,0.0003312067,0.00080956146],"domain_scores_gemma":[0.9990403,0.000040149658,0.00013391543,0.0005719839,0.000028091477,0.00018557599],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026260075,0.00009855024,0.00012946595,0.00008233507,0.00001751491,0.000026769347,0.0009965504,0.000038889255,0.000016218497],"category_scores_gemma":[0.00009128505,0.000107017215,0.00002482458,0.00041651918,0.000046859364,0.00044571486,0.000117974225,0.00013398369,0.000001832198],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000088034885,0.00003303069,0.93883026,0.000028721826,0.000003870758,0.000031854142,0.00019925443,0.000030467127,0.000041968913,0.0007759278,0.0009974419,0.059018392],"study_design_scores_gemma":[0.00022861197,0.000008819188,0.99457365,0.000038894894,0.0000010902336,0.000004997113,0.000012817581,0.0027890138,0.0017104149,0.000058652076,0.00046264817,0.00011040465],"about_ca_topic_score_codex":0.22836713,"about_ca_topic_score_gemma":0.35343733,"teacher_disagreement_score":0.1250702,"about_ca_system_score_codex":0.00058966764,"about_ca_system_score_gemma":0.00045744394,"threshold_uncertainty_score":0.77677125},"labels":[],"label_agreement":null},{"id":"W7045689207","doi":"","title":"Classification with Margin Constraints: A Unification with Applications to Optimization","year":2016,"lang":"en","type":"article","venue":"Spiral (Imperial College London)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Nucleofection; Liquation; Hyporeflexia; Tubulopathy; TSG101; Diafiltration; Gestational period","score_opus":0.016564023125231725,"score_gpt":0.24628943676978327,"score_spread":0.22972541364455154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7045689207","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024361804,0.000008326213,0.9846538,0.0060627866,0.00008847294,0.002044335,0.00017932442,0.0007899403,0.0037368864],"genre_scores_gemma":[0.62981194,0.000015449277,0.36757064,0.0004199908,0.000119899385,0.0015224688,0.000069766924,0.000032121032,0.00043774312],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976988,0.00010773792,0.00043547456,0.00088086136,0.0004725498,0.0004045878],"domain_scores_gemma":[0.9974708,0.00008957835,0.0002844001,0.0014306873,0.0005035034,0.00022104495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002982775,0.0002902732,0.0002525629,0.000297151,0.00026054517,0.00018871554,0.0010749847,0.00012303652,0.000078387195],"category_scores_gemma":[0.000060880142,0.00019370813,0.000036903053,0.0014743888,0.00027560606,0.0011605908,0.00011665263,0.000101395664,0.00016371562],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002705141,0.00015305773,0.00048659713,0.000017676428,0.000027484539,0.0000053786844,0.00010405609,0.00013196317,0.06919196,0.8965409,0.0015025428,0.03156789],"study_design_scores_gemma":[0.025884781,0.00963061,0.03631377,0.0014355134,0.00028228865,0.0007006555,0.0011171337,0.04152062,0.37703478,0.01339751,0.48397276,0.00870958],"about_ca_topic_score_codex":0.000009121754,"about_ca_topic_score_gemma":0.000023076122,"teacher_disagreement_score":0.88314337,"about_ca_system_score_codex":0.0002751999,"about_ca_system_score_gemma":0.0003334942,"threshold_uncertainty_score":0.78991884},"labels":[],"label_agreement":null},{"id":"W7083416347","doi":"10.18391/racin.v9i1.4016","title":"Noções de informação","year":2024,"lang":"pt","type":"article","venue":"Revista Analisando em Ciência da Informação","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Universidade Federal da Paraíba","keywords":"Articulation (sociology); Meaning (existential); Order (exchange)","score_opus":0.03213237957131874,"score_gpt":0.3079012637234097,"score_spread":0.27576888415209094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7083416347","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005891307,0.011199046,0.9537046,0.0017294013,0.0018147718,0.0014951081,0.0009473327,0.0036544357,0.01956401],"genre_scores_gemma":[0.9506432,0.006922972,0.019224156,0.0069322297,0.0012991277,0.0003728754,0.0013736871,0.00022900167,0.013002773],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99394274,0.0001912029,0.0020454372,0.00097308896,0.0012720879,0.0015754276],"domain_scores_gemma":[0.9954152,0.000341613,0.0005641499,0.0025997781,0.00043511429,0.0006441462],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024611044,0.0009041946,0.0009184633,0.0010653243,0.00050529535,0.00847243,0.003336256,0.00052598474,0.00051265984],"category_scores_gemma":[0.00046148052,0.00086680404,0.00057728624,0.003193898,0.00025100083,0.0069574416,0.0011235016,0.001204568,0.0024596895],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059523696,0.00010188041,0.00090406707,0.0027547693,0.00031073103,0.00021620901,0.012233855,0.000050831557,0.00042406033,0.3825168,0.25659585,0.34383142],"study_design_scores_gemma":[0.00047943956,0.00018584802,0.0010286021,0.0015655748,0.00013851564,0.0002817731,0.0006428083,0.16169445,0.0016739374,0.0004889115,0.8306461,0.0011740151],"about_ca_topic_score_codex":0.00008233073,"about_ca_topic_score_gemma":0.000019564959,"teacher_disagreement_score":0.94475186,"about_ca_system_score_codex":0.0008473736,"about_ca_system_score_gemma":0.0016564172,"threshold_uncertainty_score":0.99937826},"labels":[],"label_agreement":null},{"id":"W7084037380","doi":"10.6084/m9.figshare.29980269.v3","title":"Cost-effectiveness of insulin icodec for the treatment of type 2 diabetes in Canada","year":2025,"lang":"en","type":"article","venue":"Figshare","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Insulin degludec; Insulin; Insulin glargine; Glycemic; Type 2 diabetes; Diabetes mellitus; Insulin analog; Basal (medicine)","score_opus":0.06589184234168338,"score_gpt":0.30805307428575085,"score_spread":0.24216123194406747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7084037380","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.065679885,0.013569673,0.04003079,0.002172521,0.0013610618,0.021556666,0.8524301,0.00047074092,0.0027285363],"genre_scores_gemma":[0.9930769,0.0000216021,0.0011639536,0.000046005753,0.000004484141,0.0011952198,0.0044654342,0.0000034465245,0.0000229123],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99958694,0.000035800887,0.00012016672,0.000114237606,0.00006139001,0.00008144607],"domain_scores_gemma":[0.9985499,0.00089903024,0.00006237855,0.0003623319,0.00011754903,0.000008817201],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000048582904,0.000050664057,0.000113437236,0.000040369345,0.000015640446,0.000007387629,0.00041232238,0.000019010882,0.00014186424],"category_scores_gemma":[0.0002612935,0.00003627304,0.000018677369,0.00031471346,0.000004005345,0.00005396387,0.000043669257,0.000018671606,0.0000016661326],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009906689,0.00058718014,0.017618313,0.0019219546,0.00015670914,0.0000026537607,0.00034840454,0.0007477532,0.0040693856,0.009585459,0.1579654,0.8068977],"study_design_scores_gemma":[0.00070012023,0.00020905137,0.19400546,0.0012973718,0.000006594792,1.0217871e-7,0.000020208741,0.046848908,0.6087047,0.00068972167,0.14739285,0.00012492681],"about_ca_topic_score_codex":0.020427749,"about_ca_topic_score_gemma":0.050153382,"teacher_disagreement_score":0.9273971,"about_ca_system_score_codex":0.0002173637,"about_ca_system_score_gemma":0.00057618786,"threshold_uncertainty_score":0.9860953},"labels":[],"label_agreement":null},{"id":"W7084153168","doi":"10.64628/aam.n45tpgskj","title":"The future of renewable infrastructure is uncertain without good planning","year":2019,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Renewable energy; Production (economics); Key (lock); Work (physics); Investment (military)","score_opus":0.009536800850560521,"score_gpt":0.2611772206575125,"score_spread":0.25164041980695195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7084153168","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01008028,0.00049068674,0.9259141,0.005440866,0.0007575404,0.0005160879,0.000017495455,0.0006224456,0.056160517],"genre_scores_gemma":[0.7477807,0.00007144622,0.2412258,0.001242503,0.0001081703,0.000018706267,0.000010431094,0.00001382738,0.009528455],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99913096,0.000032669377,0.00018677155,0.00024012552,0.00023472487,0.00017473282],"domain_scores_gemma":[0.9986082,0.0000615396,0.00014175638,0.0010742692,0.000083485524,0.000030775194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021461384,0.00009394427,0.000115397816,0.0000410314,0.00008439681,0.000092534676,0.0012539447,0.000069732516,0.000040141516],"category_scores_gemma":[0.0000103906295,0.00005722055,0.000029991492,0.00028521655,0.00003448265,0.00033402847,0.00020449965,0.000111345806,0.000021454372],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022963113,0.000029067862,0.085751005,0.00005463358,0.000047235117,0.0000015527802,0.0016613862,0.0006096572,0.025331985,0.5556539,0.2623769,0.0684597],"study_design_scores_gemma":[0.00038515995,0.00012900712,0.020189468,0.00005685402,0.000004628983,0.000015030569,0.0005918658,0.040933438,0.14488406,0.035659634,0.7568192,0.0003316669],"about_ca_topic_score_codex":0.000037053152,"about_ca_topic_score_gemma":0.000004819303,"teacher_disagreement_score":0.7377004,"about_ca_system_score_codex":0.000025046364,"about_ca_system_score_gemma":0.00007383596,"threshold_uncertainty_score":0.23333864},"labels":[],"label_agreement":null},{"id":"W7096027436","doi":"","title":"� Information-Based Versus Number-Correct Routing in Multistage Classification Tests Alexander Weissman","year":2007,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Discretion; Government (linguistics); Agency (philosophy); Accreditation; Common law; Public law","score_opus":0.03198877910452739,"score_gpt":0.3129481400938276,"score_spread":0.2809593609893002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096027436","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006894487,0.0000014540504,0.9544086,0.0004405712,0.00026972397,0.00027581584,0.0000042981897,0.00074127247,0.036963798],"genre_scores_gemma":[0.8660642,0.0000014211724,0.13324535,0.0003913412,0.000020569194,0.000026845246,0.00007842237,0.00000657851,0.0001652542],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846876,0.000049286566,0.00056046626,0.00024740244,0.00032675397,0.00034733186],"domain_scores_gemma":[0.9982676,0.00049711583,0.00023887266,0.00077260676,0.00014236014,0.00008143098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010998388,0.00015229982,0.0001290287,0.0002599346,0.00009761671,0.00020634287,0.0007548797,0.00010899102,0.00007708889],"category_scores_gemma":[0.00039980104,0.00015166287,0.00003643052,0.0008080446,0.000040471157,0.0017152362,0.00008629319,0.00018832275,0.00034595464],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013457824,0.00030149115,0.18071567,0.000047923608,0.000013328371,0.000010779023,0.0015101095,0.00014302974,0.003991316,0.39452136,0.009457665,0.40915278],"study_design_scores_gemma":[0.002322993,0.00006939213,0.42681423,0.000047962174,0.0000036577546,0.000005376029,0.0004563175,0.5204002,0.034099862,0.00028047612,0.014914931,0.0005845691],"about_ca_topic_score_codex":0.00016577115,"about_ca_topic_score_gemma":0.0002564212,"teacher_disagreement_score":0.8591697,"about_ca_system_score_codex":0.00026445216,"about_ca_system_score_gemma":0.00010943404,"threshold_uncertainty_score":0.6184632},"labels":[],"label_agreement":null},{"id":"W7099024741","doi":"","title":"Saskatoon By","year":2009,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Permission; Copying; sort; Work (physics); Documentation","score_opus":0.006395969861616408,"score_gpt":0.23414138833448278,"score_spread":0.22774541847286636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099024741","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012136624,0.000018502315,0.9332588,0.005585072,0.000023653978,0.000039787836,0.000001078841,0.000779892,0.060171876],"genre_scores_gemma":[0.60153544,0.000008859597,0.38662553,0.0060630394,0.00001362444,0.0000048003103,0.000009388819,0.000002195722,0.00573716],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995839,0.000009617646,0.00007121982,0.00015180839,0.00009049976,0.00009292727],"domain_scores_gemma":[0.99946636,0.000008356815,0.000020169566,0.00045768812,0.000017976323,0.000029465802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006810167,0.00003985089,0.00003777121,0.000024581921,0.000025292285,0.00007245767,0.00055700605,0.000020939462,0.000019706029],"category_scores_gemma":[0.0000064946844,0.000034256987,0.000010983175,0.00013964983,0.000008225116,0.0004316583,0.000029932402,0.00003313155,0.00011916612],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.2233309e-7,0.00002565798,0.000029178773,2.6357435e-7,4.2326784e-7,4.1718903e-7,0.000015746646,4.796473e-8,0.02197925,0.3837762,0.45105878,0.14311385],"study_design_scores_gemma":[0.000120081626,0.00013451968,0.0061936826,0.0000035091493,6.2537083e-7,0.0000067943165,0.0000039322726,0.00552455,0.36901325,0.042955168,0.5758401,0.00020374439],"about_ca_topic_score_codex":0.00000263429,"about_ca_topic_score_gemma":4.0984298e-7,"teacher_disagreement_score":0.601414,"about_ca_system_score_codex":0.00001268809,"about_ca_system_score_gemma":0.000009080936,"threshold_uncertainty_score":0.15316792},"labels":[],"label_agreement":null},{"id":"W7099345472","doi":"","title":"Article A Survey of Mercury in Air and Precipitation across Canada: Patterns and Trends","year":2014,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mercury (programming language); Precipitation; Air pollution; MERCURE","score_opus":0.017590259538952657,"score_gpt":0.2693638939288924,"score_spread":0.2517736343899397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099345472","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.82516724,0.0000075866737,0.17421873,0.0004127187,0.000017699424,0.0000316977,0.000022384387,0.00002809914,0.00009386651],"genre_scores_gemma":[0.9953946,0.000006709146,0.004432056,0.00011650238,0.0000019990687,0.000005859664,0.00000818018,0.0000020444274,0.000032033993],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9994209,0.00008152807,0.0001428242,0.00016332208,0.0000922498,0.00009920495],"domain_scores_gemma":[0.9995372,0.00011958939,0.000048172704,0.00021973776,0.0000439131,0.000031376363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004520158,0.000044704608,0.000080519596,0.000027851222,0.00001870635,0.00001519131,0.00014101688,0.000020204969,0.0000018228045],"category_scores_gemma":[0.000077016215,0.000040765888,0.0000030557183,0.00019124988,0.000024210905,0.00023994118,0.00008527407,0.000032051543,1.672138e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003048063,0.000018596991,0.8098902,0.000013952077,0.0000019223035,2.9858214e-7,0.00048603222,0.0000023023083,0.0008066761,0.0031205176,0.00038818445,0.18526827],"study_design_scores_gemma":[0.000113013404,0.000019964189,0.9703265,0.000005270317,3.0309596e-7,9.0859726e-7,0.00001585337,0.019299151,0.009974029,0.000100692465,0.00009713511,0.000047173886],"about_ca_topic_score_codex":0.40838742,"about_ca_topic_score_gemma":0.82429624,"teacher_disagreement_score":0.41590884,"about_ca_system_score_codex":0.000019817635,"about_ca_system_score_gemma":0.000021233325,"threshold_uncertainty_score":0.5955522},"labels":[],"label_agreement":null},{"id":"W7109517645","doi":"10.5281/zenodo.17839657","title":"Converging AI innovation and quantum security for data-driven compliance, financial crime re-regulation","year":2025,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Scalability; Random forest; Quantum; Coherence (philosophical gambling strategy); Qubit; Credit card; Set (abstract data type)","score_opus":0.07767801117414146,"score_gpt":0.31692212783301965,"score_spread":0.23924411665887818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7109517645","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000937908,0.000033297296,0.98764545,0.003190368,0.00013879336,0.0006159034,0.0003002862,0.0010363258,0.0061016856],"genre_scores_gemma":[0.9678332,0.000039050665,0.022971239,0.0012275209,0.00010387897,5.215071e-7,0.007192764,0.00029721434,0.000334579],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984927,0.00014447336,0.00032195356,0.0005907714,0.00021261619,0.00023743829],"domain_scores_gemma":[0.99783397,0.00003956587,0.00015496253,0.0010032014,0.00092281227,0.000045505643],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0008121858,0.000116991265,0.00013708053,0.00036455801,0.0013974779,0.00087581325,0.0017503917,0.00006835716,0.00013802115],"category_scores_gemma":[0.0009983657,0.00013529824,0.000015809432,0.0011599798,0.00012539442,0.0011700252,0.0019317911,0.00017336641,0.00014504312],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021039741,0.000041473428,0.0000060468788,0.0000815282,0.0000088914485,5.1721753e-7,0.00020971047,0.000006643129,0.0029705819,0.62584823,0.31340942,0.0573959],"study_design_scores_gemma":[0.0003930453,0.00006261223,0.0017425929,0.000056906432,0.000006225242,0.000006554293,0.000025760346,0.20736541,0.0014157613,0.019835526,0.7689491,0.0001404984],"about_ca_topic_score_codex":0.0000066351654,"about_ca_topic_score_gemma":2.2935986e-7,"teacher_disagreement_score":0.96689534,"about_ca_system_score_codex":0.0001032246,"about_ca_system_score_gemma":0.000016111859,"threshold_uncertainty_score":0.99990255},"labels":[],"label_agreement":null},{"id":"W7109786261","doi":"10.5281/zenodo.17839658","title":"Converging AI innovation and quantum security for data-driven compliance, financial crime re-regulation","year":2025,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Scalability; Random forest; Quantum; Coherence (philosophical gambling strategy); Qubit; Credit card; Set (abstract data type)","score_opus":0.07767801117414146,"score_gpt":0.31692212783301965,"score_spread":0.23924411665887818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7109786261","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000937908,0.000033297296,0.98764545,0.003190368,0.00013879336,0.0006159034,0.0003002862,0.0010363258,0.0061016856],"genre_scores_gemma":[0.9678332,0.000039050665,0.022971239,0.0012275209,0.00010387897,5.215071e-7,0.007192764,0.00029721434,0.000334579],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984927,0.00014447336,0.00032195356,0.0005907714,0.00021261619,0.00023743829],"domain_scores_gemma":[0.99783397,0.00003956587,0.00015496253,0.0010032014,0.00092281227,0.000045505643],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0008121858,0.000116991265,0.00013708053,0.00036455801,0.0013974779,0.00087581325,0.0017503917,0.00006835716,0.00013802115],"category_scores_gemma":[0.0009983657,0.00013529824,0.000015809432,0.0011599798,0.00012539442,0.0011700252,0.0019317911,0.00017336641,0.00014504312],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021039741,0.000041473428,0.0000060468788,0.0000815282,0.0000088914485,5.1721753e-7,0.00020971047,0.000006643129,0.0029705819,0.62584823,0.31340942,0.0573959],"study_design_scores_gemma":[0.0003930453,0.00006261223,0.0017425929,0.000056906432,0.000006225242,0.000006554293,0.000025760346,0.20736541,0.0014157613,0.019835526,0.7689491,0.0001404984],"about_ca_topic_score_codex":0.0000066351654,"about_ca_topic_score_gemma":2.2935986e-7,"teacher_disagreement_score":0.96689534,"about_ca_system_score_codex":0.0001032246,"about_ca_system_score_gemma":0.000016111859,"threshold_uncertainty_score":0.99990255},"labels":[],"label_agreement":null},{"id":"W7110688175","doi":"","title":"Uzun kuyruklu görsel tanımada sınıf dengesizliğinin öz boyut kullanımı ile azaltılması","year":2024,"lang":"","type":"dissertation","venue":"OpenMETU (Middle East Technical University)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Class (philosophy); Field (mathematics); Estimation; Calibration; Curse of dimensionality; Image (mathematics)","score_opus":0.04318234343251115,"score_gpt":0.2417536205016009,"score_spread":0.19857127706908975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7110688175","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055519617,0.006449619,0.75091946,0.0038567544,0.01081234,0.010029588,0.0030858659,0.012775796,0.19651863],"genre_scores_gemma":[0.5570339,0.0054463213,0.1647438,0.00095313304,0.0013580152,0.0002447392,0.0068819765,0.0009222538,0.26241586],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98697364,0.0008625127,0.0020184496,0.005170708,0.0027739713,0.0022007155],"domain_scores_gemma":[0.9897892,0.000497101,0.0015555552,0.005452494,0.001460328,0.0012453571],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"category_scores_codex":[0.0015257756,0.0021862364,0.0023531914,0.003259906,0.0012020274,0.0020551642,0.014330361,0.0028245812,0.0009238928],"category_scores_gemma":[0.0005431306,0.002600166,0.0012494375,0.007700059,0.0007098137,0.0031429606,0.0047278916,0.0040827687,0.004982812],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006241517,0.001715608,0.00012389148,0.000852737,0.0008628094,0.0040400513,0.0026303446,0.00004234417,0.012591499,0.8352412,0.048411794,0.09286358],"study_design_scores_gemma":[0.0028596187,0.0013717563,0.0010651142,0.0057357717,0.0014131417,0.00040537675,0.006316105,0.0052150926,0.013115124,0.0077339616,0.94784933,0.006919625],"about_ca_topic_score_codex":0.00039038755,"about_ca_topic_score_gemma":0.00054576347,"teacher_disagreement_score":0.89943755,"about_ca_system_score_codex":0.0023304657,"about_ca_system_score_gemma":0.0025845864,"threshold_uncertainty_score":0.9999894},"labels":[],"label_agreement":null},{"id":"W7117312634","doi":"10.1002/alz70859_103051","title":"Detecting Site‐Level Fraud via an Artificial Intelligence/Machine Learning Paradoxical Patient Analysis in an Alzheimer's Disease Clinical Trial","year":2025,"lang":"en","type":"article","venue":"Alzheimer s & Dementia","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Clinical trial; Disease; Patient data; Baseline (sea); Work (physics)","score_opus":0.11570212675338899,"score_gpt":0.38101921126618005,"score_spread":0.26531708451279107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117312634","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09667644,0.0035004846,0.89754635,0.00035071876,0.0006147991,0.000749078,0.000025687383,0.0004920684,0.000044387005],"genre_scores_gemma":[0.941745,0.000026570717,0.05730225,0.00040668107,0.00011691307,0.00013389517,0.00024779,0.000020007126,9.2998005e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947239,0.0010761732,0.0016958116,0.0013804433,0.0005385644,0.0005850845],"domain_scores_gemma":[0.9971541,0.00029992324,0.00045875603,0.0015679812,0.00015380877,0.0003653953],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017617305,0.0003608044,0.0005648319,0.0007754162,0.00034699458,0.00040953598,0.0014593238,0.0002010402,0.00006734308],"category_scores_gemma":[0.0002417416,0.00037065666,0.0002976049,0.0021260006,0.00014402739,0.0011746628,0.00058041426,0.000703915,0.000044924418],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012080173,0.001291796,0.037128385,0.0000017618074,0.0037767638,0.00002780984,0.00035456987,0.00084973825,0.00023035814,0.005703867,0.000035145065,0.9493918],"study_design_scores_gemma":[0.001623767,0.00097023835,0.0400682,0.000021075946,0.011144511,0.0000010452034,0.00008567058,0.9254879,0.011318496,0.0074739396,0.0009986862,0.0008064776],"about_ca_topic_score_codex":0.000242378,"about_ca_topic_score_gemma":0.00060778775,"teacher_disagreement_score":0.94858533,"about_ca_system_score_codex":0.000020720947,"about_ca_system_score_gemma":0.00016843667,"threshold_uncertainty_score":0.99987453},"labels":[],"label_agreement":null},{"id":"W7117450253","doi":"10.3390/fi18010015","title":"Wangiri Fraud Detection: A Comprehensive Approach to Unlabeled Telecom Data","year":2025,"lang":"en","type":"article","venue":"Future Internet","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Exploit; Pipeline (software); Scalability; Random forest; Feature (linguistics); Class (philosophy); Multilayer perceptron; Perceptron; Feature engineering","score_opus":0.02906814930040017,"score_gpt":0.2891008305894757,"score_spread":0.26003268128907553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117450253","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00055730186,0.00016564166,0.9850746,0.0030667556,0.0011982335,0.00038925573,0.00004864457,0.0007323754,0.008767238],"genre_scores_gemma":[0.3885143,0.000026600932,0.59710604,0.008524177,0.0006689874,0.00018660439,0.00038333307,0.000025251336,0.00456469],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99835587,0.00007855095,0.00027968394,0.0008182064,0.00020969847,0.00025798523],"domain_scores_gemma":[0.99702525,0.000056617373,0.00008176845,0.0025915448,0.00016531609,0.00007948857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001545651,0.00018690163,0.0002109472,0.00024190867,0.00006649037,0.00024491348,0.003927411,0.00012098461,0.000015767182],"category_scores_gemma":[0.000052700267,0.00017298404,0.000037341597,0.00088631315,0.00003379203,0.00048106967,0.0017522096,0.00027396932,0.00015387005],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002727695,0.00015597673,0.00009646295,0.00004874278,0.00008311507,0.0000055880355,0.00047022064,0.0000057291077,0.005274755,0.07775623,0.7622884,0.15378748],"study_design_scores_gemma":[0.00020372296,0.0000502665,0.0020717233,0.000033581033,0.000007954406,0.000015645324,0.00006836844,0.025951542,0.021475218,0.0007617727,0.9491459,0.00021429015],"about_ca_topic_score_codex":0.00004055984,"about_ca_topic_score_gemma":0.000023417939,"teacher_disagreement_score":0.3879685,"about_ca_system_score_codex":0.00008889263,"about_ca_system_score_gemma":0.000060568982,"threshold_uncertainty_score":0.7298172},"labels":[],"label_agreement":null},{"id":"W7117772401","doi":"10.18280/ts.420615","title":"A Hybrid Image Analysis Model for Credit Card Transaction Monitoring and Fraud Detection","year":2025,"lang":"","type":"article","venue":"Traitement du signal","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Credit card; Credit card fraud; Database transaction; Image (mathematics); Transaction processing; Image processing","score_opus":0.021655990363434005,"score_gpt":0.27821087270595213,"score_spread":0.2565548823425181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117772401","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016390158,0.0002357243,0.9807105,0.0005296766,0.00044409183,0.0010279944,0.00026753524,0.00029820067,0.00009612429],"genre_scores_gemma":[0.91893613,0.0001988857,0.07990119,0.000064521344,0.00017636173,0.00044791432,0.00004151211,0.00001714308,0.00021632585],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971684,0.00010638816,0.00076699187,0.0010337288,0.00044944102,0.00047504282],"domain_scores_gemma":[0.99849874,0.00013663103,0.00027754105,0.00060682296,0.00035133184,0.00012895121],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00079881155,0.00036545843,0.00047430946,0.0008677064,0.0005259935,0.00059599825,0.0005613091,0.00013222212,0.000016531507],"category_scores_gemma":[0.000028162158,0.00042356705,0.00031329104,0.0010319474,0.00011644216,0.0012880554,0.00007907652,0.000246213,0.0000022930335],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031118325,0.0003812858,0.0004679116,0.00038050307,0.0014036644,0.000004287515,0.0013733937,0.01697363,0.26050743,0.0020519057,0.0006216766,0.7155231],"study_design_scores_gemma":[0.0006153248,0.00012770717,0.0019574878,0.000055250868,0.00085640664,0.0000016263576,0.000039963827,0.7730458,0.22116002,0.0014247812,0.00044817312,0.00026747503],"about_ca_topic_score_codex":0.000047081212,"about_ca_topic_score_gemma":0.000010764114,"teacher_disagreement_score":0.902546,"about_ca_system_score_codex":0.00031734296,"about_ca_system_score_gemma":0.00013467723,"threshold_uncertainty_score":0.9998216},"labels":[],"label_agreement":null},{"id":"W7124835309","doi":"10.1109/icaaic64647.2025.11331209","title":"A Constrained and Cardinality Preserved Optimal Graph Attention Network for Fraud Detections in Insurance Claim","year":2025,"lang":"","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Gibson Energy (Canada)","funders":"","keywords":"Cardinality (data modeling); Discriminative model; Graph; Adversarial system; Information loss; Interdependence; Overfitting; Centrality","score_opus":0.023977682698550766,"score_gpt":0.29164160356513186,"score_spread":0.2676639208665811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124835309","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0401874,0.00047358044,0.9528524,0.0023037815,0.0006008066,0.0018807391,0.0001561298,0.0003096756,0.001235481],"genre_scores_gemma":[0.812535,0.000219877,0.18562451,0.00023060932,0.000055167304,0.0005784994,0.000027861835,0.000009506439,0.0007190001],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99694633,0.00030402097,0.0008634194,0.0010676039,0.00021206142,0.00060658425],"domain_scores_gemma":[0.997874,0.00038583853,0.0002455531,0.0010446853,0.0003467339,0.00010317396],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013838271,0.00030643403,0.0004647631,0.00033804422,0.00046580538,0.00040938973,0.000765073,0.00027985452,0.000011956277],"category_scores_gemma":[0.00025565908,0.00033940552,0.00016635761,0.0019619872,0.000409064,0.00093634083,0.0003969401,0.00034850347,0.0000018864205],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003929568,0.00054308533,0.2672512,0.0007493512,0.00026937778,0.000006283281,0.0002625073,0.0019461749,0.0044537117,0.57412267,0.01290067,0.13710201],"study_design_scores_gemma":[0.0019013309,0.00022667661,0.6619748,0.00040975778,0.00004343147,0.000008110172,0.00008061969,0.2916848,0.002103876,0.03704998,0.00399978,0.00051684224],"about_ca_topic_score_codex":0.00025601525,"about_ca_topic_score_gemma":0.00037460518,"teacher_disagreement_score":0.77234757,"about_ca_system_score_codex":0.00011887655,"about_ca_system_score_gemma":0.00023620024,"threshold_uncertainty_score":0.9999058},"labels":[],"label_agreement":null},{"id":"W7125806151","doi":"10.21428/594757db.79c2ce52","title":"A Domain-Specific Transformer Approach for Financial Statement Fraud Detection","year":2025,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Transformer; Financial statement; Encoder; Artificial neural network; Recall","score_opus":0.015931905885661735,"score_gpt":0.262469858018004,"score_spread":0.24653795213234225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125806151","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017114244,0.000032914977,0.98642313,0.0006866233,0.00017859286,0.00073327695,0.000010935735,0.00041897397,0.011344405],"genre_scores_gemma":[0.06599533,0.00003219726,0.9318136,0.00051490247,0.000030192508,0.0006786192,0.000023598412,0.000005410973,0.0009061466],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989962,0.000022230173,0.00026426656,0.00037427107,0.00013299393,0.00021001382],"domain_scores_gemma":[0.99934465,0.00003326802,0.000046789402,0.00046520543,0.0000815725,0.00002849987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031737462,0.00010301702,0.00010964656,0.00014219157,0.00014746285,0.00010597027,0.00051788404,0.000065388296,0.000008863368],"category_scores_gemma":[0.0000054556544,0.00009241473,0.00005742434,0.0003683719,0.000027746975,0.0003656162,0.000032790307,0.00007236585,0.000007911692],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015681242,0.00007314407,0.0000066839775,0.000024326893,0.0000054394445,1.2242201e-7,0.000107892316,0.000003906246,0.013320631,0.7595064,0.01591109,0.21102469],"study_design_scores_gemma":[0.00039763632,0.000060464637,0.00046790522,0.000005533718,0.000002050705,7.3588416e-7,0.00003059946,0.004062262,0.18687394,0.028581847,0.77938795,0.00012905321],"about_ca_topic_score_codex":0.0000049120144,"about_ca_topic_score_gemma":0.0000041797894,"teacher_disagreement_score":0.7634769,"about_ca_system_score_codex":0.0001032792,"about_ca_system_score_gemma":0.000068754234,"threshold_uncertainty_score":0.37685633},"labels":[],"label_agreement":null},{"id":"W7125981108","doi":"10.1145/3768292.3793392","title":"10.1145/3768292.3793392","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Session (web analytics); Anomaly detection; Anomaly (physics); Session key; Financial fraud","score_opus":0.007658487606676427,"score_gpt":0.19367674679799587,"score_spread":0.18601825919131945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125981108","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000036122994,0.0000157125,0.007149466,0.001210305,0.0000034063946,0.00018155492,0.000012886131,0.0010834831,0.9903071],"genre_scores_gemma":[0.00018695413,4.6712887e-7,0.028845385,0.00025881038,0.000044586963,0.000038541122,0.000014559164,0.000011029392,0.97059965],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99898154,0.00003775254,0.00017341213,0.00035044656,0.00021137386,0.0002454854],"domain_scores_gemma":[0.99874765,0.00003535908,0.00003365696,0.0010162832,0.000051182713,0.000115892384],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00017078481,0.000113963346,0.00011614435,0.00009048848,0.00007239868,0.00012734374,0.0011988871,0.000050027138,0.9083082],"category_scores_gemma":[0.00002893383,0.000114191236,0.000033991837,0.0004140947,0.000025518075,0.00041398653,0.00013552538,0.00007873386,0.9726447],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037629704,0.000022619826,8.7808935e-8,0.0000012492873,0.0000023531138,0.000002014371,0.0000105010995,0.0000045686684,0.00025896044,0.00019907253,0.26372966,0.73576516],"study_design_scores_gemma":[0.000069067166,0.00006441803,0.0000707985,0.0000072710604,0.0000016043382,0.000007754337,1.0724955e-7,0.0026774132,0.0019856996,0.00011219216,0.99485266,0.00015100432],"about_ca_topic_score_codex":0.000007119588,"about_ca_topic_score_gemma":3.6611187e-8,"teacher_disagreement_score":0.7356142,"about_ca_system_score_codex":0.000040873118,"about_ca_system_score_gemma":0.000032592747,"threshold_uncertainty_score":0.46565834},"labels":[],"label_agreement":null},{"id":"W7126156478","doi":"10.1109/iconat66879.2025.11362594","title":"An Adaptive AI Model for Intelligent Fraud Detection and Customer Engagement in Digital Banking","year":2025,"lang":"","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Personalization; Database transaction; Dependability; Feature (linguistics); Customer engagement; Transaction processing; Financial transaction; Digital currency; Digital forensics; Reinforcement learning","score_opus":0.042747911791189426,"score_gpt":0.31606870319540664,"score_spread":0.2733207914042172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126156478","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013176252,0.0000750918,0.9949833,0.00042447695,0.00022098521,0.0012268716,0.000035429108,0.00022013036,0.0014960757],"genre_scores_gemma":[0.9072943,0.00008084612,0.09111409,0.00068849855,0.000022338374,0.00026319647,0.000010329786,0.0000122295505,0.00051417114],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978205,0.000067370594,0.0005738049,0.0009311534,0.00022026012,0.0003869276],"domain_scores_gemma":[0.99865514,0.00014310109,0.00013052905,0.0007429735,0.000246379,0.000081875754],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00075488345,0.00026305788,0.00024569157,0.0005869774,0.00023546332,0.0008026451,0.00066669413,0.00015398572,0.000010804651],"category_scores_gemma":[0.00009113399,0.00027679937,0.00005447137,0.00066001026,0.00010372014,0.0025586444,0.000432622,0.00033305804,0.0000071784007],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007450542,0.00024059613,0.00018721905,0.000044892124,0.000022231325,6.88978e-7,0.001404772,0.0032634658,0.00097285927,0.15175255,0.00023558245,0.84180063],"study_design_scores_gemma":[0.0002670287,0.00020828587,0.00030765915,0.000090718706,0.000010703927,7.8768375e-7,0.00027520346,0.9474707,0.022546316,0.026688546,0.0018707169,0.0002633293],"about_ca_topic_score_codex":0.000028208442,"about_ca_topic_score_gemma":0.00007141907,"teacher_disagreement_score":0.94420725,"about_ca_system_score_codex":0.00032653156,"about_ca_system_score_gemma":0.00016556388,"threshold_uncertainty_score":0.9999684},"labels":[],"label_agreement":null},{"id":"W7126435203","doi":"10.21428/594757db.ba120f9f","title":"Same File Prediction: A New Pretraining Objective forBERT-like Transformers","year":2024,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"","keywords":"Transformer; Language model; Training set; Task (project management); Task analysis; Binary classification","score_opus":0.019814064802095733,"score_gpt":0.2594525832086411,"score_spread":0.23963851840654538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126435203","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012922391,0.00013556953,0.94125545,0.0015898264,0.0004753165,0.00023603934,0.0001646544,0.0027525916,0.053377625],"genre_scores_gemma":[0.110116124,0.00009466634,0.8452307,0.0030466502,0.0004328846,0.00034233328,0.0003444465,0.000054433705,0.04033779],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99879175,0.00002197124,0.00021168015,0.0004809718,0.0002472539,0.0002463605],"domain_scores_gemma":[0.99930024,0.00013555467,0.000024281002,0.00039400667,0.000039142404,0.00010675068],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015714466,0.00013246154,0.00010972194,0.00015741398,0.00007953584,0.0003060345,0.00051536254,0.000079519494,0.0015055531],"category_scores_gemma":[0.000030363752,0.0001166902,0.000072023395,0.0006630042,0.00003706004,0.0014516733,0.000060747276,0.00018337465,0.00015707331],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034669308,0.000015743719,0.000010668729,0.000025626166,0.000035568057,0.0000072173984,0.0028025683,0.000004852533,0.0009410827,0.08370139,0.56678367,0.34566814],"study_design_scores_gemma":[0.00024234803,0.00026309703,0.0010722263,0.00018388966,0.00001519832,0.00008906938,0.00024187457,0.32148486,0.012025783,0.019092383,0.64487845,0.0004108118],"about_ca_topic_score_codex":0.00005447732,"about_ca_topic_score_gemma":0.000012879392,"teacher_disagreement_score":0.3452573,"about_ca_system_score_codex":0.00010267183,"about_ca_system_score_gemma":0.00026953785,"threshold_uncertainty_score":0.99940723},"labels":[],"label_agreement":null},{"id":"W7127420896","doi":"10.18280/ijsse.151114","title":"An Accurate Fraud Source Path Identification Using Integration of Graphical Neural Networks, Long-Short Term Memories, and XGBoost","year":2025,"lang":"","type":"article","venue":"International Journal of Safety and Security Engineering","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Term (time); Identification (biology); Path (computing); Artificial neural network; Pattern recognition (psychology); Long-term prediction","score_opus":0.011497995139968274,"score_gpt":0.2761238272722947,"score_spread":0.2646258321323264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7127420896","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21186507,0.0010661208,0.78521585,0.00041417277,0.0012372438,0.00012758073,0.000038051527,0.000030061052,0.000005857593],"genre_scores_gemma":[0.9922558,0.0025677837,0.004815793,0.00005311567,0.00024691192,0.0000016113621,0.00004153947,0.00001312015,0.0000043040845],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974151,0.00011110987,0.0013809872,0.00035300417,0.00053001585,0.00020977674],"domain_scores_gemma":[0.99774534,0.0001666546,0.00067275396,0.0003201095,0.0009588062,0.00013634628],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010504279,0.00026106654,0.00039930118,0.0006106299,0.00012624396,0.00046679183,0.00090958615,0.00019586107,0.0000035963417],"category_scores_gemma":[0.00020631726,0.0002717418,0.00010264826,0.00044626155,0.00016675208,0.0022150357,0.00024464822,0.0006228857,6.3889345e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013589319,0.0009191664,0.027494252,0.0005477951,0.0013039929,0.00015415245,0.008041812,0.25621992,0.11667865,0.09015052,0.00008450885,0.49704632],"study_design_scores_gemma":[0.00033946332,0.00008998147,0.055728246,0.0005811718,0.000058223875,0.00018921809,0.00008115783,0.93710285,0.0050777025,0.00044586245,0.00011156414,0.00019453983],"about_ca_topic_score_codex":0.000021302501,"about_ca_topic_score_gemma":0.00000858589,"teacher_disagreement_score":0.78040004,"about_ca_system_score_codex":0.00013664506,"about_ca_system_score_gemma":0.000095832285,"threshold_uncertainty_score":0.9999735},"labels":[],"label_agreement":null},{"id":"W7130377976","doi":"10.1051/e3sconf/202130901235","title":"Retraction Notice: Detecting anomalous road traffic conditions using VGG19 CNN Model","year":2021,"lang":"","type":"article","venue":"E3S Web of Conferences","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sciencetech (Canada)","funders":"","keywords":"Road traffic; Zero (linguistics)","score_opus":0.06726750627828831,"score_gpt":0.31932242512978565,"score_spread":0.25205491885149733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7130377976","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39894456,0.00071444124,0.58903843,0.0007339675,0.0016761981,0.00040662102,0.00018137072,0.0003810446,0.007923381],"genre_scores_gemma":[0.9397349,0.0002813366,0.059270628,0.00009736592,0.00016168591,0.00002063422,0.000057992802,0.00002443942,0.0003510465],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99577886,0.0003846959,0.0012679473,0.0011057315,0.00085511984,0.0006076321],"domain_scores_gemma":[0.9955622,0.0002903006,0.0012007222,0.0013274024,0.0014336372,0.00018576089],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00078870385,0.00042924643,0.00065710273,0.000398076,0.0005853532,0.0006350761,0.0011779887,0.0005219312,0.0003600737],"category_scores_gemma":[0.00057610776,0.0005021769,0.00021350037,0.0013163899,0.00044125438,0.001865991,0.00031833616,0.00080287136,0.000032671465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007712211,0.0014079488,0.0022417728,0.00063380913,0.00037130766,0.00011902846,0.003034079,0.046292737,0.46584487,0.113342024,0.0013440134,0.3652913],"study_design_scores_gemma":[0.0003226586,0.00011786037,0.0018371302,0.0003674096,0.000091272486,0.00007344854,0.000547113,0.8982807,0.095575,0.0017430314,0.00056099804,0.00048339798],"about_ca_topic_score_codex":0.00008140139,"about_ca_topic_score_gemma":0.00007669552,"teacher_disagreement_score":0.85198796,"about_ca_system_score_codex":0.00016868755,"about_ca_system_score_gemma":0.007210478,"threshold_uncertainty_score":0.999743},"labels":[],"label_agreement":null},{"id":"W7130687091","doi":"10.1109/isriti68345.2025.11393154","title":"Fake Job Detection using Bi-GRU Algorithms with Combination Random Over Sampler and Weighted Random Sampler","year":2025,"lang":"","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Random forest; Oversampling; Embedding; Precision and recall; Recall; Process (computing); Sampling (signal processing)","score_opus":0.020988863648432145,"score_gpt":0.2762294271159634,"score_spread":0.2552405634675312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7130687091","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03458432,0.0003052635,0.9597769,0.000759016,0.00083904,0.0018683583,0.000050534247,0.00062812486,0.0011884781],"genre_scores_gemma":[0.78841037,0.00035842758,0.20903073,0.00079994503,0.00009106975,0.0001396039,0.000049129732,0.000044743414,0.0010760074],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954545,0.00052146625,0.0010509217,0.0014987158,0.0007798342,0.00069455546],"domain_scores_gemma":[0.99647576,0.0006967161,0.0005202305,0.0013821875,0.00073782634,0.00018727148],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012416478,0.0006395167,0.0008011684,0.0009501505,0.0008628464,0.0012159607,0.00079022284,0.00038544735,0.00020104073],"category_scores_gemma":[0.00016595829,0.00055064174,0.00012716625,0.0020933582,0.0004280737,0.00223498,0.0004839812,0.00050116144,0.000014567413],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003079233,0.000760733,0.009139152,0.00035545157,0.0006854378,0.000015770189,0.001065786,0.000078071644,0.038170297,0.05878194,0.002061597,0.8858065],"study_design_scores_gemma":[0.024068777,0.00031334543,0.035941377,0.0003207924,0.00021360493,0.000048842634,0.00006954257,0.8661664,0.05651398,0.0075960252,0.007837926,0.00090938626],"about_ca_topic_score_codex":0.0009991367,"about_ca_topic_score_gemma":0.00023700176,"teacher_disagreement_score":0.8848972,"about_ca_system_score_codex":0.00036629717,"about_ca_system_score_gemma":0.00032734344,"threshold_uncertainty_score":0.9998209},"labels":[],"label_agreement":null},{"id":"W7130733990","doi":"10.1109/giest66547.2025.11387109","title":"Advancements and Challenges in Fraud Detection and Fairness-Aware Machine Learning: A Comprehensive Review","year":2025,"lang":"","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Adversarial system; Transparency (behavior); Scalability; Order (exchange); Key (lock); Big data; Scheme (mathematics); Class (philosophy)","score_opus":0.06285505722368981,"score_gpt":0.3111418504213519,"score_spread":0.2482867931976621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7130733990","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041837015,0.53291017,0.45287773,0.010994258,0.00020482461,0.0011533559,0.000008779788,0.00025174645,0.0011807565],"genre_scores_gemma":[0.25806004,0.73647577,0.00407462,0.00092129415,0.000009074552,0.00010751119,0.000008394767,0.0000093486515,0.0003339648],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974774,0.00034406394,0.0005951517,0.0010295503,0.00023179289,0.0003220098],"domain_scores_gemma":[0.99863714,0.00017297073,0.0002396908,0.0006562786,0.00020996218,0.00008394135],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004296157,0.0003220551,0.000523232,0.00034398248,0.00019304834,0.00013186639,0.000415613,0.00013844039,0.000026231754],"category_scores_gemma":[0.00014987767,0.00032296064,0.000032666125,0.00073571823,0.00015681935,0.0007962323,0.00079754787,0.0004574467,0.000007494712],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014074752,0.000069740454,0.0013028635,0.004425041,0.000019303283,0.0000047950616,0.00015953835,0.000001837108,0.0003986848,0.006208579,0.00007047707,0.9873251],"study_design_scores_gemma":[0.002416025,0.0007565194,0.075228125,0.01623275,0.00009525675,0.000060441864,0.00062267913,0.22361661,0.005985678,0.00651172,0.66719854,0.0012756232],"about_ca_topic_score_codex":0.000064377884,"about_ca_topic_score_gemma":0.00012571963,"teacher_disagreement_score":0.9860494,"about_ca_system_score_codex":0.00009291847,"about_ca_system_score_gemma":0.0000538207,"threshold_uncertainty_score":0.9999222},"labels":[],"label_agreement":null},{"id":"W7132447067","doi":"","title":"Performance estimation bias in class imbalance with minority subconcepts","year":2023,"lang":"en","type":"article","venue":"NPARC","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Weighting; Class (philosophy); Variety (cybernetics); Estimation; Variance (accounting); Ensemble learning","score_opus":0.037735364124937935,"score_gpt":0.27528741154097464,"score_spread":0.2375520474160367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132447067","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7653902,0.000008446401,0.20423326,0.0025997497,0.00015949988,0.00040947273,0.000015873457,0.0018929137,0.025290558],"genre_scores_gemma":[0.9240672,0.000027679233,0.0753452,0.00011402937,0.000018426965,0.000084618674,0.000036232363,0.0000065565787,0.00030006844],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880844,0.000048859016,0.00020163064,0.00035909362,0.00029662478,0.00028536347],"domain_scores_gemma":[0.9990386,0.00007366958,0.000094607145,0.00068393175,0.00006220243,0.000047034395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039168942,0.00011471505,0.00013062105,0.00018780863,0.00006679603,0.000076116696,0.00071640464,0.00005527786,0.000010428532],"category_scores_gemma":[0.000060285707,0.00010248211,0.000015698104,0.0012881923,0.00006582527,0.00083302334,0.00012340194,0.00014620363,0.00016909896],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053027103,0.00017890932,0.4736104,0.00019645152,0.000014859009,0.000068711845,0.0012594959,0.0016171804,0.03445612,0.1386626,0.029157352,0.32072487],"study_design_scores_gemma":[0.0002354233,0.000049382066,0.36789915,0.00003963963,0.0000010717459,0.0000070962114,0.00001008414,0.6169631,0.01100075,0.0022503966,0.0013827487,0.0001611387],"about_ca_topic_score_codex":0.000013363768,"about_ca_topic_score_gemma":0.0000142163135,"teacher_disagreement_score":0.61534595,"about_ca_system_score_codex":0.000080218575,"about_ca_system_score_gemma":0.00007112236,"threshold_uncertainty_score":0.41790992},"labels":[],"label_agreement":null},{"id":"W7132957422","doi":"","title":"Advanced Machine Learning Techniques for Survival Analysis in Medical Data","year":2025,"lang":"","type":"dissertation","venue":"TSpace","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Toronto","keywords":"Survival analysis; Proportional hazards model; Random forest; Survival rate; Overall survival; Binary classification; Bone marrow transplant; Ensemble learning","score_opus":0.04968440118388437,"score_gpt":0.4154718640665798,"score_spread":0.3657874628826955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132957422","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000407054,0.0010194875,0.98893386,0.002771472,0.00062588276,0.0016669135,0.0003729457,0.0009064484,0.0032959366],"genre_scores_gemma":[0.092643544,0.008765147,0.7500687,0.00056665635,0.00031691144,0.0018012427,0.10044349,0.00017403958,0.045220237],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99293387,0.00061411934,0.001452068,0.002726394,0.0014409936,0.0008325317],"domain_scores_gemma":[0.9923893,0.0013432513,0.0010660386,0.004395541,0.0005711805,0.000234657],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.004152428,0.0007492006,0.001545277,0.002213941,0.0003377823,0.00035785855,0.007994242,0.0009847246,0.00021629815],"category_scores_gemma":[0.0047596847,0.0008339589,0.0002982291,0.0057877554,0.00010582891,0.0009676273,0.0016062682,0.0016400816,0.000010903695],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005247242,0.0007081283,0.0038569402,0.0013079838,0.0011944048,0.00005336625,0.0038581477,0.00019499459,0.0025862819,0.025412817,0.0017730215,0.9585292],"study_design_scores_gemma":[0.00085259107,0.00021655136,0.0025892095,0.0010162077,0.0006915449,0.0000024513731,0.0011092739,0.88179183,0.015733667,0.000641408,0.094075345,0.0012799101],"about_ca_topic_score_codex":0.0011675351,"about_ca_topic_score_gemma":0.0067938217,"teacher_disagreement_score":0.9572493,"about_ca_system_score_codex":0.0002949574,"about_ca_system_score_gemma":0.0014397005,"threshold_uncertainty_score":0.9994111},"labels":[],"label_agreement":null},{"id":"W7132986242","doi":"","title":"Spatio-temporal and class-imbalanced data analytics in healthcare","year":2018,"lang":"","type":"dissertation","venue":"TSpace","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Overfitting; Analytics; Anomaly detection; Class (philosophy); Quality assurance; Supervised learning; Sample (material); Data analysis","score_opus":0.08361173669759331,"score_gpt":0.3928212918490413,"score_spread":0.309209555151448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132986242","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2766071,0.009201059,0.60949457,0.06876059,0.009035483,0.010491831,0.0030529327,0.0029841438,0.010372312],"genre_scores_gemma":[0.84490824,0.0025347476,0.12520033,0.0007533375,0.00037510446,0.000094998686,0.02090902,0.000111951274,0.005112284],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99385554,0.00037283025,0.0012776458,0.002663396,0.0009198703,0.00091070036],"domain_scores_gemma":[0.9918057,0.00017809964,0.0013147491,0.005719088,0.0006345298,0.00034786487],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014339775,0.00077555474,0.0010004321,0.00073246367,0.00030105675,0.0006540977,0.004319831,0.0008116575,0.00006441608],"category_scores_gemma":[0.00047321082,0.0008884523,0.00006374311,0.0017391002,0.0003128568,0.0014943469,0.0013355092,0.0010575956,0.000111336805],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015106804,0.0018213806,0.280136,0.007407572,0.00047973226,0.00037179873,0.065394826,0.0000317957,0.0026490376,0.110691756,0.18788172,0.34162372],"study_design_scores_gemma":[0.0022663532,0.0009950793,0.16000019,0.002495466,0.00013778027,0.00005069695,0.0042685433,0.66954505,0.0054007834,0.005655666,0.14574702,0.0034373673],"about_ca_topic_score_codex":0.0032095788,"about_ca_topic_score_gemma":0.01176933,"teacher_disagreement_score":0.6695132,"about_ca_system_score_codex":0.00034916776,"about_ca_system_score_gemma":0.001151942,"threshold_uncertainty_score":0.9993566},"labels":[],"label_agreement":null},{"id":"W7138983369","doi":"10.1109/globecom59602.2025.11432172","title":"AE-Multi-WGAN: A Robust Multi-Attack Detection IDS for Imbalanced Datasets","year":2025,"lang":"","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Concordia University","funders":"","keywords":"Pattern recognition (psychology); Noise (video); Feature (linguistics); Key (lock)","score_opus":0.07078819923612553,"score_gpt":0.3497726117281492,"score_spread":0.27898441249202366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7138983369","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018296267,0.00025210998,0.9886413,0.0020166375,0.0022480683,0.002943172,0.0020013629,0.001347011,0.00036736697],"genre_scores_gemma":[0.175262,0.00028270297,0.8117079,0.002564082,0.0001516387,0.0010384592,0.0011687326,0.000059164107,0.0077653215],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99447453,0.00023907733,0.0013774692,0.0022874025,0.0004724103,0.0011491282],"domain_scores_gemma":[0.9944233,0.00036276408,0.00055441837,0.003750916,0.00065214804,0.0002564775],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011164356,0.00074494,0.0007314574,0.00066710106,0.0008174419,0.0010024445,0.0033264316,0.0005516353,0.00007488035],"category_scores_gemma":[0.0007752224,0.0007719102,0.00027731186,0.0020438188,0.00029984498,0.0022072447,0.0012191831,0.000542601,0.00017990482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003845984,0.0035564366,0.0020632057,0.001331678,0.0004191907,0.000018127366,0.00055443007,0.0010885373,0.12740529,0.020813331,0.2929332,0.549432],"study_design_scores_gemma":[0.0026461913,0.00018536576,0.005155081,0.00018034787,0.00006368441,0.000008717887,0.00005774104,0.740376,0.17047165,0.00013221327,0.08001664,0.0007063607],"about_ca_topic_score_codex":0.00011595907,"about_ca_topic_score_gemma":0.00038775188,"teacher_disagreement_score":0.73928744,"about_ca_system_score_codex":0.00050333503,"about_ca_system_score_gemma":0.00047179902,"threshold_uncertainty_score":0.9994732},"labels":[],"label_agreement":null},{"id":"W7154625270","doi":"10.66573/001c.137029","title":"Linear Classifier Models for Binary Classification","year":2025,"lang":"en","type":"article","venue":"Variance","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Weighting; Classifier (UML); Binary classification; Pattern recognition (psychology); Linear classifier; Parametric statistics; Logistic regression; Binary number; A-weighting","score_opus":0.05282643759995619,"score_gpt":0.31301332742184845,"score_spread":0.26018688982189225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7154625270","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000041925054,0.00009263163,0.98037165,0.006956239,0.00041571225,0.00046504103,0.000024957792,0.0006485996,0.010983254],"genre_scores_gemma":[0.2135929,0.00007129244,0.7775628,0.001758154,0.00008028163,0.0006067151,0.000052085346,0.0000144788855,0.0062612705],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987242,0.000045223987,0.0002918282,0.00054754276,0.00014345068,0.00024775206],"domain_scores_gemma":[0.99827254,0.00014559006,0.00012242583,0.0012095288,0.00020657765,0.00004336469],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003369455,0.00013363824,0.00014969554,0.00016917416,0.00016584583,0.000107699794,0.0011899496,0.00012102314,0.0000039670967],"category_scores_gemma":[0.000097629214,0.00013544131,0.000058079142,0.00067932863,0.000048333502,0.0009182194,0.00015266343,0.00011723552,0.00003193961],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008228545,0.000049130103,0.000024028817,0.00002363115,0.000008403279,4.231891e-7,0.000033076245,0.0001349048,0.008308519,0.94706655,0.026107468,0.01823565],"study_design_scores_gemma":[0.00021703399,0.000025050107,0.0011833404,0.000032421915,0.000004807389,8.3211506e-7,0.000006016766,0.76521605,0.0053806636,0.13010843,0.09769076,0.00013457293],"about_ca_topic_score_codex":0.000004351918,"about_ca_topic_score_gemma":9.647449e-7,"teacher_disagreement_score":0.8169581,"about_ca_system_score_codex":0.000088775356,"about_ca_system_score_gemma":0.00017474977,"threshold_uncertainty_score":0.5523137},"labels":[],"label_agreement":null},{"id":"W7163318230","doi":"10.32628/cseit26123240","title":"Advances in Artificial Intelligence for Healthcare Payment Fraud Detection: A Review of NHS Applications","year":2024,"lang":"","type":"article","venue":"International Journal of Scientific Research in Computer Science Engineering and Information Technology","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"PricewaterhouseCoopers (Canada)","funders":"","keywords":"Payment; Documentation; Health care; Procurement; Payment by Results; Profiling (computer programming); Service provider; Interoperability","score_opus":0.04461140821111238,"score_gpt":0.3928407128923311,"score_spread":0.3482293046812187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7163318230","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004067743,0.016613424,0.9677353,0.01134056,0.0030324424,0.0007730933,0.000029295328,0.000051707862,0.000017418783],"genre_scores_gemma":[0.8376157,0.041402318,0.12048755,0.00007821431,0.00018323629,0.00021358236,0.000008430794,0.000008145024,0.0000027883839],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99529535,0.00006046231,0.0019769524,0.00046573833,0.0017179963,0.0004835175],"domain_scores_gemma":[0.99500036,0.00036547356,0.00045390357,0.0004725989,0.0035872867,0.0001203452],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.011299274,0.0001646292,0.00032227905,0.009857754,0.00016494683,0.0010544739,0.0028629303,0.00013141616,0.0000036107608],"category_scores_gemma":[0.00067711365,0.00015881992,0.00007339181,0.008290972,0.0011227947,0.007841719,0.00063051155,0.000817904,0.0000060165125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008478686,0.000045331846,0.000010298018,0.0015071689,0.0000054163647,0.0000038883422,0.00030068555,0.0014028081,0.0006467258,0.15967305,0.000028609076,0.83636755],"study_design_scores_gemma":[0.000111593785,0.00037122177,0.000057095855,0.012075749,0.0000027162937,0.00015617345,0.00011441878,0.87868404,0.024191523,0.030211894,0.0538463,0.00017729329],"about_ca_topic_score_codex":0.000005652968,"about_ca_topic_score_gemma":0.0000038868416,"teacher_disagreement_score":0.8772812,"about_ca_system_score_codex":0.0006381754,"about_ca_system_score_gemma":0.0010871352,"threshold_uncertainty_score":0.99998254},"labels":[],"label_agreement":null},{"id":"W7163346791","doi":"10.32628/cseit23906220","title":"A Systematic Review of Machine Learning Advances in Financial Fraud Detection for Banking Systems","year":2022,"lang":"","type":"article","venue":"International Journal of Scientific Research in Computer Science Engineering and Information Technology","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"PricewaterhouseCoopers (Canada)","funders":"","keywords":"Interpretability; Analytics; Gradient boosting; Ensemble learning; Boosting (machine learning); Equity (law); Payment; Financial services; Software deployment","score_opus":0.01724922899369588,"score_gpt":0.3107422112244929,"score_spread":0.293492982230797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7163346791","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004303226,0.017771043,0.9717857,0.0009400818,0.0040954393,0.0010280061,0.000026845386,0.000037972575,0.000011652136],"genre_scores_gemma":[0.9735356,0.0071195182,0.01904048,0.000036725898,0.00005428474,0.00019435197,0.000007519485,0.000006556791,0.000004954067],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943724,0.00021759946,0.002148068,0.00035100483,0.0024440342,0.0004668362],"domain_scores_gemma":[0.99495095,0.00040177722,0.0013352318,0.000385649,0.0028538092,0.00007256506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022825519,0.0001544308,0.0005200596,0.010657799,0.00038851768,0.0006685941,0.0033591653,0.00007934787,0.0000032660116],"category_scores_gemma":[0.0033318724,0.00015505098,0.00006987309,0.0064313626,0.0005392228,0.0066307317,0.001237428,0.0011519815,9.181374e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000135329,0.00041719532,0.0004783504,0.13891004,0.00006640247,0.000050138508,0.0035273475,0.31287366,0.0063848333,0.17039573,0.000114350056,0.36664662],"study_design_scores_gemma":[0.00042069878,0.00043688485,0.00004887984,0.03241228,0.0000039845736,0.00026706958,0.000116876654,0.9602357,0.0020610678,0.0009531832,0.002908065,0.00013528834],"about_ca_topic_score_codex":0.000009282697,"about_ca_topic_score_gemma":0.0000012278784,"teacher_disagreement_score":0.9692324,"about_ca_system_score_codex":0.00084623636,"about_ca_system_score_gemma":0.00069673976,"threshold_uncertainty_score":0.9509843},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.07618345526224594,"score_gpt":0.28703524101380407,"score_spread":0.2108517857515581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W752888290","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.075072646,0.00047702444,0.9212421,0.00019605475,0.0006396295,0.00022089787,0.00009033801,0.000077052966,0.0019842219],"genre_scores_gemma":[0.99316084,0.00021629753,0.0064015286,0.00008771746,0.00006216612,0.00000274592,0.000048325262,0.0000030457,0.000017327937],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981136,0.00014251644,0.0010353698,0.00012352245,0.00046043476,0.00012458283],"domain_scores_gemma":[0.99660516,0.00026047855,0.00156875,0.00065647607,0.00078640966,0.00012271364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013512333,0.00012914359,0.00029956654,0.0002598105,0.000044878325,0.00023011555,0.001255998,0.00008366749,0.0000013021241],"category_scores_gemma":[0.0006941609,0.00009461749,0.000032156186,0.00022783638,0.00005922015,0.0035888553,0.00023395971,0.0002581027,0.00001696548],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00094842055,0.00050764775,0.0608161,0.000979377,0.0009387216,0.000015538813,0.056305666,0.05740239,0.01703307,0.2590288,0.062352434,0.48367184],"study_design_scores_gemma":[0.0012725258,0.001233669,0.010919538,0.0012742904,0.000034534976,0.00016927939,0.013198844,0.417071,0.04823048,0.001887337,0.5040334,0.0006750891],"about_ca_topic_score_codex":0.00009760422,"about_ca_topic_score_gemma":0.0000017168096,"teacher_disagreement_score":0.9180882,"about_ca_system_score_codex":0.00009659,"about_ca_system_score_gemma":0.00015474291,"threshold_uncertainty_score":0.38583893},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.19450877797409752,"score_gpt":0.3871194660419463,"score_spread":0.19261068806784878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W83133245","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021396086,0.000006200183,0.97063863,0.003659766,0.00029741594,0.0005790643,0.00007109621,0.00034193293,0.024191905],"genre_scores_gemma":[0.9190659,0.0000046395594,0.07944835,0.00086429337,0.00017985838,0.00020079856,0.00005654,0.000012420433,0.00016722806],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978239,0.00005808276,0.00048263915,0.00062507764,0.00065693917,0.0003533873],"domain_scores_gemma":[0.9977926,0.00044087094,0.00022915677,0.00036129123,0.0011240465,0.000052054922],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064107415,0.00019822903,0.0001764227,0.00028106323,0.00030372545,0.00040311186,0.0008458019,0.0001194509,0.000031530304],"category_scores_gemma":[0.0004026912,0.00020681725,0.000081044716,0.00045763853,0.00014343778,0.0005680525,0.000094165094,0.00020224752,0.00013968014],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021530057,0.000060012964,0.000009546999,0.000003918525,0.000004168054,0.0000015234582,0.000043530574,0.00042839,0.0060445815,0.91925627,0.0014353784,0.07269118],"study_design_scores_gemma":[0.00002502334,0.00005540259,0.0002910609,0.000037774476,0.0000022175886,0.0000032809623,0.000056678084,0.2909472,0.1518375,0.5535893,0.0029301422,0.00022444954],"about_ca_topic_score_codex":0.000014871321,"about_ca_topic_score_gemma":0.00003227656,"teacher_disagreement_score":0.9188519,"about_ca_system_score_codex":0.00024299744,"about_ca_system_score_gemma":0.00026736603,"threshold_uncertainty_score":0.8433762},"labels":[],"label_agreement":null},{"id":"W832380771","doi":"10.1163/9789401206884_004","title":"Irregular -im suffixation in Tok Pisin: exploratory methods in multivariate analysis","year":2011,"lang":"en","type":"book-chapter","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Multivariate analysis; Multivariate statistics; Mathematics; Statistics","score_opus":0.07165872366497687,"score_gpt":0.33773475194727814,"score_spread":0.26607602828230126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W832380771","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000026552275,0.000121929006,0.84788513,0.00011659678,0.00011112159,0.00032178173,0.000010659006,0.00033886716,0.15109123],"genre_scores_gemma":[0.001919958,0.00016926094,0.93216884,0.00026799212,0.000033001845,0.00011123761,0.00014358056,0.000043226526,0.0651429],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972286,0.00025152662,0.00086885126,0.0010240508,0.00033366753,0.0002932597],"domain_scores_gemma":[0.9971357,0.00016787511,0.0005095209,0.0019496685,0.00015909663,0.00007816606],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016505858,0.0003817936,0.0006798773,0.0024402454,0.000037021928,0.0000994242,0.001467348,0.0004639242,0.00028981583],"category_scores_gemma":[0.000079122816,0.00037937987,0.00017364523,0.00082400383,0.000073580326,0.00090717187,0.0004359517,0.0004427325,0.000101809805],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060635534,0.00006029985,0.000158864,0.000016363689,0.00010084071,0.000018591802,0.00069997815,0.00001894521,0.0005339313,0.9296497,0.0005037727,0.06823267],"study_design_scores_gemma":[0.0013358375,0.00019169998,0.027200539,0.0003926601,0.00036599668,0.000007170807,0.00007257874,0.099287555,0.020998979,0.68968207,0.1567233,0.0037416336],"about_ca_topic_score_codex":0.00023175169,"about_ca_topic_score_gemma":0.00036068616,"teacher_disagreement_score":0.23996764,"about_ca_system_score_codex":0.00032726233,"about_ca_system_score_gemma":0.0001288016,"threshold_uncertainty_score":0.99986583},"labels":[],"label_agreement":null},{"id":"W935030780","doi":"10.1017/cbo9780511921803.005","title":"Performance Measures II","year":2011,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Confusion matrix; Artificial intelligence; Classifier (UML); Probabilistic logic; Machine learning; Computer science; Class (philosophy); Confusion; Receiver operating characteristic; Popularity; Graphical model; Pattern recognition (psychology); Natural language processing; Psychology","score_opus":0.04281761778990008,"score_gpt":0.19625850013900895,"score_spread":0.15344088234910885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W935030780","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009566744,0.000050157916,0.11033817,0.000016262156,0.00019460893,0.00027692644,0.00007980999,0.00079775095,0.88823676],"genre_scores_gemma":[0.002259855,0.00027701678,0.004810886,0.00008079727,0.000057137793,0.0000016797255,0.00003099676,0.000031552412,0.99245006],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984099,0.000028585868,0.0002051205,0.0007019376,0.00035944258,0.0002949728],"domain_scores_gemma":[0.99756426,0.000022763415,0.00029076985,0.0017220451,0.0002548389,0.00014531137],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014741668,0.00036079658,0.0003208932,0.00024988136,0.00034370416,0.000058084843,0.002643305,0.00034643305,0.000003759462],"category_scores_gemma":[0.000007068336,0.00042288745,0.00013620955,0.00001407257,0.00021542242,0.00043082028,0.0014900751,0.00044985273,0.000045621662],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011904415,0.0000073194838,0.0000012573475,0.00002742214,0.000035400317,0.000033491506,0.000047153862,1.3290766e-7,0.00007158742,0.9306047,0.04604872,0.023110911],"study_design_scores_gemma":[0.00016025871,0.00007603713,0.00003079063,0.000103724946,0.000036257614,0.000016400181,0.0000012720953,0.00022812023,0.00426009,0.000047966743,0.9945706,0.0004684653],"about_ca_topic_score_codex":0.000034079236,"about_ca_topic_score_gemma":4.8690976e-7,"teacher_disagreement_score":0.9485219,"about_ca_system_score_codex":0.00018728148,"about_ca_system_score_gemma":0.00014666002,"threshold_uncertainty_score":0.9998223},"labels":[],"label_agreement":null}]}