{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":40,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":40,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"47001aa2d831","filters":{"venue":"Advances in Data Analysis and Classification"}},"results":[{"id":"W1997354990","doi":"10.1007/s11634-013-0139-1","title":"Estimating common principal components in high dimensions","year":2013,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"","keywords":"Convergence (economics); Principal component analysis; Majorization; Orthonormal basis; Mathematical optimization; Simple (philosophy); Cluster analysis; Minification; Computer science; Matrix (chemical analysis); Function (biology); Mathematics; Algorithm; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.05393879753402075,"gpt":0.3370129092875392,"spread":0.2830741117535184,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004746126,0.0000917754,0.0002291414,0.0002465666,0.00006336966,0.0001004674,0.0006831347,0.00003935249,0.00000643834],"category_scores_gemma":[0.00004771218,0.00007898128,0.00001963824,0.0009824861,0.00003705335,0.001734228,0.0003419048,0.0001120473,0.00000641301],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002299222,"about_ca_system_score_gemma":0.000008657978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000331958,"about_ca_topic_score_gemma":0.0007587787,"domain_scores_codex":[0.9987354,0.0001455837,0.0003292958,0.0004973369,0.0001381193,0.0001542824],"domain_scores_gemma":[0.998633,0.0001271101,0.0001316905,0.001032931,0.00002597078,0.00004931675],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000257975,0.0001533634,0.1240707,0.00001737058,0.00003456285,0.000003051888,0.000204626,0.001100913,0.00162054,0.08750453,0.00003417238,0.7852536],"study_design_scores_gemma":[0.00009691018,0.00000404466,0.243932,0.00001278502,0.00002011723,5.048125e-7,0.00000888804,0.7358992,0.00001389995,0.01975477,0.0001842144,0.00007259391],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07764351,0.0004010169,0.9210874,0.0004978869,0.00005549312,0.0001080124,0.00000646554,0.00001827598,0.0001819302],"genre_scores_gemma":[0.5478708,0.0001542082,0.451796,0.0000431527,0.000007292728,0.00001492285,0.0001034154,0.000001850544,0.000008414064],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.785181,"threshold_uncertainty_score":0.3220763,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2065708566","doi":"10.1007/s11634-013-0155-1","title":"A LASSO-penalized BIC for mixture model selection","year":2013,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"","keywords":"Lasso (programming language); Model selection; Selection (genetic algorithm); Mathematics; Computer science; Artificial intelligence; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.04016452122136844,"gpt":0.3414572268898052,"spread":0.3012927056684368,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004847892,0.0001108546,0.0002245555,0.0002449915,0.00009068121,0.0001653214,0.0006492445,0.00006773708,0.000006858487],"category_scores_gemma":[0.00007043732,0.00009174125,0.00005071311,0.001086456,0.00002635374,0.002216353,0.0001133047,0.00007946464,0.000003091581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002299475,"about_ca_system_score_gemma":0.00002515913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002667621,"about_ca_topic_score_gemma":0.0002891266,"domain_scores_codex":[0.9988203,0.00007845616,0.0002639868,0.0005404883,0.0001249416,0.0001718299],"domain_scores_gemma":[0.9988116,0.0001007464,0.0001453503,0.0007928432,0.00009669481,0.00005277402],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001054161,0.0000832943,0.002885462,0.00003118517,0.0001120273,1.260987e-7,0.0001732927,0.001033944,0.005025663,0.1659119,0.0008085767,0.823924],"study_design_scores_gemma":[0.0001841632,0.00001022297,0.002994488,0.00000501982,0.00008944958,4.158372e-7,0.00001148189,0.9157028,0.0001237894,0.07753825,0.003229901,0.0001100553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007921616,0.0008806968,0.9967263,0.0009735966,0.00003280981,0.0002458682,0.0000205581,0.0000355245,0.0002924833],"genre_scores_gemma":[0.2053817,0.001025575,0.79286,0.0001544141,0.00002471284,0.0001299185,0.0001965175,0.000005197428,0.0002220124],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9146688,"threshold_uncertainty_score":0.37411,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2102723201","doi":"10.1007/s11634-013-0124-8","title":"Clustering and classification via cluster-weighted factor analyzers","year":2013,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"","keywords":"Cluster analysis; Mixture model; Expectation–maximization algorithm; Pattern recognition (psychology); Covariance matrix; Covariance; Latent variable; Ranking (information retrieval); Fuzzy clustering","retraction":null,"screen_n_in":null,"score":{"opus":0.03672495443431135,"gpt":0.317044713978554,"spread":0.2803197595442427,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004462852,0.0001754733,0.0003039362,0.0004105168,0.0001209957,0.0002975184,0.0007499901,0.00009093597,0.00002096027],"category_scores_gemma":[0.00004381423,0.0001504944,0.0000399446,0.001275117,0.00008412595,0.003279764,0.0003473224,0.0001351663,0.000009083876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003582383,"about_ca_system_score_gemma":0.00001506445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006510895,"about_ca_topic_score_gemma":0.0004249921,"domain_scores_codex":[0.9980546,0.0001871509,0.0004336303,0.000901372,0.0002002559,0.0002230024],"domain_scores_gemma":[0.9980693,0.000141736,0.000239924,0.001360574,0.00007602431,0.0001124812],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003864309,0.00003796325,0.01336154,0.00002233895,0.00007649823,4.911369e-7,0.0001856939,0.00001813141,0.003819419,0.005668062,0.00006002173,0.976746],"study_design_scores_gemma":[0.0001511853,0.00001068125,0.1710799,0.00000904,0.00007561298,0.000001881811,0.00004069572,0.8215444,0.00005147794,0.005619322,0.001252549,0.0001632172],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00826274,0.001282379,0.9885162,0.001192255,0.00006116848,0.0002030056,0.00001607092,0.00004590951,0.0004202602],"genre_scores_gemma":[0.6973604,0.002436867,0.2997976,0.0001218191,0.0000248143,0.000033326,0.000162091,0.000006581074,0.000056537],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9765828,"threshold_uncertainty_score":0.6136984,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1964231120","doi":"10.1007/s11634-014-0165-7","title":"Variational Bayes approximations for clustering via mixtures of normal inverse Gaussian distributions","year":2014,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"","keywords":"Bayes' theorem; Gaussian; Univariate; Applied mathematics; Cluster analysis; Mixture model; Inverse Gaussian distribution; Multivariate normal distribution; Mathematics; Inverse; Inverse problem; Multivariate statistics; Mathematical optimization; Computer science; Statistics; Distribution (mathematics); Mathematical analysis; Bayesian probability; Chemistry; Computational chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.02808600709019208,"gpt":0.3141116705601102,"spread":0.2860256634699181,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006883994,0.00008289042,0.0001878243,0.0002025612,0.0001099301,0.00005310127,0.0005208682,0.0000455955,0.000004332203],"category_scores_gemma":[0.0001468311,0.000074637,0.00004708285,0.0007339932,0.00005162924,0.001175064,0.0001438642,0.00005242339,4.163767e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001469446,"about_ca_system_score_gemma":0.00001873118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001477736,"about_ca_topic_score_gemma":0.0004280096,"domain_scores_codex":[0.998966,0.00009649774,0.0003199638,0.0003793857,0.0001207978,0.000117393],"domain_scores_gemma":[0.9987557,0.0002065525,0.0002029209,0.0007221245,0.0000718103,0.00004092815],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008323299,0.00008917396,0.003059453,0.00005973814,0.00008638834,7.126057e-8,0.0001533073,0.001032707,0.001559238,0.6952657,0.00007375784,0.2986121],"study_design_scores_gemma":[0.0001471837,0.00001170595,0.01447664,0.000007200678,0.00009127513,5.750022e-7,0.0000101561,0.9342356,0.000139218,0.04818898,0.002608542,0.00008293272],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001203281,0.0001536222,0.9985153,0.0005635862,0.00004734125,0.0001096411,0.0001783898,0.00001461808,0.0002971422],"genre_scores_gemma":[0.3436169,0.0001184101,0.6553992,0.0000271013,0.00002554697,0.00002831896,0.0007680875,0.000002249648,0.00001423537],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9332029,"threshold_uncertainty_score":0.3043608,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1972256887","doi":"10.1007/s11634-015-0204-z","title":"A mixture of generalized hyperbolic factor analyzers","year":2015,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Bayesian information criterion; Mixture model; Hyperbolic function; Cluster analysis; Gaussian; Generalized inverse Gaussian distribution; Maximization; Expectation–maximization algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.07739344212886445,"gpt":0.3564501671026479,"spread":0.2790567249737834,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004840535,0.00009474266,0.0002884489,0.0002787963,0.0000230697,0.00004447513,0.0008043842,0.00005152818,0.000004355059],"category_scores_gemma":[0.00008990442,0.00007630671,0.00004348171,0.00148259,0.0000493172,0.00107263,0.0001764806,0.00006699639,0.000001019195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001664614,"about_ca_system_score_gemma":0.00003622146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004005454,"about_ca_topic_score_gemma":0.0002335917,"domain_scores_codex":[0.9987878,0.0001460239,0.0002904387,0.0004636405,0.0001938655,0.0001182173],"domain_scores_gemma":[0.998415,0.00004929342,0.0001791559,0.001200237,0.00007483184,0.00008146173],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002004541,0.0001193326,0.03336242,0.00002506368,0.0002266436,0.000002564549,0.0007550401,0.0001962555,0.004151114,0.1305437,0.0002986062,0.8302992],"study_design_scores_gemma":[0.0006195405,0.00003318697,0.04873543,0.00001420318,0.0002868312,0.000002379482,0.00009954814,0.8969435,0.0007919768,0.03194673,0.0202366,0.0002900598],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008989325,0.003960836,0.9860973,0.0003752435,0.00004653846,0.0000563529,0.00003531373,0.00001556259,0.0004234626],"genre_scores_gemma":[0.6015477,0.001774765,0.3964367,0.00005811729,0.00001840162,0.000005184749,0.0001159089,0.000003085159,0.00004022803],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8967472,"threshold_uncertainty_score":0.3111697,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2061107170","doi":"10.1007/s11634-014-0168-4","title":"Feature selection for fault level diagnosis of planetary gearboxes","year":2014,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Gear and Bearing Dynamics Analysis","field":"Engineering","cited_by":33,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Feature selection; Pattern recognition (psychology); Feature (linguistics); Fault (geology); Computer science; Artificial intelligence; Kernel (algebra); Minimum redundancy feature selection; Similarity (geometry); Selection (genetic algorithm); Feature vector; Feature extraction; Ranking (information retrieval); Algorithm; Data mining; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02554607314779903,"gpt":0.2725611842871389,"spread":0.2470151111393399,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002030135,0.00007515824,0.0001975079,0.0002255238,0.00003027321,0.00001836212,0.0001508555,0.00005177122,0.00000527837],"category_scores_gemma":[0.00004844538,0.00007022228,0.00004149941,0.0005737011,0.0000196379,0.0002339068,0.00001904764,0.00005769128,6.937461e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001215206,"about_ca_system_score_gemma":0.000002583718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004384577,"about_ca_topic_score_gemma":0.003441273,"domain_scores_codex":[0.9994493,0.00001614681,0.0001533875,0.0002128725,0.0000805161,0.00008776726],"domain_scores_gemma":[0.999496,0.00009336637,0.00005626143,0.0003032996,0.00003089846,0.00002018188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001306036,0.00004857813,0.6240671,0.0001791093,0.0005548287,6.596313e-8,0.00004683783,0.1759266,0.002002685,0.001354235,0.0005465071,0.1952604],"study_design_scores_gemma":[0.00008143098,0.000008986393,0.1459514,0.000007206158,0.0003782716,1.336536e-7,0.00002677263,0.8435184,0.0001552588,0.0001983441,0.009602683,0.00007118942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2606307,0.002924923,0.7346135,0.000381171,0.00008795833,0.0002027349,0.0006793802,0.00006770562,0.0004119503],"genre_scores_gemma":[0.9874693,0.003319339,0.007210471,0.000005857026,0.0000256954,0.00002034137,0.00190905,0.000006651907,0.000033317],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.727403,"threshold_uncertainty_score":0.2863582,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2027846664","doi":"10.1007/s11634-012-0110-6","title":"Time series classification by class-specific Mahalanobis distance measures","year":2012,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Mahalanobis distance; Covariance matrix; Dynamic time warping; Covariance; Pattern recognition (psychology); Series (stratigraphy); k-nearest neighbors algorithm; Margin (machine learning)","retraction":null,"screen_n_in":null,"score":{"opus":0.03447962751202253,"gpt":0.2752292003416775,"spread":0.240749572829655,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000939471,0.0002256162,0.000399092,0.0002959714,0.0002287182,0.0002795138,0.001165141,0.0000881819,0.00004847581],"category_scores_gemma":[0.00007087881,0.0002029135,0.0000812561,0.00228788,0.000175353,0.00638432,0.0002829956,0.0001480238,0.00004874728],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007514044,"about_ca_system_score_gemma":0.00001564254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000134268,"about_ca_topic_score_gemma":0.0001622804,"domain_scores_codex":[0.9976102,0.0001508901,0.0005901475,0.0008384897,0.0004054001,0.000404862],"domain_scores_gemma":[0.997465,0.0001002508,0.000392254,0.001817665,0.00009151844,0.0001333767],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005241734,0.0004546623,0.1644502,0.00004472736,0.0004753761,0.000001826333,0.0008330108,0.0002348966,0.01392618,0.138846,0.007524646,0.6731561],"study_design_scores_gemma":[0.000186654,0.00002203009,0.09687722,0.0000177123,0.000227395,0.000004112514,0.0004736885,0.2674829,0.0002352529,0.0005322387,0.6334884,0.000452416],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004716881,0.0230635,0.9666489,0.001610948,0.0001359104,0.0001758292,0.0001856986,0.0001246244,0.003337721],"genre_scores_gemma":[0.9734232,0.01005992,0.01410349,0.00005366936,0.00009073432,0.00003199872,0.001566519,0.00001364916,0.0006568089],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9687063,"threshold_uncertainty_score":0.8274572,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1994281788","doi":"10.1007/s11634-014-0182-6","title":"Mixture model averaging for clustering","year":2014,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University; University of Guelph","funders":"","keywords":"Cluster analysis; Mixture model; Model selection; Bayesian information criterion; Pattern recognition (psychology); Bayesian probability; Rand index; Closeness; Single-linkage clustering","retraction":null,"screen_n_in":null,"score":{"opus":0.04141965676927712,"gpt":0.3381464725389695,"spread":0.2967268157696924,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007647173,0.0000854039,0.000179871,0.0001628572,0.0000796238,0.0001020406,0.0006801596,0.00004012916,6.587238e-7],"category_scores_gemma":[0.00006805253,0.0000749035,0.00003513038,0.0004782889,0.00001958452,0.001194792,0.0001886782,0.00006069493,4.501002e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000123007,"about_ca_system_score_gemma":0.000009365694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003245882,"about_ca_topic_score_gemma":0.0001614359,"domain_scores_codex":[0.998971,0.00005750171,0.0002016387,0.0005396885,0.00009337755,0.0001367351],"domain_scores_gemma":[0.9987268,0.0001087706,0.00009756102,0.000996219,0.00003241819,0.00003819961],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003821232,0.00001673968,0.0006448089,0.0000226495,0.00002759736,1.000794e-7,0.0001237534,0.005377385,0.0005454545,0.1520607,0.00005609185,0.8411208],"study_design_scores_gemma":[0.00011274,0.000005119533,0.000832351,0.000007018743,0.00005676861,3.861912e-7,0.000006225768,0.9456943,0.00003809789,0.04783491,0.005318978,0.0000931247],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001354794,0.0005505018,0.9979959,0.0006220736,0.00004287848,0.00007861712,0.00001291717,0.00002400188,0.0005376022],"genre_scores_gemma":[0.3022035,0.0004561751,0.6970089,0.0001426955,0.00002638344,0.00001601961,0.00009130057,0.000003352713,0.00005169584],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9403169,"threshold_uncertainty_score":0.3054476,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1973247608","doi":"10.1007/s11634-013-0137-3","title":"Dimension reduction for model-based clustering via mixtures of multivariate $$t$$ t -distributions","year":2013,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"","keywords":"Dimensionality reduction; Cluster analysis; Subspace topology; Dimension (graph theory); Mixture model; Mathematics; Gaussian; Reduction (mathematics); Clustering high-dimensional data; Eigenvalues and eigenvectors; Data set; Curse of dimensionality; Algorithm; Multivariate normal distribution; Pattern recognition (psychology); Computer science; Multivariate statistics; Artificial intelligence; Statistics; Combinatorics; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.03849028777574721,"gpt":0.3380154403337114,"spread":0.2995251525579642,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003929901,0.00008847016,0.0001942685,0.0001848725,0.00007938409,0.00004640202,0.0003936354,0.00005172557,0.000001749096],"category_scores_gemma":[0.00005340814,0.00007643862,0.00004671946,0.0006027631,0.00004324163,0.001184113,0.0001051145,0.00005166911,3.853091e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001983124,"about_ca_system_score_gemma":0.00001819195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004708462,"about_ca_topic_score_gemma":0.00005639262,"domain_scores_codex":[0.9989614,0.0000682758,0.000304642,0.0004469754,0.00009927084,0.0001194442],"domain_scores_gemma":[0.9987509,0.00007901612,0.0001940014,0.0008256358,0.0001131823,0.0000372279],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001957239,0.0001616474,0.0003423397,0.00007159894,0.00008551114,1.103823e-7,0.0001344162,0.0278657,0.1402936,0.05765454,0.00008578561,0.7732852],"study_design_scores_gemma":[0.0001680131,0.00001232408,0.001926079,0.00001197958,0.00008527059,3.325615e-7,0.000006544386,0.9703156,0.002664074,0.02458839,0.000137631,0.00008374889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001310196,0.0004519506,0.9974397,0.0004451676,0.00004855571,0.0002128719,0.00004230647,0.0000180161,0.00003124081],"genre_scores_gemma":[0.5021719,0.0001030659,0.4974097,0.00001075786,0.000007613687,0.00003531874,0.0002510174,0.000002117553,0.000008512945],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9424499,"threshold_uncertainty_score":0.3117076,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2112120651","doi":"10.1007/s11634-009-0056-5","title":"Regularized fuzzy clusterwise ridge regression","year":2009,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Fuzzy Systems and Optimization","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Multicollinearity; Ordinary least squares; Fuzzy logic; Statistics; Regression analysis; Mathematics; Linear regression; Regression; Cluster analysis; Regression diagnostic; Local regression; Fuzzy clustering; Data mining; Polynomial regression; Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.06134931625472312,"gpt":0.3685902464458001,"spread":0.307240930191077,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005760866,0.00012429,0.0003094891,0.0002564532,0.00008558152,0.0000599019,0.0002840914,0.00008066665,0.00001191436],"category_scores_gemma":[0.0002368202,0.00009747803,0.00004406983,0.0009091358,0.00003160975,0.0009056988,0.00005739925,0.00008212253,0.000002597768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003259009,"about_ca_system_score_gemma":0.00001113816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008973795,"about_ca_topic_score_gemma":0.0002395462,"domain_scores_codex":[0.9986541,0.0001041343,0.0004395121,0.0004592427,0.000208083,0.0001349306],"domain_scores_gemma":[0.9984447,0.0001020611,0.00028176,0.001070122,0.00005468338,0.00004663266],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003716788,0.001144791,0.04437892,0.000350941,0.0004640506,0.00001663989,0.0011376,0.001254749,0.007826945,0.3221183,0.006547023,0.6143884],"study_design_scores_gemma":[0.001910658,0.00009151076,0.1173212,0.0002807443,0.001378611,0.000006405784,0.001145523,0.7068614,0.0002574697,0.1517945,0.01823222,0.0007197491],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.145632,0.01184527,0.8092895,0.006340838,0.0004457175,0.001646131,0.0006529646,0.0003780425,0.02376954],"genre_scores_gemma":[0.9503316,0.00329292,0.04414132,0.00007195989,0.000073032,0.00001223958,0.001694584,0.00000972043,0.0003726321],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8046997,"threshold_uncertainty_score":0.3975039,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1990989764","doi":"10.1007/s11634-012-0108-0","title":"Adaptation of interval PCA to symbolic histogram variables","year":2012,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Hôpital Saint-François d'Assise","funders":"","keywords":"Principal component analysis; Histogram; Symbolic data analysis; Mathematics; Projection (relational algebra); Representation (politics); Pattern recognition (psychology); Interval (graph theory); Artificial intelligence; Algorithm; Computer science; Statistics; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.05461420121741699,"gpt":0.3280499556074983,"spread":0.2734357543900813,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002988874,0.00006221489,0.0001437689,0.0001781851,0.0000422714,0.00003195148,0.0005648713,0.00002233276,0.000004415179],"category_scores_gemma":[0.00002780327,0.000055975,0.00002308561,0.00144881,0.00002576816,0.001240218,0.0001783754,0.00004158961,0.000003696306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001529973,"about_ca_system_score_gemma":0.000007449588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005588641,"about_ca_topic_score_gemma":0.0003210331,"domain_scores_codex":[0.9992207,0.00003917347,0.0002479226,0.0002731868,0.00009712191,0.0001219191],"domain_scores_gemma":[0.9989311,0.00006802591,0.0001266544,0.0007811362,0.00003589961,0.00005722492],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004884188,0.0001756013,0.04186864,0.00001401361,0.00005018353,7.155779e-8,0.0004474611,0.003670624,0.001557359,0.1938145,0.000196505,0.7582001],"study_design_scores_gemma":[0.00009437985,0.00002070797,0.1337816,0.00001595654,0.0001181458,8.062693e-7,0.0001962031,0.7809081,0.0001401381,0.001551769,0.08302121,0.0001510021],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01221956,0.001531147,0.985399,0.0004370886,0.00004775035,0.00008406238,0.00001579547,0.0000167002,0.0002488862],"genre_scores_gemma":[0.9506439,0.0007996162,0.04827962,0.00005279109,0.00002962136,0.00002468014,0.0001441991,0.000002263088,0.00002331215],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9384243,"threshold_uncertainty_score":0.2282594,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1875624538","doi":"10.1007/s11634-015-0219-5","title":"Factor probabilistic distance clustering (FPDC): a new clustering method","year":2015,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Università degli Studi di Napoli Federico II","keywords":"Cluster analysis; Correlation clustering; CURE data clustering algorithm; Single-linkage clustering; Probabilistic logic; Canopy clustering algorithm; Computer science; Data stream clustering; Fuzzy clustering; Determining the number of clusters in a data set; Clustering high-dimensional data; k-medians clustering; Transformation (genetics); Mathematics; Pattern recognition (psychology); Data mining; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1223525331876487,"gpt":0.4083881885969034,"spread":0.2860356554092547,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007759865,0.0001954136,0.0003560179,0.0003590242,0.00009069555,0.0002865333,0.001693646,0.00006042879,0.000005051982],"category_scores_gemma":[0.0004747242,0.0001830607,0.00004044593,0.002096097,0.0000646219,0.003023096,0.001310367,0.000200985,0.000008550034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001890646,"about_ca_system_score_gemma":0.0001024315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001056882,"about_ca_topic_score_gemma":0.002681303,"domain_scores_codex":[0.9974205,0.0001697138,0.0004622464,0.001104623,0.0004795098,0.0003633558],"domain_scores_gemma":[0.9972367,0.0002181499,0.0001983853,0.001992141,0.0001043037,0.000250365],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002878092,0.00005604065,0.003260982,0.00006133363,0.00007632573,0.000009487178,0.0006257115,0.04435191,0.000288549,0.002208906,0.00004463019,0.9489874],"study_design_scores_gemma":[0.0003160083,0.00002549439,0.006204216,0.00002629951,0.00003763982,0.000005523121,0.0001393519,0.979554,0.00002533683,0.002718244,0.01073259,0.0002152854],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002538057,0.001424383,0.9970609,0.0005715584,0.0001093912,0.0001914346,0.00003066456,0.00008627451,0.0002716128],"genre_scores_gemma":[0.2334704,0.0008756719,0.7649428,0.00004584884,0.0000817183,0.00003852721,0.0001452976,0.00001666125,0.0003831265],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9487721,"threshold_uncertainty_score":0.7464998,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2057846446","doi":"10.1007/s11634-009-0054-7","title":"Tests of ignoring and eliminating in nonsymmetric correspondence analysis","year":2009,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Sensory Analysis and Statistical Methods","field":"Agricultural and Biological Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Contingency table; Residual; Contingency; Row; Table (database); Correspondence analysis; Test (biology); Mathematics; Econometrics; Statistics; Computer science; Algorithm; Data mining; Epistemology","retraction":null,"screen_n_in":null,"score":{"opus":0.06777325830079646,"gpt":0.3671167486454298,"spread":0.2993434903446333,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009544163,0.00009316943,0.0003930593,0.0003384636,0.00005510954,0.00003616,0.0002280881,0.00004636999,0.00003176236],"category_scores_gemma":[0.0007909109,0.00004562996,0.000050512,0.007328347,0.00005949934,0.0003765249,0.00005191491,0.00008212035,3.524432e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001189242,"about_ca_system_score_gemma":0.00000235738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001504522,"about_ca_topic_score_gemma":0.005823123,"domain_scores_codex":[0.9986024,0.0001877105,0.0004332467,0.0004708535,0.0001691082,0.0001367134],"domain_scores_gemma":[0.9984523,0.001079331,0.0001990715,0.0001783912,0.00004464804,0.00004623131],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00001196064,0.00005098831,0.4110016,0.000002966577,0.00004898177,0.000001166155,0.00002129387,0.0001718761,0.009783871,0.000834007,6.206787e-7,0.5780707],"study_design_scores_gemma":[0.00004792266,0.00003439583,0.8835639,0.000008433888,0.0005180296,2.573946e-7,0.0003399538,0.1145449,0.00006952192,0.0007021641,0.00008898466,0.00008149582],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9902858,0.001946587,0.007168686,0.0002290591,0.000007338222,0.00005695716,0.00006637222,0.000006091122,0.000233129],"genre_scores_gemma":[0.9917684,0.002076281,0.005882431,0.00002600522,0.0000108097,0.000002382548,0.0002194161,2.892971e-7,0.00001398974],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5779892,"threshold_uncertainty_score":0.3521028,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2004773941","doi":"10.1007/s11634-009-0046-7","title":"Parsimonious cluster systems","year":2009,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Saint Paul University","funders":"","keywords":"Bijection; Set (abstract data type); Cluster (spacecraft); Cluster analysis; Phylogenetic tree; Computer science; Combinatorics; Tree (set theory); Mathematics; Theoretical computer science; Biology; Artificial intelligence; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.0299105014580019,"gpt":0.3081043677348245,"spread":0.2781938662768226,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000393372,0.0000788238,0.0001507039,0.0002372602,0.00005563136,0.0002898456,0.001106162,0.00002304507,0.000001737611],"category_scores_gemma":[0.00002017202,0.00006791134,0.00001900066,0.001134363,0.00002019017,0.003168951,0.0002126134,0.00004941749,0.000009874257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001373193,"about_ca_system_score_gemma":0.000004947303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001264556,"about_ca_topic_score_gemma":0.00007447587,"domain_scores_codex":[0.9989251,0.00004632189,0.0002244731,0.0005094284,0.0001634084,0.0001313073],"domain_scores_gemma":[0.9984599,0.00003321559,0.0001046079,0.001349523,0.00001969152,0.00003303177],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003515743,0.00009006538,0.008573222,0.00001122136,0.0000658046,0.000003928971,0.00005908815,0.0007322886,0.00004078369,0.09652285,0.001137386,0.8927599],"study_design_scores_gemma":[0.0001226392,0.00001260243,0.04853916,0.000006594911,0.00007061402,5.191373e-7,0.00006488545,0.897334,0.000003305903,0.001429518,0.05230968,0.0001064439],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006686269,0.002581786,0.9932692,0.001306626,0.00009259788,0.00009694206,0.00002276008,0.00004452842,0.001916954],"genre_scores_gemma":[0.9786506,0.00423986,0.01591562,0.000187436,0.00004119733,0.000007458494,0.0007379366,0.000002177241,0.0002176927],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.977982,"threshold_uncertainty_score":0.2794988,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2016714679","doi":"10.1007/s11634-010-0083-2","title":"Generalized GIPSCAL re-revisited: a fast convergent algorithm with acceleration by the minimal polynomial extrapolation","year":2011,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Analytical Chemistry and Chromatography","field":"Chemistry","cited_by":10,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Korea Institute of Energy Research","keywords":"Extrapolation; Acceleration; Diagonal; Positive definiteness; Algorithm; Representation (politics); Polynomial; Mathematics; Time complexity; Matrix (chemical analysis); Computational complexity theory; Convergence (economics); Applied mathematics; Computer science; Mathematical analysis; Geometry; Positive-definite matrix","retraction":null,"screen_n_in":null,"score":{"opus":0.03893491462284368,"gpt":0.2847833179878061,"spread":0.2458484033649624,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001781297,0.0001643598,0.0002306756,0.00007000125,0.0001350653,0.0000655137,0.0003647656,0.00009323342,0.00066832],"category_scores_gemma":[0.00001736413,0.0001145812,0.00006203881,0.0006465549,0.000174506,0.0006116126,0.00005884737,0.000140273,0.000002727591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002491518,"about_ca_system_score_gemma":0.00001601239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006520842,"about_ca_topic_score_gemma":0.0001817243,"domain_scores_codex":[0.9986714,0.00003642494,0.0003763546,0.0005282751,0.0002186042,0.0001690044],"domain_scores_gemma":[0.998893,0.00004635816,0.0002198976,0.0007256153,0.00004637962,0.00006874949],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001284032,0.001531356,0.4192798,0.0003124204,0.003214289,0.00001632199,0.001614639,0.00007798092,0.1783092,0.003234594,0.008647572,0.3824778],"study_design_scores_gemma":[0.00317704,0.00009620978,0.06317114,0.00009348606,0.004762097,0.00001802951,0.005339569,0.776467,0.06752321,0.0004579385,0.07751323,0.001381122],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6447733,0.008146718,0.3244715,0.001084502,0.00006697803,0.0003819861,0.001719971,0.0001608831,0.01919418],"genre_scores_gemma":[0.9912292,0.001306976,0.002886221,0.00005216235,0.00006111167,0.00002730212,0.004245396,0.000009454249,0.0001821232],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7763889,"threshold_uncertainty_score":0.7317635,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2888010039","doi":"10.1007/s11634-018-0333-2","title":"Subspace clustering for the finite mixture of generalized hyperbolic distributions","year":2018,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Mixture model; Mathematics; Subspace topology; Applied mathematics; Hyperbolic function; Gaussian; Finite element method; Extension (predicate logic); Mathematical analysis; Computer science; Statistics; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.05135122907555946,"gpt":0.3540267272002225,"spread":0.302675498124663,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005444879,0.00007087435,0.0001636304,0.00008790426,0.000126419,0.00005218945,0.0007424978,0.00003509346,0.000002579504],"category_scores_gemma":[0.0001237847,0.00004800989,0.00004344046,0.000901714,0.0001024083,0.000526144,0.0001762643,0.00004572712,4.034654e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008757225,"about_ca_system_score_gemma":0.00001427489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000191151,"about_ca_topic_score_gemma":0.0008111006,"domain_scores_codex":[0.9991866,0.00007005515,0.0002099877,0.0003346062,0.00008736818,0.0001114233],"domain_scores_gemma":[0.9984034,0.000275139,0.000139488,0.001076288,0.00008166929,0.00002405752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002378096,0.00006019468,0.002706868,0.00002977483,0.0001825764,2.022852e-7,0.0003976642,0.0002588177,0.00379413,0.3142064,0.0002950944,0.6780445],"study_design_scores_gemma":[0.0001444856,0.00001375234,0.009194069,0.000006781815,0.0001552974,4.765305e-7,0.00002214673,0.9572683,0.0004107802,0.009455794,0.02325712,0.00007099455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005198962,0.002235397,0.9955534,0.00131753,0.00006446737,0.0001118774,0.0001082754,0.00001007214,0.0000790425],"genre_scores_gemma":[0.5408518,0.002211993,0.456569,0.00006117453,0.00005795085,0.00002594872,0.0001780929,0.000002811772,0.00004117924],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9570095,"threshold_uncertainty_score":0.1957787,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3119925796","doi":"10.1007/s11634-020-00432-5","title":"Functional data clustering by projection into latent generalized hyperbolic subspaces","year":2021,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Linear subspace; Projection (relational algebra); Dimension (graph theory); Basis (linear algebra); Mathematics; Clustering high-dimensional data; Computer science; Applied mathematics; Pattern recognition (psychology); Algorithm; Artificial intelligence; Combinatorics; Pure mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.07372087970399593,"gpt":0.3428838780099273,"spread":0.2691629983059314,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007501735,0.0001105459,0.0002112735,0.0001505175,0.0001153899,0.0001937411,0.0007997204,0.00005244611,0.00001101275],"category_scores_gemma":[0.00006616033,0.0000996309,0.00002654624,0.001271803,0.00003501187,0.002364284,0.0007471067,0.00009473329,0.000002247399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002848245,"about_ca_system_score_gemma":0.00004313829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008318118,"about_ca_topic_score_gemma":0.001912823,"domain_scores_codex":[0.9982135,0.0002222464,0.0002759944,0.0009447007,0.0002047805,0.000138768],"domain_scores_gemma":[0.9977953,0.00006476693,0.0001291002,0.001899043,0.00006364409,0.0000481247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001152325,0.000113259,0.008111451,0.00003064489,0.0001616034,0.000003492536,0.0001512849,0.0001830135,0.01393115,0.01093408,0.001591576,0.9647769],"study_design_scores_gemma":[0.0001868755,0.000005489797,0.008393896,0.000008574115,0.0001220351,0.000004963103,0.00003566576,0.9652107,0.0004191233,0.003037043,0.02243132,0.000144287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00171742,0.007425544,0.9891021,0.001360375,0.000129125,0.0000621435,0.00004803874,0.00003000739,0.0001252449],"genre_scores_gemma":[0.1958144,0.01902771,0.7782718,0.0002376191,0.0001015871,0.00002770971,0.006180467,0.000009740716,0.0003289178],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9650277,"threshold_uncertainty_score":0.406283,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2074660585","doi":"10.1007/s11634-013-0126-6","title":"Functional fuzzy clusterwise regression analysis","year":2013,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Fuzzy Systems and Optimization","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University; McGill University","funders":"","keywords":"Fuzzy logic; Regression analysis; Regression; Function (biology); Computer science; Data mining; Mathematics; Mathematical optimization; Statistics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.06690308779884142,"gpt":0.3397707871951092,"spread":0.2728676993962678,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004661735,0.0001417825,0.0003774267,0.0006543092,0.0001067375,0.0001028488,0.0002533217,0.00008410232,0.0002264257],"category_scores_gemma":[0.0001919664,0.0001093425,0.00009159363,0.002579418,0.00004899906,0.001434193,0.0001124022,0.00008901286,0.00001815978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004132095,"about_ca_system_score_gemma":0.00001239815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001015695,"about_ca_topic_score_gemma":0.001412825,"domain_scores_codex":[0.9983845,0.0001138679,0.000515731,0.0005537083,0.0002811999,0.0001510368],"domain_scores_gemma":[0.9982373,0.0001982862,0.0003229607,0.001056848,0.0001218074,0.00006280642],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008028802,0.0007753285,0.7895283,0.0002950281,0.004359764,0.000003412562,0.0005515029,0.01391446,0.001139412,0.05308996,0.01176648,0.1244961],"study_design_scores_gemma":[0.0003353066,0.00001317248,0.341666,0.00002913583,0.002933372,9.138873e-7,0.0008367517,0.6340743,0.00001498711,0.01739048,0.00244652,0.0002590191],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1494713,0.00402269,0.836571,0.001863404,0.0002419004,0.0008279352,0.0002774733,0.0001412447,0.006583065],"genre_scores_gemma":[0.9816558,0.001398104,0.01382508,0.00003772974,0.00006456579,0.00006339313,0.002298474,0.00001035047,0.0006464793],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8321845,"threshold_uncertainty_score":0.4458856,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2082905687","doi":"10.1007/s11634-013-0152-4","title":"Infinite Dirichlet mixture models learning via expectation propagation","year":2013,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Dirichlet process; Mixture model; Model selection; Dirichlet distribution; Computer science; Hierarchical Dirichlet process; Inference; Automatic summarization; Cluster analysis; Bayesian inference; Minimum description length; Artificial intelligence; Latent Dirichlet allocation; Data mining; Selection (genetic algorithm); Synthetic data; Machine learning; Bayesian probability; Topic model; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03051917684331791,"gpt":0.3035554330616236,"spread":0.2730362562183057,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004712463,0.0001259354,0.0002050678,0.0003247634,0.0001116783,0.0002010199,0.0005820705,0.00006993581,0.00001011778],"category_scores_gemma":[0.0000681405,0.000108056,0.00003333724,0.001437773,0.00003613518,0.005165918,0.0001653357,0.0001575438,0.000007110518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002418815,"about_ca_system_score_gemma":0.00001495909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004025173,"about_ca_topic_score_gemma":0.0001033815,"domain_scores_codex":[0.9984538,0.0002120679,0.0003290991,0.0006346769,0.0002082836,0.0001620532],"domain_scores_gemma":[0.9986732,0.0001014133,0.0002239781,0.0008443799,0.0001023444,0.0000546691],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003493182,0.00005313152,0.00511068,0.00002007369,0.00005683649,6.623452e-7,0.0007376985,0.002407475,0.00425498,0.0422409,0.00008301425,0.945031],"study_design_scores_gemma":[0.00009620409,0.00001206876,0.01764263,0.000008270787,0.00005359066,9.184558e-7,0.0000585048,0.9432251,0.00008765981,0.0376468,0.001033181,0.0001350856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002899401,0.00094516,0.9942775,0.0007521331,0.00003784075,0.0001744854,0.000003320515,0.00005161092,0.0008585696],"genre_scores_gemma":[0.7322728,0.00120337,0.2660077,0.00006263347,0.00002343095,0.00005219591,0.0003007442,0.00000479198,0.00007230122],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.944896,"threshold_uncertainty_score":0.4406394,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2609430174","doi":"10.1007/s11634-017-0286-x","title":"Local generalized quadratic distance metrics: application to the k-nearest neighbors classifier","year":2017,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; University of Alberta","funders":"","keywords":"k-nearest neighbors algorithm; Metric (unit); Curse of dimensionality; Computer science; Mathematics; Artificial intelligence; Algorithm; Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.04108933801155237,"gpt":0.3371891365524899,"spread":0.2960997985409375,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005638076,0.000118305,0.0001962294,0.0002164998,0.000488574,0.0005128346,0.002065712,0.00005099061,0.000007024384],"category_scores_gemma":[0.0002045033,0.0000830741,0.00003880799,0.001029534,0.0001032318,0.002118194,0.0004289081,0.000102662,0.00004028153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003584899,"about_ca_system_score_gemma":0.0000203905,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001325,"about_ca_topic_score_gemma":0.004088947,"domain_scores_codex":[0.9984591,0.00009154357,0.0003101061,0.0006874597,0.0002809839,0.0001708019],"domain_scores_gemma":[0.9965304,0.0001068806,0.0002865206,0.002927093,0.00007410027,0.00007503053],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000185592,0.00007855141,0.02218384,0.00001541783,0.00006175433,0.000001265128,0.0001678166,0.001484199,0.0006619773,0.04110655,0.001008895,0.9332111],"study_design_scores_gemma":[0.0001511249,0.000009468061,0.0981641,0.00001274956,0.00007491382,4.140764e-7,0.0001301551,0.8171003,0.0001523493,0.002037681,0.08202804,0.0001387104],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002458246,0.00072079,0.9910029,0.00495492,0.00008999153,0.000200188,0.00003816501,0.00002429979,0.0005105073],"genre_scores_gemma":[0.9846017,0.001613379,0.0129894,0.0002716813,0.00003722435,0.0001040006,0.000276435,0.000004776838,0.0001014044],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9821435,"threshold_uncertainty_score":0.4945276,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4304806684","doi":"10.1007/s11634-022-00522-6","title":"On smoothing and scaling language model for sentiment based information retrieval","year":2022,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Sentiment analysis; Latent Dirichlet allocation; Relevance (law); Social media; Smoothing; Probabilistic logic; Field (mathematics); Information retrieval; Language model; Artificial intelligence; Dirichlet distribution; Topic model; Data mining; World Wide Web; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03478667359186854,"gpt":0.3244483637770839,"spread":0.2896616901852153,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008255333,0.00007340954,0.0001394743,0.0004015766,0.000233189,0.0001599538,0.0003598009,0.00001616117,0.000007489708],"category_scores_gemma":[0.00005288199,0.00007178403,0.00003578321,0.0007872966,0.00001458067,0.001450739,0.0002165784,0.00006804402,5.185686e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003755178,"about_ca_system_score_gemma":0.00001573389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006069756,"about_ca_topic_score_gemma":0.00001421091,"domain_scores_codex":[0.9989925,0.00004885557,0.0002708233,0.0003349465,0.0002486911,0.0001041514],"domain_scores_gemma":[0.9991204,0.0001233151,0.0001833862,0.0005210144,0.00002369136,0.00002817746],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000123884,0.0001871853,0.008549796,0.0000627125,0.0002468012,0.000001014681,0.003683811,0.5996198,0.001057728,0.07212351,0.0002699586,0.3140738],"study_design_scores_gemma":[0.0002594739,0.00001465704,0.001255438,0.000004896778,0.00008295556,1.38834e-7,0.0004977383,0.9961899,0.0000608475,0.0004906481,0.001057468,0.00008583856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02241561,0.0004087288,0.9763814,0.0005250829,0.00003396491,0.0001048299,0.0000525027,0.00001748042,0.0000604553],"genre_scores_gemma":[0.9647059,0.0001250059,0.03361324,0.0002742678,0.000008015204,0.00002025254,0.001226386,0.00000255711,0.00002433719],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9427681,"threshold_uncertainty_score":0.2927268,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3041023245","doi":"10.1007/s11634-020-00408-5","title":"Active learning of constraints for weighted feature selection","year":2020,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Conseil National de la Recherche Scientifique; Agence Universitaire de la Francophonie","keywords":"Pairwise comparison; Feature selection; Laplacian matrix; Computer science; Cluster analysis; Graph; Feature (linguistics); Constraint (computer-aided design); Selection (genetic algorithm); Laplace operator; Data mining; Set (abstract data type); Machine learning; Theoretical computer science; Artificial intelligence; Mathematical optimization; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03703733615695371,"gpt":0.314984239601116,"spread":0.2779469034441623,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001141996,0.00005159187,0.000130514,0.00009869188,0.00005054383,0.00002641853,0.0002364685,0.00003730911,0.000007176081],"category_scores_gemma":[0.00009531237,0.00004588461,0.0000249625,0.0008356209,0.00003331713,0.0009849126,0.00005740676,0.0000730571,0.000001031074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007103202,"about_ca_system_score_gemma":0.00001324767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002382177,"about_ca_topic_score_gemma":0.00002390055,"domain_scores_codex":[0.9993502,0.00004333516,0.0001353458,0.0003203673,0.00008467794,0.00006599852],"domain_scores_gemma":[0.9995088,0.00008201617,0.0001488012,0.0001653681,0.00006646798,0.00002855355],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004919716,0.00004224829,0.01103187,0.00004335205,0.0001026375,2.042029e-7,0.0004303404,0.0003280987,0.02183682,0.005505817,0.0003240395,0.9603054],"study_design_scores_gemma":[0.0002396671,0.00003867721,0.01175267,0.00001369775,0.00008526795,2.161535e-7,0.0003460536,0.9742479,0.005203431,0.0008491254,0.007147717,0.00007560378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006952481,0.0002114186,0.9910444,0.001460482,0.00001640566,0.0000937155,0.00003902663,0.00002001172,0.0001620285],"genre_scores_gemma":[0.9610749,0.0007142229,0.03755042,0.00007446986,0.00001589226,0.00001273111,0.0005423628,0.000001985477,0.00001303261],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9739197,"threshold_uncertainty_score":0.187112,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2990751717","doi":"10.1007/s11634-019-00379-2","title":"Is-ClusterMPP: clustering algorithm through point processes and influence space towards high-dimensional data","year":2019,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université TÉLUQ; Université du Québec à Montréal","funders":"","keywords":"Cluster analysis; Curse of dimensionality; Algorithm; Data point; Computer science; Subspace topology; Mathematics; Statistical physics; Artificial intelligence; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.0354850183539955,"gpt":0.3152747212139836,"spread":0.2797897028599882,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005163235,0.0001747597,0.0002802095,0.000194347,0.00009763656,0.000428173,0.002087911,0.00004318513,0.00001458091],"category_scores_gemma":[0.00007525357,0.0001529915,0.00001469109,0.001321094,0.00007955178,0.01248779,0.003528133,0.000105485,0.00001503971],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001915664,"about_ca_system_score_gemma":0.00003856767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001854089,"about_ca_topic_score_gemma":0.0003261496,"domain_scores_codex":[0.9977582,0.00004585606,0.0003345522,0.00129342,0.00035222,0.0002157925],"domain_scores_gemma":[0.9968434,0.0000780042,0.0002109195,0.002736243,0.00008149642,0.00004994151],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001652698,0.0001582574,0.0232677,0.0003390957,0.0003088398,0.00001077894,0.0004886118,0.0008527351,0.000200702,0.006122715,0.0007680287,0.967466],"study_design_scores_gemma":[0.0002816986,0.00001999074,0.03521664,0.00004740275,0.0001133384,0.000002916898,0.0001102344,0.9488339,0.00003923354,0.00142666,0.01367862,0.0002293733],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008765176,0.002345034,0.9853937,0.002431798,0.0001181069,0.0002256812,0.0004240508,0.00005282688,0.000243598],"genre_scores_gemma":[0.4948376,0.01033553,0.4885501,0.0008202505,0.00007595777,0.00002100666,0.004977349,0.00001625477,0.0003660329],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9672366,"threshold_uncertainty_score":0.9053347,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4309636459","doi":"10.1007/s11634-022-00528-0","title":"A power-controlled reliability assessment for multi-class probabilistic classifiers","year":2022,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Probabilistic logic; Reliability (semiconductor); Computer science; Probabilistic classification; Classifier (UML); Statistic; Bayesian probability; Artificial intelligence; Machine learning; Class (philosophy); Naive Bayes classifier; Sample size determination; Sampling distribution; Data mining; Mathematics; Statistics; Power (physics); Support vector machine","retraction":null,"screen_n_in":null,"score":{"opus":0.1683283872417896,"gpt":0.4828551957848841,"spread":0.3145268085430944,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002753358,0.0001915504,0.0007112279,0.0002142767,0.0003124955,0.00004182408,0.000466188,0.00004916828,0.00007120394],"category_scores_gemma":[0.003041615,0.0001669409,0.0001238424,0.0007212989,0.0001261127,0.0004332759,0.0002676398,0.0002418468,3.26879e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002170563,"about_ca_system_score_gemma":0.00006909018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005943617,"about_ca_topic_score_gemma":0.0001790323,"domain_scores_codex":[0.9972079,0.0004621287,0.0007809598,0.0009408996,0.0003308213,0.000277264],"domain_scores_gemma":[0.9958302,0.002322128,0.0004130294,0.001243351,0.0001074537,0.00008379485],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007986155,0.0016705,0.004323861,0.0002515567,0.0004760705,0.000003214943,0.0002558893,0.006987224,0.0005515909,0.9152721,0.000292741,0.06911666],"study_design_scores_gemma":[0.001978014,0.00007558787,0.002509926,0.000005351586,0.0005536989,5.7724e-7,0.0006332072,0.7326756,0.00000219463,0.2531497,0.008234122,0.0001819673],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002730389,0.0003118659,0.9937934,0.0004580589,0.00009159976,0.001172911,0.0009593006,0.00003645835,0.0004459721],"genre_scores_gemma":[0.367493,0.0001830923,0.6302323,0.00005260272,0.00001311526,0.001244797,0.0005912455,0.00001662599,0.0001732427],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7256884,"threshold_uncertainty_score":0.6807653,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4387095339","doi":"10.1007/s11634-023-00558-2","title":"Parsimony and parameter estimation for mixtures of multivariate leptokurtic-normal distributions","year":2023,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"NextGenerationEU; Ministero dell'Università e della Ricerca; Natural Sciences and Engineering Research Council of Canada; Università Cattolica del Sacro Cuore","keywords":"Kurtosis; Multivariate statistics; Statistics; Mathematics; Estimation; Multivariate normal distribution; Multivariate analysis; Estimation theory; Econometrics; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.04852271423534097,"gpt":0.3659672425237264,"spread":0.3174445282883854,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005830365,0.0000734142,0.000178449,0.0001873343,0.00007225032,0.00005477617,0.0003028464,0.00004080362,8.233116e-7],"category_scores_gemma":[0.0002482008,0.00006288299,0.00003048859,0.0009470413,0.00005741126,0.0009616387,0.0001394409,0.0000418308,3.955403e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007138583,"about_ca_system_score_gemma":0.00001059931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001369277,"about_ca_topic_score_gemma":0.00006461652,"domain_scores_codex":[0.9990904,0.00006982466,0.000256997,0.0003736832,0.00008943611,0.0001196124],"domain_scores_gemma":[0.9988782,0.0003473701,0.0001362484,0.0005615412,0.00004320312,0.00003341092],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001226554,0.000044695,0.004828525,0.00004440594,0.00008932892,3.080383e-7,0.0001818796,0.0004834658,0.002363143,0.1975549,0.00008864588,0.7943084],"study_design_scores_gemma":[0.0001432242,0.00001255589,0.0627138,0.000007966669,0.0001165544,2.760513e-7,0.00001296923,0.8876049,0.0004675048,0.04809254,0.0007584865,0.00006923314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006040089,0.0004796066,0.9926611,0.0004841903,0.00003131881,0.000118717,0.0001412753,0.0000224621,0.00002126781],"genre_scores_gemma":[0.5513983,0.0006426534,0.4473392,0.00001096273,0.000006456043,0.00002451595,0.0005630404,0.000001979357,0.00001290068],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8871214,"threshold_uncertainty_score":0.2564294,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4376255225","doi":"10.1007/s11634-023-00542-w","title":"Model-based clustering of functional data via mixtures of t distributions","year":2023,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"MacEwan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Outlier; Cluster analysis; Multivariate statistics; Mixture model; Computer science; Functional data analysis; Data mining; Expectation–maximization algorithm; Multivariate normal distribution; Mathematics; Pattern recognition (psychology); Artificial intelligence; Statistics; Machine learning; Maximum likelihood","retraction":null,"screen_n_in":null,"score":{"opus":0.09709102288779793,"gpt":0.3592540555855143,"spread":0.2621630326977164,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007190524,0.0000714598,0.0001999396,0.0002653442,0.00004668143,0.00002051057,0.001026712,0.0000370743,0.000002884983],"category_scores_gemma":[0.00008249596,0.0000636797,0.0000307384,0.001725894,0.00006953242,0.0009309011,0.0004926136,0.00005640831,5.570105e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008898389,"about_ca_system_score_gemma":0.00003665416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000146113,"about_ca_topic_score_gemma":0.0002127692,"domain_scores_codex":[0.9988616,0.00006963623,0.0003235128,0.0004673698,0.0001783445,0.00009951037],"domain_scores_gemma":[0.9977496,0.0001316365,0.0001863194,0.001843931,0.00005971002,0.00002883292],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003308542,0.000219303,0.009734415,0.0001676596,0.0002367004,0.000001389366,0.0001067133,0.1072232,0.02112649,0.09392529,0.0006172267,0.7666085],"study_design_scores_gemma":[0.00009348555,0.000005314222,0.01400215,0.0000107902,0.00008894833,2.050998e-7,0.000006484017,0.9751299,0.0002568643,0.01006379,0.0002811954,0.00006085516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004974793,0.0005203408,0.9979611,0.000315984,0.00003784566,0.00004857881,0.0005304995,0.00001924469,0.00006894475],"genre_scores_gemma":[0.6929898,0.0004966792,0.3032512,0.00001245028,0.000009296819,0.000005162692,0.003222054,0.000002307225,0.00001110338],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8679067,"threshold_uncertainty_score":0.2596783,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4396529244","doi":"10.1007/s11634-024-00590-w","title":"Clustering functional data via variational inference","year":2024,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Cluster analysis; Inference; Computer science; Artificial intelligence; Data mining; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.08627126853721646,"gpt":0.3698520144562673,"spread":0.2835807459190509,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008757208,0.00009231056,0.0001395415,0.000263785,0.00006868417,0.0002812896,0.001157301,0.00004215574,0.00002335228],"category_scores_gemma":[0.00007723209,0.00008055194,0.00002028603,0.001270777,0.00003303302,0.003836329,0.0007876622,0.0001156638,0.000008540397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002177306,"about_ca_system_score_gemma":0.00005066712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000160255,"about_ca_topic_score_gemma":0.0003215552,"domain_scores_codex":[0.9984781,0.00008306338,0.0002580359,0.0008552686,0.0002087166,0.0001168576],"domain_scores_gemma":[0.9979702,0.0002349236,0.00006076045,0.001661822,0.00003207309,0.00004028079],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002534438,0.00002267433,0.002102325,0.00002214398,0.00008487708,0.000002220068,0.00004863716,0.0005393791,0.0001883808,0.1684578,0.0001492126,0.8283798],"study_design_scores_gemma":[0.00004218516,0.000003515567,0.02711534,0.00001302159,0.00008017376,0.000002504677,0.000003991246,0.9366771,0.000003072236,0.02456343,0.01140286,0.0000928085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002149399,0.003181879,0.9949618,0.0009186686,0.0001980431,0.00004581369,0.00008020679,0.00004769583,0.0005444061],"genre_scores_gemma":[0.3159589,0.001978207,0.6797007,0.00009113339,0.00009721537,0.0000104027,0.002076619,0.000004526001,0.00008232683],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9361377,"threshold_uncertainty_score":0.3284813,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2353061623","doi":"10.1007/s11634-016-0250-1","title":"Latent class model with conditional dependency per modes to cluster categorical data","year":2016,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Categorical variable; Conditional independence; Multinomial distribution; Independence (probability theory); Model selection; Latent class model; Mathematics; Local independence; Conditional probability distribution; Conditional probability; Mixture model; Latent variable; Class (philosophy); Expectation–maximization algorithm; Information Criteria; Dependency (UML); Statistics; Posterior probability; Algorithm; Latent variable model; Computer science; Artificial intelligence; Maximum likelihood; Bayesian probability","retraction":null,"screen_n_in":null,"score":{"opus":0.06299037588866112,"gpt":0.3427291082985342,"spread":0.2797387324098731,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005835284,0.0001422828,0.0002353804,0.0002241339,0.0000787901,0.0001043486,0.001702343,0.00005680015,0.000008239428],"category_scores_gemma":[0.00004594768,0.00008562627,0.00002264822,0.0006098505,0.00006158741,0.002994234,0.0007362182,0.00007947163,0.000009704541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003933023,"about_ca_system_score_gemma":0.00006707451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001325905,"about_ca_topic_score_gemma":0.0007003137,"domain_scores_codex":[0.9980097,0.000103663,0.0002887463,0.001079557,0.0003113232,0.000206954],"domain_scores_gemma":[0.9971681,0.000121593,0.0001066406,0.002413691,0.00007590759,0.0001140186],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000441798,0.0001342836,0.006920862,0.00001200549,0.0001400111,0.000003916887,0.000089621,0.003805961,0.001358567,0.6050172,0.0005383099,0.381935],"study_design_scores_gemma":[0.0002305808,0.00001715251,0.006261075,0.000008992351,0.0001053692,0.000003883767,0.000007616763,0.918695,0.00003019109,0.07256088,0.001910348,0.0001689706],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005408851,0.0002772965,0.9919681,0.006556516,0.00001962489,0.0001160779,0.0002214464,0.00002469476,0.0002753668],"genre_scores_gemma":[0.5925219,0.0005314207,0.4060578,0.0002379296,0.00002128376,0.00001915229,0.000443716,0.000005027733,0.0001617681],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.914889,"threshold_uncertainty_score":0.3491738,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4309346662","doi":"10.1007/s11634-022-00526-2","title":"A dual subspace parsimonious mixture of matrix normal distributions","year":2022,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Identifiability; Subspace topology; Dual (grammatical number); Set (abstract data type); Covariance matrix; Cluster analysis; Algorithm; Principal component analysis; Computer science; Matrix (chemical analysis); Covariance; Mathematics; Column (typography); Pattern recognition (psychology); Mathematical optimization; Data mining; Applied mathematics; Artificial intelligence; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02317261970497663,"gpt":0.3273198306380522,"spread":0.3041472109330756,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006463057,0.00008212207,0.0002050921,0.000196726,0.0001543742,0.00003736106,0.0007462246,0.00002672919,0.00001537437],"category_scores_gemma":[0.0000388962,0.0000779227,0.0000466833,0.001836227,0.00005077658,0.0007702144,0.0005376408,0.0001371012,4.793905e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002834001,"about_ca_system_score_gemma":0.00003222933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002834092,"about_ca_topic_score_gemma":0.0002025551,"domain_scores_codex":[0.9987401,0.0001923004,0.0002675198,0.000444264,0.000218673,0.0001370877],"domain_scores_gemma":[0.9985855,0.00008779094,0.0001923487,0.001059174,0.00003564835,0.00003949555],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002993576,0.0003683829,0.03485721,0.00003714448,0.0002169639,0.00001146263,0.0006199892,0.001282648,0.002421475,0.637034,0.0008338725,0.3222869],"study_design_scores_gemma":[0.0004537415,0.00006725048,0.06779222,0.000008147104,0.0004263414,0.00001523,0.0003366126,0.8499606,0.0003703118,0.02748464,0.05272523,0.0003596973],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00386551,0.002981801,0.9915729,0.0009016966,0.0000532479,0.00006938912,0.0003526467,0.00001611036,0.0001867362],"genre_scores_gemma":[0.8385336,0.0009306381,0.1597092,0.00002392163,0.00001312747,0.00002285894,0.000695982,0.000002705848,0.00006798015],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8486779,"threshold_uncertainty_score":0.3177595,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400011049","doi":"10.1007/s11634-024-00598-2","title":"Dirichlet compound negative multinomial mixture models and applications","year":2024,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Multinomial distribution; Dirichlet distribution; Mathematics; Econometrics; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.04164186050322628,"gpt":0.3451560601491029,"spread":0.3035141996458766,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004173362,0.0001198356,0.0002032959,0.0002527051,0.00009760929,0.0002948825,0.0005358549,0.0000582357,0.000002083895],"category_scores_gemma":[0.00001891517,0.0001006112,0.00003051242,0.001235089,0.0000871606,0.002107901,0.000252333,0.0001370693,0.000001987554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000202004,"about_ca_system_score_gemma":0.00002262838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002087851,"about_ca_topic_score_gemma":0.0002057411,"domain_scores_codex":[0.9986279,0.00009406106,0.0002416236,0.0007816164,0.0001253231,0.0001294979],"domain_scores_gemma":[0.9987543,0.0002424267,0.00006761464,0.0008424127,0.0000341633,0.0000591437],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000258777,0.00002574804,0.0002887306,0.0000278993,0.00006988196,0.00000182458,0.0002508739,0.00014744,0.000215548,0.3471381,0.00009393197,0.6517375],"study_design_scores_gemma":[0.00007377808,0.000004952909,0.001510635,0.00001189768,0.00011077,0.00000196207,0.00003118444,0.8431792,0.00002319816,0.1393899,0.01554916,0.0001134018],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002167474,0.01027959,0.9872217,0.0008912098,0.00004182965,0.0001591767,0.00007355732,0.00005126636,0.001064907],"genre_scores_gemma":[0.5465232,0.007149721,0.4457247,0.0001167098,0.00007343698,0.00007185662,0.000236201,0.000006775919,0.00009737707],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8430317,"threshold_uncertainty_score":0.4102807,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4313595020","doi":"10.1007/s11634-022-00532-4","title":"Flexible mixture regression with the generalized hyperbolic distribution","year":2023,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Covariate; Component (thermodynamics); Flexibility (engineering); Generalized additive model; Mathematics; Computer science; Generalized linear model; Regression; Regression analysis; Variable (mathematics); Mixture distribution; Set (abstract data type); Mathematical optimization; Applied mathematics; Algorithm; Statistics; Artificial intelligence; Random variable","retraction":null,"screen_n_in":null,"score":{"opus":0.03909977781917898,"gpt":0.3375096525388514,"spread":0.2984098747196724,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006800695,0.0001004458,0.0001691858,0.0001247459,0.0001590805,0.0001173862,0.0007781711,0.00004426467,0.000002407226],"category_scores_gemma":[0.00003241171,0.00005426909,0.00002769119,0.002893465,0.0000592595,0.0009098543,0.0002085213,0.00009941906,0.000002959446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001473847,"about_ca_system_score_gemma":0.00001755279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000013699,"about_ca_topic_score_gemma":0.0001742643,"domain_scores_codex":[0.9988252,0.0001597113,0.0001598869,0.0005049845,0.0001943542,0.0001558942],"domain_scores_gemma":[0.9984569,0.00008851672,0.0001155537,0.001266212,0.00003628891,0.00003651322],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002342112,0.00003997898,0.005318692,0.00001706543,0.0000966321,0.000004518828,0.0002377885,0.0003953086,0.001631991,0.181259,0.003394098,0.8075815],"study_design_scores_gemma":[0.0002612591,0.00001709562,0.05020155,0.0000211825,0.000161121,0.000002954894,0.00006673606,0.8712477,0.0003737993,0.01176464,0.06570283,0.0001791163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003229025,0.001537202,0.9905525,0.004313149,0.00003512985,0.00008713335,0.00003919507,0.00006710374,0.0001395942],"genre_scores_gemma":[0.8519482,0.01198751,0.1319294,0.0002808451,0.00008830884,0.00007073698,0.003072305,0.00001088557,0.0006118242],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8708524,"threshold_uncertainty_score":0.2213029,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3126183644","doi":"10.1007/s11634-022-00514-6","title":"Determinantal consensus clustering","year":2022,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données","keywords":"Cluster analysis; Point process; Single-linkage clustering; Mathematics; Computer science; Kernel (algebra); Similarity (geometry); Consensus clustering; Data mining; Artificial intelligence; Correlation clustering; CURE data clustering algorithm; Combinatorics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.05356536631324153,"gpt":0.3602556970197126,"spread":0.306690330706471,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005485023,0.00008563674,0.0001654217,0.0003517447,0.0002456435,0.00008224849,0.001265327,0.00001569213,0.00001458489],"category_scores_gemma":[0.00005678923,0.00008972069,0.00002499196,0.001626731,0.00006012684,0.0007518104,0.002097455,0.0001677363,0.000002669271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008235084,"about_ca_system_score_gemma":0.00002479426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002429567,"about_ca_topic_score_gemma":0.0003516591,"domain_scores_codex":[0.9984491,0.0001305959,0.0002501829,0.0006516093,0.0003140772,0.0002043887],"domain_scores_gemma":[0.9984227,0.0001243367,0.0001095061,0.001271933,0.00002391619,0.00004754801],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000188204,0.00008613971,0.01163345,0.0000209205,0.00006165215,0.00004230277,0.0002330005,0.02283611,0.001232044,0.002685562,0.00003614254,0.9611139],"study_design_scores_gemma":[0.0001464006,0.00002084786,0.01368304,0.000002383693,0.00002080049,0.00001757898,0.0002092212,0.9743686,0.00002815395,0.0005126451,0.01087912,0.0001111869],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01108113,0.001344704,0.9864076,0.0005261349,0.00009652943,0.0001037743,0.00005829574,0.0000477075,0.0003340819],"genre_scores_gemma":[0.9338086,0.0006270735,0.06518655,0.00004168615,0.00001583208,0.00005068858,0.0001461176,0.00000566454,0.0001178499],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9610026,"threshold_uncertainty_score":0.3658704,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4403793086","doi":"10.1007/s11634-024-00608-3","title":"A sparse exponential family latent block model for co-clustering","year":2024,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Amirkabir University of Technology","keywords":"Exponential family; Cluster analysis; Exponential function; Block (permutation group theory); Computer science; Mathematics; Statistics; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.1106521907296518,"gpt":0.3939182569241741,"spread":0.2832660661945223,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004919061,0.0001253006,0.0002013982,0.0004114871,0.00009624384,0.0003152643,0.000919737,0.00004483496,0.000001416985],"category_scores_gemma":[0.00004270332,0.0001168762,0.00005412638,0.001013714,0.00005205139,0.002007997,0.0004618937,0.0001166282,0.000005920032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006436358,"about_ca_system_score_gemma":0.0000412907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001096731,"about_ca_topic_score_gemma":0.0001718823,"domain_scores_codex":[0.9982603,0.00003571996,0.0003125142,0.0008694025,0.0002675817,0.0002544707],"domain_scores_gemma":[0.9986327,0.0001286727,0.0000592343,0.001066762,0.00004788631,0.00006468582],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003813337,0.0001053288,0.0005508971,0.0002404655,0.0002728841,0.00001527303,0.0005921093,0.2729095,0.00873776,0.009510467,0.0001898523,0.7068374],"study_design_scores_gemma":[0.0001395845,0.00001385399,0.0009181609,0.00002781455,0.00006120405,0.000002017602,0.00003890939,0.9932954,0.00007059254,0.001543072,0.003753434,0.0001360062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002230519,0.002894171,0.9939939,0.0003608124,0.00009432009,0.0001818023,0.00008897216,0.00008319182,0.00007227846],"genre_scores_gemma":[0.8218928,0.003761108,0.1734907,0.00003380478,0.00005794426,0.0001128372,0.0003537054,0.00001356196,0.0002835142],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8205032,"threshold_uncertainty_score":0.4766075,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4416664067","doi":"10.1007/s11634-025-00659-0","title":"Data-driven logistic regression ensembles with applications in genomics","year":2025,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Mitacs; KU Leuven","keywords":"Genomics; Regularization (linguistics); Ranking (information retrieval); Big data; Logistic regression; Computational genomics; Predictive modelling; Binary number","retraction":null,"screen_n_in":null,"score":{"opus":0.04371606132484556,"gpt":0.3582000692644834,"spread":0.3144840079396379,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002213954,0.0001178131,0.0001741981,0.0002729305,0.00006909957,0.00003545015,0.0006455354,0.00008204431,0.000003895722],"category_scores_gemma":[0.00005402833,0.00009373429,0.0000159186,0.0009316706,0.00009131808,0.00004487159,0.0002862845,0.0000769231,9.63899e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002730294,"about_ca_system_score_gemma":0.00007634482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002160052,"about_ca_topic_score_gemma":0.003675209,"domain_scores_codex":[0.9986485,0.00006560219,0.0002814081,0.0007913672,0.00009146596,0.0001216588],"domain_scores_gemma":[0.9978922,0.00002812368,0.0001454732,0.001861143,0.00004212317,0.00003091769],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003161228,0.0004614903,0.6008784,0.0001322506,0.0003101368,0.000001696665,0.00007322144,0.005047634,0.2056777,0.007598767,0.002209791,0.1772928],"study_design_scores_gemma":[0.0009195814,0.00004222035,0.406303,0.00009418023,0.0004599224,0.00000118679,0.001364272,0.07820422,0.003498315,0.0007776644,0.507939,0.000396442],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1560013,0.01811891,0.8202986,0.001254952,0.00008051469,0.0007814444,0.0008383157,0.00002796483,0.002597986],"genre_scores_gemma":[0.9700208,0.01214206,0.004079203,0.00006594024,0.00002607975,0.00008406489,0.01337106,0.00000673392,0.000204068],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8162194,"threshold_uncertainty_score":0.3822373,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2891365885","doi":"10.1007/s11634-019-00377-4","title":"Mixtures of skewed matrix variate bilinear factor analyzers","year":2019,"lang":"en","type":"preprint","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Random variate; Kurtosis; Skewness; Bilinear interpolation; Statistics; Mathematics; Skew; Matrix (chemical analysis); Gaussian; Inverse Gaussian distribution; Applied mathematics; Computer science; Distribution (mathematics); Mathematical analysis; Physics; Random variable","retraction":null,"screen_n_in":null,"score":{"opus":0.04467400490465936,"gpt":0.3678903485041041,"spread":0.3232163435994448,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009005688,0.0002587916,0.0007678918,0.0006869909,0.00003793219,0.0001423728,0.002203358,0.0002345952,0.00001534412],"category_scores_gemma":[0.000125499,0.0002187024,0.0001544544,0.001269568,0.00007489824,0.0008215855,0.001393934,0.0003413674,0.000002815233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003397816,"about_ca_system_score_gemma":0.0001026041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009683098,"about_ca_topic_score_gemma":0.000162292,"domain_scores_codex":[0.9971559,0.0003081337,0.0007094358,0.001301351,0.0003242035,0.0002009454],"domain_scores_gemma":[0.9953215,0.0002109582,0.0007477511,0.003536132,0.0001184001,0.00006524362],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006707089,0.0004436291,0.04105168,0.001079728,0.00227241,0.000007548884,0.001300456,0.01117181,0.006304374,0.1263597,0.0002767969,0.8096648],"study_design_scores_gemma":[0.0001798341,0.00001511967,0.02813052,0.00005857535,0.0005117267,5.036781e-7,0.00002076827,0.9442941,0.0003174202,0.02447638,0.001678573,0.000316484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002516718,0.006359986,0.9897391,0.0002898215,0.0002260959,0.0002193454,0.0003878228,0.00002871353,0.0002323672],"genre_scores_gemma":[0.4791266,0.009791402,0.5099332,0.00003013361,0.00004167623,0.00001067414,0.0009557945,0.00001013918,0.0001004137],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9331223,"threshold_uncertainty_score":0.8918424,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4410920770","doi":"10.1007/s11634-025-00637-6","title":"Mixed-type kernel-based quantification of similarity for clustering","year":2025,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus","funders":"University of British Columbia","keywords":"Kernel (algebra); Similarity (geometry); Cluster analysis; Artificial intelligence; Computer science; Pattern recognition (psychology); Type (biology); Mathematics; Data mining; Combinatorics; Geology","retraction":null,"screen_n_in":null,"score":{"opus":0.09468252969729223,"gpt":0.3986018150346892,"spread":0.303919285337397,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007282557,0.00009228375,0.0002336786,0.0004744635,0.00008273157,0.00006631353,0.00102033,0.00005051414,0.000001248201],"category_scores_gemma":[0.0003614655,0.00009222626,0.00003814689,0.002260755,0.00007912428,0.0009227574,0.0003066101,0.00007833189,5.714208e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004572521,"about_ca_system_score_gemma":0.00006128224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001905201,"about_ca_topic_score_gemma":0.0005105329,"domain_scores_codex":[0.998602,0.00007170324,0.0003811547,0.0006155725,0.0001730955,0.0001565289],"domain_scores_gemma":[0.9977986,0.0003435829,0.0001736069,0.001463783,0.0001916574,0.0000287283],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009822736,0.0002304762,0.02233702,0.00044095,0.000177571,6.462937e-7,0.0000657501,0.06547756,0.009222901,0.03621181,0.00007663969,0.8656604],"study_design_scores_gemma":[0.0002208657,0.00001707895,0.03020122,0.00002705108,0.00005896796,8.629065e-8,0.00004268535,0.9622673,0.0017153,0.001978925,0.003390278,0.00008026157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001399341,0.0009905266,0.9965732,0.0006058022,0.00009909812,0.0001865774,0.00003814236,0.00002632849,0.00008105559],"genre_scores_gemma":[0.7883241,0.0006748906,0.2105113,0.0000283213,0.000008981265,0.00003427511,0.0003567276,0.000003904143,0.00005750622],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8967897,"threshold_uncertainty_score":0.3760878,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4407498245","doi":"10.1007/s11634-025-00625-w","title":"Random models for adjusting fuzzy rand index extensions","year":2025,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Index (typography); Fuzzy logic; Computer science; Econometrics; Mathematics; Statistics; Artificial intelligence; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.05220024079240108,"gpt":0.3365206615945156,"spread":0.2843204208021145,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005863271,0.00009589837,0.0002580617,0.0003081441,0.0001665965,0.0001288935,0.0007314798,0.00004772499,0.000001049203],"category_scores_gemma":[0.00014074,0.00007816678,0.00005105996,0.001370326,0.00004262792,0.001430164,0.0002493836,0.00006806314,3.665116e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001587189,"about_ca_system_score_gemma":0.00002810682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001973735,"about_ca_topic_score_gemma":0.0002970965,"domain_scores_codex":[0.9987664,0.00005198847,0.0003194417,0.0005943886,0.00011157,0.0001562712],"domain_scores_gemma":[0.9984388,0.0003131328,0.0001190519,0.001029303,0.00006816065,0.00003159472],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007454485,0.00009823727,0.008015384,0.00004755661,0.0001600093,0.000001135112,0.0001367598,0.03307793,0.000111082,0.1792589,0.0005300593,0.7784885],"study_design_scores_gemma":[0.000760702,0.000005785444,0.01026996,0.00001659315,0.0001398222,2.619391e-7,0.00008946963,0.9423291,0.000003962161,0.04182717,0.004470405,0.00008675858],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005710316,0.004230565,0.9915176,0.0009189952,0.00008002145,0.000188433,0.0000303373,0.00002890243,0.00243413],"genre_scores_gemma":[0.9247416,0.003607666,0.07096878,0.0001848559,0.00002014732,0.00005377555,0.0003383746,0.00000218555,0.00008257719],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9241706,"threshold_uncertainty_score":0.3187549,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2790767741","doi":"10.1007/s11634-020-00395-7","title":"Clustering discrete-valued time series","year":2020,"lang":"en","type":"preprint","venue":"Advances in Data Analysis and Classification","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Cluster analysis; Series (stratigraphy); Autoregressive model; Computer science; Model selection; Expectation–maximization algorithm; STAR model; Time series; Data mining; Focus (optics); Algorithm; Mathematics; Artificial intelligence; Autoregressive integrated moving average; Machine learning; Econometrics; Statistics; Maximum likelihood","retraction":null,"screen_n_in":null,"score":{"opus":0.04408920708021554,"gpt":0.3089382067535628,"spread":0.2648489996733472,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005150835,0.0002864969,0.000691583,0.0003515886,0.0001373116,0.0005765776,0.00220803,0.0001070803,0.00003183499],"category_scores_gemma":[0.000122372,0.0002651998,0.0001430776,0.001542065,0.00009279507,0.002245084,0.004392934,0.0003437322,0.00001830201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004599354,"about_ca_system_score_gemma":0.00004416305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006130091,"about_ca_topic_score_gemma":0.0007722097,"domain_scores_codex":[0.9971097,0.0001297786,0.0006685615,0.001524795,0.0003221358,0.0002450376],"domain_scores_gemma":[0.9968222,0.00005741776,0.000543157,0.002414443,0.00006334101,0.00009942154],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001252748,0.0002304992,0.02905586,0.0008762024,0.003714038,0.0000570653,0.002459282,0.06493548,0.001773975,0.0482964,0.0008139188,0.847662],"study_design_scores_gemma":[0.00007277453,0.00001199945,0.009191272,0.00004549327,0.0004570551,0.000001260537,0.00009801405,0.9817107,0.00001479054,0.00272351,0.005369612,0.0003035089],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004130786,0.002901177,0.9929453,0.002077617,0.00009714593,0.0001426142,0.0001619953,0.00009699073,0.001164084],"genre_scores_gemma":[0.6937626,0.009001171,0.2899006,0.0001497276,0.0002248549,0.00005865178,0.006423358,0.0000323706,0.0004466554],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9167752,"threshold_uncertainty_score":0.99998,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4200498417","doi":"10.1007/s11634-021-00487-y","title":"Correction to: Multivariate cluster weighted models using skewed distributions","year":2021,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Multivariate statistics; Cluster (spacecraft); Statistics; Line (geometry); Econometrics; Computer science; Mathematics; Programming language; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.2059572849996396,"gpt":0.4522187383613219,"spread":0.2462614533616823,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001060309,0.0001022153,0.0002390785,0.0003309455,0.0002237467,0.0002164265,0.000500499,0.00004944309,0.00004753983],"category_scores_gemma":[0.001112225,0.00008665877,0.0000568761,0.004331267,0.00005382087,0.001078723,0.0003208373,0.0001056042,0.000009886865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005972941,"about_ca_system_score_gemma":0.0000428201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001259829,"about_ca_topic_score_gemma":0.002099989,"domain_scores_codex":[0.9979625,0.0001547283,0.0005713279,0.0007966957,0.0003634459,0.0001513405],"domain_scores_gemma":[0.9974797,0.0004947345,0.0002254682,0.001403452,0.0003214066,0.00007522776],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008849773,0.0007724629,0.04984137,0.00001388421,0.0002743156,0.000005783192,0.0005543814,0.06717389,0.01931942,0.09290442,0.0128929,0.7561587],"study_design_scores_gemma":[0.00008183689,0.000004581695,0.014455,0.00001330403,0.0001160473,0.000002398294,0.0001954387,0.9447105,0.0002778078,0.02602824,0.01400836,0.0001064887],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01597475,0.0002197303,0.9816148,0.0009383769,0.0001302733,0.000127238,0.0003067959,0.00003410285,0.0006538847],"genre_scores_gemma":[0.9164014,0.0002571827,0.08161585,0.00006788514,0.00003012659,0.00002941,0.001259952,0.000005476213,0.0003327397],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9004266,"threshold_uncertainty_score":0.3533842,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4389888669","doi":"10.1007/s11634-023-00576-0","title":"QDA classification of high-dimensional data with rare and weak signals","year":2023,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Natural Science Foundation of Shandong Province","keywords":"Quadratic classifier; Linear discriminant analysis; Mathematics; Artificial intelligence; Covariance; Pattern recognition (psychology); Covariance matrix; Gaussian; Classifier (UML); Machine learning; Statistics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.05659637533914804,"gpt":0.3390542180021777,"spread":0.2824578426630296,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009373218,0.0001071377,0.000238219,0.0004632644,0.00007156174,0.00009208015,0.00106684,0.00005159778,0.000005180569],"category_scores_gemma":[0.00008338087,0.00008889627,0.00001259149,0.00227712,0.0001122003,0.002592635,0.0005918288,0.0000858841,0.0000031295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001117821,"about_ca_system_score_gemma":0.0000414795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004998143,"about_ca_topic_score_gemma":0.0006827355,"domain_scores_codex":[0.998321,0.000124725,0.0003567482,0.0007733195,0.0003072971,0.0001169001],"domain_scores_gemma":[0.9972945,0.0002021065,0.0002840493,0.002084116,0.00009255255,0.00004260687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008629236,0.000316934,0.1010685,0.0001313212,0.0004616633,0.000005991198,0.0006615485,0.003179015,0.01398795,0.3107383,0.003386132,0.5659763],"study_design_scores_gemma":[0.0001719785,0.00002894134,0.2674691,0.00002377835,0.00008922293,0.000001501771,0.0001416422,0.7252573,0.0003373321,0.003063682,0.003287242,0.0001282719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08161987,0.001010908,0.9132318,0.003110168,0.00002888442,0.0002438411,0.0003000277,0.0001738604,0.0002806564],"genre_scores_gemma":[0.9611545,0.001754317,0.03347698,0.00004781835,0.00001006795,0.00001678831,0.003494378,0.000005466973,0.00003975009],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8797548,"threshold_uncertainty_score":0.3625085,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}