{"meta":{"query_hash":"47001aa2d831","filters":{"venue":"Advances in Data Analysis and Classification"},"cohort_total":40,"direct_labels_cover":0,"predictions_cover":40,"exported":40,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/47001aa2d831","api":"https://metacan.xera.ac/api/v1/cohort?venue=Advances+in+Data+Analysis+and+Classification"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.12235253318764872,"score_gpt":0.4083881885969034,"score_spread":0.2860356554092547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1875624538","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00025380575,0.001424383,0.9970609,0.00057155837,0.00010939121,0.00019143459,0.000030664556,0.00008627451,0.00027161284],"genre_scores_gemma":[0.23347037,0.0008756719,0.76494277,0.00004584884,0.000081718295,0.000038527214,0.00014529764,0.000016661248,0.00038312652],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99742055,0.00016971379,0.0004622464,0.0011046231,0.0004795098,0.00036335576],"domain_scores_gemma":[0.99723667,0.00021814989,0.00019838534,0.0019921414,0.00010430371,0.00025036503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077598647,0.00019541361,0.0003560179,0.00035902418,0.000090695554,0.0002865333,0.0016936463,0.000060428785,0.000005051982],"category_scores_gemma":[0.0004747242,0.00018306069,0.000040445928,0.0020960968,0.0000646219,0.0030230957,0.0013103675,0.00020098496,0.000008550034],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028780923,0.000056040648,0.0032609822,0.00006133363,0.000076325734,0.0000094871775,0.00062571146,0.044351906,0.000288549,0.0022089055,0.000044630193,0.94898736],"study_design_scores_gemma":[0.0003160083,0.000025494386,0.0062042163,0.000026299507,0.000037639824,0.000005523121,0.00013935193,0.979554,0.000025336833,0.002718244,0.010732594,0.00021528536],"about_ca_topic_score_codex":0.00010568818,"about_ca_topic_score_gemma":0.0026813033,"teacher_disagreement_score":0.9487721,"about_ca_system_score_codex":0.0001890646,"about_ca_system_score_gemma":0.00010243148,"threshold_uncertainty_score":0.74649984},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.028086007090192076,"score_gpt":0.3141116705601102,"score_spread":0.2860256634699181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964231120","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000120328106,0.00015362217,0.9985153,0.0005635862,0.000047341255,0.0001096411,0.00017838979,0.000014618084,0.0002971422],"genre_scores_gemma":[0.34361687,0.000118410106,0.6553992,0.000027101303,0.000025546971,0.000028318958,0.00076808746,0.0000022496477,0.00001423537],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998966,0.000096497744,0.00031996376,0.00037938575,0.0001207978,0.00011739299],"domain_scores_gemma":[0.9987557,0.00020655249,0.00020292086,0.0007221245,0.000071810304,0.000040928153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006883994,0.00008289042,0.00018782428,0.00020256125,0.00010993011,0.000053101274,0.00052086817,0.0000455955,0.000004332203],"category_scores_gemma":[0.00014683107,0.000074637,0.000047082845,0.00073399325,0.000051629242,0.0011750644,0.00014386424,0.000052423387,4.1637674e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008323299,0.00008917396,0.0030594526,0.000059738144,0.00008638834,7.126057e-8,0.00015330725,0.001032707,0.0015592381,0.6952657,0.00007375784,0.29861215],"study_design_scores_gemma":[0.00014718367,0.00001170595,0.014476636,0.000007200678,0.00009127513,5.750022e-7,0.000010156096,0.9342356,0.00013921795,0.04818898,0.002608542,0.00008293272],"about_ca_topic_score_codex":0.0000147773635,"about_ca_topic_score_gemma":0.00042800963,"teacher_disagreement_score":0.93320286,"about_ca_system_score_codex":0.000014694457,"about_ca_system_score_gemma":0.000018731178,"threshold_uncertainty_score":0.30436084},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.07739344212886445,"score_gpt":0.3564501671026479,"score_spread":0.2790567249737834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972256887","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008989325,0.0039608357,0.98609734,0.0003752435,0.00004653846,0.000056352896,0.00003531373,0.000015562595,0.00042346262],"genre_scores_gemma":[0.60154766,0.0017747646,0.39643666,0.00005811729,0.000018401619,0.0000051847487,0.00011590888,0.0000030851593,0.000040228028],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987878,0.00014602394,0.00029043874,0.0004636405,0.00019386546,0.000118217315],"domain_scores_gemma":[0.998415,0.000049293423,0.00017915595,0.001200237,0.00007483184,0.00008146173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048405345,0.00009474266,0.0002884489,0.00027879633,0.000023069702,0.000044475135,0.0008043842,0.000051528183,0.000004355059],"category_scores_gemma":[0.000089904424,0.000076306715,0.000043481712,0.0014825902,0.0000493172,0.0010726303,0.00017648064,0.00006699639,0.0000010191947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020045409,0.0001193326,0.03336242,0.000025063682,0.00022664363,0.000002564549,0.00075504015,0.0001962555,0.0041511143,0.1305437,0.00029860623,0.8302992],"study_design_scores_gemma":[0.0006195405,0.000033186967,0.048735432,0.000014203179,0.0002868312,0.000002379482,0.00009954814,0.8969435,0.00079197675,0.031946734,0.0202366,0.0002900598],"about_ca_topic_score_codex":0.00004005454,"about_ca_topic_score_gemma":0.00023359168,"teacher_disagreement_score":0.89674723,"about_ca_system_score_codex":0.000016646138,"about_ca_system_score_gemma":0.000036221456,"threshold_uncertainty_score":0.31116974},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03849028777574721,"score_gpt":0.3380154403337114,"score_spread":0.2995251525579642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973247608","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001310196,0.00045195065,0.9974397,0.00044516756,0.00004855571,0.0002128719,0.00004230647,0.000018016099,0.00003124081],"genre_scores_gemma":[0.50217193,0.00010306591,0.49740967,0.000010757864,0.000007613687,0.000035318735,0.0002510174,0.000002117553,0.000008512945],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989614,0.0000682758,0.00030464196,0.00044697543,0.000099270845,0.00011944423],"domain_scores_gemma":[0.9987509,0.00007901612,0.00019400138,0.0008256358,0.00011318229,0.0000372279],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039299013,0.00008847016,0.00019426848,0.00018487254,0.00007938409,0.000046402023,0.00039363545,0.000051725572,0.0000017490958],"category_scores_gemma":[0.00005340814,0.00007643862,0.00004671946,0.00060276315,0.000043241627,0.0011841133,0.00010511453,0.00005166911,3.853091e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001957239,0.00016164737,0.00034233966,0.000071598944,0.000085511136,1.1038232e-7,0.00013441619,0.027865699,0.14029361,0.057654537,0.00008578561,0.77328515],"study_design_scores_gemma":[0.00016801308,0.000012324081,0.0019260794,0.0000119795795,0.000085270585,3.3256154e-7,0.0000065443855,0.97031564,0.0026640743,0.024588391,0.00013763095,0.00008374889],"about_ca_topic_score_codex":0.00004708462,"about_ca_topic_score_gemma":0.000056392622,"teacher_disagreement_score":0.9424499,"about_ca_system_score_codex":0.00001983124,"about_ca_system_score_gemma":0.000018191946,"threshold_uncertainty_score":0.31170765},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.05461420121741699,"score_gpt":0.32804995560749833,"score_spread":0.27343575439008133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990989764","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012219563,0.0015311472,0.985399,0.00043708863,0.00004775035,0.000084062376,0.000015795473,0.000016700202,0.00024888624],"genre_scores_gemma":[0.9506439,0.00079961616,0.048279624,0.000052791092,0.000029621358,0.00002468014,0.00014419915,0.0000022630884,0.000023312148],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922067,0.00003917347,0.0002479226,0.00027318683,0.00009712191,0.0001219191],"domain_scores_gemma":[0.99893105,0.00006802591,0.00012665437,0.00078113616,0.00003589961,0.000057224923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029888743,0.00006221489,0.00014376889,0.00017818512,0.0000422714,0.000031951477,0.0005648713,0.000022332759,0.000004415179],"category_scores_gemma":[0.000027803273,0.000055975004,0.000023085613,0.0014488104,0.000025768162,0.0012402177,0.00017837541,0.00004158961,0.000003696306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048841885,0.00017560134,0.04186864,0.0000140136135,0.000050183527,7.1557785e-8,0.00044746112,0.0036706238,0.0015573589,0.19381452,0.00019650496,0.7582001],"study_design_scores_gemma":[0.00009437985,0.000020707974,0.13378155,0.000015956542,0.00011814583,8.062693e-7,0.00019620305,0.7809081,0.00014013807,0.0015517686,0.08302121,0.00015100205],"about_ca_topic_score_codex":0.000055886412,"about_ca_topic_score_gemma":0.00032103306,"teacher_disagreement_score":0.93842435,"about_ca_system_score_codex":0.000015299729,"about_ca_system_score_gemma":0.000007449588,"threshold_uncertainty_score":0.22825944},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04141965676927712,"score_gpt":0.3381464725389695,"score_spread":0.2967268157696924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994281788","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013547942,0.0005505018,0.9979959,0.0006220736,0.00004287848,0.00007861712,0.000012917174,0.000024001884,0.0005376022],"genre_scores_gemma":[0.30220348,0.00045617507,0.6970089,0.0001426955,0.000026383439,0.000016019607,0.00009130057,0.0000033527133,0.00005169584],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897105,0.00005750171,0.00020163869,0.0005396885,0.00009337755,0.00013673514],"domain_scores_gemma":[0.99872684,0.00010877065,0.000097561024,0.000996219,0.00003241819,0.000038199614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076471735,0.0000854039,0.00017987099,0.0001628572,0.0000796238,0.00010204065,0.0006801596,0.00004012916,6.587238e-7],"category_scores_gemma":[0.00006805253,0.0000749035,0.000035130382,0.00047828894,0.000019584522,0.0011947922,0.00018867824,0.000060694925,4.501002e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038212315,0.000016739676,0.0006448089,0.0000226495,0.000027597363,1.00079426e-7,0.00012375339,0.005377385,0.0005454545,0.15206075,0.00005609185,0.84112084],"study_design_scores_gemma":[0.00011273996,0.000005119533,0.000832351,0.0000070187425,0.00005676861,3.8619118e-7,0.000006225768,0.94569427,0.000038097885,0.047834914,0.0053189783,0.0000931247],"about_ca_topic_score_codex":0.000003245882,"about_ca_topic_score_gemma":0.00016143586,"teacher_disagreement_score":0.9403169,"about_ca_system_score_codex":0.000012300705,"about_ca_system_score_gemma":0.0000093656945,"threshold_uncertainty_score":0.30544764},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.05393879753402075,"score_gpt":0.3370129092875392,"score_spread":0.28307411175351843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997354990","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07764351,0.0004010169,0.9210874,0.0004978869,0.00005549312,0.00010801239,0.00000646554,0.000018275985,0.00018193024],"genre_scores_gemma":[0.54787076,0.00015420822,0.45179597,0.000043152704,0.0000072927282,0.000014922851,0.00010341536,0.0000018505435,0.000008414064],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873537,0.0001455837,0.00032929578,0.0004973369,0.00013811929,0.00015428239],"domain_scores_gemma":[0.99863297,0.00012711014,0.00013169053,0.0010329311,0.000025970783,0.00004931675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047461264,0.0000917754,0.00022914135,0.00024656663,0.00006336966,0.000100467354,0.0006831347,0.000039352493,0.00000643834],"category_scores_gemma":[0.000047712176,0.00007898128,0.000019638244,0.0009824861,0.000037053345,0.0017342276,0.00034190482,0.00011204728,0.0000064130104],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025797503,0.00015336343,0.12407073,0.00001737058,0.000034562847,0.0000030518884,0.00020462596,0.0011009129,0.0016205398,0.08750453,0.000034172375,0.7852536],"study_design_scores_gemma":[0.00009691018,0.00000404466,0.24393202,0.000012785019,0.000020117228,5.048125e-7,0.00000888804,0.7358992,0.000013899946,0.019754775,0.00018421441,0.00007259391],"about_ca_topic_score_codex":0.000331958,"about_ca_topic_score_gemma":0.00075877865,"teacher_disagreement_score":0.785181,"about_ca_system_score_codex":0.000022992223,"about_ca_system_score_gemma":0.0000086579785,"threshold_uncertainty_score":0.3220763},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.029910501458001896,"score_gpt":0.30810436773482447,"score_spread":0.2781938662768226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004773941","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006686269,0.002581786,0.9932692,0.0013066261,0.00009259788,0.00009694206,0.000022760083,0.000044528424,0.001916954],"genre_scores_gemma":[0.9786506,0.0042398595,0.01591562,0.00018743603,0.000041197327,0.0000074584937,0.0007379366,0.0000021772412,0.00021769274],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989251,0.000046321893,0.00022447307,0.00050942844,0.00016340843,0.00013130732],"domain_scores_gemma":[0.99845994,0.000033215587,0.000104607876,0.0013495233,0.00001969152,0.00003303177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039337197,0.000078823796,0.00015070387,0.00023726022,0.000055631364,0.00028984557,0.0011061622,0.000023045073,0.0000017376109],"category_scores_gemma":[0.000020172018,0.00006791134,0.000019000658,0.0011343631,0.000020190175,0.0031689506,0.00021261343,0.000049417486,0.000009874257],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035157434,0.000090065376,0.008573222,0.000011221364,0.000065804605,0.000003928971,0.000059088146,0.00073228864,0.00004078369,0.09652285,0.0011373864,0.89275986],"study_design_scores_gemma":[0.00012263916,0.0000126024315,0.048539158,0.000006594911,0.00007061402,5.191373e-7,0.000064885455,0.89733404,0.0000033059027,0.0014295176,0.052309677,0.000106443935],"about_ca_topic_score_codex":0.00001264556,"about_ca_topic_score_gemma":0.00007447587,"teacher_disagreement_score":0.977982,"about_ca_system_score_codex":0.000013731929,"about_ca_system_score_gemma":0.000004947303,"threshold_uncertainty_score":0.27949876},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03893491462284368,"score_gpt":0.2847833179878061,"score_spread":0.24584840336496241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016714679","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6447733,0.008146718,0.32447147,0.0010845016,0.000066978035,0.0003819861,0.001719971,0.00016088314,0.01919418],"genre_scores_gemma":[0.99122924,0.001306976,0.0028862213,0.000052162348,0.00006111167,0.000027302121,0.004245396,0.000009454249,0.00018212319],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867135,0.00003642494,0.0003763546,0.0005282751,0.00021860417,0.00016900437],"domain_scores_gemma":[0.998893,0.000046358164,0.00021989764,0.0007256153,0.000046379617,0.00006874949],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001781297,0.00016435984,0.00023067556,0.00007000125,0.00013506529,0.0000655137,0.00036476564,0.000093233415,0.00066832],"category_scores_gemma":[0.000017364127,0.00011458125,0.00006203881,0.0006465549,0.00017450604,0.00061161263,0.000058847374,0.00014027304,0.0000027275914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012840321,0.0015313557,0.4192798,0.00031242042,0.0032142892,0.000016321992,0.0016146391,0.00007798092,0.17830917,0.0032345937,0.008647572,0.3824778],"study_design_scores_gemma":[0.00317704,0.00009620978,0.06317114,0.00009348606,0.0047620973,0.000018029512,0.005339569,0.77646697,0.06752321,0.00045793847,0.077513225,0.0013811223],"about_ca_topic_score_codex":0.00006520842,"about_ca_topic_score_gemma":0.00018172427,"teacher_disagreement_score":0.77638894,"about_ca_system_score_codex":0.000024915178,"about_ca_system_score_gemma":0.000016012395,"threshold_uncertainty_score":0.73176354},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Mahalanobis distance; Covariance matrix; Dynamic time warping; Covariance; Pattern recognition (psychology); Series (stratigraphy); k-nearest neighbors algorithm; Margin (machine learning)","score_opus":0.03447962751202253,"score_gpt":0.27522920034167747,"score_spread":0.24074957282965495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027846664","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004716881,0.023063496,0.9666489,0.0016109481,0.00013591042,0.00017582919,0.00018569858,0.0001246244,0.003337721],"genre_scores_gemma":[0.9734232,0.010059917,0.014103494,0.000053669355,0.00009073432,0.000031998716,0.0015665191,0.000013649157,0.0006568089],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976102,0.00015089013,0.0005901475,0.00083848974,0.0004054001,0.00040486196],"domain_scores_gemma":[0.99746495,0.00010025078,0.000392254,0.0018176647,0.000091518436,0.0001333767],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000939471,0.00022561624,0.00039909195,0.00029597137,0.00022871823,0.00027951383,0.0011651405,0.0000881819,0.000048475806],"category_scores_gemma":[0.000070878814,0.00020291349,0.0000812561,0.0022878796,0.00017535298,0.00638432,0.0002829956,0.0001480238,0.000048747275],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005241734,0.00045466234,0.16445018,0.00004472736,0.00047537612,0.0000018263335,0.0008330108,0.00023489656,0.013926182,0.13884597,0.007524646,0.6731561],"study_design_scores_gemma":[0.000186654,0.000022030092,0.09687722,0.000017712304,0.00022739495,0.0000041125136,0.00047368847,0.2674829,0.00023525293,0.0005322387,0.63348836,0.00045241605],"about_ca_topic_score_codex":0.000013426798,"about_ca_topic_score_gemma":0.0001622804,"teacher_disagreement_score":0.9687063,"about_ca_system_score_codex":0.00007514044,"about_ca_system_score_gemma":0.000015642538,"threshold_uncertainty_score":0.82745725},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.06777325830079646,"score_gpt":0.36711674864542976,"score_spread":0.2993434903446333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057846446","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99028575,0.001946587,0.007168686,0.00022905914,0.0000073382216,0.00005695716,0.000066372224,0.0000060911216,0.00023312902],"genre_scores_gemma":[0.9917684,0.0020762808,0.0058824313,0.000026005217,0.000010809696,0.0000023825482,0.00021941608,2.8929713e-7,0.000013989744],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986024,0.00018771048,0.00043324666,0.0004708535,0.00016910823,0.00013671335],"domain_scores_gemma":[0.9984523,0.0010793307,0.00019907145,0.00017839117,0.000044648044,0.000046231315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009544163,0.00009316943,0.00039305934,0.0003384636,0.000055109544,0.000036159996,0.00022808815,0.000046369987,0.000031762364],"category_scores_gemma":[0.0007909109,0.000045629957,0.000050511997,0.0073283473,0.000059499336,0.00037652487,0.000051914914,0.00008212035,3.5244324e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011960637,0.000050988314,0.4110016,0.0000029665769,0.00004898177,0.0000011661547,0.000021293872,0.00017187612,0.0097838715,0.000834007,6.2067875e-7,0.5780707],"study_design_scores_gemma":[0.000047922662,0.000034395827,0.88356394,0.000008433888,0.00051802956,2.5739462e-7,0.0003399538,0.11454489,0.00006952192,0.00070216414,0.000088984656,0.00008149582],"about_ca_topic_score_codex":0.0001504522,"about_ca_topic_score_gemma":0.0058231233,"teacher_disagreement_score":0.5779892,"about_ca_system_score_codex":0.000011892417,"about_ca_system_score_gemma":0.0000023573803,"threshold_uncertainty_score":0.3521028},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.025546073147799032,"score_gpt":0.27256118428713894,"score_spread":0.2470151111393399,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061107170","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26063067,0.0029249233,0.7346135,0.00038117103,0.00008795833,0.00020273487,0.0006793802,0.00006770562,0.0004119503],"genre_scores_gemma":[0.98746926,0.0033193387,0.0072104707,0.0000058570263,0.0000256954,0.000020341373,0.0019090498,0.000006651907,0.000033317003],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994493,0.000016146809,0.00015338749,0.00021287246,0.000080516096,0.000087767265],"domain_scores_gemma":[0.999496,0.00009336637,0.000056261426,0.0003032996,0.000030898464,0.000020181884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020301348,0.00007515824,0.00019750786,0.00022552378,0.000030273206,0.000018362116,0.00015085553,0.00005177122,0.0000052783703],"category_scores_gemma":[0.00004844538,0.00007022228,0.000041499414,0.0005737011,0.000019637904,0.00023390682,0.00001904764,0.00005769128,6.937461e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000130603585,0.00004857813,0.62406707,0.00017910925,0.0005548287,6.596313e-8,0.00004683783,0.17592664,0.002002685,0.001354235,0.00054650713,0.19526039],"study_design_scores_gemma":[0.00008143098,0.000008986393,0.14595136,0.000007206158,0.0003782716,1.3365359e-7,0.00002677263,0.8435184,0.00015525878,0.00019834412,0.009602683,0.00007118942],"about_ca_topic_score_codex":0.000043845772,"about_ca_topic_score_gemma":0.0034412728,"teacher_disagreement_score":0.72740304,"about_ca_system_score_codex":0.000012152063,"about_ca_system_score_gemma":0.0000025837176,"threshold_uncertainty_score":0.28635818},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Lasso (programming language); Model selection; Selection (genetic algorithm); Mathematics; Computer science; Artificial intelligence; Statistics","score_opus":0.04016452122136844,"score_gpt":0.34145722688980523,"score_spread":0.3012927056684368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065708566","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00079216156,0.00088069675,0.9967263,0.0009735966,0.00003280981,0.00024586823,0.0000205581,0.000035524503,0.00029248325],"genre_scores_gemma":[0.20538168,0.0010255753,0.79286,0.0001544141,0.000024712845,0.00012991848,0.00019651755,0.0000051974284,0.0002220124],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988203,0.000078456156,0.0002639868,0.0005404883,0.0001249416,0.00017182995],"domain_scores_gemma":[0.9988116,0.00010074643,0.00014535026,0.0007928432,0.000096694814,0.000052774016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004847892,0.00011085458,0.00022455551,0.00024499153,0.000090681206,0.00016532137,0.00064924447,0.000067737084,0.0000068584873],"category_scores_gemma":[0.00007043732,0.000091741254,0.000050713108,0.0010864557,0.000026353737,0.0022163533,0.00011330469,0.00007946464,0.000003091581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010541607,0.0000832943,0.0028854616,0.00003118517,0.00011202732,1.2609871e-7,0.0001732927,0.0010339442,0.005025663,0.1659119,0.0008085767,0.823924],"study_design_scores_gemma":[0.0001841632,0.000010222973,0.0029944885,0.00000501982,0.00008944958,4.1583718e-7,0.000011481892,0.91570276,0.0001237894,0.07753825,0.0032299014,0.00011005527],"about_ca_topic_score_codex":0.00002667621,"about_ca_topic_score_gemma":0.00028912665,"teacher_disagreement_score":0.9146688,"about_ca_system_score_codex":0.00002299475,"about_ca_system_score_gemma":0.000025159128,"threshold_uncertainty_score":0.37410995},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06690308779884142,"score_gpt":0.33977078719510917,"score_spread":0.27286769939626776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074660585","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14947134,0.0040226895,0.836571,0.0018634042,0.00024190037,0.00082793523,0.00027747333,0.00014124475,0.0065830653],"genre_scores_gemma":[0.98165584,0.0013981044,0.013825078,0.000037729737,0.000064565786,0.000063393134,0.0022984738,0.000010350472,0.0006464793],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983845,0.000113867856,0.000515731,0.0005537083,0.00028119987,0.00015103679],"domain_scores_gemma":[0.9982373,0.00019828619,0.00032296067,0.0010568483,0.00012180745,0.000062806415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046617354,0.00014178245,0.00037742674,0.00065430923,0.00010673746,0.00010284876,0.0002533217,0.00008410232,0.00022642569],"category_scores_gemma":[0.00019196642,0.000109342465,0.000091593625,0.002579418,0.000048999063,0.0014341933,0.00011240218,0.000089012865,0.000018159784],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008028802,0.00077532855,0.78952825,0.00029502806,0.0043597636,0.0000034125617,0.0005515029,0.013914462,0.001139412,0.053089958,0.011766478,0.12449612],"study_design_scores_gemma":[0.00033530657,0.000013172477,0.34166598,0.000029135826,0.0029333718,9.1388733e-7,0.0008367517,0.63407433,0.000014987115,0.017390478,0.0024465201,0.0002590191],"about_ca_topic_score_codex":0.000101569545,"about_ca_topic_score_gemma":0.0014128246,"teacher_disagreement_score":0.8321845,"about_ca_system_score_codex":0.000041320953,"about_ca_system_score_gemma":0.00001239815,"threshold_uncertainty_score":0.44588563},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.030519176843317914,"score_gpt":0.3035554330616236,"score_spread":0.2730362562183057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082905687","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028994011,0.00094516005,0.9942775,0.0007521331,0.00003784075,0.00017448538,0.0000033205147,0.000051610925,0.0008585696],"genre_scores_gemma":[0.7322728,0.0012033697,0.26600772,0.000062633466,0.000023430954,0.000052195912,0.00030074417,0.0000047919802,0.00007230122],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984538,0.00021206788,0.0003290991,0.0006346769,0.00020828363,0.00016205321],"domain_scores_gemma":[0.9986732,0.000101413316,0.00022397809,0.0008443799,0.00010234444,0.000054669097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047124628,0.00012593545,0.0002050678,0.00032476344,0.00011167833,0.00020101987,0.0005820705,0.00006993581,0.000010117777],"category_scores_gemma":[0.0000681405,0.00010805596,0.000033337237,0.0014377735,0.00003613518,0.0051659183,0.00016533573,0.00015754381,0.0000071105183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034931825,0.000053131524,0.0051106797,0.000020073687,0.000056836492,6.623452e-7,0.00073769846,0.002407475,0.0042549805,0.0422409,0.00008301425,0.94503105],"study_design_scores_gemma":[0.00009620409,0.000012068764,0.017642634,0.0000082707875,0.00005359066,9.184558e-7,0.000058504804,0.9432251,0.00008765981,0.037646797,0.0010331814,0.00013508557],"about_ca_topic_score_codex":0.000040251725,"about_ca_topic_score_gemma":0.000103381455,"teacher_disagreement_score":0.944896,"about_ca_system_score_codex":0.00002418815,"about_ca_system_score_gemma":0.000014959085,"threshold_uncertainty_score":0.4406394},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03672495443431135,"score_gpt":0.317044713978554,"score_spread":0.28031975954424265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102723201","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00826274,0.0012823791,0.9885162,0.0011922547,0.00006116848,0.00020300556,0.000016070924,0.00004590951,0.00042026024],"genre_scores_gemma":[0.6973604,0.0024368668,0.29979756,0.00012181905,0.000024814304,0.000033326,0.00016209098,0.000006581074,0.000056537],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805456,0.00018715094,0.00043363028,0.000901372,0.00020025592,0.00022300241],"domain_scores_gemma":[0.9980693,0.00014173605,0.000239924,0.0013605742,0.000076024306,0.00011248118],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044628515,0.0001754733,0.0003039362,0.00041051683,0.000120995726,0.00029751836,0.0007499901,0.00009093597,0.000020960268],"category_scores_gemma":[0.000043814234,0.00015049441,0.000039944596,0.001275117,0.00008412595,0.0032797635,0.0003473224,0.00013516628,0.000009083876],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003864309,0.000037963255,0.013361536,0.000022338945,0.000076498225,4.911369e-7,0.00018569393,0.00001813141,0.0038194186,0.005668062,0.000060021728,0.97674596],"study_design_scores_gemma":[0.00015118535,0.00001068125,0.17107995,0.00000904,0.00007561298,0.0000018818112,0.000040695715,0.8215444,0.00005147794,0.0056193224,0.0012525495,0.00016321716],"about_ca_topic_score_codex":0.00006510895,"about_ca_topic_score_gemma":0.00042499215,"teacher_disagreement_score":0.97658277,"about_ca_system_score_codex":0.00003582383,"about_ca_system_score_gemma":0.000015064449,"threshold_uncertainty_score":0.61369836},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06134931625472312,"score_gpt":0.36859024644580013,"score_spread":0.307240930191077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112120651","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14563195,0.01184527,0.8092895,0.0063408376,0.00044571754,0.0016461309,0.00065296463,0.0003780425,0.02376954],"genre_scores_gemma":[0.95033157,0.00329292,0.044141322,0.00007195989,0.000073032,0.000012239577,0.0016945836,0.00000972043,0.0003726321],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865407,0.00010413432,0.00043951208,0.00045924273,0.00020808297,0.00013493063],"domain_scores_gemma":[0.99844474,0.000102061145,0.00028176003,0.0010701215,0.000054683376,0.000046632664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005760866,0.00012429003,0.0003094891,0.00025645318,0.00008558152,0.000059901897,0.00028409142,0.00008066665,0.000011914359],"category_scores_gemma":[0.00023682017,0.00009747803,0.000044069828,0.0009091358,0.00003160975,0.0009056988,0.000057399247,0.00008212253,0.0000025977681],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003716788,0.0011447907,0.04437892,0.000350941,0.00046405062,0.000016639893,0.0011376,0.0012547489,0.007826945,0.32211828,0.006547023,0.6143884],"study_design_scores_gemma":[0.0019106579,0.00009151076,0.11732121,0.00028074434,0.0013786106,0.0000064057845,0.0011455229,0.70686144,0.00025746974,0.15179448,0.018232223,0.0007197491],"about_ca_topic_score_codex":0.000008973795,"about_ca_topic_score_gemma":0.0002395462,"teacher_disagreement_score":0.80469966,"about_ca_system_score_codex":0.00003259009,"about_ca_system_score_gemma":0.000011138161,"threshold_uncertainty_score":0.39750385},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06299037588866112,"score_gpt":0.3427291082985342,"score_spread":0.27973873240987307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2353061623","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00054088514,0.00027729647,0.9919681,0.006556516,0.000019624886,0.00011607788,0.00022144642,0.00002469476,0.00027536682],"genre_scores_gemma":[0.5925219,0.0005314207,0.40605778,0.00023792959,0.000021283759,0.000019152292,0.000443716,0.000005027733,0.00016176808],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99800974,0.00010366303,0.00028874626,0.001079557,0.0003113232,0.000206954],"domain_scores_gemma":[0.9971681,0.00012159301,0.00010664057,0.0024136913,0.00007590759,0.00011401863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005835284,0.00014228282,0.00023538037,0.00022413392,0.0000787901,0.00010434863,0.0017023431,0.00005680015,0.000008239428],"category_scores_gemma":[0.000045947676,0.00008562627,0.000022648219,0.0006098505,0.00006158741,0.0029942337,0.0007362182,0.00007947163,0.000009704541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044179797,0.00013428362,0.0069208625,0.000012005486,0.0001400111,0.0000039168867,0.000089621004,0.003805961,0.0013585672,0.60501724,0.0005383099,0.38193503],"study_design_scores_gemma":[0.00023058076,0.000017152512,0.0062610754,0.000008992351,0.00010536925,0.000003883767,0.0000076167635,0.918695,0.000030191086,0.07256088,0.0019103478,0.00016897057],"about_ca_topic_score_codex":0.000013259052,"about_ca_topic_score_gemma":0.00070031366,"teacher_disagreement_score":0.914889,"about_ca_system_score_codex":0.000039330233,"about_ca_system_score_gemma":0.00006707451,"threshold_uncertainty_score":0.3491738},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.041089338011552366,"score_gpt":0.3371891365524899,"score_spread":0.29609979854093754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2609430174","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002458246,0.00072079,0.9910029,0.0049549197,0.00008999153,0.00020018805,0.000038165006,0.000024299787,0.0005105073],"genre_scores_gemma":[0.9846017,0.001613379,0.012989399,0.0002716813,0.00003722435,0.00010400058,0.000276435,0.000004776838,0.000101404374],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984591,0.000091543574,0.00031010612,0.00068745966,0.0002809839,0.00017080187],"domain_scores_gemma":[0.99653035,0.000106880594,0.00028652063,0.0029270926,0.000074100266,0.00007503053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005638076,0.000118305,0.0001962294,0.00021649981,0.00048857403,0.00051283464,0.0020657121,0.00005099061,0.0000070243836],"category_scores_gemma":[0.00020450326,0.0000830741,0.000038807986,0.0010295339,0.00010323179,0.0021181935,0.0004289081,0.00010266199,0.000040281528],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000185592,0.00007855141,0.022183841,0.000015417827,0.00006175433,0.0000012651279,0.00016781656,0.0014841988,0.00066197733,0.04110655,0.0010088955,0.93321115],"study_design_scores_gemma":[0.00015112494,0.000009468061,0.0981641,0.000012749556,0.00007491382,4.1407637e-7,0.00013015511,0.8171003,0.00015234933,0.0020376814,0.08202804,0.00013871035],"about_ca_topic_score_codex":0.0001325,"about_ca_topic_score_gemma":0.004088947,"teacher_disagreement_score":0.98214346,"about_ca_system_score_codex":0.00003584899,"about_ca_system_score_gemma":0.0000203905,"threshold_uncertainty_score":0.4945276},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; 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","score_opus":0.04408920708021554,"score_gpt":0.30893820675356276,"score_spread":0.26484899967334724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790767741","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041307858,0.0029011774,0.9929453,0.0020776172,0.00009714593,0.00014261418,0.00016199527,0.00009699073,0.0011640837],"genre_scores_gemma":[0.6937626,0.009001171,0.28990057,0.0001497276,0.00022485486,0.000058651778,0.006423358,0.000032370604,0.0004466554],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971097,0.00012977862,0.0006685615,0.0015247952,0.00032213578,0.0002450376],"domain_scores_gemma":[0.99682224,0.000057417757,0.00054315705,0.0024144426,0.00006334101,0.000099421544],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005150835,0.0002864969,0.000691583,0.0003515886,0.00013731162,0.0005765776,0.0022080299,0.00010708033,0.000031834992],"category_scores_gemma":[0.00012237199,0.00026519984,0.0001430776,0.0015420646,0.00009279507,0.0022450841,0.004392934,0.00034373216,0.000018302013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012527478,0.00023049924,0.029055858,0.00087620236,0.0037140378,0.0000570653,0.0024592816,0.064935476,0.0017739745,0.048296403,0.0008139188,0.84766203],"study_design_scores_gemma":[0.00007277453,0.000011999449,0.009191272,0.000045493274,0.00045705508,0.000001260537,0.000098014054,0.98171073,0.000014790537,0.00272351,0.005369612,0.00030350892],"about_ca_topic_score_codex":0.00006130091,"about_ca_topic_score_gemma":0.00077220966,"teacher_disagreement_score":0.9167752,"about_ca_system_score_codex":0.000045993544,"about_ca_system_score_gemma":0.00004416305,"threshold_uncertainty_score":0.99998003},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.05135122907555946,"score_gpt":0.3540267272002225,"score_spread":0.30267549812466304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888010039","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005198962,0.0022353968,0.99555343,0.0013175302,0.00006446737,0.00011187743,0.000108275366,0.000010072136,0.000079042504],"genre_scores_gemma":[0.54085183,0.0022119933,0.456569,0.00006117453,0.00005795085,0.000025948722,0.00017809295,0.0000028117724,0.000041179243],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991866,0.00007005515,0.00020998773,0.00033460624,0.00008736818,0.000111423265],"domain_scores_gemma":[0.9984034,0.000275139,0.00013948804,0.001076288,0.00008166929,0.000024057525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005444879,0.000070874354,0.0001636304,0.000087904256,0.000126419,0.00005218945,0.0007424978,0.000035093457,0.000002579504],"category_scores_gemma":[0.00012378472,0.000048009893,0.000043440457,0.000901714,0.00010240833,0.000526144,0.0001762643,0.000045727116,4.0346535e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023780956,0.000060194678,0.0027068679,0.000029774828,0.00018257642,2.0228521e-7,0.0003976642,0.0002588177,0.0037941302,0.3142064,0.00029509445,0.6780445],"study_design_scores_gemma":[0.00014448562,0.000013752344,0.009194069,0.000006781815,0.0001552974,4.7653052e-7,0.000022146725,0.9572683,0.00041078022,0.009455794,0.023257118,0.00007099455],"about_ca_topic_score_codex":0.000019115096,"about_ca_topic_score_gemma":0.00081110065,"teacher_disagreement_score":0.9570095,"about_ca_system_score_codex":0.000008757225,"about_ca_system_score_gemma":0.000014274887,"threshold_uncertainty_score":0.19577867},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; 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","score_opus":0.04467400490465936,"score_gpt":0.3678903485041041,"score_spread":0.3232163435994448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891365885","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025167179,0.0063599865,0.9897391,0.0002898215,0.0002260959,0.00021934538,0.0003878228,0.000028713526,0.00023236722],"genre_scores_gemma":[0.47912657,0.009791402,0.50993323,0.000030133615,0.000041676227,0.00001067414,0.0009557945,0.000010139183,0.00010041367],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971559,0.00030813375,0.00070943584,0.0013013508,0.0003242035,0.00020094539],"domain_scores_gemma":[0.9953215,0.00021095821,0.0007477511,0.0035361324,0.00011840014,0.00006524362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009005688,0.00025879164,0.00076789176,0.00068699085,0.00003793219,0.00014237278,0.0022033579,0.00023459517,0.000015344123],"category_scores_gemma":[0.00012549905,0.00021870238,0.0001544544,0.0012695685,0.00007489824,0.0008215855,0.001393934,0.00034136735,0.0000028152326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006707089,0.00044362908,0.04105168,0.0010797285,0.0022724096,0.000007548884,0.001300456,0.011171809,0.006304374,0.1263597,0.00027679693,0.8096648],"study_design_scores_gemma":[0.0001798341,0.000015119673,0.028130524,0.00005857535,0.00051172666,5.036781e-7,0.000020768271,0.9442941,0.00031742023,0.024476383,0.0016785734,0.000316484],"about_ca_topic_score_codex":0.00009683098,"about_ca_topic_score_gemma":0.000162292,"teacher_disagreement_score":0.9331223,"about_ca_system_score_codex":0.000033978158,"about_ca_system_score_gemma":0.00010260409,"threshold_uncertainty_score":0.8918424},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0354850183539955,"score_gpt":0.31527472121398364,"score_spread":0.27978970285998817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990751717","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008765176,0.002345034,0.9853937,0.0024317985,0.000118106866,0.00022568119,0.00042405076,0.000052826883,0.000243598],"genre_scores_gemma":[0.49483755,0.01033553,0.48855007,0.00082025054,0.00007595777,0.00002100666,0.0049773487,0.000016254768,0.00036603288],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99775815,0.000045856057,0.00033455217,0.0012934195,0.00035222003,0.00021579253],"domain_scores_gemma":[0.9968434,0.000078004196,0.00021091952,0.002736243,0.00008149642,0.000049941515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005163235,0.00017475974,0.0002802095,0.00019434698,0.00009763656,0.00042817302,0.0020879111,0.00004318513,0.000014580913],"category_scores_gemma":[0.00007525357,0.00015299155,0.000014691094,0.0013210935,0.00007955178,0.0124877915,0.0035281326,0.00010548496,0.00001503971],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001652698,0.00015825745,0.023267705,0.00033909568,0.00030883984,0.000010778941,0.00048861175,0.0008527351,0.000200702,0.006122715,0.0007680287,0.967466],"study_design_scores_gemma":[0.00028169862,0.000019990744,0.03521664,0.000047402755,0.00011333838,0.0000029168984,0.00011023435,0.9488339,0.000039233535,0.0014266595,0.013678622,0.00022937325],"about_ca_topic_score_codex":0.00018540888,"about_ca_topic_score_gemma":0.0003261496,"teacher_disagreement_score":0.96723664,"about_ca_system_score_codex":0.000019156643,"about_ca_system_score_gemma":0.000038567672,"threshold_uncertainty_score":0.9053347},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.03703733615695371,"score_gpt":0.31498423960111605,"score_spread":0.27794690344416234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041023245","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006952481,0.00021141859,0.9910444,0.0014604817,0.000016405658,0.0000937155,0.00003902663,0.000020011725,0.00016202846],"genre_scores_gemma":[0.9610749,0.0007142229,0.037550423,0.00007446986,0.000015892261,0.000012731108,0.0005423628,0.000001985477,0.000013032609],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99935025,0.000043335156,0.00013534584,0.00032036728,0.00008467794,0.00006599852],"domain_scores_gemma":[0.9995088,0.00008201617,0.0001488012,0.00016536812,0.000066467976,0.000028553552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000114199596,0.000051591873,0.000130514,0.00009869188,0.000050543826,0.000026418526,0.00023646849,0.000037309106,0.0000071760805],"category_scores_gemma":[0.00009531237,0.000045884608,0.000024962495,0.0008356209,0.000033317127,0.0009849126,0.000057406756,0.0000730571,0.0000010310744],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004919716,0.00004224829,0.011031867,0.000043352047,0.00010263752,2.0420295e-7,0.00043034044,0.00032809866,0.02183682,0.005505817,0.00032403952,0.9603054],"study_design_scores_gemma":[0.00023966706,0.00003867721,0.011752672,0.000013697753,0.00008526795,2.161535e-7,0.0003460536,0.9742479,0.0052034315,0.0008491254,0.007147717,0.000075603784],"about_ca_topic_score_codex":0.0000023821774,"about_ca_topic_score_gemma":0.00002390055,"teacher_disagreement_score":0.97391975,"about_ca_system_score_codex":0.0000071032023,"about_ca_system_score_gemma":0.000013247672,"threshold_uncertainty_score":0.187112},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.07372087970399593,"score_gpt":0.3428838780099273,"score_spread":0.2691629983059314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119925796","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017174196,0.007425544,0.9891021,0.0013603751,0.00012912502,0.000062143496,0.000048038743,0.00003000739,0.00012524493],"genre_scores_gemma":[0.19581445,0.019027706,0.7782718,0.00023761914,0.00010158708,0.000027709712,0.0061804666,0.0000097407155,0.00032891778],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982135,0.00022224642,0.00027599436,0.0009447007,0.00020478053,0.00013876798],"domain_scores_gemma":[0.99779534,0.00006476693,0.00012910021,0.0018990426,0.00006364409,0.000048124697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007501735,0.00011054587,0.00021127345,0.00015051755,0.00011538986,0.00019374107,0.0007997204,0.000052446107,0.00001101275],"category_scores_gemma":[0.00006616033,0.000099630895,0.000026546244,0.0012718029,0.00003501187,0.002364284,0.00074710674,0.00009473329,0.000002247399],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011523251,0.00011325901,0.008111451,0.000030644886,0.00016160336,0.0000034925356,0.00015128491,0.00018301349,0.013931154,0.010934081,0.0015915764,0.96477693],"study_design_scores_gemma":[0.00018687546,0.000005489797,0.008393896,0.000008574115,0.00012203511,0.0000049631035,0.000035665762,0.96521074,0.0004191233,0.0030370427,0.022431318,0.00014428704],"about_ca_topic_score_codex":0.00008318118,"about_ca_topic_score_gemma":0.0019128231,"teacher_disagreement_score":0.9650277,"about_ca_system_score_codex":0.000028482447,"about_ca_system_score_gemma":0.000043138294,"threshold_uncertainty_score":0.406283},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.053565366313241526,"score_gpt":0.36025569701971255,"score_spread":0.306690330706471,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126183644","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011081129,0.0013447038,0.98640764,0.00052613486,0.00009652943,0.000103774284,0.00005829574,0.000047707497,0.0003340819],"genre_scores_gemma":[0.93380857,0.00062707346,0.065186545,0.000041686155,0.000015832082,0.00005068858,0.00014611761,0.00000566454,0.00011784994],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844915,0.00013059586,0.00025018287,0.00065160927,0.00031407716,0.00020438866],"domain_scores_gemma":[0.99842274,0.00012433672,0.000109506145,0.0012719334,0.000023916187,0.00004754801],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054850226,0.00008563674,0.00016542169,0.00035174473,0.00024564355,0.000082248494,0.0012653265,0.000015692127,0.000014584888],"category_scores_gemma":[0.00005678923,0.00008972069,0.000024991961,0.001626731,0.000060126844,0.0007518104,0.002097455,0.00016773632,0.0000026692712],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018820405,0.00008613971,0.011633455,0.000020920503,0.00006165215,0.000042302767,0.00023300051,0.022836113,0.0012320436,0.0026855622,0.00003614254,0.96111387],"study_design_scores_gemma":[0.00014640059,0.000020847858,0.013683039,0.0000023836928,0.000020800491,0.000017578981,0.00020922121,0.97436863,0.000028153954,0.0005126451,0.010879119,0.00011118691],"about_ca_topic_score_codex":0.000024295667,"about_ca_topic_score_gemma":0.0003516591,"teacher_disagreement_score":0.96100265,"about_ca_system_score_codex":0.00008235084,"about_ca_system_score_gemma":0.00002479426,"threshold_uncertainty_score":0.36587036},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Multivariate statistics; Cluster (spacecraft); Statistics; Line (geometry); Econometrics; Computer science; Mathematics; Programming language; Geometry","score_opus":0.2059572849996396,"score_gpt":0.45221873836132187,"score_spread":0.24626145336168226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200498417","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015974753,0.00021973025,0.9816148,0.0009383769,0.00013027329,0.000127238,0.00030679588,0.000034102846,0.00065388466],"genre_scores_gemma":[0.9164014,0.00025718272,0.08161585,0.000067885136,0.000030126586,0.000029410005,0.0012599524,0.0000054762127,0.00033273967],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979625,0.0001547283,0.00057132787,0.0007966957,0.00036344593,0.00015134054],"domain_scores_gemma":[0.99747974,0.0004947345,0.00022546816,0.0014034525,0.00032140658,0.000075227756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010603085,0.000102215316,0.00023907854,0.00033094548,0.00022374671,0.00021642649,0.00050049904,0.000049443093,0.000047539826],"category_scores_gemma":[0.0011122247,0.00008665877,0.0000568761,0.004331267,0.00005382087,0.0010787235,0.00032083734,0.000105604224,0.000009886865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008849773,0.00077246287,0.04984137,0.000013884213,0.0002743156,0.0000057831917,0.0005543814,0.06717389,0.019319415,0.09290442,0.012892901,0.7561587],"study_design_scores_gemma":[0.00008183689,0.0000045816946,0.014455,0.000013304028,0.00011604731,0.0000023982936,0.00019543868,0.9447105,0.0002778078,0.026028236,0.014008364,0.00010648875],"about_ca_topic_score_codex":0.0001259829,"about_ca_topic_score_gemma":0.0020999894,"teacher_disagreement_score":0.9004266,"about_ca_system_score_codex":0.00005972941,"about_ca_system_score_gemma":0.000042820102,"threshold_uncertainty_score":0.35338423},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.034786673591868544,"score_gpt":0.32444836377708386,"score_spread":0.2896616901852153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4304806684","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02241561,0.00040872878,0.97638136,0.00052508287,0.000033964912,0.00010482988,0.0000525027,0.000017480425,0.0000604553],"genre_scores_gemma":[0.96470594,0.00012500591,0.03361324,0.0002742678,0.000008015204,0.000020252535,0.0012263859,0.00000255711,0.000024337192],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989925,0.000048855574,0.00027082334,0.0003349465,0.0002486911,0.00010415137],"domain_scores_gemma":[0.9991204,0.00012331513,0.00018338619,0.0005210144,0.000023691358,0.00002817746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008255333,0.000073409545,0.00013947434,0.0004015766,0.000233189,0.00015995376,0.0003598009,0.00001616117,0.000007489708],"category_scores_gemma":[0.000052881995,0.00007178403,0.00003578321,0.0007872966,0.0000145806725,0.0014507388,0.0002165784,0.00006804402,5.1856864e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012388405,0.00018718529,0.008549796,0.000062712505,0.0002468012,0.0000010146813,0.0036838108,0.5996198,0.0010577283,0.072123505,0.00026995857,0.3140738],"study_design_scores_gemma":[0.0002594739,0.000014657045,0.0012554383,0.0000048967777,0.000082955565,1.3883398e-7,0.0004977383,0.9961899,0.000060847502,0.0004906481,0.0010574681,0.00008583856],"about_ca_topic_score_codex":0.000006069756,"about_ca_topic_score_gemma":0.000014210911,"teacher_disagreement_score":0.9427681,"about_ca_system_score_codex":0.00003755178,"about_ca_system_score_gemma":0.00001573389,"threshold_uncertainty_score":0.29272678},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.023172619704976628,"score_gpt":0.3273198306380522,"score_spread":0.30414721093307556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309346662","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00386551,0.0029818006,0.99157286,0.0009016966,0.0000532479,0.00006938912,0.00035264666,0.000016110356,0.00018673616],"genre_scores_gemma":[0.8385336,0.0009306381,0.1597092,0.000023921632,0.000013127471,0.000022858936,0.00069598196,0.0000027058484,0.00006798015],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874014,0.00019230042,0.0002675198,0.00044426403,0.00021867304,0.00013708773],"domain_scores_gemma":[0.9985855,0.00008779094,0.00019234867,0.0010591741,0.00003564835,0.00003949555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064630574,0.000082122075,0.00020509206,0.00019672603,0.0001543742,0.000037361056,0.0007462246,0.000026729193,0.000015374366],"category_scores_gemma":[0.0000388962,0.0000779227,0.000046683304,0.0018362268,0.00005077658,0.0007702144,0.0005376408,0.00013710125,4.793905e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029935763,0.0003683829,0.034857206,0.000037144477,0.00021696386,0.000011462626,0.0006199892,0.0012826481,0.002421475,0.637034,0.00083387253,0.32228693],"study_design_scores_gemma":[0.0004537415,0.000067250476,0.06779222,0.000008147104,0.00042634143,0.000015230001,0.00033661257,0.84996057,0.00037031175,0.027484644,0.052725233,0.00035969733],"about_ca_topic_score_codex":0.000028340924,"about_ca_topic_score_gemma":0.00020255511,"teacher_disagreement_score":0.84867793,"about_ca_system_score_codex":0.000028340008,"about_ca_system_score_gemma":0.00003222933,"threshold_uncertainty_score":0.31775954},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"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","score_opus":0.16832838724178958,"score_gpt":0.48285519578488406,"score_spread":0.31452680854309445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309636459","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027303887,0.00031186588,0.9937934,0.00045805887,0.00009159976,0.0011729106,0.00095930055,0.000036458354,0.00044597208],"genre_scores_gemma":[0.36749297,0.00018309233,0.63023233,0.000052602718,0.000013115258,0.0012447966,0.0005912455,0.000016625987,0.00017324272],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99720794,0.00046212872,0.0007809598,0.0009408996,0.0003308213,0.00027726401],"domain_scores_gemma":[0.99583024,0.0023221276,0.00041302943,0.0012433511,0.000107453736,0.000083794854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002753358,0.0001915504,0.00071122794,0.00021427672,0.00031249545,0.00004182408,0.00046618795,0.000049168277,0.00007120394],"category_scores_gemma":[0.0030416152,0.00016694091,0.00012384242,0.0007212989,0.00012611267,0.00043327594,0.00026763979,0.00024184678,3.26879e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079861545,0.0016705,0.004323861,0.00025155675,0.00047607053,0.0000032149428,0.00025588935,0.0069872243,0.0005515909,0.91527206,0.000292741,0.06911666],"study_design_scores_gemma":[0.001978014,0.00007558787,0.002509926,0.000005351586,0.0005536989,5.7724003e-7,0.0006332072,0.7326756,0.0000021946303,0.25314972,0.008234122,0.00018196735],"about_ca_topic_score_codex":0.000005943617,"about_ca_topic_score_gemma":0.00017903231,"teacher_disagreement_score":0.7256884,"about_ca_system_score_codex":0.00021705627,"about_ca_system_score_gemma":0.00006909018,"threshold_uncertainty_score":0.6807653},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.039099777819178984,"score_gpt":0.3375096525388514,"score_spread":0.2984098747196724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313595020","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003229025,0.001537202,0.9905525,0.0043131486,0.00003512985,0.000087133354,0.00003919507,0.00006710374,0.00013959418],"genre_scores_gemma":[0.8519482,0.011987506,0.13192941,0.0002808451,0.00008830884,0.000070736976,0.0030723053,0.000010885566,0.00061182416],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988252,0.00015971129,0.00015988687,0.00050498446,0.0001943542,0.0001558942],"domain_scores_gemma":[0.9984569,0.00008851672,0.00011555368,0.0012662115,0.00003628891,0.000036513222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006800695,0.00010044579,0.00016918576,0.00012474587,0.00015908049,0.000117386204,0.0007781711,0.000044264674,0.0000024072258],"category_scores_gemma":[0.000032411706,0.000054269087,0.000027691189,0.002893465,0.0000592595,0.0009098543,0.00020852132,0.00009941906,0.0000029594457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023421122,0.000039978982,0.005318692,0.000017065431,0.0000966321,0.0000045188276,0.00023778854,0.00039530863,0.0016319915,0.18125899,0.003394098,0.80758154],"study_design_scores_gemma":[0.00026125915,0.000017095625,0.050201546,0.000021182495,0.00016112096,0.0000029548937,0.00006673606,0.8712477,0.0003737993,0.01176464,0.065702826,0.00017911626],"about_ca_topic_score_codex":0.000013699005,"about_ca_topic_score_gemma":0.00017426432,"teacher_disagreement_score":0.8708524,"about_ca_system_score_codex":0.000014738471,"about_ca_system_score_gemma":0.00001755279,"threshold_uncertainty_score":0.22130291},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.09709102288779793,"score_gpt":0.3592540555855143,"score_spread":0.2621630326977164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376255225","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004974793,0.0005203408,0.9979611,0.00031598404,0.000037845657,0.00004857881,0.0005304995,0.000019244691,0.00006894475],"genre_scores_gemma":[0.69298977,0.0004966792,0.30325118,0.000012450278,0.000009296819,0.0000051626917,0.0032220539,0.0000023072246,0.000011103381],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988616,0.000069636226,0.0003235128,0.00046736977,0.00017834455,0.00009951037],"domain_scores_gemma":[0.99774957,0.00013163645,0.00018631945,0.0018439309,0.00005971002,0.000028832923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007190524,0.0000714598,0.00019993963,0.00026534416,0.00004668143,0.00002051057,0.0010267118,0.000037074296,0.0000028849827],"category_scores_gemma":[0.000082495964,0.0000636797,0.000030738396,0.0017258943,0.00006953242,0.0009309011,0.00049261365,0.00005640831,5.5701054e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033085416,0.00021930301,0.009734415,0.00016765957,0.0002367004,0.0000013893662,0.000106713334,0.10722319,0.021126494,0.09392529,0.0006172267,0.76660854],"study_design_scores_gemma":[0.00009348555,0.000005314222,0.014002148,0.0000107902,0.000088948334,2.0509981e-7,0.000006484017,0.9751299,0.00025686427,0.010063786,0.00028119545,0.000060855164],"about_ca_topic_score_codex":0.000014611297,"about_ca_topic_score_gemma":0.00021276924,"teacher_disagreement_score":0.86790675,"about_ca_system_score_codex":0.000008898389,"about_ca_system_score_gemma":0.00003665416,"threshold_uncertainty_score":0.25967827},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.04852271423534097,"score_gpt":0.3659672425237264,"score_spread":0.31744452828838543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387095339","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006040089,0.00047960656,0.99266106,0.00048419033,0.00003131881,0.000118716955,0.00014127532,0.000022462104,0.000021267813],"genre_scores_gemma":[0.5513983,0.0006426534,0.4473392,0.0000109627335,0.0000064560427,0.000024515952,0.0005630404,0.000001979357,0.000012900681],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909043,0.00006982466,0.00025699695,0.00037368323,0.000089436115,0.00011961243],"domain_scores_gemma":[0.99887824,0.00034737008,0.00013624837,0.00056154124,0.000043203123,0.000033410917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005830365,0.0000734142,0.00017844903,0.00018733428,0.000072250325,0.00005477617,0.00030284643,0.000040803625,8.233116e-7],"category_scores_gemma":[0.00024820075,0.00006288299,0.000030488589,0.0009470413,0.000057411264,0.0009616387,0.00013944086,0.000041830805,3.955403e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012265539,0.000044694996,0.004828525,0.000044405937,0.00008932892,3.080383e-7,0.00018187962,0.00048346576,0.0023631426,0.19755495,0.00008864588,0.7943084],"study_design_scores_gemma":[0.00014322418,0.0000125558945,0.0627138,0.000007966669,0.00011655443,2.7605125e-7,0.000012969227,0.8876049,0.00046750478,0.04809254,0.0007584865,0.00006923314],"about_ca_topic_score_codex":0.000013692767,"about_ca_topic_score_gemma":0.00006461652,"teacher_disagreement_score":0.88712144,"about_ca_system_score_codex":0.0000071385825,"about_ca_system_score_gemma":0.000010599314,"threshold_uncertainty_score":0.25642937},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.05659637533914804,"score_gpt":0.33905421800217767,"score_spread":0.28245784266302965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389888669","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.081619866,0.001010908,0.9132318,0.0031101676,0.000028884417,0.00024384106,0.00030002766,0.00017386036,0.00028065644],"genre_scores_gemma":[0.96115446,0.0017543166,0.03347698,0.000047818347,0.000010067952,0.00001678831,0.0034943777,0.0000054669727,0.000039750088],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998321,0.00012472497,0.0003567482,0.0007733195,0.00030729707,0.00011690012],"domain_scores_gemma":[0.99729455,0.00020210647,0.00028404925,0.002084116,0.00009255255,0.000042606865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009373218,0.00010713773,0.00023821901,0.00046326435,0.000071561735,0.000092080154,0.0010668397,0.00005159778,0.000005180569],"category_scores_gemma":[0.00008338087,0.00008889627,0.000012591492,0.0022771196,0.00011220029,0.002592635,0.0005918288,0.0000858841,0.0000031295],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086292355,0.00031693402,0.101068534,0.0001313212,0.00046166332,0.0000059911977,0.00066154846,0.0031790151,0.013987954,0.31073833,0.0033861317,0.5659763],"study_design_scores_gemma":[0.00017197846,0.000028941344,0.26746908,0.000023778348,0.00008922293,0.0000015017707,0.00014164222,0.72525734,0.00033733208,0.0030636822,0.003287242,0.00012827195],"about_ca_topic_score_codex":0.00004998143,"about_ca_topic_score_gemma":0.0006827355,"teacher_disagreement_score":0.8797548,"about_ca_system_score_codex":0.000011178215,"about_ca_system_score_gemma":0.000041479496,"threshold_uncertainty_score":0.36250848},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Cluster analysis; Inference; Computer science; Artificial intelligence; Data mining; Machine learning","score_opus":0.08627126853721646,"score_gpt":0.3698520144562673,"score_spread":0.28358074591905086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396529244","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000021493992,0.003181879,0.9949618,0.00091866864,0.00019804314,0.00004581369,0.00008020679,0.000047695834,0.00054440607],"genre_scores_gemma":[0.31595886,0.0019782071,0.6797007,0.00009113339,0.00009721537,0.000010402698,0.0020766188,0.0000045260012,0.000082326835],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847806,0.00008306338,0.00025803593,0.0008552686,0.00020871664,0.00011685765],"domain_scores_gemma":[0.99797016,0.00023492365,0.000060760445,0.001661822,0.000032073087,0.00004028079],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008757208,0.00009231056,0.00013954146,0.000263785,0.00006868417,0.00028128963,0.001157301,0.00004215574,0.000023352282],"category_scores_gemma":[0.00007723209,0.000080551945,0.000020286032,0.0012707771,0.000033033022,0.0038363286,0.0007876622,0.00011566379,0.000008540397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025344384,0.00002267433,0.0021023245,0.00002214398,0.00008487708,0.000002220068,0.00004863716,0.0005393791,0.00018838084,0.16845778,0.00014921265,0.8283798],"study_design_scores_gemma":[0.000042185162,0.000003515567,0.027115336,0.000013021591,0.00008017376,0.0000025046768,0.000003991246,0.9366771,0.0000030722365,0.024563426,0.0114028575,0.0000928085],"about_ca_topic_score_codex":0.000016025499,"about_ca_topic_score_gemma":0.00032155516,"teacher_disagreement_score":0.93613774,"about_ca_system_score_codex":0.000021773058,"about_ca_system_score_gemma":0.000050667117,"threshold_uncertainty_score":0.3284813},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Multinomial distribution; Dirichlet distribution; Mathematics; Econometrics; Mathematical analysis","score_opus":0.04164186050322628,"score_gpt":0.3451560601491029,"score_spread":0.3035141996458766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400011049","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021674736,0.010279588,0.9872217,0.0008912098,0.000041829648,0.00015917668,0.00007355732,0.000051266365,0.0010649074],"genre_scores_gemma":[0.5465232,0.0071497215,0.44572473,0.00011670979,0.000073436975,0.00007185662,0.00023620104,0.000006775919,0.000097377066],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986279,0.00009406106,0.00024162364,0.00078161637,0.00012532309,0.00012949792],"domain_scores_gemma":[0.99875426,0.00024242667,0.000067614645,0.0008424127,0.000034163302,0.0000591437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041733618,0.00011983563,0.00020329586,0.00025270507,0.00009760929,0.00029488248,0.0005358549,0.000058235702,0.0000020838947],"category_scores_gemma":[0.000018915165,0.00010061124,0.000030512418,0.0012350893,0.0000871606,0.0021079006,0.000252333,0.00013706935,0.0000019875545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025877698,0.000025748044,0.0002887306,0.000027899297,0.000069881964,0.0000018245802,0.00025087388,0.00014744,0.00021554797,0.34713808,0.00009393197,0.65173745],"study_design_scores_gemma":[0.00007377808,0.000004952909,0.0015106347,0.000011897685,0.000110770015,0.0000019620695,0.000031184438,0.84317917,0.000023198158,0.13938989,0.015549164,0.000113401824],"about_ca_topic_score_codex":0.00002087851,"about_ca_topic_score_gemma":0.00020574113,"teacher_disagreement_score":0.8430317,"about_ca_system_score_codex":0.000020200405,"about_ca_system_score_gemma":0.000022628376,"threshold_uncertainty_score":0.41028073},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.1106521907296518,"score_gpt":0.39391825692417415,"score_spread":0.2832660661945223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403793086","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022305192,0.0028941708,0.99399394,0.00036081244,0.000094320094,0.00018180233,0.00008897216,0.000083191815,0.00007227846],"genre_scores_gemma":[0.8218928,0.0037611085,0.17349073,0.00003380478,0.000057944257,0.000112837246,0.00035370537,0.000013561958,0.00028351418],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982603,0.00003571996,0.0003125142,0.0008694025,0.0002675817,0.00025447074],"domain_scores_gemma":[0.9986327,0.00012867272,0.000059234302,0.0010667623,0.00004788631,0.00006468582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004919061,0.00012530062,0.00020139824,0.00041148707,0.00009624384,0.00031526433,0.00091973704,0.00004483496,0.0000014169848],"category_scores_gemma":[0.000042703323,0.00011687625,0.000054126383,0.0010137138,0.00005205139,0.0020079971,0.00046189365,0.00011662819,0.0000059200315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038133374,0.000105328814,0.0005508971,0.00024046545,0.00027288412,0.000015273032,0.0005921093,0.27290946,0.00873776,0.009510467,0.0001898523,0.70683736],"study_design_scores_gemma":[0.00013958453,0.000013853992,0.00091816095,0.000027814547,0.000061204046,0.0000020176017,0.000038909388,0.9932954,0.00007059254,0.0015430724,0.0037534337,0.00013600617],"about_ca_topic_score_codex":0.00001096731,"about_ca_topic_score_gemma":0.00017188226,"teacher_disagreement_score":0.8205032,"about_ca_system_score_codex":0.00006436358,"about_ca_system_score_gemma":0.0000412907,"threshold_uncertainty_score":0.4766075},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.052200240792401084,"score_gpt":0.3365206615945156,"score_spread":0.2843204208021145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407498245","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005710316,0.004230565,0.9915176,0.0009189952,0.00008002145,0.00018843297,0.000030337302,0.00002890243,0.0024341298],"genre_scores_gemma":[0.9247416,0.0036076657,0.07096878,0.0001848559,0.000020147321,0.000053775548,0.0003383746,0.0000021855499,0.000082577186],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876636,0.00005198847,0.00031944166,0.00059438864,0.00011156996,0.00015627117],"domain_scores_gemma":[0.9984388,0.00031313283,0.00011905194,0.0010293031,0.000068160654,0.00003159472],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005863271,0.000095898366,0.0002580617,0.00030814408,0.00016659645,0.00012889353,0.0007314798,0.000047724985,0.0000010492031],"category_scores_gemma":[0.00014074003,0.000078166784,0.00005105996,0.001370326,0.00004262792,0.0014301644,0.00024938356,0.00006806314,3.6651159e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007454485,0.000098237266,0.008015384,0.000047556612,0.0001600093,0.0000011351117,0.00013675982,0.033077925,0.00011108202,0.17925885,0.0005300593,0.77848846],"study_design_scores_gemma":[0.000760702,0.0000057854436,0.010269964,0.00001659315,0.00013982216,2.6193905e-7,0.00008946963,0.9423291,0.000003962161,0.04182717,0.0044704047,0.00008675858],"about_ca_topic_score_codex":0.00001973735,"about_ca_topic_score_gemma":0.00029709653,"teacher_disagreement_score":0.9241706,"about_ca_system_score_codex":0.00001587189,"about_ca_system_score_gemma":0.000028106817,"threshold_uncertainty_score":0.3187549},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.09468252969729223,"score_gpt":0.3986018150346892,"score_spread":0.303919285337397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410920770","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001399341,0.0009905266,0.99657315,0.00060580217,0.00009909812,0.00018657742,0.00003814236,0.000026328491,0.000081055594],"genre_scores_gemma":[0.7883241,0.00067489065,0.21051128,0.000028321303,0.000008981265,0.00003427511,0.00035672757,0.000003904143,0.000057506222],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998602,0.00007170324,0.00038115468,0.0006155725,0.00017309554,0.00015652893],"domain_scores_gemma":[0.9977986,0.0003435829,0.0001736069,0.0014637832,0.00019165743,0.000028728302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007282557,0.00009228375,0.00023367858,0.0004744635,0.00008273157,0.00006631353,0.0010203299,0.000050514136,0.0000012482006],"category_scores_gemma":[0.0003614655,0.00009222626,0.00003814689,0.002260755,0.00007912428,0.00092275743,0.00030661013,0.00007833189,5.714208e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009822736,0.00023047617,0.022337018,0.00044094995,0.00017757098,6.462937e-7,0.0000657501,0.06547756,0.009222901,0.036211815,0.00007663969,0.8656604],"study_design_scores_gemma":[0.00022086574,0.000017078946,0.030201219,0.000027051085,0.00005896796,8.6290655e-8,0.000042685348,0.9622673,0.0017152996,0.0019789254,0.0033902777,0.00008026157],"about_ca_topic_score_codex":0.000019052015,"about_ca_topic_score_gemma":0.0005105329,"teacher_disagreement_score":0.8967897,"about_ca_system_score_codex":0.000045725214,"about_ca_system_score_gemma":0.00006128224,"threshold_uncertainty_score":0.37608778},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.04371606132484556,"score_gpt":0.35820006926448344,"score_spread":0.3144840079396379,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416664067","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15600128,0.018118907,0.8202986,0.0012549522,0.00008051469,0.0007814444,0.0008383157,0.000027964832,0.0025979865],"genre_scores_gemma":[0.9700208,0.012142056,0.004079203,0.00006594024,0.000026079746,0.000084064886,0.0133710615,0.00000673392,0.00020406797],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986485,0.00006560219,0.00028140808,0.0007913672,0.00009146596,0.0001216588],"domain_scores_gemma":[0.9978922,0.000028123677,0.00014547323,0.0018611433,0.00004212317,0.000030917687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022139544,0.00011781312,0.00017419805,0.00027293054,0.000069099566,0.00003545015,0.00064553536,0.00008204431,0.000003895722],"category_scores_gemma":[0.000054028333,0.00009373429,0.000015918597,0.0009316706,0.00009131808,0.000044871595,0.00028628454,0.000076923105,9.63899e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003161228,0.00046149033,0.60087836,0.00013225057,0.0003101368,0.0000016966649,0.00007322144,0.005047634,0.20567769,0.007598767,0.0022097907,0.17729284],"study_design_scores_gemma":[0.00091958145,0.00004222035,0.406303,0.00009418023,0.0004599224,0.00000118679,0.0013642724,0.07820422,0.0034983146,0.0007776644,0.507939,0.00039644202],"about_ca_topic_score_codex":0.000021600523,"about_ca_topic_score_gemma":0.0036752091,"teacher_disagreement_score":0.81621945,"about_ca_system_score_codex":0.000027302944,"about_ca_system_score_gemma":0.00007634482,"threshold_uncertainty_score":0.38223734},"labels":[],"label_agreement":null}]}