{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":40,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":40,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"47001aa2d831","filters":{"venue":"Advances in Data Analysis and Classification"}},"results":[{"id":"W1997354990","doi":"10.1007/s11634-013-0139-1","title":"Estimating common principal components in high dimensions","year":2013,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"","keywords":"Convergence (economics); Principal component analysis; Majorization; Orthonormal basis; Mathematical optimization; Simple (philosophy); Cluster analysis; Minification; Computer science; Matrix (chemical analysis); Function (biology); Mathematics; Algorithm; Artificial intelligence","authors":[{"name":"Ryan P. Browne","is_ca":true},{"name":"Paul D. McNicholas","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05393879753402075,"gpt":0.3370129092875392,"spread":0.2830741117535184,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00753192,0.002091794,0.003357604,0.003852696,0.001494899,0.003625935,0.002957196,0.002680634,0.001561746],"category_scores_gemma":[0.0335472,0.001870248,0.002867298,0.004644762,0.002506052,0.005637416,0.004340088,0.004284294,0.000998782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009701941,"about_ca_system_score_gemma":0.002106128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005776784,"about_ca_topic_score_gemma":0.006505601,"domain_scores_codex":[0.994212,0.002859949,0.0004110298,0.001081906,0.001114398,0.0003207461],"domain_scores_gemma":[0.9782326,0.0163379,0.001114746,0.00234136,0.00163789,0.0003355247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004839246,0.0003944511,0.008977471,0.0008383442,0.0007109278,0.0002775374,0.0009530223,0.4116863,0.006055087,0.1198556,0.00772257,0.4420449],"study_design_scores_gemma":[0.0000293445,0.0000349473,0.001550609,0.00004854618,0.00005933584,0.00009357566,0.0001096842,0.8646457,0.0008817219,0.1309422,0.001552417,0.00005170341],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008128011,0.0005022664,0.9908482,0.0001254214,0.00002140641,0.00002321256,0.00005501074,0.0001292158,0.0001672073],"genre_scores_gemma":[0.1866393,0.001887521,0.8075024,0.0001812837,0.0002572765,0.0003756192,0.001101561,0.0002253854,0.001829726],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00753192,"threshold_uncertainty_score":0.03983313,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2065708566","doi":"10.1007/s11634-013-0155-1","title":"A LASSO-penalized BIC for mixture model selection","year":2013,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"","keywords":"Lasso (programming language); Model selection; Selection (genetic algorithm); Mathematics; Computer science; Artificial intelligence; Statistics","authors":[{"name":"Sakyajit Bhattacharya","is_ca":true},{"name":"Paul D. McNicholas","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04016452122136844,"gpt":0.3414572268898052,"spread":0.3012927056684368,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01173313,0.002041687,0.00389001,0.002406634,0.001723203,0.002857681,0.005500396,0.003192741,0.006356998],"category_scores_gemma":[0.03979413,0.001675904,0.002102177,0.003109239,0.001907303,0.002678585,0.005531386,0.007030465,0.004031744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001132333,"about_ca_system_score_gemma":0.003643443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005393117,"about_ca_topic_score_gemma":0.008165307,"domain_scores_codex":[0.9883373,0.007835603,0.0004284114,0.0009649674,0.00208611,0.0003475723],"domain_scores_gemma":[0.9885582,0.006629931,0.000385454,0.001504465,0.002457001,0.000464972],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008140252,0.0003916768,0.002031547,0.0006353387,0.0006790624,0.0002607791,0.0003693659,0.379583,0.005785726,0.1555263,0.04292194,0.4110012],"study_design_scores_gemma":[0.00004142516,0.00004377523,0.0002382526,0.00005064406,0.0000366133,0.00008976458,0.0000237265,0.9455036,0.0006646877,0.05020513,0.003056814,0.00004566369],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0009504786,0.0002067855,0.9976071,0.000205962,0.00006079603,0.00003718826,0.00008079899,0.0003799548,0.0004710528],"genre_scores_gemma":[0.05332834,0.0004324702,0.9379418,0.0006264013,0.0002992085,0.0005547467,0.00130173,0.001017357,0.004497998],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01173313,"threshold_uncertainty_score":0.06205148,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2102723201","doi":"10.1007/s11634-013-0124-8","title":"Clustering and classification via cluster-weighted factor analyzers","year":2013,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"","keywords":"Cluster analysis; Mixture model; Expectation–maximization algorithm; Pattern recognition (psychology); Covariance matrix; Covariance; Latent variable; Ranking (information retrieval); Fuzzy clustering","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.03672495443431135,"gpt":0.317044713978554,"spread":0.2803197595442427,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007909577,0.001650219,0.001816836,0.004424331,0.001417054,0.00340909,0.002748349,0.001454451,0.003442097],"category_scores_gemma":[0.02991197,0.0009174381,0.002473462,0.004993352,0.001690049,0.004283885,0.003277497,0.002439454,0.001919965],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009859847,"about_ca_system_score_gemma":0.001952761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004016915,"about_ca_topic_score_gemma":0.004531449,"domain_scores_codex":[0.9927346,0.003250446,0.0004710254,0.001595014,0.001616129,0.0003329008],"domain_scores_gemma":[0.9903898,0.005241272,0.0005653328,0.001245765,0.002353479,0.000204407],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007525697,0.0002147263,0.003105762,0.0002607504,0.000564081,0.0001345276,0.0006881983,0.1003728,0.01327359,0.1244728,0.004745431,0.7514148],"study_design_scores_gemma":[0.0000393616,0.00004843883,0.001097208,0.00003162779,0.000108322,0.0001078422,0.0001147671,0.8420078,0.003513041,0.1501734,0.002699435,0.00005880538],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002505711,0.00008065372,0.9967979,0.00004097323,0.00001071012,0.000030799,0.000039066,0.0002762012,0.0002180726],"genre_scores_gemma":[0.08463693,0.0002492234,0.9127181,0.00007391344,0.00006172367,0.0002819456,0.0004701904,0.0003058965,0.001202065],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007909577,"threshold_uncertainty_score":0.04183036,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1964231120","doi":"10.1007/s11634-014-0165-7","title":"Variational Bayes approximations for clustering via mixtures of normal inverse Gaussian distributions","year":2014,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"","keywords":"Bayes' theorem; Gaussian; Univariate; Applied mathematics; Cluster analysis; Mixture model; Inverse Gaussian distribution; Multivariate normal distribution; Mathematics; Inverse; Inverse problem; Multivariate statistics; Mathematical optimization; Computer science; Statistics; Distribution (mathematics); Mathematical analysis; Bayesian probability; Chemistry; Computational chemistry","authors":[{"name":"Sanjeena Subedi","is_ca":true},{"name":"Paul D. McNicholas","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02808600709019208,"gpt":0.3141116705601102,"spread":0.2860256634699181,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01072123,0.001901564,0.00403691,0.003678869,0.001567718,0.004480257,0.007006572,0.003645211,0.003283729],"category_scores_gemma":[0.03816178,0.00281741,0.003833889,0.003978901,0.003986657,0.006767203,0.004178036,0.007167796,0.0016083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004440893,"about_ca_system_score_gemma":0.003170539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01891154,"about_ca_topic_score_gemma":0.0205848,"domain_scores_codex":[0.9943641,0.003066254,0.0002788938,0.0009192177,0.001089635,0.0002818704],"domain_scores_gemma":[0.9847596,0.0114281,0.0006497463,0.001346876,0.001489021,0.0003265611],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001424107,0.00008258574,0.0009468427,0.000282504,0.0002116961,0.00004816417,0.0004719657,0.5851262,0.0008111953,0.3268229,0.004470282,0.0805833],"study_design_scores_gemma":[0.00001064568,0.000007232966,0.0001074029,0.00002609196,0.00001511307,0.00001938942,0.00001886896,0.8813138,0.0001388404,0.1174018,0.0009240475,0.00001681808],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001197622,0.000353605,0.9978762,0.0001036547,0.00002161824,0.00001951124,0.00004155043,0.00009896346,0.0002873029],"genre_scores_gemma":[0.1154626,0.001886026,0.8745106,0.0002697157,0.0003252232,0.000469622,0.001167782,0.0005825007,0.005325856],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01891154,"threshold_uncertainty_score":0.05669999,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1972256887","doi":"10.1007/s11634-015-0204-z","title":"A mixture of generalized hyperbolic factor analyzers","year":2015,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Bayesian information criterion; Mixture model; Hyperbolic function; Cluster analysis; Gaussian; Generalized inverse Gaussian distribution; Maximization; Expectation–maximization algorithm","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.07739344212886445,"gpt":0.3564501671026479,"spread":0.2790567249737834,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006069948,0.001429688,0.001899252,0.002423189,0.001340263,0.004325124,0.003402245,0.002346258,0.008299369],"category_scores_gemma":[0.01843472,0.001383459,0.002489727,0.003026334,0.00256162,0.006548292,0.004272107,0.002902353,0.003184758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001285023,"about_ca_system_score_gemma":0.001803274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003893228,"about_ca_topic_score_gemma":0.003312906,"domain_scores_codex":[0.9947247,0.002200027,0.0002725328,0.00138582,0.001055517,0.0003614211],"domain_scores_gemma":[0.9929157,0.003344555,0.0003285444,0.001435089,0.001616453,0.0003594976],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008261484,0.0001594402,0.006130991,0.00024287,0.0004441124,0.0003622912,0.0007172791,0.08510745,0.01399834,0.5273771,0.006837149,0.3577969],"study_design_scores_gemma":[0.00003594207,0.00008120538,0.0009212317,0.00004543754,0.0001017574,0.000386671,0.0001169875,0.7880461,0.003240573,0.2009909,0.005937116,0.00009612975],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005721012,0.0001627543,0.9924744,0.0001219152,0.00002966796,0.00003845117,0.00007171569,0.0003037979,0.001076238],"genre_scores_gemma":[0.2519441,0.0008674809,0.7311154,0.0004595966,0.0002257763,0.0002546762,0.00063065,0.0006352412,0.01386713],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008299369,"threshold_uncertainty_score":0.03210133,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2061107170","doi":"10.1007/s11634-014-0168-4","title":"Feature selection for fault level diagnosis of planetary gearboxes","year":2014,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Gear and Bearing Dynamics Analysis","field":"Engineering","cited_by":33,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Feature selection; Pattern recognition (psychology); Feature (linguistics); Fault (geology); Computer science; Artificial intelligence; Kernel (algebra); Minimum redundancy feature selection; Similarity (geometry); Selection (genetic algorithm); Feature vector; Feature extraction; Ranking (information retrieval); Algorithm; Data mining; Mathematics","authors":[{"name":"Zhiliang Liu","is_ca":false},{"name":"Xiaomin Zhao","is_ca":true},{"name":"Ming J. Zuo","is_ca":true},{"name":"Hongbing Xu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02554607314779903,"gpt":0.2725611842871389,"spread":0.2470151111393399,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000599621,0.0005375102,0.0008145125,0.001259856,0.0002677834,0.0005612024,0.0004436581,0.0003551446,0.001099729],"category_scores_gemma":[0.002012222,0.0001345511,0.0004549178,0.0006980528,0.0001578752,0.0004139912,0.0003600461,0.0004001456,0.0003275687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001802432,"about_ca_system_score_gemma":0.0003266061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001493328,"about_ca_topic_score_gemma":0.001187697,"domain_scores_codex":[0.9996734,0.00005976977,0.0000391338,0.00006645783,0.0001062263,0.00005511724],"domain_scores_gemma":[0.9990742,0.0005439704,0.00006799604,0.0000804157,0.000192913,0.0000404455],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008771881,0.0002633136,0.01374992,0.0001740966,0.00009955946,0.0002634012,0.00008133008,0.04169902,0.05032932,0.0006690455,0.004670557,0.8871232],"study_design_scores_gemma":[0.00004197871,0.0002488607,0.02491604,0.00002111543,0.00008003488,0.0002775705,0.0000828025,0.9458085,0.02476136,0.001999629,0.001739826,0.00002233148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.363656,0.001172175,0.6305453,0.0002466464,0.0001309205,0.00006747674,0.001040363,0.002151455,0.0009896485],"genre_scores_gemma":[0.953136,0.0001569682,0.04475262,0.0000304551,0.00004358812,0.00003948226,0.001101898,0.0000373037,0.0007016862],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001493328,"threshold_uncertainty_score":0.003678977,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2027846664","doi":"10.1007/s11634-012-0110-6","title":"Time series classification by class-specific Mahalanobis distance measures","year":2012,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Mahalanobis distance; Covariance matrix; Dynamic time warping; Covariance; Pattern recognition (psychology); Series (stratigraphy); k-nearest neighbors algorithm; Margin (machine learning)","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.03447962751202253,"gpt":0.2752292003416775,"spread":0.240749572829655,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001978007,0.0006995988,0.0009237257,0.003597757,0.0006462683,0.002111334,0.0009113082,0.001047442,0.001523852],"category_scores_gemma":[0.007447287,0.0001786865,0.001185421,0.003312698,0.0005216214,0.002018635,0.0009542584,0.001219943,0.001424776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006291059,"about_ca_system_score_gemma":0.000775134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001354882,"about_ca_topic_score_gemma":0.001513549,"domain_scores_codex":[0.9978111,0.0004662678,0.0002745534,0.0004608075,0.0008619557,0.0001253985],"domain_scores_gemma":[0.9972531,0.0008680813,0.0002942668,0.0004646489,0.001029697,0.00009019436],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004324056,0.0003326479,0.01662831,0.0003115177,0.0003833321,0.00008988371,0.0002806281,0.0491658,0.01723975,0.01780066,0.006301923,0.8910331],"study_design_scores_gemma":[0.00001711575,0.0001975224,0.01872346,0.0000561855,0.0001078848,0.0003021366,0.0002819299,0.9355018,0.01468467,0.02479894,0.005242471,0.00008588527],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1014182,0.0009042564,0.8921347,0.0002353061,0.0002254643,0.0001342109,0.0006766318,0.0009954716,0.003275762],"genre_scores_gemma":[0.6742879,0.0008103878,0.3173637,0.00008677576,0.0001985215,0.0003110074,0.002842909,0.0002139807,0.00388477],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003597757,"threshold_uncertainty_score":0.01046085,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1994281788","doi":"10.1007/s11634-014-0182-6","title":"Mixture model averaging for clustering","year":2014,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University; University of Guelph","funders":"","keywords":"Cluster analysis; Mixture model; Model selection; Bayesian information criterion; Pattern recognition (psychology); Bayesian probability; Rand index; Closeness; Single-linkage clustering","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.04141965676927712,"gpt":0.3381464725389695,"spread":0.2967268157696924,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006213329,0.00192812,0.004913501,0.004395217,0.001754555,0.003106258,0.004763944,0.003299264,0.003907935],"category_scores_gemma":[0.02098458,0.001872896,0.003574226,0.00663276,0.002266364,0.00487944,0.003423433,0.00568718,0.002751433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002263075,"about_ca_system_score_gemma":0.00196348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009253786,"about_ca_topic_score_gemma":0.008729414,"domain_scores_codex":[0.9942139,0.002626828,0.0003173823,0.001228602,0.001396735,0.00021653],"domain_scores_gemma":[0.9925,0.004041153,0.0003757376,0.001630711,0.001289783,0.0001626256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001439985,0.00008894203,0.0007286933,0.0006135478,0.0006140641,0.00007531377,0.0002954455,0.2851124,0.00317624,0.3712723,0.0160521,0.3218271],"study_design_scores_gemma":[0.000008676136,0.00001494823,0.0002785522,0.0000341739,0.0000517553,0.00004563636,0.00001398891,0.7879755,0.0008179138,0.2048595,0.00585945,0.00004001728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004849828,0.001002409,0.997735,0.00009090996,0.00005319141,0.00001346866,0.0000464115,0.0002264237,0.0003472153],"genre_scores_gemma":[0.05342329,0.003053226,0.9353981,0.0002791935,0.0005472989,0.0003798727,0.001291358,0.0008382494,0.004789365],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009253786,"threshold_uncertainty_score":0.03285956,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1973247608","doi":"10.1007/s11634-013-0137-3","title":"Dimension reduction for model-based clustering via mixtures of multivariate $$t$$ t -distributions","year":2013,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"","keywords":"Dimensionality reduction; Cluster analysis; Subspace topology; Dimension (graph theory); Mixture model; Mathematics; Gaussian; Reduction (mathematics); Clustering high-dimensional data; Eigenvalues and eigenvectors; Data set; Curse of dimensionality; Algorithm; Multivariate normal distribution; Pattern recognition (psychology); Computer science; Multivariate statistics; Artificial intelligence; Statistics; Combinatorics; Physics","authors":[{"name":"Katherine Morris","is_ca":true},{"name":"Paul D. McNicholas","is_ca":true},{"name":"Luca Scrucca","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03849028777574721,"gpt":0.3380154403337114,"spread":0.2995251525579642,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005381884,0.001588288,0.002795683,0.002246988,0.00162221,0.002821217,0.003298984,0.002215198,0.00194345],"category_scores_gemma":[0.02138951,0.00148622,0.004931434,0.002717648,0.001733172,0.003383893,0.00473338,0.005299333,0.001367863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001771148,"about_ca_system_score_gemma":0.002233796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006043152,"about_ca_topic_score_gemma":0.006206737,"domain_scores_codex":[0.9947396,0.002720426,0.0003583889,0.000868594,0.001091775,0.0002212527],"domain_scores_gemma":[0.9916093,0.005275462,0.0004669073,0.001460576,0.0009457963,0.0002419402],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003872689,0.0002602938,0.002158423,0.0004750349,0.0005553988,0.0001195116,0.0006240212,0.5362306,0.005529373,0.1338432,0.01034125,0.3094756],"study_design_scores_gemma":[0.00001101595,0.00001607277,0.0002205252,0.00001540985,0.00002638947,0.00004011266,0.00001875106,0.9416967,0.0005990653,0.05653613,0.0007966928,0.00002313319],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002219324,0.0001726335,0.9970881,0.000117907,0.00001930327,0.00002208547,0.00005632671,0.0001932196,0.000111023],"genre_scores_gemma":[0.09811257,0.0006339349,0.8974491,0.0002358408,0.0001429237,0.0005050857,0.00120928,0.0004088729,0.001302342],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006043152,"threshold_uncertainty_score":0.02846247,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2112120651","doi":"10.1007/s11634-009-0056-5","title":"Regularized fuzzy clusterwise ridge regression","year":2009,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Fuzzy Systems and Optimization","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Multicollinearity; Ordinary least squares; Fuzzy logic; Statistics; Regression analysis; Mathematics; Linear regression; Regression; Cluster analysis; Regression diagnostic; Local regression; Fuzzy clustering; Data mining; Polynomial regression; Computer science; Artificial intelligence","authors":[{"name":"Hye Won Suk","is_ca":true},{"name":"Heungsun Hwang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06134931625472312,"gpt":0.3685902464458001,"spread":0.307240930191077,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004149397,0.0005855731,0.001647048,0.0008667912,0.0004654595,0.001205444,0.00160862,0.001048943,0.001444261],"category_scores_gemma":[0.00744277,0.0004463839,0.001142848,0.001073154,0.00117274,0.001074536,0.001436768,0.001487071,0.0005571151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005887095,"about_ca_system_score_gemma":0.0009929484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001386951,"about_ca_topic_score_gemma":0.001687466,"domain_scores_codex":[0.9983321,0.0006639203,0.00008013029,0.0003373717,0.0004655404,0.000120918],"domain_scores_gemma":[0.9964377,0.001077845,0.0002853857,0.0009794986,0.001127922,0.00009161613],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000601325,0.0001408393,0.00301511,0.0002528203,0.0003537226,0.0001457764,0.0001747366,0.5920129,0.0192677,0.1143568,0.00582763,0.2638508],"study_design_scores_gemma":[0.000006892353,0.0000241181,0.0003360315,0.000005189861,0.00001333967,0.00002497468,0.000006755847,0.9863944,0.001556025,0.01108302,0.0005394538,0.00000969173],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01803867,0.0001840432,0.980794,0.00009909261,0.00003948686,0.00001437835,0.00006137837,0.0002329186,0.0005359954],"genre_scores_gemma":[0.4531646,0.0003469692,0.5406927,0.0001278939,0.0001820025,0.00009640268,0.0005058295,0.0002546202,0.00462899],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004149397,"threshold_uncertainty_score":0.02194434,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1990989764","doi":"10.1007/s11634-012-0108-0","title":"Adaptation of interval PCA to symbolic histogram variables","year":2012,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Hôpital Saint-François d'Assise","funders":"","keywords":"Principal component analysis; Histogram; Symbolic data analysis; Mathematics; Projection (relational algebra); Representation (politics); Pattern recognition (psychology); Interval (graph theory); Artificial intelligence; Algorithm; Computer science; Statistics; Combinatorics","authors":[{"name":"Sun Makosso‐Kallyth","is_ca":true},{"name":"Edwin Diday","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05461420121741699,"gpt":0.3280499556074983,"spread":0.2734357543900813,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006543301,0.0004911057,0.0005849643,0.0008448911,0.0002705738,0.0008958235,0.001015983,0.0003065857,0.003878416],"category_scores_gemma":[0.004369394,0.0002261049,0.0006408197,0.001722267,0.0004485486,0.001044546,0.001189364,0.001309866,0.001300883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002285816,"about_ca_system_score_gemma":0.0005750516,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001815573,"about_ca_topic_score_gemma":0.001655492,"domain_scores_codex":[0.9994085,0.0001629049,0.00002771686,0.0001427126,0.0002058567,0.00005223011],"domain_scores_gemma":[0.9989171,0.0002937554,0.0000479238,0.0003333714,0.0003584502,0.00004949838],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002136151,0.0001499288,0.001414172,0.0001149226,0.0000789679,0.00007266406,0.0000942049,0.07943669,0.019132,0.01868819,0.003966426,0.8766381],"study_design_scores_gemma":[0.0000147521,0.00006766618,0.002463425,0.0000119639,0.00002721752,0.00009473828,0.00002618077,0.9725105,0.004984131,0.01580672,0.003967138,0.0000256384],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01353473,0.0001959604,0.9830343,0.00005738418,0.0001158127,0.00003408061,0.0001087994,0.0009170456,0.002002024],"genre_scores_gemma":[0.4214427,0.0008092537,0.5707063,0.0001082906,0.0003597115,0.0001973696,0.0008992968,0.0006372371,0.004839857],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003878416,"threshold_uncertainty_score":0.01297456,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1875624538","doi":"10.1007/s11634-015-0219-5","title":"Factor probabilistic distance clustering (FPDC): a new clustering method","year":2015,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Università degli Studi di Napoli Federico II","keywords":"Cluster analysis; Correlation clustering; CURE data clustering algorithm; Single-linkage clustering; Probabilistic logic; Canopy clustering algorithm; Computer science; Data stream clustering; Fuzzy clustering; Determining the number of clusters in a data set; Clustering high-dimensional data; k-medians clustering; Transformation (genetics); Mathematics; Pattern recognition (psychology); Data mining; Artificial intelligence","authors":[{"name":"Cristina Tortora","is_ca":true},{"name":"Mireille Gettler Summa","is_ca":false},{"name":"Marina Marino","is_ca":false},{"name":"Francesco Palumbo","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1223525331876487,"gpt":0.4083881885969034,"spread":0.2860356554092547,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003778153,0.001651355,0.002357854,0.004552346,0.002273035,0.002663393,0.003781514,0.002633164,0.002269584],"category_scores_gemma":[0.01006012,0.0008283834,0.002251578,0.007889587,0.00191876,0.003343272,0.003421049,0.003131452,0.002072471],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001588143,"about_ca_system_score_gemma":0.003317046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00695526,"about_ca_topic_score_gemma":0.006318159,"domain_scores_codex":[0.9926645,0.001718713,0.0004203482,0.001765367,0.003192136,0.0002389112],"domain_scores_gemma":[0.9955818,0.001092435,0.0003546501,0.001032431,0.0017796,0.0001590322],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002777667,0.0001161251,0.002149991,0.0006989858,0.0003766307,0.00009979348,0.0004075757,0.08116129,0.008370257,0.06646979,0.01916501,0.8207068],"study_design_scores_gemma":[0.0000643426,0.0001748436,0.001919891,0.000127623,0.0002036109,0.0009411274,0.0001695635,0.8280228,0.009874055,0.09945981,0.05880877,0.0002335353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001195118,0.0007192656,0.9967601,0.0001268068,0.0001219096,0.00005409133,0.000117448,0.0003584719,0.0005468645],"genre_scores_gemma":[0.03915475,0.001205466,0.9558839,0.0001815532,0.000273096,0.0002045026,0.0006311561,0.0002979931,0.002167532],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00695526,"threshold_uncertainty_score":0.01998109,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2057846446","doi":"10.1007/s11634-009-0054-7","title":"Tests of ignoring and eliminating in nonsymmetric correspondence analysis","year":2009,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Sensory Analysis and Statistical Methods","field":"Agricultural and Biological Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Contingency table; Residual; Contingency; Row; Table (database); Correspondence analysis; Test (biology); Mathematics; Econometrics; Statistics; Computer science; Algorithm; Data mining; Epistemology","authors":[{"name":"Yoshio Takane","is_ca":true},{"name":"Sunho Jung","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06777325830079646,"gpt":0.3671167486454298,"spread":0.2993434903446333,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1008185,0.001596526,0.002696299,0.004592804,0.004481687,0.004700281,0.004404558,0.003132294,0.007654856],"category_scores_gemma":[0.4591068,0.0008446871,0.003992441,0.005633133,0.01519198,0.009585312,0.00672,0.006790774,0.0006789374],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001687341,"about_ca_system_score_gemma":0.003761027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00146547,"about_ca_topic_score_gemma":0.0009296139,"domain_scores_codex":[0.7809508,0.1397617,0.01435314,0.03147719,0.02958273,0.003874331],"domain_scores_gemma":[0.2049822,0.7404242,0.01352696,0.02977983,0.008444496,0.002842291],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.009920369,0.001579242,0.2723689,0.00206746,0.007796431,0.005270192,0.01024566,0.02329415,0.01294513,0.3500842,0.009477292,0.294951],"study_design_scores_gemma":[0.0007977926,0.003917983,0.115105,0.0004010817,0.001350892,0.002789754,0.005620055,0.1448899,0.01111158,0.7034617,0.01003668,0.000517469],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5268863,0.0008944632,0.4483539,0.002245605,0.0007813001,0.0009609953,0.00129056,0.0005511821,0.01803566],"genre_scores_gemma":[0.929972,0.0001292737,0.06652335,0.0005969481,0.0002741492,0.0007638178,0.0008264178,0.0001776865,0.0007363779],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.1008185,"threshold_uncertainty_score":0.5331855,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2004773941","doi":"10.1007/s11634-009-0046-7","title":"Parsimonious cluster systems","year":2009,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Saint Paul University","funders":"","keywords":"Bijection; Set (abstract data type); Cluster (spacecraft); Cluster analysis; Phylogenetic tree; Computer science; Combinatorics; Tree (set theory); Mathematics; Theoretical computer science; Biology; Artificial intelligence; Genetics","authors":[{"name":"François Brucker","is_ca":false},{"name":"Alain Gély","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0299105014580019,"gpt":0.3081043677348245,"spread":0.2781938662768226,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00206463,0.0007526736,0.001443988,0.002624195,0.0044756,0.003083754,0.00315229,0.001845445,0.01779564],"category_scores_gemma":[0.01265275,0.0008135227,0.0009691936,0.003480742,0.002141717,0.0042084,0.005456557,0.002399822,0.003996974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001220879,"about_ca_system_score_gemma":0.00163633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001847877,"about_ca_topic_score_gemma":0.003662731,"domain_scores_codex":[0.9977663,0.0007014115,0.0001272974,0.0005891153,0.0005636182,0.0002522292],"domain_scores_gemma":[0.9936168,0.001509587,0.0002974354,0.002636782,0.001393872,0.0005455425],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007157352,0.0001136812,0.00324291,0.0002923218,0.0001409931,0.0002760017,0.001112958,0.06115267,0.005251992,0.7358726,0.018846,0.1729821],"study_design_scores_gemma":[0.00008046757,0.0001108239,0.001370211,0.00004282012,0.00005878577,0.0003322695,0.0002902407,0.2643508,0.002081293,0.709029,0.02220149,0.00005180445],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06363475,0.0007909833,0.911894,0.001104639,0.000278029,0.0003211832,0.0008778848,0.001636708,0.01946173],"genre_scores_gemma":[0.4594582,0.0005254091,0.5052471,0.0004091971,0.0001991763,0.0004650775,0.002484122,0.0006811668,0.03053056],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01779564,"threshold_uncertainty_score":0.05953228,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2016714679","doi":"10.1007/s11634-010-0083-2","title":"Generalized GIPSCAL re-revisited: a fast convergent algorithm with acceleration by the minimal polynomial extrapolation","year":2011,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Analytical Chemistry and Chromatography","field":"Chemistry","cited_by":10,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Korea Institute of Energy Research","keywords":"Extrapolation; Acceleration; Diagonal; Positive definiteness; Algorithm; Representation (politics); Polynomial; Mathematics; Time complexity; Matrix (chemical analysis); Computational complexity theory; Convergence (economics); Applied mathematics; Computer science; Mathematical analysis; Geometry; Positive-definite matrix","authors":[{"name":"Sébastien Loisel","is_ca":false},{"name":"Yoshio Takane","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03893491462284368,"gpt":0.2847833179878061,"spread":0.2458484033649624,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001288773,0.001261482,0.001683063,0.001093916,0.0007890523,0.001201863,0.002471613,0.001318228,0.008340525],"category_scores_gemma":[0.005473914,0.0004964425,0.0009891825,0.001519283,0.0007540517,0.001281099,0.002461435,0.002640448,0.003989259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005732554,"about_ca_system_score_gemma":0.002282296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004641566,"about_ca_topic_score_gemma":0.007381017,"domain_scores_codex":[0.999244,0.000216244,0.00003870369,0.0001184419,0.0002981919,0.00008448344],"domain_scores_gemma":[0.998717,0.0003982656,0.00005964315,0.0003714567,0.0003724073,0.00008126652],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008863381,0.0001925649,0.001104145,0.0003966451,0.0001569467,0.0003292676,0.0002457584,0.1470604,0.01600688,0.04374998,0.02329189,0.7665792],"study_design_scores_gemma":[0.00007612089,0.00007254833,0.0002097312,0.00002140864,0.00002141324,0.0001222748,0.00003204234,0.9752192,0.005518249,0.01214049,0.006542898,0.00002366927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009341317,0.0003242138,0.9851313,0.0002370373,0.0001633371,0.00007324365,0.000104689,0.002547387,0.002077571],"genre_scores_gemma":[0.0688623,0.0001507077,0.9255678,0.0001645738,0.00008862489,0.0001436446,0.0003119409,0.0008580252,0.003852332],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008340525,"threshold_uncertainty_score":0.02790189,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2888010039","doi":"10.1007/s11634-018-0333-2","title":"Subspace clustering for the finite mixture of generalized hyperbolic distributions","year":2018,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Mixture model; Mathematics; Subspace topology; Applied mathematics; Hyperbolic function; Gaussian; Finite element method; Extension (predicate logic); Mathematical analysis; Computer science; Statistics; Physics","authors":[{"name":"Nam‐Hwui Kim","is_ca":true},{"name":"Ryan P. Browne","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05135122907555946,"gpt":0.3540267272002225,"spread":0.302675498124663,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007026915,0.001213174,0.002559379,0.003090153,0.001534034,0.00309868,0.004380107,0.002382828,0.003864953],"category_scores_gemma":[0.02137806,0.001264386,0.003061007,0.00282982,0.003150081,0.004783451,0.004131792,0.003914506,0.001760068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002338896,"about_ca_system_score_gemma":0.002376851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008353349,"about_ca_topic_score_gemma":0.008369314,"domain_scores_codex":[0.9955986,0.002379004,0.0002220899,0.0008580683,0.0007269824,0.0002152848],"domain_scores_gemma":[0.9904374,0.005746431,0.0006485922,0.001598688,0.001182813,0.0003860082],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002080582,0.00009597844,0.001581629,0.0003143442,0.0002564047,0.00007829454,0.0005372898,0.4240179,0.002229314,0.4474622,0.004406297,0.1188123],"study_design_scores_gemma":[0.000008261008,0.00001173581,0.0002029862,0.00001697647,0.00001250833,0.00002660505,0.0000295763,0.8667464,0.0002319217,0.1317184,0.000967546,0.00002717176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003349117,0.000236801,0.9957947,0.0001011064,0.00001448692,0.000027778,0.00007061401,0.0001442552,0.000261136],"genre_scores_gemma":[0.1931338,0.001456522,0.7947109,0.0002797144,0.0002350282,0.0005927373,0.001880886,0.0006390075,0.007071392],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008353349,"threshold_uncertainty_score":0.0371623,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3119925796","doi":"10.1007/s11634-020-00432-5","title":"Functional data clustering by projection into latent generalized hyperbolic subspaces","year":2021,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Linear subspace; Projection (relational algebra); Dimension (graph theory); Basis (linear algebra); Mathematics; Clustering high-dimensional data; Computer science; Applied mathematics; Pattern recognition (psychology); Algorithm; Artificial intelligence; Combinatorics; Pure mathematics","authors":[{"name":"Alex Sharp","is_ca":true},{"name":"Ryan P. Browne","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07372087970399593,"gpt":0.3428838780099273,"spread":0.2691629983059314,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004697367,0.001081122,0.00174132,0.002402109,0.001102105,0.002333311,0.002328334,0.00115384,0.001996169],"category_scores_gemma":[0.01054606,0.00114595,0.002373074,0.002392168,0.002530766,0.003309672,0.004857969,0.002713906,0.0008902682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001122664,"about_ca_system_score_gemma":0.001706185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003392217,"about_ca_topic_score_gemma":0.002925285,"domain_scores_codex":[0.9961728,0.002270163,0.0001739831,0.0006615818,0.0005734573,0.0001480055],"domain_scores_gemma":[0.9951956,0.002343928,0.000378317,0.001097938,0.0007891793,0.0001950227],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000336078,0.0001809043,0.003055003,0.0004013847,0.0004345978,0.0001044312,0.001079868,0.3426888,0.006467077,0.3244637,0.003881836,0.3169063],"study_design_scores_gemma":[0.00001089205,0.00002756881,0.000400703,0.00002079979,0.00001917687,0.00004291565,0.00006567218,0.8750829,0.0007551656,0.1224943,0.001050658,0.00002927453],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00349009,0.0000609708,0.9960813,0.00005302835,0.000005555524,0.00002118165,0.00003515478,0.00009588221,0.0001569204],"genre_scores_gemma":[0.2077168,0.0004942819,0.787617,0.0001101688,0.00007710472,0.000369252,0.0008116728,0.0003716488,0.002432064],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004697367,"threshold_uncertainty_score":0.02484232,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2074660585","doi":"10.1007/s11634-013-0126-6","title":"Functional fuzzy clusterwise regression analysis","year":2013,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Fuzzy Systems and Optimization","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University; McGill University","funders":"","keywords":"Fuzzy logic; Regression analysis; Regression; Function (biology); Computer science; Data mining; Mathematics; Mathematical optimization; Statistics; Artificial intelligence","authors":[{"name":"Tianyu Tan","is_ca":true},{"name":"Hye Won Suk","is_ca":true},{"name":"Heungsun Hwang","is_ca":true},{"name":"Jooseop Lim","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06690308779884142,"gpt":0.3397707871951092,"spread":0.2728676993962678,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008975799,0.001256322,0.001947972,0.002704692,0.0009737163,0.001627964,0.002064614,0.001082458,0.003623448],"category_scores_gemma":[0.0169161,0.0005025953,0.001810965,0.002514661,0.001516832,0.001722032,0.001646042,0.002196217,0.001219645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001237761,"about_ca_system_score_gemma":0.001655965,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002437465,"about_ca_topic_score_gemma":0.001958241,"domain_scores_codex":[0.9953672,0.002795091,0.0001619026,0.0006682365,0.0008314513,0.0001762525],"domain_scores_gemma":[0.9917437,0.003956578,0.0004584107,0.001481313,0.002209027,0.0001509314],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004322935,0.0001306417,0.003521316,0.0005519594,0.0007514685,0.0001479464,0.0002708862,0.2184053,0.006486703,0.3971244,0.01255927,0.3596179],"study_design_scores_gemma":[0.00001489031,0.00007956688,0.001647939,0.00004068362,0.0001040807,0.0000953355,0.00005002399,0.8898934,0.003038222,0.09959567,0.005404671,0.00003547456],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005668289,0.0004365663,0.9922655,0.0001752977,0.00006743444,0.00002547451,0.00007847563,0.0002194323,0.001063552],"genre_scores_gemma":[0.3449507,0.001421835,0.6393348,0.0003042216,0.0004722566,0.0003104015,0.001186474,0.0006490854,0.01137009],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008975799,"threshold_uncertainty_score":0.04746914,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2082905687","doi":"10.1007/s11634-013-0152-4","title":"Infinite Dirichlet mixture models learning via expectation propagation","year":2013,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Dirichlet process; Mixture model; Model selection; Dirichlet distribution; Computer science; Hierarchical Dirichlet process; Inference; Automatic summarization; Cluster analysis; Bayesian inference; Minimum description length; Artificial intelligence; Latent Dirichlet allocation; Data mining; Selection (genetic algorithm); Synthetic data; Machine learning; Bayesian probability; Topic model; Mathematics","authors":[{"name":"Wentao Fan","is_ca":true},{"name":"Nizar Bouguila","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03051917684331791,"gpt":0.3035554330616236,"spread":0.2730362562183057,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009573735,0.001870275,0.00482599,0.003270885,0.001611129,0.004529855,0.006645836,0.003988808,0.004819538],"category_scores_gemma":[0.03479207,0.002593705,0.003377579,0.004297863,0.003481496,0.008995174,0.00505566,0.0071494,0.002241221],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002411637,"about_ca_system_score_gemma":0.002277368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006404571,"about_ca_topic_score_gemma":0.009121533,"domain_scores_codex":[0.9926249,0.004136672,0.0003628814,0.001350019,0.001166619,0.0003588374],"domain_scores_gemma":[0.9733279,0.02263919,0.0007508483,0.001583438,0.001395915,0.0003026846],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003472658,0.0002169459,0.001558091,0.0003685621,0.0003328364,0.0001374787,0.0004615,0.4553556,0.0009176211,0.352229,0.007576832,0.1804982],"study_design_scores_gemma":[0.00001970947,0.00001044046,0.0001038736,0.00002810284,0.00002429293,0.00003078115,0.00001342922,0.83741,0.0002479044,0.1610682,0.001018398,0.00002484266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001668642,0.0003744709,0.9970862,0.0002222114,0.00002806746,0.00001701212,0.00005878383,0.0001780583,0.0003664835],"genre_scores_gemma":[0.2049044,0.00255463,0.7782052,0.0008312665,0.0007445607,0.0007768663,0.001901872,0.0005728711,0.009508403],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009573735,"threshold_uncertainty_score":0.0506314,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2609430174","doi":"10.1007/s11634-017-0286-x","title":"Local generalized quadratic distance metrics: application to the k-nearest neighbors classifier","year":2017,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; University of Alberta","funders":"","keywords":"k-nearest neighbors algorithm; Metric (unit); Curse of dimensionality; Computer science; Mathematics; Artificial intelligence; Algorithm; Pattern recognition (psychology)","authors":[{"name":"Karim T. Abou–Moustafa","is_ca":true},{"name":"Frank P. Ferrie","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04108933801155237,"gpt":0.3371891365524899,"spread":0.2960997985409375,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00289624,0.0005635872,0.001783171,0.001932335,0.0008106453,0.00164025,0.001655589,0.001057819,0.0015112],"category_scores_gemma":[0.01125266,0.0002611639,0.0006417136,0.002730469,0.000857917,0.001989581,0.001660727,0.001084542,0.0007494597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001095037,"about_ca_system_score_gemma":0.001596332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007449297,"about_ca_topic_score_gemma":0.00758002,"domain_scores_codex":[0.9971367,0.0008895987,0.0001845852,0.0003410667,0.001362382,0.00008564015],"domain_scores_gemma":[0.9954803,0.001690959,0.0003184446,0.0004231805,0.001937118,0.0001499619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002357273,0.0001897508,0.003625311,0.0003301128,0.000109122,0.0001044932,0.0003008085,0.1798418,0.00680084,0.04227563,0.007809927,0.7583765],"study_design_scores_gemma":[0.000009836979,0.00006229608,0.001051745,0.00001571404,0.00001392944,0.0001032698,0.00004887582,0.9796543,0.001241154,0.01534797,0.002427018,0.00002384713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0206105,0.001212596,0.9757326,0.0002144159,0.00007803053,0.00005802288,0.0001236867,0.0003883278,0.001581919],"genre_scores_gemma":[0.3620388,0.0008857284,0.632534,0.00009333518,0.0001455306,0.0001482374,0.0004802608,0.0002535486,0.003420584],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007449297,"threshold_uncertainty_score":0.01531696,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4304806684","doi":"10.1007/s11634-022-00522-6","title":"On smoothing and scaling language model for sentiment based information retrieval","year":2022,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Sentiment analysis; Latent Dirichlet allocation; Relevance (law); Social media; Smoothing; Probabilistic logic; Field (mathematics); Information retrieval; Language model; Artificial intelligence; Dirichlet distribution; Topic model; Data mining; World Wide Web; Mathematics","authors":[{"name":"Fatma Najar","is_ca":true},{"name":"Nizar Bouguila","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03478667359186854,"gpt":0.3244483637770839,"spread":0.2896616901852153,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002782253,0.0007808447,0.001431227,0.001347361,0.0008017309,0.001268848,0.00128988,0.0009715706,0.00236985],"category_scores_gemma":[0.00852502,0.0004100677,0.001358571,0.00180163,0.0006150722,0.003250121,0.0009398902,0.001733877,0.00139732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000764398,"about_ca_system_score_gemma":0.0009994721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006687724,"about_ca_topic_score_gemma":0.00496448,"domain_scores_codex":[0.9987638,0.0004388864,0.0001227122,0.0002308648,0.0003317134,0.0001120368],"domain_scores_gemma":[0.9968335,0.001815393,0.00015372,0.0003574342,0.0007620864,0.00007781758],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005661633,0.0003990508,0.002193838,0.0003664278,0.0002872972,0.0002429901,0.0004741639,0.2714321,0.02650361,0.09194465,0.01491754,0.5906722],"study_design_scores_gemma":[0.000008687254,0.00003512726,0.0002065445,0.000005642713,0.0000218821,0.00002200613,0.00001466932,0.9823437,0.001053925,0.01527693,0.000997135,0.00001383472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01557853,0.0007476521,0.9815026,0.0003293231,0.0001509957,0.00005953692,0.0001356218,0.0007500749,0.0007457561],"genre_scores_gemma":[0.4817678,0.001965324,0.5005162,0.0006039741,0.0006954779,0.0003693293,0.00157143,0.0004736639,0.01203673],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006687724,"threshold_uncertainty_score":0.01471412,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3041023245","doi":"10.1007/s11634-020-00408-5","title":"Active learning of constraints for weighted feature selection","year":2020,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Conseil National de la Recherche Scientifique; Agence Universitaire de la Francophonie","keywords":"Pairwise comparison; Feature selection; Laplacian matrix; Computer science; Cluster analysis; Graph; Feature (linguistics); Constraint (computer-aided design); Selection (genetic algorithm); Laplace operator; Data mining; Set (abstract data type); Machine learning; Theoretical computer science; Artificial intelligence; Mathematical optimization; Mathematics","authors":[{"name":"Samah Hijazi","is_ca":false},{"name":"Denis Hamad","is_ca":false},{"name":"Mariam Kalakech","is_ca":false},{"name":"Ali Kalakech","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03703733615695371,"gpt":0.314984239601116,"spread":0.2779469034441623,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004850321,0.001429875,0.00312221,0.001381105,0.0007099782,0.002044236,0.004445631,0.00223061,0.004404713],"category_scores_gemma":[0.01561612,0.001430277,0.001275785,0.001976438,0.00183509,0.003432598,0.002896661,0.002943406,0.0007639159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009934272,"about_ca_system_score_gemma":0.00143018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003349069,"about_ca_topic_score_gemma":0.003897906,"domain_scores_codex":[0.9976335,0.001171333,0.0001399189,0.0003890828,0.0004986331,0.0001674914],"domain_scores_gemma":[0.988227,0.009264238,0.0004079156,0.0006761056,0.001142484,0.0002822212],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005331479,0.0003062326,0.0009757907,0.0004486448,0.0002953494,0.0001261243,0.0001595945,0.5887405,0.005793086,0.1027906,0.008514685,0.2913163],"study_design_scores_gemma":[0.00002048146,0.00002724676,0.00005192175,0.00001099171,0.000009236604,0.00001032032,0.000004501647,0.9843411,0.0005435785,0.01449755,0.0004770211,0.000006000786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004080869,0.0002223109,0.9949996,0.000110312,0.00003018966,0.0000280946,0.00005180097,0.000117212,0.0003595995],"genre_scores_gemma":[0.4331415,0.0008006272,0.5555823,0.0005060359,0.0003645394,0.0009560666,0.001216052,0.0004926582,0.006940247],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004850321,"threshold_uncertainty_score":0.02565128,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2990751717","doi":"10.1007/s11634-019-00379-2","title":"Is-ClusterMPP: clustering algorithm through point processes and influence space towards high-dimensional data","year":2019,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université TÉLUQ; Université du Québec à Montréal","funders":"","keywords":"Cluster analysis; Curse of dimensionality; Algorithm; Data point; Computer science; Subspace topology; Mathematics; Statistical physics; Artificial intelligence; Physics","authors":[{"name":"Khadidja Henni","is_ca":true},{"name":"Pierre‐Yves Louis","is_ca":false},{"name":"Brigitte Vannier","is_ca":false},{"name":"Ahmed Moussa","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0354850183539955,"gpt":0.3152747212139836,"spread":0.2797897028599882,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001543198,0.001473635,0.001792116,0.002692093,0.002249887,0.002122053,0.003843968,0.001788906,0.00567957],"category_scores_gemma":[0.005146992,0.0007726229,0.0019873,0.004605439,0.0009175259,0.001861171,0.003612816,0.001935967,0.003733907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009206271,"about_ca_system_score_gemma":0.00239973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007608857,"about_ca_topic_score_gemma":0.00921559,"domain_scores_codex":[0.9985548,0.0003041665,0.0000734127,0.0003008549,0.0006615447,0.0001053311],"domain_scores_gemma":[0.998744,0.0002818114,0.00006124617,0.000295683,0.0005531962,0.00006419126],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000522938,0.0002166722,0.003270246,0.0005382485,0.0004199035,0.0002109037,0.0005673259,0.1598764,0.01122658,0.03657522,0.03134681,0.7552288],"study_design_scores_gemma":[0.00005653395,0.0000642848,0.000786491,0.00002549942,0.0000550326,0.0001797401,0.00006965774,0.9575888,0.008739226,0.01932897,0.01306617,0.00003951669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002526742,0.0001110167,0.9930995,0.00007164905,0.0000528801,0.0000919236,0.0002084213,0.003133362,0.0007044295],"genre_scores_gemma":[0.04310918,0.0001681819,0.951667,0.00007781869,0.0000639659,0.0003566966,0.00119598,0.0008934099,0.002467859],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007608857,"threshold_uncertainty_score":0.01900005,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4309636459","doi":"10.1007/s11634-022-00528-0","title":"A power-controlled reliability assessment for multi-class probabilistic classifiers","year":2022,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Probabilistic logic; Reliability (semiconductor); Computer science; Probabilistic classification; Classifier (UML); Statistic; Bayesian probability; Artificial intelligence; Machine learning; Class (philosophy); Naive Bayes classifier; Sample size determination; Sampling distribution; Data mining; Mathematics; Statistics; Power (physics); Support vector machine","authors":[{"name":"Hyukjun Gweon","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1683283872417896,"gpt":0.4828551957848841,"spread":0.3145268085430944,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01330647,0.001408744,0.001591396,0.003121646,0.0009901348,0.002389849,0.002815577,0.001990469,0.002686918],"category_scores_gemma":[0.0635392,0.0005953461,0.001420805,0.001827172,0.002360127,0.003794708,0.002420679,0.00205662,0.0008435481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001083029,"about_ca_system_score_gemma":0.001174999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001422423,"about_ca_topic_score_gemma":0.001043025,"domain_scores_codex":[0.9891439,0.004048062,0.0004643455,0.001761784,0.004250381,0.0003315706],"domain_scores_gemma":[0.9593536,0.02275105,0.002324846,0.006704351,0.008526643,0.0003394915],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0009073204,0.0002416494,0.007044361,0.0006892686,0.0003633817,0.0003274956,0.0007265987,0.3947591,0.03790169,0.097262,0.004568814,0.4552083],"study_design_scores_gemma":[0.00002026836,0.0002661149,0.002073162,0.00005443479,0.00008198764,0.000221744,0.00004406545,0.9502766,0.008158584,0.03725028,0.001505589,0.00004726527],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009315494,0.0002201483,0.988844,0.00008139711,0.00003336987,0.00007397034,0.00004911564,0.0002622081,0.001120269],"genre_scores_gemma":[0.6957506,0.0004283348,0.2997295,0.0001732647,0.0002568743,0.0004879978,0.0004190274,0.0003734051,0.002381019],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01330647,"threshold_uncertainty_score":0.07037216,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4387095339","doi":"10.1007/s11634-023-00558-2","title":"Parsimony and parameter estimation for mixtures of multivariate leptokurtic-normal distributions","year":2023,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"NextGenerationEU; Ministero dell'Università e della Ricerca; Natural Sciences and Engineering Research Council of Canada; Università Cattolica del Sacro Cuore","keywords":"Kurtosis; Multivariate statistics; Statistics; Mathematics; Estimation; Multivariate normal distribution; Multivariate analysis; Estimation theory; Econometrics; Economics","authors":[{"name":"Ryan P. Browne","is_ca":true},{"name":"Luca Bagnato","is_ca":false},{"name":"Antonio Punzo","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04852271423534097,"gpt":0.3659672425237264,"spread":0.3174445282883854,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01368259,0.001460876,0.002021907,0.004237074,0.001420216,0.003140056,0.00296471,0.002437763,0.00400633],"category_scores_gemma":[0.05782954,0.001436788,0.002649646,0.003310749,0.002799546,0.004198149,0.004075691,0.00383134,0.001505875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001394344,"about_ca_system_score_gemma":0.001135738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002303893,"about_ca_topic_score_gemma":0.003396441,"domain_scores_codex":[0.991886,0.005557474,0.0003296142,0.001061816,0.0008858854,0.0002791992],"domain_scores_gemma":[0.9711168,0.02368636,0.001624582,0.002090759,0.00111258,0.0003689032],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004323815,0.0001411342,0.007818972,0.0004388703,0.0003621131,0.0004418404,0.001248211,0.3589011,0.004920646,0.4437521,0.005029914,0.1765128],"study_design_scores_gemma":[0.00002112389,0.00002045699,0.000987681,0.00006138628,0.00003032573,0.0001506398,0.0000475127,0.8246418,0.0005807036,0.1717783,0.001627566,0.00005240706],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00693874,0.0002017048,0.9922312,0.0001211064,0.00001172605,0.00003588732,0.0000671468,0.00009918639,0.0002932916],"genre_scores_gemma":[0.2548406,0.0008563959,0.7395378,0.0001967301,0.0001356774,0.0004640724,0.00131318,0.0003767977,0.002278727],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01368259,"threshold_uncertainty_score":0.07236129,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4376255225","doi":"10.1007/s11634-023-00542-w","title":"Model-based clustering of functional data via mixtures of t distributions","year":2023,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"MacEwan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Outlier; Cluster analysis; Multivariate statistics; Mixture model; Computer science; Functional data analysis; Data mining; Expectation–maximization algorithm; Multivariate normal distribution; Mathematics; Pattern recognition (psychology); Artificial intelligence; Statistics; Machine learning; Maximum likelihood","authors":[{"name":"Cristina Antón","is_ca":true},{"name":"Iain Smith","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09709102288779793,"gpt":0.3592540555855143,"spread":0.2621630326977164,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007277831,0.001446305,0.003024496,0.003750999,0.001407098,0.003436013,0.003818878,0.003080642,0.001789078],"category_scores_gemma":[0.02507465,0.001464859,0.00561419,0.003921086,0.002403313,0.004053733,0.003232171,0.003759125,0.001369663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001835018,"about_ca_system_score_gemma":0.001605601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007539074,"about_ca_topic_score_gemma":0.006891557,"domain_scores_codex":[0.9956596,0.002355977,0.0002422677,0.00095533,0.0005760968,0.0002106786],"domain_scores_gemma":[0.990516,0.006392336,0.0008671282,0.001116484,0.0008677205,0.0002402496],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004625094,0.0001884365,0.002785181,0.0003832122,0.0005255898,0.0001263578,0.0006939837,0.6992131,0.004411909,0.09104504,0.003627635,0.196537],"study_design_scores_gemma":[0.00001698126,0.00002276144,0.0004020793,0.00002455067,0.00003204271,0.0000541124,0.00002747363,0.9407816,0.0005241168,0.05753042,0.000550959,0.00003299139],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002929911,0.0001342965,0.99653,0.00006675407,0.00001311823,0.00002315716,0.00003962765,0.0001490828,0.0001140511],"genre_scores_gemma":[0.2127285,0.00093885,0.7816223,0.0002380674,0.0001677728,0.000605853,0.00124341,0.0005149559,0.001940184],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007539074,"threshold_uncertainty_score":0.03848928,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4396529244","doi":"10.1007/s11634-024-00590-w","title":"Clustering functional data via variational inference","year":2024,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Cluster analysis; Inference; Computer science; Artificial intelligence; Data mining; Machine learning","authors":[{"name":"Chengqian Xian","is_ca":true},{"name":"Camila P. E. de Souza","is_ca":true},{"name":"John Jewell","is_ca":true},{"name":"Ronaldo Dias","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08627126853721646,"gpt":0.3698520144562673,"spread":0.2835807459190509,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009425928,0.001590494,0.003531893,0.005221094,0.001389198,0.003792173,0.004740745,0.00304232,0.002155049],"category_scores_gemma":[0.02762215,0.002510516,0.003935583,0.004050656,0.004524178,0.004793063,0.004004447,0.005485832,0.0008576019],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002524189,"about_ca_system_score_gemma":0.002345353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007764962,"about_ca_topic_score_gemma":0.00799351,"domain_scores_codex":[0.9947522,0.002980637,0.0002872013,0.0009683251,0.0008354206,0.00017618],"domain_scores_gemma":[0.9835639,0.01280324,0.0008175221,0.0015899,0.001011725,0.0002137317],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001352699,0.0001136995,0.001992902,0.0004693738,0.0004621166,0.00007526291,0.0004063081,0.4930463,0.002019351,0.3615371,0.003977016,0.1357654],"study_design_scores_gemma":[0.00001004861,0.000009144213,0.0001782473,0.00003006576,0.0000188073,0.0000252314,0.00001496798,0.8521677,0.0002564364,0.1464468,0.0008232494,0.00001940236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001326316,0.0002049063,0.9980797,0.0001302846,0.00001144144,0.00001430358,0.00003048072,0.00007375656,0.0001288712],"genre_scores_gemma":[0.1426009,0.00153668,0.8508759,0.0003312075,0.0002641609,0.0004205116,0.001136259,0.000440556,0.002393835],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009425928,"threshold_uncertainty_score":0.04984963,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2353061623","doi":"10.1007/s11634-016-0250-1","title":"Latent class model with conditional dependency per modes to cluster categorical data","year":2016,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Categorical variable; Conditional independence; Multinomial distribution; Independence (probability theory); Model selection; Latent class model; Mathematics; Local independence; Conditional probability distribution; Conditional probability; Mixture model; Latent variable; Class (philosophy); Expectation–maximization algorithm; Information Criteria; Dependency (UML); Statistics; Posterior probability; Algorithm; Latent variable model; Computer science; Artificial intelligence; Maximum likelihood; Bayesian probability","authors":[{"name":"Matthieu Marbac","is_ca":true},{"name":"Christophe Biernacki","is_ca":false},{"name":"Vincent Vandewalle","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06299037588866112,"gpt":0.3427291082985342,"spread":0.2797387324098731,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01219668,0.001402874,0.002796453,0.003363688,0.001755256,0.00297979,0.005208896,0.002758097,0.005521871],"category_scores_gemma":[0.03276096,0.001197342,0.004630076,0.005112762,0.002592946,0.005133397,0.004148247,0.008260289,0.003027399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001885491,"about_ca_system_score_gemma":0.003162571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007979418,"about_ca_topic_score_gemma":0.009922139,"domain_scores_codex":[0.9912641,0.004722388,0.0004403418,0.001707656,0.001344306,0.0005212763],"domain_scores_gemma":[0.9846033,0.009483431,0.0008073425,0.003326491,0.001427176,0.0003522961],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0009822195,0.0007671589,0.01020862,0.0004316874,0.001105227,0.0001667387,0.00180286,0.2093832,0.00442143,0.3980517,0.01868621,0.3539929],"study_design_scores_gemma":[0.00004147753,0.00004052242,0.001031275,0.00007564566,0.000112715,0.00009619234,0.00008906439,0.784454,0.0007011048,0.2104989,0.002789744,0.00006932936],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002342682,0.0001581766,0.9966697,0.000166335,0.00003571122,0.00004713747,0.0001415363,0.0002055219,0.0002332547],"genre_scores_gemma":[0.1754778,0.0007566862,0.8133237,0.0006807277,0.0003425291,0.001505488,0.002456525,0.0006730594,0.004783508],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01219668,"threshold_uncertainty_score":0.06450295,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4309346662","doi":"10.1007/s11634-022-00526-2","title":"A dual subspace parsimonious mixture of matrix normal distributions","year":2022,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Identifiability; Subspace topology; Dual (grammatical number); Set (abstract data type); Covariance matrix; Cluster analysis; Algorithm; Principal component analysis; Computer science; Matrix (chemical analysis); Covariance; Mathematics; Column (typography); Pattern recognition (psychology); Mathematical optimization; Data mining; Applied mathematics; Artificial intelligence; Statistics","authors":[{"name":"Alex Sharp","is_ca":true},{"name":"Glen Chalatov","is_ca":true},{"name":"Ryan P. Browne","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02317261970497663,"gpt":0.3273198306380522,"spread":0.3041472109330756,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003833834,0.0008178892,0.001612793,0.001750447,0.0008387475,0.002225527,0.002398764,0.001931193,0.004027731],"category_scores_gemma":[0.00833473,0.001008135,0.00165844,0.002126275,0.00157976,0.003190071,0.003495932,0.002417246,0.002144741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000874656,"about_ca_system_score_gemma":0.001256975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002559455,"about_ca_topic_score_gemma":0.00240121,"domain_scores_codex":[0.9972711,0.001313505,0.0001049246,0.0004815582,0.0006509395,0.0001779714],"domain_scores_gemma":[0.9968686,0.001462362,0.0001967397,0.0005159239,0.0006892589,0.0002671373],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006050544,0.0002134747,0.00197846,0.000262347,0.000189529,0.0001762438,0.0003673414,0.334546,0.008873777,0.4103501,0.006736966,0.2357007],"study_design_scores_gemma":[0.00001661797,0.00002872275,0.0001631386,0.00001558715,0.00001894264,0.0001051556,0.00001935824,0.9317113,0.0007364209,0.06473294,0.002425669,0.00002615395],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004785498,0.0001510305,0.993915,0.0001159732,0.00002943961,0.00001618827,0.00007115108,0.0000954129,0.0008202586],"genre_scores_gemma":[0.2028205,0.0007589037,0.7807552,0.0003630753,0.0002335318,0.0002418326,0.001075061,0.0003045204,0.0134473],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004027731,"threshold_uncertainty_score":0.02027547,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400011049","doi":"10.1007/s11634-024-00598-2","title":"Dirichlet compound negative multinomial mixture models and applications","year":2024,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Multinomial distribution; Dirichlet distribution; Mathematics; Econometrics; Mathematical analysis","authors":[{"name":"Ornela Bregu","is_ca":true},{"name":"Nizar Bouguila","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04164186050322628,"gpt":0.3451560601491029,"spread":0.3035141996458766,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008056026,0.001641302,0.003900463,0.003468963,0.00151995,0.003965876,0.003869125,0.003613523,0.004667853],"category_scores_gemma":[0.02936632,0.001930175,0.00290566,0.005582453,0.003544869,0.005557096,0.003885264,0.006109428,0.001712198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002427894,"about_ca_system_score_gemma":0.001374974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005336058,"about_ca_topic_score_gemma":0.00521206,"domain_scores_codex":[0.9958514,0.002291118,0.0002084745,0.0006844956,0.0007902162,0.0001743675],"domain_scores_gemma":[0.9820047,0.01475726,0.0007018113,0.001106499,0.001136639,0.0002930382],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009977524,0.0001006121,0.001341533,0.0003273773,0.0001464115,0.000149949,0.000414414,0.07952327,0.0006883218,0.8297479,0.006145345,0.0813151],"study_design_scores_gemma":[0.00001307358,0.00001070132,0.0002825678,0.00006457775,0.00003272497,0.0001566077,0.00003861,0.3970131,0.0002106741,0.5969927,0.005146412,0.0000383327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004391673,0.007492473,0.9837782,0.001174677,0.0001503993,0.00002926499,0.0001497817,0.0002209858,0.002612571],"genre_scores_gemma":[0.2586828,0.02434259,0.6881556,0.001350775,0.002533684,0.0007639112,0.001568887,0.0006915852,0.02191014],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008056026,"threshold_uncertainty_score":0.04260486,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4313595020","doi":"10.1007/s11634-022-00532-4","title":"Flexible mixture regression with the generalized hyperbolic distribution","year":2023,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Covariate; Component (thermodynamics); Flexibility (engineering); Generalized additive model; Mathematics; Computer science; Generalized linear model; Regression; Regression analysis; Variable (mathematics); Mixture distribution; Set (abstract data type); Mathematical optimization; Applied mathematics; Algorithm; Statistics; Artificial intelligence; Random variable","authors":[{"name":"Nam‐Hwui Kim","is_ca":true},{"name":"Ryan P. Browne","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03909977781917898,"gpt":0.3375096525388514,"spread":0.2984098747196724,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01401133,0.001672509,0.003284589,0.00208468,0.001057485,0.003085904,0.005615221,0.003162066,0.003894434],"category_scores_gemma":[0.0255356,0.002443261,0.003538703,0.003495777,0.003103502,0.006117386,0.005627927,0.005774812,0.001972205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001843381,"about_ca_system_score_gemma":0.002002396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007310715,"about_ca_topic_score_gemma":0.006627447,"domain_scores_codex":[0.9932648,0.003966053,0.0002667632,0.001268375,0.000941089,0.0002928672],"domain_scores_gemma":[0.9871035,0.008858199,0.0007972166,0.002045036,0.0009202416,0.0002758659],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003952297,0.0001208348,0.002673112,0.0003367208,0.0004675477,0.0001937494,0.0003953279,0.4722601,0.002992911,0.3797789,0.003948001,0.1364376],"study_design_scores_gemma":[0.00002689463,0.00001980953,0.0003414633,0.00002894392,0.00003848167,0.00004888228,0.00001436136,0.913575,0.0003842156,0.08411697,0.001366383,0.00003855965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002775738,0.0003751951,0.996205,0.0001603171,0.00002684265,0.00002106034,0.00004566599,0.0001406351,0.000249453],"genre_scores_gemma":[0.2399151,0.002195682,0.7436481,0.0005226735,0.000402973,0.0005143235,0.0009715068,0.0005683806,0.01126139],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01401133,"threshold_uncertainty_score":0.07409984,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3126183644","doi":"10.1007/s11634-022-00514-6","title":"Determinantal consensus clustering","year":2022,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données","keywords":"Cluster analysis; Point process; Single-linkage clustering; Mathematics; Computer science; Kernel (algebra); Similarity (geometry); Consensus clustering; Data mining; Artificial intelligence; Correlation clustering; CURE data clustering algorithm; Combinatorics; Statistics","authors":[{"name":"Serge Vicente","is_ca":true},{"name":"Alejandro Murua","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05356536631324153,"gpt":0.3602556970197126,"spread":0.306690330706471,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003315515,0.0008061324,0.001995974,0.002650865,0.002048289,0.002706718,0.002535805,0.002153284,0.005756711],"category_scores_gemma":[0.0125733,0.0008660825,0.001236802,0.002226648,0.002571058,0.002565794,0.003932743,0.002266012,0.002652831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001660636,"about_ca_system_score_gemma":0.001844325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002190369,"about_ca_topic_score_gemma":0.002883878,"domain_scores_codex":[0.9961513,0.001358851,0.0001644325,0.001072169,0.00102097,0.0002321437],"domain_scores_gemma":[0.9926735,0.002004514,0.0004127488,0.002033559,0.002433442,0.00044222],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002640874,0.0001006267,0.001801766,0.0002755873,0.0002303547,0.0001728358,0.0004868227,0.2231059,0.008048375,0.5463808,0.017673,0.2014598],"study_design_scores_gemma":[0.00001881896,0.00003977936,0.0006082726,0.00001942948,0.00002069033,0.0001106424,0.00008450648,0.819455,0.00255164,0.1700531,0.006997537,0.0000407363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01146197,0.000429882,0.9809026,0.0003303656,0.0001447537,0.00004847888,0.0000787851,0.0004959992,0.00610717],"genre_scores_gemma":[0.6241547,0.0007937188,0.3486748,0.000512854,0.0004031296,0.0002564195,0.001036152,0.0007658947,0.02340237],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005756711,"threshold_uncertainty_score":0.01925808,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4403793086","doi":"10.1007/s11634-024-00608-3","title":"A sparse exponential family latent block model for co-clustering","year":2024,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Amirkabir University of Technology","keywords":"Exponential family; Cluster analysis; Exponential function; Block (permutation group theory); Computer science; Mathematics; Statistics; Combinatorics","authors":[{"name":"Saeid Hoseinipour","is_ca":false},{"name":"Mina Aminghafari","is_ca":true},{"name":"Adel Mohammadpour","is_ca":false},{"name":"Mohamed Nadif","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1106521907296518,"gpt":0.3939182569241741,"spread":0.2832660661945223,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004749235,0.001030877,0.002345404,0.001578022,0.00128157,0.001998482,0.005507947,0.003246905,0.005791572],"category_scores_gemma":[0.01377371,0.001231188,0.002102315,0.003799724,0.001856501,0.004344972,0.002942815,0.004161143,0.004105047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001823943,"about_ca_system_score_gemma":0.002412805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01371387,"about_ca_topic_score_gemma":0.01758404,"domain_scores_codex":[0.9969138,0.001545831,0.0001262636,0.0006396584,0.0004936605,0.0002807683],"domain_scores_gemma":[0.9931178,0.003804082,0.0004775564,0.001303769,0.00100075,0.0002960499],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003649851,0.0001868754,0.00193243,0.0002177287,0.0001989559,0.0001440348,0.0003761801,0.6011391,0.002199114,0.2966936,0.0110189,0.08552806],"study_design_scores_gemma":[0.00001102342,0.00001357773,0.0001423582,0.00001025825,0.00001435416,0.00002731167,0.00001441044,0.9650204,0.0001362125,0.03350099,0.001095231,0.00001383032],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003486987,0.0002607537,0.9950067,0.0001851129,0.00004285424,0.00003803735,0.0003144799,0.0001868597,0.0004782562],"genre_scores_gemma":[0.4075176,0.002051769,0.5575198,0.0006490221,0.0004447926,0.001241961,0.005608128,0.0006342183,0.02433267],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01371387,"threshold_uncertainty_score":0.02726811,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4416664067","doi":"10.1007/s11634-025-00659-0","title":"Data-driven logistic regression ensembles with applications in genomics","year":2025,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Mitacs; KU Leuven","keywords":"Genomics; Regularization (linguistics); Ranking (information retrieval); Big data; Logistic regression; Computational genomics; Predictive modelling; Binary number","authors":[{"name":"Anthony-Alexander Christidis","is_ca":true},{"name":"Stefan Van Aelst","is_ca":false},{"name":"Ruben H. Zamar","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04371606132484556,"gpt":0.3582000692644834,"spread":0.3144840079396379,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006074179,0.0009649617,0.00194217,0.0009789836,0.0005485788,0.0009754499,0.001443698,0.001139533,0.001371274],"category_scores_gemma":[0.01949812,0.0007420417,0.00122237,0.001633874,0.0004483767,0.001209567,0.002001808,0.002961843,0.0008683425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005073737,"about_ca_system_score_gemma":0.0009016838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003317514,"about_ca_topic_score_gemma":0.004326662,"domain_scores_codex":[0.997794,0.001276008,0.0001103297,0.0003004904,0.0004320981,0.0000869552],"domain_scores_gemma":[0.9883874,0.008677856,0.0003378244,0.0008785953,0.001488781,0.0002294734],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002462555,0.0001786662,0.00395111,0.0001144184,0.0003192663,0.00009720036,0.00009593565,0.6940308,0.002481186,0.009210921,0.005581143,0.2836932],"study_design_scores_gemma":[0.000006431828,0.00001168617,0.000182009,0.000005842267,0.00001109451,0.000009505055,0.000003932451,0.9934741,0.0003873272,0.005468916,0.0004329537,0.000006238212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0157878,0.000925765,0.9807741,0.000428741,0.0001270882,0.00003313901,0.0002626169,0.001207839,0.0004529265],"genre_scores_gemma":[0.4526488,0.001229443,0.5394014,0.0004300185,0.0005364518,0.0003303893,0.001733635,0.0004433919,0.003246481],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006074179,"threshold_uncertainty_score":0.03212368,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2891365885","doi":"10.1007/s11634-019-00377-4","title":"Mixtures of skewed matrix variate bilinear factor analyzers","year":2019,"lang":"en","type":"preprint","venue":"Advances in Data Analysis and Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Random variate; Kurtosis; Skewness; Bilinear interpolation; Statistics; Mathematics; Skew; Matrix (chemical analysis); Gaussian; Inverse Gaussian distribution; Applied mathematics; Computer science; Distribution (mathematics); Mathematical analysis; Physics; Random variable","authors":[{"name":"Michael P. B. Gallaugher","is_ca":true},{"name":"Paul D. McNicholas","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04467400490465936,"gpt":0.3678903485041041,"spread":0.3232163435994448,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005543455,0.001357571,0.001391422,0.002351631,0.0008219182,0.003635082,0.001696851,0.001309056,0.007207683],"category_scores_gemma":[0.02638771,0.001194027,0.001713773,0.003504408,0.001658359,0.005170983,0.003699074,0.002110586,0.002688116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008807502,"about_ca_system_score_gemma":0.001105687,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00151916,"about_ca_topic_score_gemma":0.00187707,"domain_scores_codex":[0.9936886,0.002782838,0.0002878919,0.001262313,0.00146828,0.0005100989],"domain_scores_gemma":[0.9899585,0.004789167,0.0007184,0.002102587,0.002003954,0.0004274208],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001612653,0.0002633872,0.008328746,0.0002949326,0.0003583111,0.0004106176,0.000951223,0.130996,0.03137155,0.3584635,0.005496493,0.4614527],"study_design_scores_gemma":[0.00003852657,0.00009655882,0.001968697,0.00004833831,0.00006450767,0.0004238355,0.0001645766,0.8031267,0.007931267,0.1804619,0.005576789,0.00009825015],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009858417,0.0001154585,0.9888225,0.00006347895,0.00002625371,0.00003952519,0.0001102169,0.0002879966,0.000676151],"genre_scores_gemma":[0.3501466,0.0007431766,0.6372366,0.0002508969,0.0001716062,0.0003855242,0.001122529,0.0006511174,0.009292029],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007207683,"threshold_uncertainty_score":0.02931696,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4410920770","doi":"10.1007/s11634-025-00637-6","title":"Mixed-type kernel-based quantification of similarity for clustering","year":2025,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus","funders":"University of British Columbia","keywords":"Kernel (algebra); Similarity (geometry); Cluster analysis; Artificial intelligence; Computer science; Pattern recognition (psychology); Type (biology); Mathematics; Data mining; Combinatorics; Geology","authors":[{"name":"Jesse S. Ghashti","is_ca":true},{"name":"John R. J. Thompson","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09468252969729223,"gpt":0.3986018150346892,"spread":0.303919285337397,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004179106,0.0008677308,0.001396968,0.003277224,0.0008860683,0.003434006,0.002756606,0.001724749,0.002433672],"category_scores_gemma":[0.01622689,0.0005507589,0.00144146,0.003712505,0.001743302,0.006097429,0.003415375,0.002599036,0.001396168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001504592,"about_ca_system_score_gemma":0.001152497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001005123,"about_ca_topic_score_gemma":0.0009494374,"domain_scores_codex":[0.9949899,0.001794164,0.0004168333,0.0008368284,0.001728719,0.0002334693],"domain_scores_gemma":[0.9921311,0.002429958,0.0007295678,0.002188446,0.002203021,0.0003178754],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006174163,0.0002247204,0.003117995,0.000748225,0.000374769,0.0001329201,0.0005781871,0.09166138,0.05027343,0.5174769,0.00507403,0.32972],"study_design_scores_gemma":[0.00001688494,0.0001188521,0.001326105,0.00004173738,0.00005375566,0.000333112,0.00009355048,0.8702254,0.01355907,0.1092321,0.004924844,0.00007460771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003950176,0.0001970154,0.9949944,0.00004525857,0.0000267404,0.00002350899,0.0000480186,0.0001823748,0.0005325302],"genre_scores_gemma":[0.2452939,0.0004076402,0.7498999,0.0001221717,0.00012909,0.000213252,0.0003725477,0.0003152687,0.003246163],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004179106,"threshold_uncertainty_score":0.02210146,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4407498245","doi":"10.1007/s11634-025-00625-w","title":"Random models for adjusting fuzzy rand index extensions","year":2025,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Index (typography); Fuzzy logic; Computer science; Econometrics; Mathematics; Statistics; Artificial intelligence; World Wide Web","authors":[{"name":"Ryan DeWolfe","is_ca":true},{"name":"Jeffrey L. Andrews","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05220024079240108,"gpt":0.3365206615945156,"spread":0.2843204208021145,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02709519,0.001515757,0.002426815,0.002986227,0.0009398346,0.003328631,0.005067119,0.002484437,0.006751842],"category_scores_gemma":[0.08941673,0.00127564,0.002669191,0.002768908,0.002104772,0.006165864,0.002755288,0.00423486,0.001555508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002092316,"about_ca_system_score_gemma":0.001295819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002950877,"about_ca_topic_score_gemma":0.003523794,"domain_scores_codex":[0.9868886,0.008756097,0.0003474732,0.002172385,0.001399335,0.0004359932],"domain_scores_gemma":[0.9557358,0.03121128,0.002604575,0.007689727,0.002289296,0.0004692587],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003364939,0.0001472688,0.002042898,0.0001643275,0.0003680981,0.0001045462,0.0002288476,0.5566649,0.0005851823,0.3380443,0.004451964,0.0968613],"study_design_scores_gemma":[0.00002639652,0.00004741302,0.0003916636,0.00003245072,0.00004571984,0.00003590464,0.00001725321,0.8743458,0.0002173339,0.1231766,0.001630403,0.00003285845],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007361723,0.0003448383,0.9902499,0.0002008078,0.00008122703,0.00006050643,0.00008259199,0.0002851646,0.001333176],"genre_scores_gemma":[0.4249198,0.0008763602,0.5561008,0.0005082238,0.0003676965,0.0007363635,0.0009056834,0.0007098223,0.0148753],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02709519,"threshold_uncertainty_score":0.1432948,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2790767741","doi":"10.1007/s11634-020-00395-7","title":"Clustering discrete-valued time series","year":2020,"lang":"en","type":"preprint","venue":"Advances in Data Analysis and Classification","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Cluster analysis; Series (stratigraphy); Autoregressive model; Computer science; Model selection; Expectation–maximization algorithm; STAR model; Time series; Data mining; Focus (optics); Algorithm; Mathematics; Artificial intelligence; Autoregressive integrated moving average; Machine learning; Econometrics; Statistics; Maximum likelihood","authors":[{"name":"Tyler Roick","is_ca":true},{"name":"Dimitris Karlis","is_ca":false},{"name":"Paul D. McNicholas","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04408920708021554,"gpt":0.3089382067535628,"spread":0.2648489996733472,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00158642,0.0005958013,0.0009992094,0.002497562,0.0004577492,0.001828027,0.0008596104,0.001090571,0.00155667],"category_scores_gemma":[0.00756284,0.0003095076,0.0008095002,0.002617721,0.0006603351,0.001506133,0.0007238329,0.0009912367,0.000627438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006944213,"about_ca_system_score_gemma":0.00054711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001893283,"about_ca_topic_score_gemma":0.001298426,"domain_scores_codex":[0.9991755,0.0002149751,0.00008012659,0.0002318274,0.0002475566,0.0000499647],"domain_scores_gemma":[0.9977748,0.001200049,0.0001686256,0.0004045977,0.0003894252,0.00006246851],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002607809,0.000234479,0.008395463,0.0005612091,0.0004130388,0.0001354455,0.00037786,0.2454876,0.01611102,0.05886011,0.00765068,0.6615123],"study_design_scores_gemma":[0.000008764542,0.00002616322,0.002347045,0.00002356886,0.00003446524,0.00004101699,0.00006728913,0.9516242,0.001775183,0.04232885,0.001712165,0.00001126796],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06062938,0.001861376,0.934795,0.0004425725,0.0002481934,0.00006474152,0.0002615743,0.0003638564,0.00133338],"genre_scores_gemma":[0.6272942,0.002552121,0.361295,0.0001294591,0.0005377012,0.0001432921,0.002674824,0.0001849886,0.005188356],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002497562,"threshold_uncertainty_score":0.00838989,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4200498417","doi":"10.1007/s11634-021-00487-y","title":"Correction to: Multivariate cluster weighted models using skewed distributions","year":2021,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Multivariate statistics; Cluster (spacecraft); Statistics; Line (geometry); Econometrics; Computer science; Mathematics; Programming language; Geometry","authors":[{"name":"Michael P. B. Gallaugher","is_ca":false},{"name":"Salvatore D. Tomarchio","is_ca":false},{"name":"Paul D. McNicholas","is_ca":true},{"name":"Antonio Punzo","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2059572849996396,"gpt":0.4522187383613219,"spread":0.2462614533616823,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01063271,0.004390727,0.005316165,0.006449226,0.004009197,0.005705215,0.006473968,0.008941461,0.2108985],"category_scores_gemma":[0.189497,0.002913306,0.003471575,0.008055618,0.002175579,0.004969412,0.005041189,0.01056598,0.09058345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003341643,"about_ca_system_score_gemma":0.006244827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008127699,"about_ca_topic_score_gemma":0.01353799,"domain_scores_codex":[0.9868482,0.00319191,0.002132882,0.002775734,0.00398533,0.001066044],"domain_scores_gemma":[0.8623195,0.03221925,0.007996543,0.02804672,0.06577625,0.003641692],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001713598,0.00002656418,0.0003407649,0.0003215675,0.0001145125,0.0003844213,0.0000656535,0.0009477968,0.0002510303,0.003139331,0.9798086,0.01442841],"study_design_scores_gemma":[0.0004675219,0.000103039,0.003309346,0.000814818,0.0003241507,0.002485679,0.0003475182,0.04099325,0.003421476,0.05089583,0.8964042,0.0004331603],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"other","genre_scores_codex":[0.002339798,0.001210584,0.06668356,0.03608512,0.8684462,0.0001548264,0.01116083,0.01036299,0.003555987],"genre_scores_gemma":[0.2027721,0.003815111,0.21977,0.04843771,0.2012097,0.001589812,0.02586212,0.02712845,0.2694149],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.2108985,"threshold_uncertainty_score":0.7055256,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4389888669","doi":"10.1007/s11634-023-00576-0","title":"QDA classification of high-dimensional data with rare and weak signals","year":2023,"lang":"en","type":"article","venue":"Advances in Data Analysis and Classification","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Natural Science Foundation of Shandong Province","keywords":"Quadratic classifier; Linear discriminant analysis; Mathematics; Artificial intelligence; Covariance; Pattern recognition (psychology); Covariance matrix; Gaussian; Classifier (UML); Machine learning; Statistics; Computer science","authors":[{"name":"Hanning Chen","is_ca":false},{"name":"Qiang Zhao","is_ca":false},{"name":"Jingjing Wu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05659637533914804,"gpt":0.3390542180021777,"spread":0.2824578426630296,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00395244,0.0006807324,0.001444922,0.001799702,0.001014603,0.002220787,0.001408469,0.001309479,0.002048327],"category_scores_gemma":[0.01164469,0.0003762413,0.001006214,0.001583654,0.001254216,0.001631861,0.001709853,0.001591108,0.001001334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006797023,"about_ca_system_score_gemma":0.001083568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001425268,"about_ca_topic_score_gemma":0.001529152,"domain_scores_codex":[0.9982028,0.00052955,0.0001639861,0.0003938735,0.00052378,0.0001859379],"domain_scores_gemma":[0.9941141,0.003132976,0.0004301899,0.001034365,0.001093055,0.000195379],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001099243,0.0004793627,0.01397172,0.0007824735,0.0003424858,0.0004509617,0.0005379663,0.1432407,0.04703628,0.06824257,0.01218565,0.7116305],"study_design_scores_gemma":[0.00001960639,0.00006568817,0.00305813,0.00002758933,0.00003637886,0.0001775988,0.00009377649,0.9563338,0.005575442,0.03220052,0.002388069,0.00002347309],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0385666,0.0005995861,0.9585385,0.0004862807,0.0001987511,0.00004037986,0.0002999258,0.0003442847,0.0009256777],"genre_scores_gemma":[0.7182433,0.000830434,0.2720972,0.0004741006,0.0006094776,0.0001947222,0.001834124,0.0001647845,0.005551821],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00395244,"threshold_uncertainty_score":0.02090275,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}