{"meta":{"query_hash":"7bf2fb011e30","filters":{"venue":"Journal of Classification"},"cohort_total":46,"direct_labels_cover":0,"predictions_cover":46,"exported":46,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/7bf2fb011e30","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Classification"},"results":[{"id":"W1510262632","doi":"10.1007/s00357-019-09319-3","title":"A Mixture of Coalesced Generalized Hyperbolic Distributions","year":2019,"lang":"en","type":"preprint","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Waterloo; MacEwan University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Bayesian information criterion; Identifiability; Mathematics; Convexity; Hyperbolic function; Applied mathematics; Regular polygon; Distribution (mathematics); Selection (genetic algorithm); Function (biology); Class (philosophy); Model selection; Mathematical analysis; Computer science; Statistics; Artificial intelligence; Geometry","score_opus":0.044589174929418086,"score_gpt":0.31198831372007,"score_spread":0.2673991387906519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1510262632","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012484822,0.0010307805,0.9817224,0.0023809986,0.0013611375,0.00021417966,0.00003154206,0.000018159262,0.0007559663],"genre_scores_gemma":[0.56370044,0.0003779661,0.4353949,0.00006686174,0.00024579023,0.0000053378353,0.000018074214,0.0000109274915,0.00017967058],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997845,0.00034265828,0.0009320594,0.00026933986,0.00044890112,0.00016204499],"domain_scores_gemma":[0.99599594,0.00010426396,0.0021077192,0.00088018976,0.0008041894,0.00010770027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000946112,0.00019656795,0.00060815463,0.00023623297,0.00003969381,0.00009492286,0.0012610436,0.00035066638,0.000008878662],"category_scores_gemma":[0.00014474719,0.00016024889,0.00038731046,0.00023619004,0.00005098196,0.00020975347,0.00024670173,0.0007149424,0.0000046945943],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000110639616,0.0006151004,0.00061129645,0.0005777118,0.00039876642,0.000016587574,0.0010363173,0.00084043975,0.16854744,0.67137104,0.019754857,0.1361198],"study_design_scores_gemma":[0.0040768445,0.00060458714,0.06726368,0.0021389965,0.0007597637,0.00054072065,0.000055995108,0.28017205,0.055357553,0.5441098,0.043321468,0.0015985535],"about_ca_topic_score_codex":0.000004699643,"about_ca_topic_score_gemma":7.02355e-7,"teacher_disagreement_score":0.55121565,"about_ca_system_score_codex":0.0001082211,"about_ca_system_score_gemma":0.0005916136,"threshold_uncertainty_score":0.653476},"labels":[],"label_agreement":null},{"id":"W1898940374","doi":"10.1007/s00357-015-9188-9","title":"Fractionally-Supervised Classification","year":2015,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; McGill University","funders":"","keywords":"Pattern recognition (psychology); A priori and a posteriori; Mixture model; Gaussian; Statistical classification; One-class classification","score_opus":0.12305360804815736,"score_gpt":0.3333380223894209,"score_spread":0.21028441434126355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1898940374","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038200316,0.00018650849,0.9791811,0.0081115095,0.0007998519,0.0000672083,4.6202342e-7,0.000031373165,0.0078019593],"genre_scores_gemma":[0.53449017,0.00004075111,0.4646477,0.00026824969,0.00030758043,0.000003146377,0.0000015246544,0.0000066872562,0.00023417566],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844766,0.00020640326,0.0005173742,0.0001639611,0.00053753715,0.00012704394],"domain_scores_gemma":[0.9978383,0.00009368473,0.00061372144,0.00036811113,0.00087859924,0.00020759027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015324042,0.000095774856,0.00017084867,0.00019492976,0.000053980562,0.00012524499,0.0006047123,0.000093841234,0.000007826966],"category_scores_gemma":[0.00025298406,0.00007868541,0.00009549817,0.000338146,0.00002756579,0.001163794,0.00002885226,0.00022599156,0.000035653582],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046070887,0.0002050306,0.00070127106,0.00000868293,0.00003434387,0.000007831388,0.00075584714,0.000031293475,0.031006087,0.55235523,0.017972376,0.39687595],"study_design_scores_gemma":[0.0025724915,0.0005670213,0.11293639,0.00008477765,0.00007220502,0.00058543397,0.00042270852,0.36737117,0.005199163,0.36135578,0.14828308,0.0005497838],"about_ca_topic_score_codex":0.0000014172886,"about_ca_topic_score_gemma":4.9845465e-7,"teacher_disagreement_score":0.53067017,"about_ca_system_score_codex":0.00013528118,"about_ca_system_score_gemma":0.00035853952,"threshold_uncertainty_score":0.32086977},"labels":[],"label_agreement":null},{"id":"W191887720","doi":"10.1007/s00357-001-0018-x","title":"Optimal Variable Weighting for Ultrametric and Additive Trees and K-means Partitioning: Methods and Software","year":2001,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":96,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Ultrametric space; Weighting; Outlier; Cluster analysis; Recursive partitioning; Variable (mathematics); Partition (number theory); Computer science; Monte Carlo method; Algorithm; Data mining; Tree (set theory); Mathematics; Statistics; Artificial intelligence; Machine learning; Combinatorics","score_opus":0.05001129746715327,"score_gpt":0.3724863672266711,"score_spread":0.32247506975951784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W191887720","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015805902,0.00047603608,0.9828693,0.00060460385,0.00006293168,0.00010030159,0.000003035528,0.000016717291,0.000061148996],"genre_scores_gemma":[0.050768156,0.00049365254,0.94851923,0.000021192764,0.00009047117,0.000009946366,0.00000117563,0.0000067726733,0.000089414316],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991181,0.00010043989,0.00026511378,0.00018484457,0.00017054024,0.00016097433],"domain_scores_gemma":[0.99804926,0.001163131,0.0002613934,0.00010891132,0.00030605105,0.000111224996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009789171,0.000081072314,0.00015913566,0.00021528782,0.0001748815,0.00019319459,0.00013896528,0.00004785697,0.0000022926909],"category_scores_gemma":[0.0011560133,0.00006697453,0.000021864014,0.0003489734,0.00006757401,0.0007619719,0.00005215023,0.00014765527,1.7929298e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044644246,0.000043701817,0.0012165692,0.000030705443,0.00003550225,0.0000052725513,0.0005676752,0.0009850807,0.0071133985,0.004193003,0.00008686008,0.9856776],"study_design_scores_gemma":[0.0010311614,0.0005498572,0.03813516,0.000100978345,0.000029601966,0.0006520379,0.00042493333,0.9371274,0.0023920445,0.008861195,0.010516808,0.00017880222],"about_ca_topic_score_codex":0.0000018269924,"about_ca_topic_score_gemma":6.0261385e-7,"teacher_disagreement_score":0.9854988,"about_ca_system_score_codex":0.000042879732,"about_ca_system_score_gemma":0.00004823581,"threshold_uncertainty_score":0.2731142},"labels":[],"label_agreement":null},{"id":"W1983989808","doi":"10.1007/s00357-005-0018-3","title":"Analysis of Global k-Means, an Incremental Heuristic for Minimum Sum-of-Squares Clustering","year":2005,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Group for Research in Decision Analysis; HEC Montréal","funders":"","keywords":"Cluster analysis; Heuristic; Explained sum of squares; Mathematics; Artificial intelligence; Pattern recognition (psychology); Combinatorics; Computer science; Statistics","score_opus":0.05400124671072944,"score_gpt":0.37078076021751716,"score_spread":0.31677951350678774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983989808","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18669271,0.000090315574,0.8125758,0.00038128174,0.00009166473,0.000091501395,0.00001540492,0.000008854119,0.00005241456],"genre_scores_gemma":[0.82781535,0.000019293862,0.17204139,0.000012288097,0.00008786331,0.0000029831074,0.000004215231,0.0000047152034,0.0000119249635],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982712,0.000086230015,0.00075468747,0.00017284496,0.0005417122,0.0001733099],"domain_scores_gemma":[0.9980418,0.00014827203,0.00079937995,0.00035010767,0.0005602585,0.000100173784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073080196,0.00009106649,0.0003127032,0.0002971351,0.000049900682,0.000045000157,0.00072677096,0.000048058693,0.0000048261177],"category_scores_gemma":[0.00016380679,0.00008478457,0.00017005266,0.00079685653,0.000056853016,0.00069852616,0.00008169061,0.000088959336,6.9184006e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055011985,0.0010129098,0.01764364,0.00024406721,0.0011812566,0.000007753379,0.0017418456,0.1683648,0.12094622,0.0058836616,0.00018945071,0.6822343],"study_design_scores_gemma":[0.000463261,0.0003702082,0.051718276,0.00003155972,0.00011390897,0.000012124917,0.0001942893,0.94354504,0.0030202328,0.00021361133,0.00023812227,0.00007934187],"about_ca_topic_score_codex":0.000010167962,"about_ca_topic_score_gemma":0.00005019471,"teacher_disagreement_score":0.7751803,"about_ca_system_score_codex":0.00024575883,"about_ca_system_score_gemma":0.00011184475,"threshold_uncertainty_score":0.34574145},"labels":[],"label_agreement":null},{"id":"W2014176749","doi":"10.1007/s00357-007-0014-x","title":"Algorithms for ℓ1-Embeddability and Related Problems","year":2007,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Computational Geometry and Mesh Generation","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Group for Research in Decision Analysis; HEC Montréal","funders":"","keywords":"Mathematics; Heuristics; Constructive; Tabu search; Quadratic equation; Combinatorics; Variable (mathematics); Column generation; Algorithm; Mathematical optimization; Discrete mathematics; Computer science; Geometry; Process (computing); Mathematical analysis","score_opus":0.046190332217472735,"score_gpt":0.31476854169308316,"score_spread":0.2685782094756104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014176749","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058744665,0.00018693009,0.9385704,0.0016248196,0.00041918736,0.00013562948,5.349564e-7,0.000013809316,0.0003040479],"genre_scores_gemma":[0.8866874,0.000019747058,0.112986445,0.000043416872,0.00012498599,0.0000022597876,0.000002694937,0.0000028877507,0.00013013392],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912786,0.00002972722,0.00043876516,0.00011971115,0.00019188324,0.00009207302],"domain_scores_gemma":[0.998796,0.00021145145,0.00036819172,0.00010963807,0.00044709886,0.00006766256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001900075,0.000053152493,0.00009289204,0.00014542509,0.00007480118,0.00006014186,0.0001496777,0.000049556846,0.00000212375],"category_scores_gemma":[0.00016041019,0.000045538694,0.00004777572,0.00026205607,0.000021871741,0.00046016023,0.000015556037,0.00008190021,0.0000013914773],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003700943,0.00019518052,0.0010764825,0.000046625053,0.000041717907,0.0000021389274,0.0009659808,0.0017114361,0.03307602,0.109164394,0.00085757865,0.85282546],"study_design_scores_gemma":[0.0015824339,0.0006248697,0.31227788,0.000045944984,0.000032518048,0.0003380637,0.000111715744,0.52235544,0.008101582,0.12863344,0.025659837,0.0002362603],"about_ca_topic_score_codex":4.634946e-7,"about_ca_topic_score_gemma":9.1295067e-7,"teacher_disagreement_score":0.8525892,"about_ca_system_score_codex":0.00004599901,"about_ca_system_score_gemma":0.000065864224,"threshold_uncertainty_score":0.1857014},"labels":[],"label_agreement":null},{"id":"W2016102556","doi":"10.1007/s00357-007-0011-0","title":"The Metric Bridge Partition Problem: Partitioning of a Metric Space into Two Subspaces Linked by an Edge in Any Optimal Realization","year":2007,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Digital Image Processing Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Combinatorics; Mathematics; Vertex (graph theory); Realization (probability); Partition (number theory); Linear subspace; Discrete mathematics; Metric space; Graph; Geometry","score_opus":0.03605375981681319,"score_gpt":0.3333145787183773,"score_spread":0.2972608189015641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016102556","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08356915,0.00066043815,0.9138452,0.0010417064,0.00008383455,0.00016358578,7.7537703e-7,0.00005655676,0.0005787929],"genre_scores_gemma":[0.9168137,0.0001752841,0.08288333,0.000024470497,0.00005127639,0.0000079552465,0.0000067396304,0.000010080066,0.000027191669],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99802214,0.00015324203,0.0008673013,0.0001979507,0.000538078,0.00022126133],"domain_scores_gemma":[0.9972318,0.00024307067,0.0013682971,0.0002933809,0.0007706265,0.00009287094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035045093,0.00011556298,0.00019363349,0.0007960386,0.00012562511,0.00041237846,0.00061432755,0.000069468144,7.1452985e-7],"category_scores_gemma":[0.0005731937,0.000092612296,0.000056540026,0.0028940116,0.00009355736,0.00297307,0.000049866885,0.00019858066,0.0000012764251],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027548452,0.0016421934,0.0333352,0.00019057185,0.000073354975,0.000022336602,0.004578991,0.0018827956,0.19439252,0.10706688,0.006054845,0.6504848],"study_design_scores_gemma":[0.002050924,0.0017640484,0.3508917,0.0006947368,0.00009008787,0.00014188465,0.0006725619,0.21252547,0.35107842,0.073940225,0.0054174974,0.00073240756],"about_ca_topic_score_codex":0.000049759587,"about_ca_topic_score_gemma":0.00006272179,"teacher_disagreement_score":0.8332445,"about_ca_system_score_codex":0.00021351034,"about_ca_system_score_gemma":0.00013507438,"threshold_uncertainty_score":0.39765748},"labels":[],"label_agreement":null},{"id":"W2019936812","doi":"10.1007/s00357-013-9138-3","title":"Model Selection for the Trend Vector Model","year":2013,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Model selection; Bayesian information criterion; Statistics; Mathematics; Selection (genetic algorithm); Marginal likelihood; Likelihood function; Akaike information criterion; Likelihood-ratio test; Estimator; Curse of dimensionality; Statistic; Estimation theory; Computer science; Maximum likelihood; Artificial intelligence","score_opus":0.04080810075278901,"score_gpt":0.27637256924185954,"score_spread":0.23556446848907053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019936812","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22735594,0.0002092069,0.77078784,0.0010228135,0.0001124499,0.00015942048,0.0000037037694,0.0000022281267,0.0003463715],"genre_scores_gemma":[0.95207965,0.00003589902,0.046296675,0.00010606546,0.00031018344,0.000026217944,0.000006373488,0.000009006745,0.001129915],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995366,0.000014857427,0.00020034157,0.00007901817,0.00008589168,0.00008332784],"domain_scores_gemma":[0.9994699,0.000018682349,0.0001901724,0.00010689158,0.00017900835,0.00003539094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012381247,0.0000600288,0.00006239724,0.000020785183,0.000068679095,0.000020735642,0.00013101679,0.000069513466,0.0000069120697],"category_scores_gemma":[0.000042829324,0.000039767692,0.000075732976,0.00003201668,0.000027697877,0.000006378054,0.0000073838573,0.00006179909,0.0000018188874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009562515,0.000073676725,0.00023317356,0.000009095547,0.000064557185,4.4112567e-9,0.00011730963,0.19541985,0.7510219,0.00949678,0.025979592,0.01748844],"study_design_scores_gemma":[0.00058809377,0.0004157107,0.036747,0.0000067195324,0.00007588271,0.000015373282,0.00011070616,0.92401624,0.01826252,0.015325402,0.00431811,0.00011825888],"about_ca_topic_score_codex":0.0000010796804,"about_ca_topic_score_gemma":0.0000045426946,"teacher_disagreement_score":0.73275936,"about_ca_system_score_codex":0.0000110100455,"about_ca_system_score_gemma":0.00007937864,"threshold_uncertainty_score":0.16216795},"labels":[],"label_agreement":null},{"id":"W2049017883","doi":"10.1007/s00357-014-9161-z","title":"Ward’s Hierarchical Agglomerative Clustering Method: Which Algorithms Implement Ward’s Criterion?","year":2014,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":3773,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Hierarchical clustering; Cluster analysis; Software; Computer science; Data mining; Algorithm; Single-linkage clustering; Mathematics; Artificial intelligence; Canopy clustering algorithm; Correlation clustering","score_opus":0.039587181575319444,"score_gpt":0.3420034486997508,"score_spread":0.30241626712443137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049017883","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006096494,0.000034450775,0.9821557,0.009945096,0.00074303616,0.000107541535,0.0000020955315,0.00003368818,0.00088193855],"genre_scores_gemma":[0.59669477,0.000078167395,0.40216312,0.0004994149,0.00043978708,0.000012953855,0.0000067725564,0.000011320979,0.00009371327],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99781543,0.00046120174,0.00069326174,0.0002513793,0.00054909755,0.00022961444],"domain_scores_gemma":[0.99811137,0.00022670985,0.0005606153,0.0003128958,0.00061513117,0.00017327492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017024663,0.00014204928,0.0002627907,0.00024205736,0.0001636271,0.000211833,0.00053190294,0.000087405824,0.000041111205],"category_scores_gemma":[0.00022492687,0.000112180525,0.00011404553,0.00031190235,0.000018026252,0.000835699,0.00011412654,0.00032805093,0.000035685152],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007510906,0.00017982788,0.00015779455,0.00003946656,0.000059314694,0.0000062353524,0.0025390985,0.00027296814,0.079747185,0.007689397,0.006977123,0.9022565],"study_design_scores_gemma":[0.0013765275,0.0007773882,0.013563637,0.00022198365,0.000039135357,0.00022034005,0.00043220224,0.8955165,0.020709002,0.010227477,0.056556992,0.0003587762],"about_ca_topic_score_codex":0.000005961238,"about_ca_topic_score_gemma":0.0000065776444,"teacher_disagreement_score":0.9018977,"about_ca_system_score_codex":0.000092000206,"about_ca_system_score_gemma":0.0000976369,"threshold_uncertainty_score":0.4574589},"labels":[],"label_agreement":null},{"id":"W2071486909","doi":"10.1007/s00357-009-9028-x","title":"Assessing Congruence Among Ultrametric Distance Matrices","year":2009,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Ultrametric space; Mathematics; Resampling; Congruence (geometry); Type I and type II errors; Permutation (music); Mantel test; Distance matrices in phylogeny; Combinatorics; Statistics; Statistic; Normalization (sociology); Discrete mathematics; Biology; Genetics","score_opus":0.042940639641067625,"score_gpt":0.35797349114821986,"score_spread":0.3150328515071522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071486909","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07474333,0.00033800848,0.92258096,0.0011741068,0.00021848352,0.000058406735,2.2979287e-7,0.00003440423,0.00085209816],"genre_scores_gemma":[0.8849389,0.00012158555,0.11471693,0.00004235502,0.00010075978,8.962088e-7,2.6588384e-7,0.000004023842,0.00007430088],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9983991,0.000086072614,0.00046210297,0.00018042083,0.0006612075,0.00021108941],"domain_scores_gemma":[0.99816054,0.00021991433,0.0006808185,0.00032305636,0.0004946874,0.00012098737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007072142,0.00009023771,0.00016417282,0.00035752356,0.0001074563,0.0005479723,0.0009179914,0.00004963483,0.0000025357217],"category_scores_gemma":[0.0004349057,0.000077053264,0.00006199399,0.0012371137,0.000054939617,0.003419289,0.000027229002,0.0003006731,0.000006556572],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013612681,0.00014820862,0.0035798098,0.000019862302,0.000013127678,0.00005826721,0.00027111234,0.0014736828,0.027971247,0.011054778,0.00022971189,0.9551666],"study_design_scores_gemma":[0.00044796694,0.00026228346,0.77283394,0.00015077124,0.000009393786,0.00017559949,0.00018495352,0.21146055,0.005331699,0.00711744,0.0018028328,0.0002225917],"about_ca_topic_score_codex":0.0000020152397,"about_ca_topic_score_gemma":4.252685e-7,"teacher_disagreement_score":0.954944,"about_ca_system_score_codex":0.00018102779,"about_ca_system_score_gemma":0.00011504898,"threshold_uncertainty_score":0.5284109},"labels":[],"label_agreement":null},{"id":"W2073247434","doi":"10.1007/s00357-003-0011-7","title":"Maximum Split Clustering Under Connectivity Constraints","year":2003,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Université de Montréal","funders":"","keywords":"Heuristic; Partition (number theory); Mathematics; Combinatorics; Contiguity; Cluster analysis; Set (abstract data type); Algorithm; Computer science; Mathematical optimization","score_opus":0.04863080670212839,"score_gpt":0.2771362547617657,"score_spread":0.2285054480596373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073247434","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009223128,0.000030075322,0.97927123,0.0013221256,0.0005824126,0.000052459254,6.9860005e-7,0.00001759689,0.009500244],"genre_scores_gemma":[0.95428103,0.000019931353,0.045348044,0.00014133441,0.000056484914,8.579206e-7,7.223523e-7,0.0000036222082,0.00014797848],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9991812,0.00007897802,0.00027163356,0.00012040829,0.00023088351,0.00011690354],"domain_scores_gemma":[0.99920475,0.000058208374,0.0003227768,0.00024236226,0.00011356933,0.000058342364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007665323,0.00006570296,0.00010779184,0.000110310124,0.000057541867,0.00017451443,0.0003816576,0.000028846427,0.000030632516],"category_scores_gemma":[0.000079459845,0.000057475805,0.000049988575,0.00018104388,0.00004210016,0.0009958277,0.00003882856,0.00011183559,0.000023571023],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000078346675,0.00015804912,0.0010532723,0.000019319992,0.00005685407,0.000021108635,0.00014147493,0.00020427049,0.0044162706,0.69377244,0.0019605889,0.2981885],"study_design_scores_gemma":[0.0049644527,0.0006124853,0.3473048,0.0002457052,0.00012450379,0.001048304,0.0017262312,0.23108646,0.008008535,0.24981746,0.15390626,0.0011548091],"about_ca_topic_score_codex":5.891668e-7,"about_ca_topic_score_gemma":0.0000010426616,"teacher_disagreement_score":0.94505787,"about_ca_system_score_codex":0.000053055403,"about_ca_system_score_gemma":0.000054380296,"threshold_uncertainty_score":0.23437953},"labels":[],"label_agreement":null},{"id":"W2075711194","doi":"10.1007/s00357-013-9139-2","title":"Variable Selection for Clustering and Classification","year":2013,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Cluster analysis; Feature selection; Variable (mathematics); Computer science; Selection (genetic algorithm); Data mining; Artificial intelligence; Clustering high-dimensional data; Machine learning; Pattern recognition (psychology); Subspace topology; Mathematics","score_opus":0.041396182228672196,"score_gpt":0.2910300057636183,"score_spread":0.24963382353494612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075711194","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020145224,0.00006972812,0.99424326,0.0023559737,0.0002580519,0.00019500282,2.720282e-7,0.000019069748,0.0008441006],"genre_scores_gemma":[0.24790847,0.000021542854,0.75164086,0.00009746139,0.00013481545,0.00001813907,5.2613694e-7,0.0000052043742,0.00017298477],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992038,0.000069475,0.00034381254,0.00013896756,0.00013094724,0.000112984555],"domain_scores_gemma":[0.99883235,0.0001118957,0.00040765127,0.0001368922,0.00043881926,0.000072418145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000704496,0.0000701527,0.0001256638,0.0001235963,0.00008875782,0.00018865659,0.00020144535,0.00007039843,0.0000053935632],"category_scores_gemma":[0.000096123826,0.000058737332,0.00003867103,0.00018009804,0.000015326346,0.0010104377,0.000018681038,0.000101870166,0.0000032745206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010358867,0.000037916758,0.00024814988,0.000029570974,0.000015699858,6.8388964e-8,0.00017617119,0.000020623653,0.18399602,0.43486783,0.002414632,0.37818295],"study_design_scores_gemma":[0.00036191105,0.00014172698,0.021294802,0.00002768415,0.000015990376,0.00007206561,0.000025033487,0.80933774,0.0013749086,0.16157229,0.005679195,0.000096647134],"about_ca_topic_score_codex":0.00000340306,"about_ca_topic_score_gemma":8.3700263e-7,"teacher_disagreement_score":0.8093171,"about_ca_system_score_codex":0.00005022326,"about_ca_system_score_gemma":0.00006278161,"threshold_uncertainty_score":0.23952389},"labels":[],"label_agreement":null},{"id":"W2076089275","doi":"10.1007/s00357-006-0018-y","title":"Generation of Random Clusters with Specified Degree of Separation","year":2006,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":122,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Mathematics; Cluster (spacecraft); Constraint (computer-aided design); Dimension (graph theory); Degree (music); Outlier; Covariance; Set (abstract data type); Separation (statistics); Combinatorics; Pattern recognition (psychology); Algorithm; Artificial intelligence; Computer science; Statistics","score_opus":0.12329393467636098,"score_gpt":0.3420131434182264,"score_spread":0.21871920874186546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076089275","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12572671,0.000064481355,0.87302876,0.00035306838,0.000101897785,0.00010618728,7.50785e-7,0.000006781293,0.00061137823],"genre_scores_gemma":[0.89267373,0.000022590893,0.1070485,0.0000048774773,0.00014792754,0.0000022548936,0.000002833118,0.0000054840293,0.00009178695],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985024,0.000096578115,0.00060392095,0.000115925315,0.0005807628,0.0001004392],"domain_scores_gemma":[0.99816036,0.00009120929,0.00071751536,0.00025741925,0.000738736,0.00003478672],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005271394,0.000073226955,0.00019998883,0.00022205782,0.0000363423,0.000033534463,0.0003234625,0.000043269658,0.0000024403305],"category_scores_gemma":[0.000043890694,0.000057005953,0.00005477055,0.00034719723,0.000059311147,0.00063305564,0.000024134495,0.000107719265,0.0000010443578],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058290275,0.00024972885,0.0006657574,0.00006340298,0.00004816011,0.0000074598806,0.00045348122,0.063721836,0.8272604,0.0076680942,0.0006943919,0.09858439],"study_design_scores_gemma":[0.002772119,0.00063780084,0.043042485,0.0000885496,0.000022476754,0.00009263968,0.00009039294,0.6862508,0.2654493,0.0009384516,0.00047254763,0.00014242246],"about_ca_topic_score_codex":0.000007405482,"about_ca_topic_score_gemma":0.000009717539,"teacher_disagreement_score":0.76694703,"about_ca_system_score_codex":0.000080868216,"about_ca_system_score_gemma":0.00011532332,"threshold_uncertainty_score":0.23246354},"labels":[],"label_agreement":null},{"id":"W2076491140","doi":"10.1007/s00357-014-9155-x","title":"Globally Optimal Clusterwise Regression By Column Generation Enhanced with Heuristics, Sequencing and Ending Subset Optimization","year":2014,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Multi-Criteria Decision Making","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Heuristics; Column generation; Heuristic; Column (typography); Branch and bound; Mathematical optimization; Mathematics; Combinatorial optimization; Computer science; Algorithm","score_opus":0.1351499648291038,"score_gpt":0.3820421806903929,"score_spread":0.24689221586128912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076491140","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31283945,0.00007550382,0.6858668,0.00044597784,0.00034118918,0.0001194847,0.0000063267744,0.000012110708,0.00029321696],"genre_scores_gemma":[0.8775432,0.00005920372,0.12180181,0.00011676233,0.00029566034,0.0000030052709,0.000014324105,0.000017516186,0.00014852812],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956335,0.00053338875,0.001370866,0.0004131599,0.0018422981,0.00020680204],"domain_scores_gemma":[0.9950278,0.0007058885,0.0021850707,0.00039621597,0.0014979956,0.00018707734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045366175,0.00019174999,0.00039187202,0.00036588867,0.0002754388,0.00086478743,0.00045912364,0.00013500088,0.00006283021],"category_scores_gemma":[0.0039805714,0.0001340446,0.000063432155,0.0004770575,0.00009742834,0.0011029404,0.00006309301,0.00021291063,0.0000075707994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006584963,0.00011735391,0.002939248,0.000018431632,0.00003687788,0.000010788704,0.0010737166,0.1867382,0.6761633,0.0009068518,0.014673995,0.11666275],"study_design_scores_gemma":[0.0011606466,0.00031410583,0.002673908,0.0001629055,0.000038162332,0.000115881376,0.00073428196,0.982957,0.008829438,0.00028650725,0.0025177873,0.0002093768],"about_ca_topic_score_codex":0.0000034600362,"about_ca_topic_score_gemma":0.000008364948,"teacher_disagreement_score":0.7962188,"about_ca_system_score_codex":0.00024017072,"about_ca_system_score_gemma":0.00013162708,"threshold_uncertainty_score":0.8339165},"labels":[],"label_agreement":null},{"id":"W2077969766","doi":"10.1007/s00357-013-9127-6","title":"Optimal Quantization of the Support of a Continuous Multivariate Distribution based on Mutual Information","year":2013,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton; Université de Sherbrooke","funders":"","keywords":"Mutual information; Multivariate statistics; Mathematics; Multivariate analysis; Pattern recognition (psychology); Artificial intelligence; Quantization (signal processing); Statistics; Computer science","score_opus":0.022056487569102282,"score_gpt":0.2730957291643648,"score_spread":0.25103924159526253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077969766","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08785865,0.0000031021234,0.91045743,0.00097025733,0.00029000416,0.00014194133,0.0000046741907,0.0000064235405,0.00026753856],"genre_scores_gemma":[0.9708387,0.0000020796606,0.029016694,0.00007801729,0.000026838288,0.000002301179,0.000009650887,0.0000024567091,0.000023265187],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985187,0.00022283812,0.00068169273,0.0000598387,0.00043394897,0.000082958584],"domain_scores_gemma":[0.9972052,0.00013398,0.0014306277,0.00024219905,0.0009568635,0.00003113262],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092101184,0.00006793455,0.00015815416,0.000112617265,0.000047591166,0.00006258517,0.00037724088,0.000057071873,0.000011276718],"category_scores_gemma":[0.00047245322,0.00004556889,0.000100808094,0.0003167062,0.00004635639,0.0011620509,0.000022362965,0.000116478834,0.0000071428717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005841429,0.0009762956,0.0057427236,0.00018810584,0.000090524845,0.0000017820038,0.0036496087,0.033258528,0.5968605,0.05593065,0.010396271,0.29232082],"study_design_scores_gemma":[0.0011889663,0.00046262634,0.23153174,0.00008668003,0.00002445546,0.000012987468,0.000080138,0.6704112,0.094544925,0.0004581923,0.0011123755,0.000085684784],"about_ca_topic_score_codex":0.000011706569,"about_ca_topic_score_gemma":1.574894e-7,"teacher_disagreement_score":0.88298005,"about_ca_system_score_codex":0.000046190344,"about_ca_system_score_gemma":0.00014535214,"threshold_uncertainty_score":0.18582453},"labels":[],"label_agreement":null},{"id":"W2133276644","doi":"10.1007/s00357-008-9016-6","title":"The Metric Cutpoint Partition Problem","year":2008,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Digital Image Processing Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Combinatorics; Mathematics; Vertex (graph theory); Partition (number theory); Linear subspace; Realization (probability); Discrete mathematics; Graph; Metric (unit); Metric space; Statistics; Geometry","score_opus":0.04848917196264458,"score_gpt":0.2817536667559093,"score_spread":0.23326449479326472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133276644","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035427376,0.0003692675,0.9826975,0.005757574,0.00013970531,0.000067719986,1.3109776e-7,0.00007818635,0.0073471675],"genre_scores_gemma":[0.89564955,0.00023951248,0.10374951,0.00007474634,0.00005886122,0.0000050245253,2.2624747e-7,0.000004064676,0.00021849167],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99905425,0.000045680907,0.00036984705,0.00008273739,0.0003452379,0.0001022318],"domain_scores_gemma":[0.9986346,0.000093532166,0.0005433877,0.00022844356,0.00045481455,0.000045242406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060369336,0.00005427385,0.00007802755,0.00013561983,0.00018044583,0.00023957247,0.0006153536,0.000026235391,7.0197905e-7],"category_scores_gemma":[0.00020164617,0.000034168996,0.000056169596,0.00051640015,0.00006676367,0.001448462,0.000039877406,0.00012237472,0.000012699469],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024377368,0.00027233767,0.0010521316,0.00001899695,0.000031953212,0.000030773866,0.00057616236,0.000022983724,0.014820426,0.14939128,0.04485361,0.78890496],"study_design_scores_gemma":[0.0008816865,0.0010304017,0.0931251,0.0002264542,0.000040164632,0.00336587,0.00012375465,0.05021715,0.14068408,0.48387274,0.22586611,0.0005664808],"about_ca_topic_score_codex":5.40837e-7,"about_ca_topic_score_gemma":2.4171936e-7,"teacher_disagreement_score":0.89210683,"about_ca_system_score_codex":0.000065695276,"about_ca_system_score_gemma":0.00012084407,"threshold_uncertainty_score":0.23102029},"labels":[],"label_agreement":null},{"id":"W2560940630","doi":"10.1007/s00357-018-9280-z","title":"On Fractionally-Supervised Classification: Weight Selection and Extension to the Multivariate t-Distribution","year":2018,"lang":"en","type":"preprint","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Extension (predicate logic); Multivariate statistics; Selection (genetic algorithm); Cluster analysis; Gaussian; Artificial intelligence; Resolution (logic); Multivariate normal distribution; Model selection; Pattern recognition (psychology); Computer science; Machine learning; Mathematics; Chemistry","score_opus":0.053785955787808676,"score_gpt":0.32347412047800156,"score_spread":0.26968816469019286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560940630","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013071592,0.00014034273,0.9597095,0.024275655,0.0020478512,0.0004086888,0.000012350795,0.00004343668,0.000290555],"genre_scores_gemma":[0.75311506,0.0002490286,0.24414209,0.000745769,0.0015224776,0.00003756497,0.000034238394,0.00002222484,0.00013157837],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99710065,0.00058785465,0.0008096846,0.00058483926,0.0007088319,0.00020811442],"domain_scores_gemma":[0.9960466,0.00031584024,0.0012523871,0.0007528038,0.0014473812,0.00018498894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022843024,0.0002767486,0.0003454133,0.00025027426,0.00033880427,0.00036754357,0.00081159506,0.00036222563,0.000014023086],"category_scores_gemma":[0.00048081164,0.00019101004,0.00016209038,0.00040157765,0.00004972462,0.00040111766,0.0002214328,0.0009337657,0.00002896159],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000508017,0.0005548849,0.0001785831,0.000100813355,0.00023274284,0.000007322149,0.0013332835,0.00088555145,0.041804746,0.41497552,0.0637968,0.47562173],"study_design_scores_gemma":[0.00074771896,0.0005787878,0.17582136,0.0004895136,0.0001380101,0.0001920421,0.000033221568,0.64445615,0.0024980083,0.13806733,0.036458388,0.0005194351],"about_ca_topic_score_codex":0.0000073173896,"about_ca_topic_score_gemma":0.000004053704,"teacher_disagreement_score":0.74004346,"about_ca_system_score_codex":0.0003085084,"about_ca_system_score_gemma":0.0003185026,"threshold_uncertainty_score":0.7789163},"labels":[],"label_agreement":null},{"id":"W2767631755","doi":"10.1007/s00357-019-9309-y","title":"Mixtures of Hidden Truncation Hyperbolic Factor Analyzers","year":2019,"lang":"en","type":"preprint","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Truncation (statistics); Cluster analysis; Factor (programming language); Gaussian; Applied mathematics; Computer science; Mixture model; Process (computing); Mathematics; Statistics; Pattern recognition (psychology); Algorithm; Artificial intelligence; Physics","score_opus":0.05285534351087375,"score_gpt":0.3160797611992984,"score_spread":0.2632244176884247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767631755","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03608747,0.00094007625,0.95881265,0.0014980682,0.0014858098,0.00019443569,0.000008430769,0.000017497683,0.00095554313],"genre_scores_gemma":[0.6941253,0.00032542986,0.30509079,0.000058031408,0.00024857343,0.0000028400166,0.000005381241,0.000012144702,0.00013148335],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9976392,0.00031643172,0.0009873605,0.00030531967,0.00059826614,0.00015345355],"domain_scores_gemma":[0.99541634,0.00015370447,0.0027112735,0.0008699754,0.0007480906,0.000100631216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087005354,0.00020966888,0.00058306614,0.0004726166,0.000030024896,0.000114937364,0.0013598935,0.00033747696,0.00001348668],"category_scores_gemma":[0.00016273466,0.00017018135,0.0003554904,0.0002492623,0.000041113042,0.0003699029,0.00017769133,0.00062503124,0.000006058878],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000077424935,0.0003152455,0.0018173935,0.0005119159,0.00040261634,0.0000061440874,0.0032151595,0.00048656994,0.17102072,0.05721246,0.003765258,0.7611691],"study_design_scores_gemma":[0.0022490644,0.00073491834,0.34636486,0.0016131904,0.00061362545,0.00018687063,0.00014321873,0.18028267,0.11934217,0.33827105,0.008574242,0.0016241033],"about_ca_topic_score_codex":0.000008159918,"about_ca_topic_score_gemma":8.07471e-7,"teacher_disagreement_score":0.75954497,"about_ca_system_score_codex":0.00012527856,"about_ca_system_score_gemma":0.0005506697,"threshold_uncertainty_score":0.6939794},"labels":[],"label_agreement":null},{"id":"W2922529999","doi":"10.1007/s00357-024-09479-x","title":"Flexible Clustering with a Sparse Mixture of Generalized Hyperbolic Distributions","year":2024,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Canada Research Chairs; E.W.R. Steacie Memorial Fund","keywords":"Cluster analysis; Parametrization (atmospheric modeling); Covariance; Mathematics; Covariance matrix; Component (thermodynamics); Interpretation (philosophy); Matrix (chemical analysis); Clustering high-dimensional data; Mixture model; Algorithm; Computer science; Applied mathematics; Statistics","score_opus":0.037729005645200264,"score_gpt":0.2992783221185225,"score_spread":0.26154931647332225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2922529999","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0074669044,0.000916456,0.9880754,0.002530957,0.00030416687,0.00006056374,0.0000038408143,0.0000308672,0.0006108605],"genre_scores_gemma":[0.5795296,0.00008920309,0.42007533,0.00003134865,0.000118885415,0.0000023147227,0.0000014229512,0.000005839773,0.00014606558],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908674,0.00008533622,0.00035389428,0.00013107825,0.00023259352,0.0001103768],"domain_scores_gemma":[0.9991975,0.000054911372,0.0002324294,0.00024330163,0.00020148681,0.000070411734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047223436,0.000083402774,0.00018240535,0.00015157783,0.0000407692,0.000105647705,0.00031858947,0.000054953303,0.0000057176417],"category_scores_gemma":[0.000025433006,0.000056691464,0.00009046362,0.0004500297,0.000033831308,0.00042685764,0.000028358249,0.00017503569,0.0000022450024],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005684119,0.00011365635,0.00009102429,0.00012549773,0.00011223254,0.00003480899,0.00084970193,0.00026194614,0.1599978,0.5976136,0.0025565892,0.23818631],"study_design_scores_gemma":[0.0018733443,0.00089810987,0.014301251,0.0014236275,0.0003147976,0.0021950544,0.00008684601,0.67871696,0.10514747,0.11400681,0.08038071,0.00065502024],"about_ca_topic_score_codex":0.0000024990877,"about_ca_topic_score_gemma":0.0000017271096,"teacher_disagreement_score":0.678455,"about_ca_system_score_codex":0.000046347646,"about_ca_system_score_gemma":0.00017173345,"threshold_uncertainty_score":0.23118109},"labels":[],"label_agreement":null},{"id":"W2953751292","doi":"10.1007/s00357-022-09427-7","title":"Model-Based Clustering and Classification Using Mixtures of Multivariate Skewed Power Exponential Distributions","year":2023,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Waterloo; Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Stiefel manifold; Mixture model; Skewness; Mathematics; Expectation–maximization algorithm; Cluster analysis; Exponential family; Multivariate statistics; Multivariate normal distribution; Exponential function; Gaussian; Maximization; Linear discriminant analysis; Kurtosis; Applied mathematics; Statistics; Pattern recognition (psychology); Artificial intelligence; Computer science; Mathematical optimization; Maximum likelihood; Mathematical analysis; Chemistry","score_opus":0.08359715212252727,"score_gpt":0.34054818044832663,"score_spread":0.25695102832579936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953751292","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.076929815,0.000052237217,0.92160094,0.000937536,0.00027193036,0.00009545691,0.0000066588045,0.000030039157,0.000075409764],"genre_scores_gemma":[0.6846407,0.000015764932,0.31526428,0.000017216911,0.000035825942,0.0000021049912,0.000003949527,0.000006490771,0.000013643128],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985898,0.00017613836,0.00058458507,0.00019190181,0.00029848402,0.00015909015],"domain_scores_gemma":[0.9984236,0.00012224742,0.0007228759,0.0002931515,0.0003454703,0.000092683775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097477733,0.00011203283,0.00021838595,0.000290899,0.000116907075,0.000080734324,0.00031244877,0.000101015605,0.0000016410952],"category_scores_gemma":[0.0001414769,0.000098151366,0.000100709265,0.00045426094,0.00006064581,0.0004602293,0.000055940927,0.00016152785,0.0000010061451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042263924,0.00008205882,0.00011356664,0.000032349675,0.000025885454,0.0000028012605,0.00045483094,0.0044988813,0.9273871,0.047192056,0.00013470472,0.020033501],"study_design_scores_gemma":[0.0004301507,0.000043551787,0.015658328,0.000060053397,0.000026569087,0.000013917965,0.000018602663,0.966782,0.008288469,0.008505892,0.00007861864,0.00009387846],"about_ca_topic_score_codex":0.0000028338873,"about_ca_topic_score_gemma":8.522307e-7,"teacher_disagreement_score":0.9622831,"about_ca_system_score_codex":0.00006088556,"about_ca_system_score_gemma":0.00015616746,"threshold_uncertainty_score":0.40024966},"labels":[],"label_agreement":null},{"id":"W3006387108","doi":"10.1007/s00357-019-09353-1","title":"Modified Subspace Constrained Mean Shift Algorithm","year":2020,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Advanced Data Compression Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; St. Michael's Hospital; Public Safety Canada; University of Toronto","funders":"","keywords":"Algorithm; Mathematics; Principal component analysis; Kernel (algebra); Subspace topology; Kernel density estimation; Mean-shift; Cluster analysis; Kernel principal component analysis; Projection (relational algebra); Kernel method; Pattern recognition (psychology); Computer science; Artificial intelligence; Support vector machine; Statistics","score_opus":0.05620725276592743,"score_gpt":0.3001003185265803,"score_spread":0.2438930657606529,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006387108","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007533085,0.000075728996,0.985932,0.01231265,0.00013854343,0.00008501483,0.000004199395,0.00012151792,0.00057702366],"genre_scores_gemma":[0.60414326,0.00003348298,0.39527023,0.0004155266,0.00011690388,0.0000018977437,0.000002055173,0.0000058055557,0.0000108077675],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874514,0.00008853225,0.00046014905,0.00018565197,0.00039364045,0.00012689485],"domain_scores_gemma":[0.99851626,0.000091435744,0.0006572486,0.00032544337,0.00022523933,0.0001843832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029224242,0.00010083281,0.00019244227,0.00009483856,0.000056064593,0.00009315892,0.0009555002,0.00005666293,0.000009913984],"category_scores_gemma":[0.00013683797,0.000085079126,0.00007366733,0.0003087582,0.00004868972,0.0010328698,0.00009379042,0.00024796615,0.000011922615],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005364776,0.00014787547,0.00010044298,0.000023796161,0.00004341926,0.000058385936,0.0021753605,0.00028379212,0.08616811,0.1658786,0.013139379,0.7319272],"study_design_scores_gemma":[0.0016559303,0.00066742924,0.006789507,0.00012300724,0.000032988522,0.0001621027,0.00029926244,0.8238884,0.08612233,0.041727487,0.0379998,0.0005317175],"about_ca_topic_score_codex":7.1149174e-7,"about_ca_topic_score_gemma":1.6684255e-7,"teacher_disagreement_score":0.82360464,"about_ca_system_score_codex":0.000040196406,"about_ca_system_score_gemma":0.00009262183,"threshold_uncertainty_score":0.3469426},"labels":[],"label_agreement":null},{"id":"W3041770541","doi":"10.1007/s00357-020-09376-z","title":"Editorial: Journal of Classification Vol. 37-2","year":2020,"lang":"en","type":"editorial","venue":"Journal of Classification","topic":"Optics and Image Analysis","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Computer science","score_opus":0.021693667172733223,"score_gpt":0.263290762339074,"score_spread":0.2415970951663408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041770541","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001550376,0.00039394203,0.0024922194,0.0026696776,0.9920815,0.00012042192,0.000011521929,0.000016891005,0.0020587505],"genre_scores_gemma":[0.007036033,0.00071703567,0.0005191289,0.00012204773,0.9911013,0.000002618503,0.00012864325,0.00007540344,0.00029776018],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99434036,0.00006410901,0.0024416777,0.00027851597,0.0026205673,0.0002547827],"domain_scores_gemma":[0.9720304,0.00031440973,0.010854347,0.0003738097,0.016361825,0.00006518426],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0022549594,0.00037097008,0.0010304214,0.0008770382,0.00014552519,0.0011133249,0.001054407,0.000732346,0.00011686485],"category_scores_gemma":[0.009882241,0.00031338862,0.00075977755,0.00090034824,0.00008655621,0.0027476293,0.00008481239,0.0017286151,0.000123828],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019743215,0.0001526729,0.00009221922,0.00020187332,0.00029117492,0.000009594978,0.00002488592,0.000014639678,0.0028400316,0.00041318007,0.99128056,0.004481758],"study_design_scores_gemma":[0.00085421326,0.000098413824,0.00051338226,0.00023069534,0.0014067414,0.000003030551,0.0002448577,0.0014842122,0.000027351656,0.00086820574,0.99398994,0.00027892564],"about_ca_topic_score_codex":0.00002182101,"about_ca_topic_score_gemma":0.000006404351,"teacher_disagreement_score":0.022309922,"about_ca_system_score_codex":0.00025865386,"about_ca_system_score_gemma":0.00077496126,"threshold_uncertainty_score":0.9999318},"labels":[],"label_agreement":null},{"id":"W3118804762","doi":"10.1007/s00357-023-09452-0","title":"Logistic Normal Multinomial Factor Analyzers for Clustering Microbiome Data","year":2023,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Simons Foundation","keywords":"Cluster analysis; Microbiome; Multinomial logistic regression; Mixture model; Computer science; Multinomial distribution; Expectation–maximization algorithm; Human microbiome; Gaussian; Data mining; Pattern recognition (psychology); Artificial intelligence; Statistics; Mathematics; Machine learning; Bioinformatics; Biology; Maximum likelihood","score_opus":0.2580616931963199,"score_gpt":0.39386718861884285,"score_spread":0.13580549542252296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118804762","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00561377,0.000027843069,0.99210674,0.0012461385,0.0007879135,0.00010087004,0.000027336882,0.000032538563,0.000056834095],"genre_scores_gemma":[0.52222747,0.000023714209,0.47728947,0.00004845569,0.00027928097,0.0000019885795,0.000017797925,0.0000072664507,0.00010453774],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899715,0.000068564834,0.00041498285,0.00019645772,0.00014919447,0.00017363939],"domain_scores_gemma":[0.99865735,0.00019404569,0.0004234542,0.00048785834,0.00016105738,0.00007626737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096145004,0.00008160436,0.00017356557,0.00023228202,0.000076054646,0.00012203741,0.001113236,0.000060272367,0.0000033964698],"category_scores_gemma":[0.00020628587,0.00006791438,0.00007589762,0.00031742142,0.000024207073,0.0006486744,0.00015401775,0.00011196848,0.000008865377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009481213,0.00008196249,0.000380216,0.00009299022,0.000095589436,0.000017229591,0.00084021327,0.00039971733,0.30589873,0.0064581432,0.008620711,0.6770197],"study_design_scores_gemma":[0.00067770324,0.00009322194,0.014824545,0.000029819068,0.000027012793,0.000036361336,0.000040345352,0.97271085,0.0018348799,0.0016250222,0.007954042,0.00014620334],"about_ca_topic_score_codex":0.0000019905635,"about_ca_topic_score_gemma":0.0000039230654,"teacher_disagreement_score":0.97231114,"about_ca_system_score_codex":0.00004604909,"about_ca_system_score_gemma":0.00009782496,"threshold_uncertainty_score":0.2769468},"labels":[],"label_agreement":null},{"id":"W3158446859","doi":"10.1007/s00357-021-09389-2","title":"Matrix Normal Cluster-Weighted Models","year":2021,"lang":"en","type":"preprint","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Università di Catania","keywords":"Covariate; Univariate; Mathematics; Cluster analysis; Independence (probability theory); Statistics; Data set; Multivariate statistics; Grouped data; Econometrics; Conditional independence","score_opus":0.04685364537515465,"score_gpt":0.31580409727873926,"score_spread":0.26895045190358463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158446859","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004691984,0.0013970897,0.98556316,0.0037897425,0.002010912,0.00014790465,0.000002810623,0.000036660596,0.002359716],"genre_scores_gemma":[0.2621274,0.00044277287,0.73645866,0.0001800226,0.00046473314,0.000005925898,0.000007945125,0.000016377686,0.0002961387],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972402,0.00045659143,0.0010377107,0.0003864216,0.00064982846,0.0002292464],"domain_scores_gemma":[0.99617994,0.00011106473,0.0016576974,0.0009110211,0.00096249813,0.00017779866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014749824,0.00024557576,0.0005277235,0.00031423056,0.00007267418,0.0005301679,0.0015014006,0.0004068637,0.000012066054],"category_scores_gemma":[0.000052459018,0.00021218935,0.00038518448,0.00026573573,0.0000312403,0.000994449,0.00054037716,0.0010958195,0.0000040737923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112490685,0.000704012,0.000088131696,0.0005239274,0.00048090462,0.00020259712,0.004707369,0.009718851,0.011251869,0.41532326,0.010158347,0.54672825],"study_design_scores_gemma":[0.0004006408,0.0000518038,0.00058140955,0.00027245237,0.000072957475,0.0002518804,0.000031013617,0.8347261,0.0012982426,0.16096331,0.0010586022,0.00029161113],"about_ca_topic_score_codex":0.0000044999438,"about_ca_topic_score_gemma":0.0000016330735,"teacher_disagreement_score":0.8250072,"about_ca_system_score_codex":0.00015674913,"about_ca_system_score_gemma":0.0007388181,"threshold_uncertainty_score":0.8652831},"labels":[],"label_agreement":null},{"id":"W4200604627","doi":"10.1007/s00357-021-09404-6","title":"Editorial: Journal of Classification Vol. 38-3","year":2021,"lang":"en","type":"editorial","venue":"Journal of Classification","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Mathematics; Computer science","score_opus":0.02128713241038138,"score_gpt":0.2993501570993756,"score_spread":0.27806302468899424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200604627","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010170262,0.0011780268,0.32091105,0.0010910528,0.67620087,0.00013856858,0.000014003503,0.00004723224,0.00040900224],"genre_scores_gemma":[0.0013589916,0.0042266506,0.01725723,0.000031162956,0.97614074,0.000009678611,0.000055788925,0.000060172435,0.00085957395],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99123913,0.00068940734,0.0034712208,0.0005221682,0.003683693,0.00039435513],"domain_scores_gemma":[0.964263,0.0011518347,0.010770009,0.0012081757,0.022286225,0.00032071336],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0046859602,0.00050299545,0.0012412773,0.0010304878,0.00018072814,0.0008106399,0.0033777817,0.0015462629,0.000042432832],"category_scores_gemma":[0.008356964,0.00043211918,0.00083842524,0.0012759678,0.00017772407,0.0020962525,0.00017073311,0.0027498906,0.000024348115],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007658708,0.00028810964,0.000008211954,0.000106538755,0.00013471053,0.000016746675,0.00018158043,0.0000012420494,0.014903607,0.0024307363,0.96236527,0.019486636],"study_design_scores_gemma":[0.00074264733,0.00048828206,0.00016109695,0.00050054863,0.00016811151,0.000067485096,0.00017033605,0.00055073714,0.006778176,0.0023893476,0.98759395,0.00038925375],"about_ca_topic_score_codex":0.0000036309832,"about_ca_topic_score_gemma":0.0000011638705,"teacher_disagreement_score":0.30365384,"about_ca_system_score_codex":0.000866342,"about_ca_system_score_gemma":0.0046005873,"threshold_uncertainty_score":0.99999607},"labels":[],"label_agreement":null},{"id":"W4206298479","doi":"10.1007/s00357-021-09396-3","title":"Chimeral Clustering","year":2021,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Pattern recognition (psychology); Artificial intelligence; Mathematics; Computer science","score_opus":0.04135846136028306,"score_gpt":0.301972910995361,"score_spread":0.26061444963507796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206298479","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024410356,0.0002395996,0.98919696,0.004024351,0.00049174216,0.000013825315,1.0971204e-7,0.00000918519,0.003583177],"genre_scores_gemma":[0.34044743,0.000049545317,0.6588308,0.00023449586,0.00016521208,3.6471528e-7,2.1088475e-7,0.0000027683443,0.0002691564],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933267,0.00009423674,0.0002493001,0.00008466952,0.00016350596,0.000075643096],"domain_scores_gemma":[0.9992709,0.000034399905,0.00022068493,0.00019768701,0.00022139376,0.000054936736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039614365,0.000042970765,0.00009911951,0.000052203097,0.000035197707,0.00008393276,0.00024873548,0.000032511347,0.000008407175],"category_scores_gemma":[0.000057298304,0.000035933925,0.00006714352,0.00016691943,0.000008173702,0.00037602888,0.00003601404,0.00011867158,0.0000043260497],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000064314618,0.00006545495,0.00014448537,0.000010637782,0.000022631919,0.000047231028,0.00042114675,0.000032475968,0.11334942,0.17821094,0.0015678242,0.7061213],"study_design_scores_gemma":[0.0019521782,0.00030050954,0.10472994,0.00023665841,0.000069035355,0.0038206584,0.00013340978,0.47516146,0.106166594,0.22613358,0.08069808,0.0005978754],"about_ca_topic_score_codex":2.6259377e-7,"about_ca_topic_score_gemma":6.1449583e-7,"teacher_disagreement_score":0.70552343,"about_ca_system_score_codex":0.000024751984,"about_ca_system_score_gemma":0.00011085511,"threshold_uncertainty_score":0.14653428},"labels":[],"label_agreement":null},{"id":"W4214724944","doi":"10.1007/s00357-021-09407-3","title":"On Assessments of Agreement Between Fuzzy Partitions","year":2022,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Interpretability; Fuzzy logic; Probabilistic logic; Property (philosophy); Monte Carlo method; Mathematics; Measure (data warehouse); Cluster (spacecraft); Computer science; Data mining; Artificial intelligence; Statistics","score_opus":0.07695818300159624,"score_gpt":0.33464940112893354,"score_spread":0.2576912181273373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214724944","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08978313,0.00004466159,0.8783214,0.007607693,0.0011581425,0.00023244863,0.00004223867,0.00002425191,0.02278602],"genre_scores_gemma":[0.9914338,0.000010389131,0.008097925,0.000079987236,0.00006552647,0.0000058975143,0.000013370176,0.0000024508074,0.00029063944],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99882615,0.00008793773,0.00035987087,0.00009097474,0.00055802835,0.00007702604],"domain_scores_gemma":[0.998996,0.00005800454,0.0005718875,0.00025638106,0.00008171337,0.000036006182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006486143,0.00004609738,0.000102184626,0.00018246459,0.00010047892,0.000043583193,0.0006263214,0.000009044619,0.00005056536],"category_scores_gemma":[0.00001628726,0.00004212467,0.000055539458,0.00027739428,0.00001229126,0.00042806467,0.00012833282,0.00012235352,0.000008720878],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034266246,0.0012746705,0.008663041,0.000033918834,0.00024821464,0.000019026134,0.0003834755,0.0017010348,0.004045664,0.535459,0.07229538,0.37584233],"study_design_scores_gemma":[0.0028942928,0.004338931,0.6409728,0.00010553843,0.00019587229,0.000022877086,0.0008237033,0.03002525,0.0038155166,0.1517295,0.16457438,0.00050134887],"about_ca_topic_score_codex":0.0000011443844,"about_ca_topic_score_gemma":1.3576877e-7,"teacher_disagreement_score":0.90165067,"about_ca_system_score_codex":0.00007552034,"about_ca_system_score_gemma":0.00004415225,"threshold_uncertainty_score":0.17177942},"labels":[],"label_agreement":null},{"id":"W4220965753","doi":"10.1007/s00357-022-09410-2","title":"Editorial: Journal of Classification Vol. 39-1","year":2022,"lang":"en","type":"editorial","venue":"Journal of Classification","topic":"Optics and Image Analysis","field":"Business, Management and Accounting","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Mathematics; Pattern recognition (psychology); Artificial intelligence; Computer science","score_opus":0.018933321706511377,"score_gpt":0.26371312415886977,"score_spread":0.2447798024523584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220965753","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00035695767,0.000418992,0.0012573658,0.0011041525,0.9943996,0.00012426425,0.000016144799,0.00001456758,0.0023079305],"genre_scores_gemma":[0.005195895,0.0008920403,0.00030488474,0.0000743152,0.9925241,0.000005806546,0.00018686388,0.000077865225,0.00073823996],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9937467,0.000091592665,0.0024195455,0.0002770599,0.0031910592,0.00027402534],"domain_scores_gemma":[0.9741774,0.00037946648,0.01166243,0.0004705585,0.013270949,0.00003916716],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0038616748,0.0003527609,0.0009410076,0.0016372006,0.0002592458,0.00096913753,0.0012001998,0.0005573712,0.0005944128],"category_scores_gemma":[0.0072186263,0.00030990472,0.00077641394,0.0009789008,0.0000812015,0.0027008094,0.00013232569,0.002013544,0.000054229688],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000188395,0.00023886909,0.00010414335,0.00014287299,0.00027982623,0.00000932633,0.000024671152,0.0000433714,0.0014308946,0.00061896484,0.99288344,0.0040352233],"study_design_scores_gemma":[0.0008466691,0.000104435974,0.00044016395,0.00012333649,0.0012861856,0.000004822021,0.00045981706,0.0009990878,0.000011026033,0.0011904183,0.99425405,0.0002800088],"about_ca_topic_score_codex":0.000033649227,"about_ca_topic_score_gemma":0.000006722568,"teacher_disagreement_score":0.019569289,"about_ca_system_score_codex":0.00045388073,"about_ca_system_score_gemma":0.0008384463,"threshold_uncertainty_score":0.9999353},"labels":[],"label_agreement":null},{"id":"W4285797528","doi":"10.1007/s00357-022-09418-8","title":"Editorial: Journal of Classification Vol. 39-2","year":2022,"lang":"en","type":"editorial","venue":"Journal of Classification","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Pattern recognition (psychology); Artificial intelligence; Mathematics; Computer science","score_opus":0.022274262870595644,"score_gpt":0.29671976253157534,"score_spread":0.2744454996609797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285797528","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013205487,0.00078248174,0.23325689,0.0011604548,0.7640658,0.00020611656,0.000026389283,0.0000653182,0.00042337624],"genre_scores_gemma":[0.0014911384,0.0029565059,0.009935274,0.000039552495,0.98454684,0.000021045078,0.00005937295,0.00006838446,0.0008819099],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9904479,0.00080782344,0.0034341565,0.00051243545,0.004399621,0.00039810824],"domain_scores_gemma":[0.9731012,0.001270575,0.012289518,0.0012011785,0.011894271,0.00024326291],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0061538224,0.000490632,0.0011244004,0.0013517054,0.00029514832,0.00057893683,0.004484469,0.0010571228,0.00011605173],"category_scores_gemma":[0.006211239,0.00043066664,0.0007907815,0.0013277424,0.00016995207,0.002079179,0.00025680507,0.0034128036,0.000022242795],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013203385,0.00030527185,0.000009703452,0.00007892412,0.00011687131,0.000010793747,0.00021083374,0.000002753185,0.007873765,0.003679625,0.9679652,0.019614253],"study_design_scores_gemma":[0.00076162844,0.00084403943,0.00017532233,0.00016738287,0.00017040192,0.00006335444,0.00019000421,0.0006216789,0.0017487032,0.004214832,0.9906573,0.00038531577],"about_ca_topic_score_codex":0.0000055618157,"about_ca_topic_score_gemma":7.350183e-7,"teacher_disagreement_score":0.22332162,"about_ca_system_score_codex":0.001321163,"about_ca_system_score_gemma":0.0037684592,"threshold_uncertainty_score":0.9998145},"labels":[],"label_agreement":null},{"id":"W4321098151","doi":"10.1007/s00357-023-09430-6","title":"Classification Trees with Mismeasured Responses","year":2023,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Waterloo","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Set (abstract data type); Computer science; Inference; Identification (biology); Decision tree; Tree (set theory); Variety (cybernetics); Feature (linguistics); Machine learning; Artificial intelligence; Statistics; Data mining; Mathematics","score_opus":0.0656833040863915,"score_gpt":0.3119337141698363,"score_spread":0.24625041008344478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321098151","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23855099,0.0002229313,0.7001578,0.05462408,0.00079674163,0.00032441405,0.000008082096,0.00064110005,0.004673816],"genre_scores_gemma":[0.98679084,0.00014190322,0.01178819,0.000084868254,0.00016865869,0.000011504084,0.000024426761,0.000016016382,0.00097361096],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9978126,0.00033502656,0.0005995523,0.00028508948,0.0007516314,0.00021606272],"domain_scores_gemma":[0.99730515,0.00032213485,0.0009761798,0.00070050656,0.000565819,0.00013022716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017592937,0.00014710543,0.00021537053,0.0006313982,0.0001729696,0.00023440215,0.00086773233,0.00009034878,0.000007881916],"category_scores_gemma":[0.0005825993,0.000110688845,0.00008174038,0.0014088148,0.00006597642,0.0010225414,0.00003733488,0.0002945246,0.0001394416],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075613445,0.00041370184,0.058968574,0.00006892058,0.0001607817,0.00006450116,0.002177806,0.0006423156,0.27112612,0.16944562,0.030910049,0.46526548],"study_design_scores_gemma":[0.0005677702,0.00026502032,0.90312,0.00005415108,0.00002319681,0.000104483515,0.000304457,0.05471612,0.000784831,0.0009991772,0.038897373,0.00016344059],"about_ca_topic_score_codex":0.0000035549876,"about_ca_topic_score_gemma":0.0000068906675,"teacher_disagreement_score":0.8441514,"about_ca_system_score_codex":0.00009029844,"about_ca_system_score_gemma":0.00031109067,"threshold_uncertainty_score":0.45137602},"labels":[],"label_agreement":null},{"id":"W4366997948","doi":"10.1007/s00357-023-09436-0","title":"Editorial: Journal of Classification Vol. 40-1","year":2023,"lang":"en","type":"editorial","venue":"Journal of Classification","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Mathematics; Pattern recognition (psychology); Artificial intelligence; Computer science","score_opus":0.02877144256539424,"score_gpt":0.3114594561092894,"score_spread":0.28268801354389517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366997948","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00000955374,0.00036108744,0.26040533,0.0010820262,0.7376175,0.00017169642,0.000020495285,0.00011537759,0.0002169418],"genre_scores_gemma":[0.0008669455,0.003565892,0.008464313,0.000021219183,0.9860128,0.0000134557495,0.000046855777,0.00008665621,0.00092183956],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9912465,0.00054515275,0.0034991633,0.00049944606,0.0037650068,0.00044472865],"domain_scores_gemma":[0.9692842,0.0020430204,0.011008215,0.0011420054,0.016193697,0.00032887908],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.005954289,0.0005029004,0.0011543487,0.0014683896,0.00018905563,0.00066380156,0.0038829367,0.0015286864,0.000016565018],"category_scores_gemma":[0.011852516,0.00042353588,0.00076706917,0.0016015659,0.00018726454,0.0020204121,0.00017208491,0.0026111184,0.000094109644],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011211137,0.00018428541,0.0000060814177,0.00010424103,0.00012323227,0.000011375271,0.00016528569,0.0000018255108,0.008721834,0.0018583334,0.96932626,0.019385152],"study_design_scores_gemma":[0.000697549,0.0005876071,0.00043621336,0.00043489705,0.00016757277,0.000027564121,0.0001168997,0.00092470687,0.0024653198,0.004158524,0.9895977,0.00038548876],"about_ca_topic_score_codex":0.0000059844174,"about_ca_topic_score_gemma":0.0000017249264,"teacher_disagreement_score":0.25194103,"about_ca_system_score_codex":0.00083683257,"about_ca_system_score_gemma":0.0030668937,"threshold_uncertainty_score":0.99982166},"labels":[],"label_agreement":null},{"id":"W4382654511","doi":"10.1007/s00357-023-09442-2","title":"Editorial: Journal of Classification Vol. 40-2","year":2023,"lang":"en","type":"editorial","venue":"Journal of Classification","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Mathematics; Computer science","score_opus":0.029120320865816274,"score_gpt":0.3119859986530865,"score_spread":0.28286567778727023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382654511","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009428384,0.00036217095,0.26052603,0.001084776,0.73748976,0.00017162363,0.000019720246,0.000115434275,0.00022104471],"genre_scores_gemma":[0.00086696615,0.0035753676,0.008448422,0.000021210646,0.9860263,0.00001344274,0.000046451023,0.000086662876,0.00091519905],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9912483,0.0005454956,0.003498165,0.0004994086,0.0037639837,0.00044464154],"domain_scores_gemma":[0.9692947,0.0020441443,0.011004843,0.0011418903,0.01618689,0.00032748067],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.00595285,0.00050285045,0.0011543053,0.0014685798,0.000189021,0.0006632451,0.0038819937,0.0015286646,0.000016329852],"category_scores_gemma":[0.011837202,0.00042352005,0.0007669238,0.0016061433,0.00018737242,0.0020200557,0.00017205018,0.002631612,0.000094046954],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000111837726,0.00018415248,0.0000060177645,0.00010415305,0.00012386766,0.000011355854,0.00016376356,0.0000017990127,0.0087036425,0.001848434,0.9684284,0.020312605],"study_design_scores_gemma":[0.0006960565,0.0005857435,0.00043486315,0.0004355821,0.00016854778,0.000027550846,0.00011638574,0.00094497757,0.002484675,0.00419909,0.9895212,0.0003853177],"about_ca_topic_score_codex":0.0000060413204,"about_ca_topic_score_gemma":0.0000017265723,"teacher_disagreement_score":0.2520776,"about_ca_system_score_codex":0.00083646463,"about_ca_system_score_gemma":0.0030637833,"threshold_uncertainty_score":0.99982166},"labels":[],"label_agreement":null},{"id":"W4388630951","doi":"10.1007/s00357-023-09453-z","title":"Model-Based Clustering with Nested Gaussian Clusters","year":2023,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Linear subspace; Pattern recognition (psychology); Artificial intelligence; Mathematics; Hierarchical clustering; Model selection; Single-linkage clustering; Mixture model; Bayesian information criterion; Gaussian; Computer science; Determining the number of clusters in a data set; Correlation clustering; CURE data clustering algorithm; Physics","score_opus":0.05773895718962707,"score_gpt":0.3019908204385257,"score_spread":0.24425186324889864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388630951","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052537774,0.00001561036,0.9874095,0.0061464016,0.00019638616,0.00007576718,4.066858e-7,0.00006827138,0.0008339346],"genre_scores_gemma":[0.5659461,0.000007777114,0.43362364,0.00021316792,0.00006362073,0.000002804751,8.936834e-7,0.000008828161,0.00013316609],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988919,0.00010219536,0.00034013222,0.00015846793,0.00033341194,0.0001738871],"domain_scores_gemma":[0.99891776,0.000070008,0.0003924678,0.00032399426,0.00018236593,0.0001134011],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007934082,0.00010000658,0.00016646073,0.00029370227,0.000076760465,0.0001154777,0.00048013084,0.00005949392,0.0000013325025],"category_scores_gemma":[0.000028820026,0.00007231359,0.000068296395,0.0006310452,0.000027676599,0.00048683304,0.000030703337,0.00017105325,0.0000074333107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031066782,0.00021486686,0.0008343571,0.00015986014,0.00010431243,0.00015991976,0.002729619,0.23828313,0.045107007,0.07072105,0.006485363,0.63488984],"study_design_scores_gemma":[0.00043527165,0.00009950671,0.0035251775,0.00006422978,0.000011892002,0.000042262276,0.000022549739,0.991638,0.0005085725,0.003195755,0.0003615633,0.000095192314],"about_ca_topic_score_codex":7.7581376e-7,"about_ca_topic_score_gemma":0.0000030728295,"teacher_disagreement_score":0.7533549,"about_ca_system_score_codex":0.000056355293,"about_ca_system_score_gemma":0.0001954444,"threshold_uncertainty_score":0.29488626},"labels":[],"label_agreement":null},{"id":"W4388731756","doi":"10.1007/s00357-023-09454-y","title":"Editorial: Journal of Classification Vol. 40-3","year":2023,"lang":"en","type":"editorial","venue":"Journal of Classification","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Computer science","score_opus":0.028885792649539624,"score_gpt":0.31177137130583826,"score_spread":0.28288557865629865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388731756","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009394142,0.00035917346,0.26174974,0.0010890538,0.7362708,0.000171408,0.000020107149,0.000115187664,0.0002151609],"genre_scores_gemma":[0.0008624639,0.0035703604,0.0085306475,0.000021231426,0.9859579,0.000013447574,0.000046532357,0.00008667491,0.0009106963],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9912427,0.0005454298,0.003500388,0.0004996931,0.0037668403,0.00044494568],"domain_scores_gemma":[0.9692728,0.0020448696,0.011010882,0.0011426414,0.016199782,0.0003290473],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.005959436,0.0005030437,0.0011548836,0.0014692306,0.00018918929,0.00066392706,0.0038841066,0.0015293391,0.000016499864],"category_scores_gemma":[0.011866108,0.0004236578,0.0007672521,0.0016066901,0.00018734286,0.0020206205,0.0001721374,0.0026331567,0.00009406121],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001121558,0.00018424801,0.000006010806,0.00010419343,0.00012318847,0.000011371665,0.00016350938,0.0000018351413,0.008639407,0.0018845807,0.96863925,0.020130262],"study_design_scores_gemma":[0.0006983797,0.0005869495,0.00043423235,0.00043612797,0.00016760395,0.000027569067,0.00011708446,0.00094566995,0.0024522557,0.004269514,0.98947906,0.00038556944],"about_ca_topic_score_codex":0.000005980051,"about_ca_topic_score_gemma":0.0000016989712,"teacher_disagreement_score":0.2532191,"about_ca_system_score_codex":0.0008373916,"about_ca_system_score_gemma":0.003072996,"threshold_uncertainty_score":0.99982154},"labels":[],"label_agreement":null},{"id":"W4390639551","doi":"10.1007/s00357-023-09460-0","title":"Unsupervised Classification with a Family of Parsimonious Contaminated Shifted Asymmetric Laplace Mixtures","year":2024,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Outlier; Series (stratigraphy); Mathematics; Bayesian information criterion; Bayesian probability; Expectation–maximization algorithm; Artificial intelligence; Computer science; Convergence (economics); Pattern recognition (psychology); Model selection; Algorithm; Statistics; Maximum likelihood","score_opus":0.029639951270204308,"score_gpt":0.28335772333249026,"score_spread":0.25371777206228596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390639551","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04169319,0.0024630798,0.95128626,0.0019703945,0.00039638265,0.00018127,0.0000038185044,0.0000652911,0.0019403268],"genre_scores_gemma":[0.84627855,0.00022579018,0.15317929,0.000086415734,0.000082858394,0.0000062592685,0.0000037158782,0.000016449154,0.000120679775],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99784815,0.00031186859,0.0007508222,0.0002991233,0.0005929951,0.00019702649],"domain_scores_gemma":[0.99781436,0.00036780757,0.00060294266,0.00043708333,0.0006553067,0.00012249872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001247521,0.00018123034,0.00035718762,0.00071750284,0.00005734936,0.00018933429,0.0006685243,0.00014974334,0.0000028509498],"category_scores_gemma":[0.00012227509,0.0001289207,0.0001364921,0.0018340747,0.00007411966,0.0007314997,0.000028710383,0.00035813748,0.0000055091236],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018408829,0.00027086484,0.0004924477,0.00018384772,0.0002165911,0.00006126295,0.0013652154,0.000026036858,0.14575434,0.23714884,0.0025302183,0.6117663],"study_design_scores_gemma":[0.0036121109,0.002622273,0.27414733,0.0015470791,0.0005222424,0.0006022583,0.0006130379,0.59507024,0.06434594,0.040439244,0.015452038,0.0010261842],"about_ca_topic_score_codex":0.0000073523715,"about_ca_topic_score_gemma":0.000001871278,"teacher_disagreement_score":0.80458534,"about_ca_system_score_codex":0.00011218456,"about_ca_system_score_gemma":0.0003742388,"threshold_uncertainty_score":0.52572334},"labels":[],"label_agreement":null},{"id":"W4393073718","doi":"10.1007/s00357-024-09469-z","title":"Editorial: Journal of Classification Vol. 41-1","year":2024,"lang":"en","type":"editorial","venue":"Journal of Classification","topic":"Optics and Image Analysis","field":"Business, Management and Accounting","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Pattern recognition (psychology); Artificial intelligence; Mathematics; Computer science","score_opus":0.018330536475646586,"score_gpt":0.2715214721715441,"score_spread":0.2531909356958975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393073718","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019279362,0.000917097,0.0015890297,0.0015387347,0.99274474,0.00011057175,0.000013691791,0.000020648882,0.0028727183],"genre_scores_gemma":[0.005995201,0.0011135672,0.0003254674,0.000055365366,0.9911719,0.0000033125004,0.00011037108,0.00008963583,0.0011351684],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99440825,0.00005118263,0.0024151525,0.00028889943,0.002569096,0.00026739005],"domain_scores_gemma":[0.97636276,0.00030959392,0.007467448,0.00041626475,0.015395211,0.00004869484],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0031726789,0.00037832276,0.00092674606,0.0017756742,0.00012666578,0.0016670814,0.0009365918,0.000804413,0.00012274034],"category_scores_gemma":[0.006036498,0.00030518253,0.0008230367,0.0009799782,0.0000900927,0.0026254642,0.00008899311,0.0018970086,0.000225016],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011674409,0.00014699277,0.00003681319,0.00034256544,0.00036092778,0.000013030867,0.000023815228,0.000014663114,0.0016138164,0.000828374,0.99139357,0.0051087188],"study_design_scores_gemma":[0.0005439888,0.000073673684,0.00018064977,0.0004916869,0.0019808228,0.0000051064344,0.00023178328,0.0016852368,0.000020141062,0.002387337,0.99212384,0.0002757053],"about_ca_topic_score_codex":0.000024805186,"about_ca_topic_score_gemma":0.00000963418,"teacher_disagreement_score":0.018045492,"about_ca_system_score_codex":0.00032542978,"about_ca_system_score_gemma":0.0007870833,"threshold_uncertainty_score":0.99994004},"labels":[],"label_agreement":null},{"id":"W4396675678","doi":"10.1007/s00357-024-09470-6","title":"Skew Multiple Scaled Mixtures of Normal Distributions with Flexible Tail Behavior and Their Application to Clustering","year":2024,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"National Science Council","keywords":"Cluster analysis; Skew; Mathematics; Skew normal distribution; Pattern recognition (psychology); Statistics; Normal distribution; Computer science; Statistical physics; Artificial intelligence; Physics","score_opus":0.021196143170225674,"score_gpt":0.28421407031829893,"score_spread":0.26301792714807326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396675678","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04023567,0.00031315218,0.95785916,0.001198785,0.00010484164,0.0001628411,0.000008536945,0.000025736656,0.00009127647],"genre_scores_gemma":[0.7626197,0.000020438625,0.23722629,0.000020282989,0.000058212943,0.000016151094,0.0000022473785,0.0000051084203,0.00003157363],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922305,0.000051194602,0.0003156477,0.00015613422,0.00015223192,0.00010172785],"domain_scores_gemma":[0.99923974,0.00008871563,0.00017760963,0.00020960675,0.00019120376,0.00009309731],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004227879,0.00008701604,0.00014994577,0.0001426346,0.00006093058,0.00010676192,0.00024002497,0.000048544916,0.0000012749695],"category_scores_gemma":[0.000025096228,0.00005875392,0.000048906335,0.00033364818,0.00003374329,0.00038687687,0.000043172637,0.00013213913,0.0000011238078],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050067567,0.00011029227,0.0011293032,0.000078261975,0.000032440166,0.000003389568,0.0010702106,0.000086100765,0.34562922,0.035021845,0.00022613259,0.6165627],"study_design_scores_gemma":[0.0013297834,0.0010410661,0.1866015,0.00075005693,0.00019839942,0.00079877255,0.00019952325,0.519261,0.26106068,0.015292253,0.012859499,0.0006074594],"about_ca_topic_score_codex":0.000005228114,"about_ca_topic_score_gemma":0.000005649018,"teacher_disagreement_score":0.72238404,"about_ca_system_score_codex":0.000037733716,"about_ca_system_score_gemma":0.00007375535,"threshold_uncertainty_score":0.23959154},"labels":[],"label_agreement":null},{"id":"W4399158654","doi":"10.1007/s00357-024-09473-3","title":"Finding Outliers in Gaussian Model-based Clustering","year":2024,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Canada Research Chairs","keywords":"Outlier; Cluster analysis; Pattern recognition (psychology); Artificial intelligence; Mathematics; Gaussian; Computer science; Statistics; Physics","score_opus":0.05584761604273475,"score_gpt":0.3315201195779214,"score_spread":0.27567250353518663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399158654","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023546137,0.00025459356,0.99164337,0.0036419954,0.0004884013,0.000045626897,3.112279e-7,0.00002538339,0.0015457183],"genre_scores_gemma":[0.62439203,0.000012139382,0.3753906,0.00008069272,0.00005578778,0.000001342517,1.7876725e-7,0.0000050776816,0.0000621913],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990753,0.000078028796,0.00037095379,0.00014422629,0.00020307243,0.00012843485],"domain_scores_gemma":[0.99950194,0.00006950654,0.00013971276,0.00017696862,0.000047321755,0.00006455803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010505695,0.00007363899,0.00012762594,0.00038570073,0.000029782694,0.00018846261,0.0003445548,0.000059824346,0.0000021870533],"category_scores_gemma":[0.000036577367,0.00006040191,0.00007756175,0.00035043093,0.0000137221905,0.0005459177,0.00002063885,0.00024887302,0.0000035338207],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022404434,0.000068449466,0.00019590506,0.00010999118,0.000019556164,0.000085664666,0.0022271823,0.029846894,0.023879398,0.1958383,0.0007715416,0.7469347],"study_design_scores_gemma":[0.00013568862,0.00002635254,0.0008587963,0.00016450977,0.000005184045,0.000021659613,0.000013669968,0.9800603,0.0005967746,0.017569562,0.000481574,0.00006597536],"about_ca_topic_score_codex":8.547074e-7,"about_ca_topic_score_gemma":0.0000024825943,"teacher_disagreement_score":0.9502134,"about_ca_system_score_codex":0.00013029727,"about_ca_system_score_gemma":0.00019583298,"threshold_uncertainty_score":0.24631186},"labels":[],"label_agreement":null},{"id":"W4400293933","doi":"10.1007/s00357-024-09485-z","title":"Editorial: Journal of Classification Vol. 41-2","year":2024,"lang":"en","type":"editorial","venue":"Journal of Classification","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Pattern recognition (psychology); Artificial intelligence; Computer science; Mathematics","score_opus":0.02155354905929521,"score_gpt":0.3052997013690565,"score_spread":0.2837461523097613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400293933","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000069475536,0.0016333107,0.2612477,0.0015736971,0.7347525,0.00017681289,0.000021357147,0.000089442394,0.0004982709],"genre_scores_gemma":[0.0017407469,0.0035623845,0.010245225,0.000028750293,0.9829981,0.000011735383,0.00003461586,0.00007682692,0.0013016291],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9916576,0.00045422668,0.003425154,0.0005339235,0.0035408423,0.00038823285],"domain_scores_gemma":[0.975936,0.0010373067,0.007873215,0.001062015,0.013788013,0.00030348546],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.005074794,0.00052623346,0.001107761,0.0014685545,0.00014403481,0.0009982527,0.003504687,0.0015251826,0.000023652969],"category_scores_gemma":[0.005175478,0.00042418262,0.0008445847,0.0013230406,0.00018886787,0.0020247332,0.00017256745,0.0032152098,0.00009222304],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008119968,0.00018610376,0.0000034037114,0.00018729772,0.00014909515,0.000014943581,0.00020328592,9.204189e-7,0.008855056,0.0049014115,0.96106225,0.024355007],"study_design_scores_gemma":[0.0004898649,0.0005953031,0.0000723162,0.000665842,0.0002620335,0.00006704672,0.00009558431,0.0010565551,0.0031719801,0.00841679,0.98472714,0.0003795682],"about_ca_topic_score_codex":0.000004194865,"about_ca_topic_score_gemma":0.0000010696682,"teacher_disagreement_score":0.25100246,"about_ca_system_score_codex":0.00094989943,"about_ca_system_score_gemma":0.0035007873,"threshold_uncertainty_score":0.999821},"labels":[],"label_agreement":null},{"id":"W4403170718","doi":"10.1007/s00357-024-09493-z","title":"Mixed-Type Distance Shrinkage and Selection for Clustering via Kernel Metric Learning","year":2024,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"University of British Columbia","keywords":"Cluster analysis; Shrinkage; Selection (genetic algorithm); Mathematics; Kernel (algebra); Artificial intelligence; Metric (unit); Pattern recognition (psychology); Type (biology); Statistics; Computer science; Combinatorics; Geology; Engineering","score_opus":0.04542069984512903,"score_gpt":0.3289202876242669,"score_spread":0.28349958777913786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403170718","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0072160005,0.0012154287,0.9902298,0.00059986924,0.00050836,0.00009857723,3.1385656e-7,0.00006112916,0.000070506416],"genre_scores_gemma":[0.8892338,0.00021719925,0.10985783,0.000009029581,0.0002004097,0.0000057707207,6.5299344e-7,0.000013413461,0.0004618576],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989573,0.00006211611,0.0003079694,0.00020710258,0.00029629047,0.00016922758],"domain_scores_gemma":[0.9990738,0.0002766084,0.00017341567,0.0000933591,0.00030702993,0.00007578929],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075670634,0.00008384466,0.00012923001,0.00036694607,0.00012366395,0.0002952709,0.0002494611,0.000048921,0.0000015248296],"category_scores_gemma":[0.00026728588,0.00007526204,0.000049232665,0.00085396867,0.000023538576,0.0008602858,0.0000635217,0.0003073739,0.000003951629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048393224,0.000028108414,0.0003118636,0.00022550773,0.00004706786,0.000008781315,0.00037386644,0.009022033,0.057373703,0.004867884,0.00017613491,0.92751664],"study_design_scores_gemma":[0.00016214541,0.00023058942,0.0037502497,0.000075513584,0.000009140526,0.00015469531,0.000036498124,0.9805384,0.0015903487,0.001294729,0.012076724,0.000080941485],"about_ca_topic_score_codex":0.0000015926535,"about_ca_topic_score_gemma":0.0000028285485,"teacher_disagreement_score":0.9715164,"about_ca_system_score_codex":0.00018256462,"about_ca_system_score_gemma":0.000072012976,"threshold_uncertainty_score":0.3069097},"labels":[],"label_agreement":null},{"id":"W4403438151","doi":"10.1007/s00357-024-09494-y","title":"Vine Copula-Based Classifiers with Applications","year":2024,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Horticultural and Viticultural Research","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Technische Universität München; Deutsche Forschungsgemeinschaft","keywords":"Copula (linguistics); Vine copula; Artificial intelligence; Pattern recognition (psychology); Computer science; Mathematics; Natural language processing; Machine learning; Statistics; Econometrics","score_opus":0.05394189423688334,"score_gpt":0.3027071154114639,"score_spread":0.24876522117458055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403438151","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9675521,0.00079529063,0.0016547701,0.027354376,0.0001485162,0.00037152847,0.000021486938,0.000086454806,0.0020154335],"genre_scores_gemma":[0.99845123,0.000055858512,0.00036862283,0.000088421504,0.00043276028,0.000024102135,0.000034433673,0.0000010951029,0.0005434673],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99892896,0.000050311268,0.00030025118,0.00014413147,0.0004129041,0.00016346238],"domain_scores_gemma":[0.9991778,0.00017843519,0.0001224223,0.00004098914,0.00034119148,0.00013916095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025991592,0.00009614128,0.0001309335,0.000028760764,0.00011777724,0.00017175368,0.00019070286,0.00006203281,0.0001904801],"category_scores_gemma":[0.0000345198,0.000026124631,0.00010034976,0.0005762434,0.00007125941,0.00025335263,0.000008148374,0.00022229353,0.000055982557],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007892309,0.00009133788,0.0009171859,0.000032035474,0.0000341114,0.000015160479,0.000034023913,0.000022142543,0.76080126,0.0034768253,0.003196581,0.23130044],"study_design_scores_gemma":[0.00032988613,0.0013632126,0.19045322,0.00030121236,0.000110630004,0.00016505383,0.0011033295,0.0042668306,0.023037683,0.0006151298,0.7779113,0.00034248742],"about_ca_topic_score_codex":0.0000068805493,"about_ca_topic_score_gemma":0.000039329556,"teacher_disagreement_score":0.77471477,"about_ca_system_score_codex":0.000077018274,"about_ca_system_score_gemma":0.000046633544,"threshold_uncertainty_score":0.20856236},"labels":[],"label_agreement":null},{"id":"W4404725773","doi":"10.1007/s00357-024-09496-w","title":"Editorial: Journal of Classification Vol. 41-3","year":2024,"lang":"en","type":"editorial","venue":"Journal of Classification","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; MacEwan University","funders":"","keywords":"Mathematics; Artificial intelligence; Pattern recognition (psychology); Computer science","score_opus":0.021368677956954095,"score_gpt":0.30503049146691724,"score_spread":0.28366181350996317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404725773","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000068856775,0.0016184979,0.26041043,0.0015483613,0.7356259,0.00017687432,0.00002138608,0.00009168285,0.00049998326],"genre_scores_gemma":[0.001679587,0.0034513741,0.010303181,0.000028845765,0.9830617,0.0000117454,0.00003423248,0.000076841854,0.001352539],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9916566,0.00045366073,0.0034281125,0.0005338404,0.0035398025,0.0003880113],"domain_scores_gemma":[0.97593826,0.0010334724,0.007883422,0.0010619228,0.013780236,0.00030267544],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0050729066,0.00052602676,0.0011085784,0.0014673957,0.0001438862,0.0010129979,0.003500687,0.0015247833,0.000023964056],"category_scores_gemma":[0.005174808,0.00042407663,0.0008441088,0.0013218233,0.00018857239,0.002022946,0.00017242212,0.0032143092,0.00009263359],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007938262,0.00018583509,0.0000033300942,0.00018668284,0.0001489173,0.000015086473,0.00020068146,9.702059e-7,0.008644076,0.0050019254,0.9606737,0.024859421],"study_design_scores_gemma":[0.000489803,0.0005931192,0.000074243726,0.0006647356,0.00026177437,0.00006754613,0.0000922715,0.0011197015,0.003105015,0.008334811,0.9848177,0.00037931584],"about_ca_topic_score_codex":0.0000041201733,"about_ca_topic_score_gemma":0.0000010167789,"teacher_disagreement_score":0.25010723,"about_ca_system_score_codex":0.0009560823,"about_ca_system_score_gemma":0.0035715941,"threshold_uncertainty_score":0.9998211},"labels":[],"label_agreement":null},{"id":"W4408349876","doi":"10.1007/s00357-025-09505-6","title":"Editorial: Journal of Classification Vol. 42-1","year":2025,"lang":"en","type":"editorial","venue":"Journal of Classification","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Pattern recognition (psychology); Artificial intelligence; Computer science; Mathematics","score_opus":0.017133976611363583,"score_gpt":0.3023350735259501,"score_spread":0.28520109691458656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408349876","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000042871375,0.0007050484,0.36320168,0.001238651,0.63391244,0.00016947064,0.00001706945,0.00005326802,0.0006980666],"genre_scores_gemma":[0.0011053211,0.0034501413,0.014521221,0.00004472686,0.9789512,0.000012020532,0.00003933385,0.000041466683,0.0018345396],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99190915,0.0005786882,0.0034991368,0.0004898952,0.0031431997,0.000379954],"domain_scores_gemma":[0.9685805,0.001436818,0.010168669,0.0011708718,0.018385505,0.0002576319],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.004804299,0.0005020671,0.0011899293,0.0015238163,0.00018967655,0.0006454083,0.003986119,0.0015686066,0.000019556215],"category_scores_gemma":[0.008503011,0.0004239729,0.00076594326,0.0013722306,0.0001788899,0.001931746,0.00017113524,0.002680415,0.0000210056],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011946401,0.00024825556,0.000009253005,0.00014394392,0.00013265906,0.0000059651106,0.00011839485,0.0000013264845,0.005804494,0.0046310783,0.95881516,0.02997001],"study_design_scores_gemma":[0.00079839485,0.0004892188,0.0001865567,0.000623828,0.00021249332,0.000025091078,0.000082594976,0.00070001744,0.003912527,0.0046899565,0.9879307,0.00034860885],"about_ca_topic_score_codex":0.0000052720184,"about_ca_topic_score_gemma":0.0000011907696,"teacher_disagreement_score":0.34868047,"about_ca_system_score_codex":0.000931314,"about_ca_system_score_gemma":0.004820086,"threshold_uncertainty_score":0.9998488},"labels":[],"label_agreement":null},{"id":"W4412177048","doi":"10.1007/s00357-025-09514-5","title":"Editorial: Journal of Classification Vol. 42-2","year":2025,"lang":"en","type":"editorial","venue":"Journal of Classification","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Pattern recognition (psychology); Mathematics; Artificial intelligence; Computer science","score_opus":0.017361618188325673,"score_gpt":0.3030496181655725,"score_spread":0.28568799997724686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412177048","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000042200422,0.000706364,0.36436254,0.0012397068,0.63275534,0.00016910449,0.000016877846,0.00005319748,0.00069268985],"genre_scores_gemma":[0.0010726828,0.0034525527,0.0146043,0.000044669974,0.97893256,0.000012187875,0.000039400722,0.00004144526,0.0018002224],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9919112,0.0005788962,0.0034981803,0.0004898641,0.0031419739,0.00037991666],"domain_scores_gemma":[0.96858877,0.0014373014,0.010166028,0.0011705377,0.018380823,0.0002565244],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.004802191,0.0005020685,0.0011899614,0.0015234877,0.00018963944,0.00064488396,0.0039842497,0.0015683664,0.000019189425],"category_scores_gemma":[0.0084891105,0.0004239923,0.00076585676,0.0013756644,0.00017886094,0.001931378,0.00017113595,0.0026797531,0.000020757489],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000119223085,0.00024804875,0.0000093072385,0.0001438483,0.00013255911,0.000005957865,0.00011902095,0.0000013053818,0.0058621983,0.004636532,0.9578754,0.030846648],"study_design_scores_gemma":[0.00079427584,0.00048822354,0.00018517186,0.0006247538,0.00021227036,0.000025067216,0.00008201609,0.0007103904,0.0038839437,0.004702095,0.9879434,0.0003483779],"about_ca_topic_score_codex":0.000005444608,"about_ca_topic_score_gemma":0.000001233598,"teacher_disagreement_score":0.34975824,"about_ca_system_score_codex":0.0009411233,"about_ca_system_score_gemma":0.0048857485,"threshold_uncertainty_score":0.9998628},"labels":[],"label_agreement":null},{"id":"W4415830087","doi":"10.1007/s00357-025-09525-2","title":"Editorial: Journal of Classification Vol. 42-3","year":2025,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Library Science and Information Systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"","score_opus":0.025546650572988605,"score_gpt":0.27815162940695665,"score_spread":0.25260497883396804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415830087","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011638328,0.00026637505,0.8147137,0.009522025,0.15461086,0.00015706924,0.0000012769168,0.000029612163,0.009060715],"genre_scores_gemma":[0.9716762,0.00016503973,0.0070676324,0.0004089468,0.019956887,0.0000023880173,0.0000014670281,0.000005207346,0.00071625935],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997219,0.00014396175,0.0015003226,0.00010562333,0.00088973815,0.00014131189],"domain_scores_gemma":[0.9944768,0.00013905227,0.0025047967,0.0003551196,0.0024211414,0.000103074824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022568468,0.000098918375,0.00025474816,0.0006498361,0.00011035867,0.0004197158,0.0014641184,0.0001139993,0.000009888116],"category_scores_gemma":[0.0005039352,0.00007477124,0.00015837446,0.0010011955,0.00005763711,0.0073650084,0.000049112376,0.00028136515,0.000024283183],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040338284,0.00010140139,0.002170644,0.000032870394,0.00004163499,0.0000011914832,0.001393095,0.00009231186,0.014947592,0.062011022,0.8817476,0.037420265],"study_design_scores_gemma":[0.0009159627,0.00027537276,0.03761696,0.0001991209,0.000015728083,0.0000695967,0.0014532816,0.020332718,0.0043681404,0.005805773,0.9288015,0.00014585187],"about_ca_topic_score_codex":0.0000010597283,"about_ca_topic_score_gemma":1.689876e-7,"teacher_disagreement_score":0.9600378,"about_ca_system_score_codex":0.00012571596,"about_ca_system_score_gemma":0.00083844364,"threshold_uncertainty_score":0.5339453},"labels":[],"label_agreement":null},{"id":"W4415853390","doi":"10.1007/s00357-025-09526-1","title":"Extending Cluster-Weighted Factor Analyzers for Multivariate Prediction and Interpretability","year":2025,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Canada Excellence Research Chairs, Government of Canada","keywords":"Interpretability; Disjoint sets; Multivariate statistics; Maximization; Latent variable; Set (abstract data type); Support vector machine; Expectation–maximization algorithm; Factor analysis","score_opus":0.028036922328684596,"score_gpt":0.33200583274420276,"score_spread":0.30396891041551816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415853390","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020289145,0.00013856652,0.9768464,0.0017022856,0.00063078065,0.00016564602,0.0000044373337,0.0000183378,0.00020438098],"genre_scores_gemma":[0.65802133,0.000025565387,0.34178478,0.00006308432,0.000045932757,0.0000043736904,6.421052e-7,0.0000023400498,0.000051920662],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990617,0.00014229857,0.00041955608,0.0001706385,0.000110489935,0.000095307165],"domain_scores_gemma":[0.9989172,0.0002571135,0.0003328927,0.00019117698,0.00024739665,0.0000542027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008680017,0.000075982665,0.00016604863,0.00020191782,0.000078152894,0.00009880346,0.00022622659,0.000068597124,0.0000015489297],"category_scores_gemma":[0.0001947672,0.000059643746,0.00008151997,0.00019537385,0.00002605014,0.0005313146,0.0000349124,0.00012197997,1.5173957e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012551295,0.00009356703,0.0026890107,0.00007781176,0.0000921218,5.028776e-7,0.00084713515,0.000010474872,0.06269575,0.09184448,0.00043924115,0.8410844],"study_design_scores_gemma":[0.0008622014,0.00012504036,0.10375128,0.000111554764,0.00004992449,0.000011027264,0.00003426795,0.81515783,0.0050754705,0.072936684,0.0017959995,0.00008872017],"about_ca_topic_score_codex":0.0000015116419,"about_ca_topic_score_gemma":7.394852e-7,"teacher_disagreement_score":0.84099567,"about_ca_system_score_codex":0.000081680795,"about_ca_system_score_gemma":0.00006828355,"threshold_uncertainty_score":0.24322014},"labels":[],"label_agreement":null},{"id":"W4416943890","doi":"10.1007/s00357-025-09522-5","title":"Implications of Different Encodings of Binned Data when Clustering","year":2025,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Encoding (memory); Latent class model; ENCODE; Class (philosophy); Pattern recognition (psychology); Medoid; Latent variable; Single-linkage clustering","score_opus":0.088042672940701,"score_gpt":0.3476281171019941,"score_spread":0.2595854441612931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416943890","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005843073,0.00012997477,0.98680097,0.0052623204,0.00020208729,0.00006785444,0.0000044651842,0.0000062870536,0.0016829437],"genre_scores_gemma":[0.69577974,0.0000750279,0.3039989,0.00004958895,0.0000246135,0.0000011276377,0.0000018641123,0.0000022537554,0.00006689803],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99893117,0.000083849176,0.0006151246,0.00013647419,0.0001582336,0.00007515172],"domain_scores_gemma":[0.99801064,0.0001391744,0.000760181,0.00076222763,0.00029191066,0.000035862413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006536663,0.000062898034,0.0002148752,0.00021244552,0.000031083582,0.00002694438,0.0012474846,0.000045825764,0.0000030122128],"category_scores_gemma":[0.00011864037,0.000049214992,0.000058835245,0.00023542107,0.00003252217,0.0003754964,0.00019768406,0.00010271172,2.3591538e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001970893,0.00016671896,0.0015541295,0.00008912861,0.000058554757,2.935418e-7,0.0005066506,0.000009971957,0.2663858,0.3499724,0.002227678,0.37900895],"study_design_scores_gemma":[0.0012649992,0.00024904133,0.24907629,0.00066975254,0.00017439606,0.000036730715,0.0001099894,0.21117005,0.06963415,0.4628275,0.0045343027,0.00025279835],"about_ca_topic_score_codex":0.000003186197,"about_ca_topic_score_gemma":0.0000032315481,"teacher_disagreement_score":0.6899367,"about_ca_system_score_codex":0.00003166405,"about_ca_system_score_gemma":0.00010603595,"threshold_uncertainty_score":0.23181576},"labels":[],"label_agreement":null}]}