{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":421,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":421,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"dc115bc2231e","filters":{"topic":"Advanced Clustering Algorithms Research"}},"results":[{"id":"W151377110","doi":"10.1007/978-3-642-37456-2_14","title":"Density-Based Clustering Based on Hierarchical Density Estimates","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":2412,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Cluster analysis; Hierarchical clustering; Data mining; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.02155881081884803,"gpt":0.2774625965106832,"spread":0.2559037856918352,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001052845,0.0008777426,0.0008121474,0.001471137,0.0005455339,0.001057072,0.004706081,0.0004710053,0.00004578003],"category_scores_gemma":[0.0003945358,0.0008144166,0.0002083274,0.0008059339,0.001213467,0.0005700341,0.002449255,0.00205431,0.0002466564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008054438,"about_ca_system_score_gemma":0.0009778027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004348464,"about_ca_topic_score_gemma":0.00008872511,"domain_scores_codex":[0.9931122,0.00008708959,0.0006162942,0.002569691,0.002237341,0.00137739],"domain_scores_gemma":[0.9941137,0.002007819,0.0002604406,0.00265572,0.0004708926,0.0004914713],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001960235,0.00004747265,0.0000446695,0.00007673001,0.000006522412,0.0003030121,0.00007823299,0.6124852,0.0002108438,0.001298455,0.00001197622,0.3854173],"study_design_scores_gemma":[0.0004330807,0.0003426055,0.0002479205,0.0005968327,0.000004715842,0.00004912816,3.867472e-8,0.9581263,0.003744454,0.03548161,0.0001738449,0.0007994969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001602876,0.0000440658,0.9947513,0.00155443,0.001182852,0.0006549079,0.000004236771,0.0004354038,0.001212505],"genre_scores_gemma":[0.1128377,0.000004031501,0.8837252,0.002809397,0.0003212957,0.00002467051,0.000007883185,0.00007255353,0.0001971979],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3846178,"threshold_uncertainty_score":0.9999799,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W182707955","doi":"10.1137/1.9781611972764.29","title":"Density-Based Clustering over an Evolving Data Stream with Noise","year":2006,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":1000,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Cluster analysis; Noise (video); Data mining; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.03032982938399182,"gpt":0.3020425877552507,"spread":0.2717127583712589,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000275563,0.0001766192,0.0001513009,0.0001307894,0.0001815008,0.0004560052,0.002062413,0.0000438822,0.00003242761],"category_scores_gemma":[0.00002656558,0.0001455876,0.00001740601,0.0004121062,0.00006038192,0.002184626,0.001332481,0.0001755995,0.00002418359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008756757,"about_ca_system_score_gemma":0.0001236976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001008662,"about_ca_topic_score_gemma":0.001484942,"domain_scores_codex":[0.9979243,0.00005600346,0.0001747116,0.0007856931,0.0005699436,0.0004893601],"domain_scores_gemma":[0.9971623,0.00009492016,0.00005172751,0.002413934,0.0001358883,0.000141168],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002293291,0.001521568,0.04469807,0.0002968129,0.00009534013,0.001735543,0.0003833964,0.6265996,0.02511273,0.005678869,0.004260951,0.2893878],"study_design_scores_gemma":[0.0004971521,0.0001102731,0.01100977,0.00002507097,0.000002642831,0.000022436,0.00001069151,0.9856527,0.001930206,0.0001543643,0.0003555551,0.0002291121],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03383157,0.00001679622,0.9637616,0.0001642087,0.0000625453,0.0001432477,0.000005801495,0.0004070088,0.001607275],"genre_scores_gemma":[0.4777761,4.654788e-7,0.5215636,0.0001107763,0.0000825446,0.000004849921,0.00002679125,0.00001811896,0.0004167395],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4439445,"threshold_uncertainty_score":0.5936891,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1987111416","doi":"10.1002/widm.30","title":"Density‐based clustering","year":2011,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":810,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Outlier; Data set; Computer science; Data mining; Cluster (spacecraft); Set (abstract data type); Single-linkage clustering; DBSCAN; Pattern recognition (psychology); Correlation clustering; CURE data clustering algorithm; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1565194252285615,"gpt":0.3728985120791855,"spread":0.216379086850624,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.001249449,0.0003746131,0.0005722687,0.0002261274,0.0003815498,0.0003492721,0.0029982,0.00008797894,0.00001849859],"category_scores_gemma":[0.0001654331,0.0003151953,0.0001024128,0.0004673195,0.0002003556,0.003246274,0.01558232,0.0002762846,0.0001242306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006526555,"about_ca_system_score_gemma":0.0001208292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008572723,"about_ca_topic_score_gemma":0.00009555346,"domain_scores_codex":[0.9970751,0.0002733188,0.0006131985,0.001249951,0.0002089093,0.0005795358],"domain_scores_gemma":[0.9964978,0.0001803237,0.0001862953,0.002831871,0.00007036999,0.0002333453],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006613664,0.0002984927,0.0007937707,0.0006553823,0.00004833922,0.0001500915,0.007479899,0.000005711416,0.0002462685,0.000263545,0.007463695,0.9825287],"study_design_scores_gemma":[0.001571717,0.0008989761,0.002683229,0.007354008,0.0001017259,0.000534586,0.001346366,0.9414206,0.0008216036,0.001104654,0.04011967,0.002042859],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006676279,0.01631011,0.9686033,0.0001469664,0.0008680844,0.0004533319,0.00005175355,0.0002121513,0.006678066],"genre_scores_gemma":[0.3157856,0.004738836,0.6746106,0.000310734,0.0006231533,0.0002075017,0.0003054043,0.0001246883,0.003293408],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9804858,"threshold_uncertainty_score":0.99993,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2270192120","doi":"10.1371/journal.pone.0144059","title":"A Comparison Study on Similarity and Dissimilarity Measures in Clustering Continuous Data","year":2015,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":408,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"IBM (Canada)","funders":"Universiti Malaya","keywords":"Similarity (geometry); Cluster analysis; Computer science; Data mining; Benchmark (surveying); Distance measures; Similarity measure; Measure (data warehouse); Cluster (spacecraft); Pattern recognition (psychology); Artificial intelligence; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.4315200459840546,"gpt":0.4023074041110184,"spread":0.02921264187303624,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001359528,0.0001717244,0.0004234931,0.0001451788,0.00008667685,0.000228345,0.001563195,0.00005693714,0.000001098661],"category_scores_gemma":[0.0007806861,0.0001682708,0.00001037008,0.0003336209,0.00005996576,0.0006011096,0.002909433,0.0004810266,0.00000939965],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000107117,"about_ca_system_score_gemma":0.00006203075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001897275,"about_ca_topic_score_gemma":0.0005908677,"domain_scores_codex":[0.9972825,0.0002679074,0.0003030888,0.0007500186,0.001001245,0.0003952508],"domain_scores_gemma":[0.9978405,0.0001788096,0.00006778325,0.0015519,0.0001215215,0.0002395502],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004827943,0.03187959,0.8636237,0.0002435435,0.0003874583,0.0005972164,0.01910749,0.00197927,0.001824261,0.0002853788,0.0003865876,0.07920274],"study_design_scores_gemma":[0.002137215,0.0009779115,0.08587564,0.0001654021,0.00001857557,0.000004503942,0.0008618334,0.9081994,0.0007884608,0.0005243316,0.00009685096,0.0003499153],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8611459,0.0002131435,0.1353776,0.001318403,0.00008157251,0.001013372,0.00002034751,0.0002453682,0.0005843471],"genre_scores_gemma":[0.9568639,0.000007065973,0.04293545,0.0000598997,0.00004276871,0.00002637491,0.000004790929,0.00001388652,0.00004584976],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9062201,"threshold_uncertainty_score":0.6861886,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1973892392","doi":"10.1016/s0167-8655(02)00130-7","title":"Collaborative fuzzy clustering","year":2002,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":282,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Partition (number theory); Computer science; Data mining; Fuzzy clustering; Fuzzy logic; Theoretical computer science; Basis (linear algebra); Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03460746886099782,"gpt":0.2677783852425724,"spread":0.2331709163815745,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001476737,0.0001795274,0.0001539477,0.0001978331,0.0001687844,0.0002402516,0.0005807647,0.00004750667,0.0002230743],"category_scores_gemma":[0.00004300358,0.0001904389,0.00005467992,0.0005564661,0.00005848612,0.0008094682,0.0002812129,0.0002346105,0.001774137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00010423,"about_ca_system_score_gemma":0.000007001006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000101087,"about_ca_topic_score_gemma":0.000009510104,"domain_scores_codex":[0.998292,0.0001245547,0.0002346039,0.0004884921,0.0003994963,0.0004608709],"domain_scores_gemma":[0.9991207,0.0001170049,0.00008825053,0.0004151584,0.0001235606,0.0001353776],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002826753,0.00004631335,0.0002066886,0.00002692239,0.00002389546,0.0001227841,0.001022304,0.0003376847,0.004254335,0.000004981078,0.002884682,0.9910666],"study_design_scores_gemma":[0.0031539,0.0003134024,0.003533142,0.0003164759,0.00001895015,0.0003411532,0.0002787236,0.9623886,0.01485813,0.00126235,0.01159175,0.0019434],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02282984,0.00005380341,0.965444,0.008426816,0.0004479688,0.0002501696,0.00001743516,0.000335118,0.00219491],"genre_scores_gemma":[0.8383354,0.0001270265,0.1454315,0.01486503,0.0005268403,0.0002564427,0.00002734131,0.00006675348,0.0003636544],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9891232,"threshold_uncertainty_score":0.9990031,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2408186052","doi":"10.1137/1.9781611973440.96","title":"Density-Based Clustering Validation","year":2014,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":262,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Cluster analysis; Computer science; Data mining; Kernel density estimation; Cluster (spacecraft); Kernel (algebra); Mathematics; Artificial intelligence; Pattern recognition (psychology); Statistics; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.02015969811375551,"gpt":0.284899446381844,"spread":0.2647397482680885,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003345482,0.00007191177,0.00007471737,0.00008736449,0.00009496776,0.0001362622,0.0005213515,0.00002822451,0.00001461886],"category_scores_gemma":[0.00008506835,0.0000668047,0.00002554242,0.0002239116,0.00001867684,0.0003083158,0.0002727801,0.00008212535,0.0001627923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004044336,"about_ca_system_score_gemma":0.00002268143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001463024,"about_ca_topic_score_gemma":0.000006047398,"domain_scores_codex":[0.999074,0.00006507905,0.000103645,0.0002597054,0.0002699811,0.0002275224],"domain_scores_gemma":[0.9992111,0.0001151694,0.00002530429,0.0004945309,0.00007578744,0.00007809412],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001173274,0.00007471466,0.0007118647,0.00006462028,0.00001092541,0.00001509127,0.0001882131,0.1316565,0.01551126,0.0356356,0.000393315,0.8157262],"study_design_scores_gemma":[0.0001836892,0.00003806444,0.0004239237,0.000005903991,4.485261e-7,0.000004353851,0.000001849713,0.9618256,0.03412879,0.001366258,0.001930673,0.00009043209],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00417472,0.00000161157,0.9903093,0.0007407663,0.0001419303,0.00006346686,7.707574e-8,0.0003184702,0.004249689],"genre_scores_gemma":[0.5202144,3.001173e-7,0.4789862,0.0002843829,0.00004120487,0.000005648779,8.886765e-7,0.000005674014,0.0004613044],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8301691,"threshold_uncertainty_score":0.2724217,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1560541823","doi":"10.1007/978-3-540-24741-8_9","title":"LIMBO: Scalable Clustering of Categorical Data","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":260,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Categorical variable; Cluster analysis; Computer science; Data mining; Tuple; Data stream clustering; Hierarchical clustering; Bottleneck; Scalability; Measure (data warehouse); CURE data clustering algorithm; Correlation clustering; Clustering high-dimensional data; Artificial intelligence; Machine learning; Database; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04748493022922919,"gpt":0.3097387021538155,"spread":0.2622537719245863,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001205164,0.0005360007,0.0007265948,0.0009317759,0.0002067775,0.0003800489,0.01159087,0.0003363326,0.00002770917],"category_scores_gemma":[0.0002157368,0.0005094908,0.00009256483,0.001027056,0.00102307,0.001230497,0.01265155,0.001174847,0.00004592852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006443911,"about_ca_system_score_gemma":0.001318411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001051044,"about_ca_topic_score_gemma":0.00008379173,"domain_scores_codex":[0.9941866,0.00003491182,0.0007281851,0.002292896,0.00177164,0.0009858136],"domain_scores_gemma":[0.9940843,0.0004851949,0.0003175676,0.004507013,0.0003407173,0.0002651922],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008135601,0.0000479449,0.00001008101,0.0001401343,0.00001441524,0.0002130566,0.0002861826,0.2899748,0.0002000741,0.009538195,0.00001000874,0.6995569],"study_design_scores_gemma":[0.0003047069,0.0001768092,0.00002781117,0.0003663483,0.000004556136,0.0001226205,1.089588e-7,0.8738716,0.0009581893,0.1231642,0.0005002025,0.0005027671],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000009869559,0.0004661749,0.9950686,0.0005129403,0.001207093,0.0003564725,0.00001442922,0.0001526264,0.002211819],"genre_scores_gemma":[0.05062989,0.0001027665,0.9481131,0.0002377613,0.000391141,0.000006198369,0.000015594,0.00005766701,0.0004458115],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6990542,"threshold_uncertainty_score":0.9997357,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2111596024","doi":"10.1109/tpami.2007.1138","title":"Cumulative Voting Consensus Method for Partitions with Variable Number of Clusters","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":232,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Categorical variable; Probabilistic logic; Voting; Entropy (arrow of time); Consensus clustering; Data mining; Algorithm; Mathematics; Correlation clustering; Artificial intelligence; CURE data clustering algorithm; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.03456688832831332,"gpt":0.3610294286362877,"spread":0.3264625403079743,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007467918,0.0001684701,0.0003078692,0.0003402854,0.0002108573,0.00004999258,0.0002716447,0.00005009751,0.00004297823],"category_scores_gemma":[0.00001466368,0.000141651,0.0001328719,0.001294473,0.00009600412,0.000165017,0.000007474865,0.000203425,0.000003188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004051741,"about_ca_system_score_gemma":0.00002877269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009647158,"about_ca_topic_score_gemma":0.0007331924,"domain_scores_codex":[0.9984789,0.0000767215,0.0003983771,0.0004466329,0.0002804596,0.0003189383],"domain_scores_gemma":[0.9980628,0.001083485,0.0001434794,0.0003385895,0.0002456164,0.0001260448],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006891842,0.0001524747,0.0004719722,0.00004380516,0.0007000642,0.000007383599,0.000493784,0.4737448,0.0003543707,0.0005830588,0.000001758445,0.5233777],"study_design_scores_gemma":[0.0001712373,0.0001470511,0.0001653752,0.00003228495,0.0002152806,0.00002517952,0.00009869716,0.9163387,0.08211159,0.0004946573,0.000027325,0.0001726352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0010281,0.0000104408,0.9983413,0.0001633653,0.00005894132,0.0002094367,0.00004588146,0.00004687442,0.00009570571],"genre_scores_gemma":[0.6322931,0.000005698924,0.3674509,0.00008259188,0.000006479512,0.00001816033,0.000001884175,0.000008189438,0.0001330135],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.631265,"threshold_uncertainty_score":0.577636,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2951747536","doi":"10.1145/3321386","title":"Hierarchical Clustering","year":2019,"lang":"en","type":"article","venue":"Journal of the ACM","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":207,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Engineering and Physical Sciences Research Council; Alan Turing Institute; National Science Foundation","keywords":"Cluster analysis; Hierarchical clustering; Granularity; Constrained clustering; Computer science; Correlation clustering; Data mining; Similarity (geometry); Hierarchy; Fuzzy clustering; Set (abstract data type); Function (biology); Canopy clustering algorithm; Mathematics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.02099676116478523,"gpt":0.2989714861892535,"spread":0.2779747250244682,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0004515873,0.0000569661,0.0001164736,0.00006657489,0.0000518067,0.00007850627,0.005555212,0.00002559039,0.00001483971],"category_scores_gemma":[0.0005712245,0.00003355165,0.0001024155,0.0002163844,0.00002536377,0.0003552454,0.003345351,0.000412583,0.00005258473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006266297,"about_ca_system_score_gemma":0.00006907001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001144069,"about_ca_topic_score_gemma":4.525223e-7,"domain_scores_codex":[0.9989683,0.00007333234,0.0002020441,0.00009282117,0.0004773493,0.0001861742],"domain_scores_gemma":[0.9981945,0.0001612248,0.0001421991,0.00134037,0.00009110627,0.00007063348],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002605464,0.0003397878,0.01395366,0.0001956662,0.0002985558,0.0003990525,0.004266337,0.1048614,0.114969,0.008268516,0.01228789,0.7398996],"study_design_scores_gemma":[0.004037344,0.001283341,0.06833528,0.000659005,0.000019512,0.006002082,0.0001490699,0.6501594,0.02214833,0.1732931,0.07318375,0.0007297871],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3427949,0.0001725143,0.625608,0.02657444,0.003073317,0.0001580271,4.281071e-7,0.00003359558,0.001584792],"genre_scores_gemma":[0.6952841,0.00001602953,0.3021037,0.0004175355,0.0002760451,6.433836e-7,1.722687e-8,0.00001071909,0.001891257],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7391698,"threshold_uncertainty_score":0.9998252,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2029698681","doi":"10.1145/2395116.2395117","title":"The effectiveness of lloyd-type methods for the k-means problem","year":2012,"lang":"en","type":"article","venue":"Journal of the ACM","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":185,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Office of Naval Research; Israel Science Foundation; United States-Israel Binational Science Foundation; National Science Foundation","keywords":"Computer science; Cluster analysis; Heuristic; Probabilistic logic; Popularity; Process (computing); Algorithm; Type (biology); Quality (philosophy); Data mining; Artificial intelligence; Mathematical optimization; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.05066538846456285,"gpt":0.4219683914484055,"spread":0.3713030029838426,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01005281,0.00007751206,0.0001559341,0.00003287038,0.0002896452,0.0000621501,0.005372208,0.00002942334,9.354039e-7],"category_scores_gemma":[0.004780509,0.00002969299,0.0001665504,0.0003454996,0.0001063325,0.0003077902,0.001410516,0.0002876012,0.00000135541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006615232,"about_ca_system_score_gemma":0.00009080346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000380759,"about_ca_topic_score_gemma":5.937566e-7,"domain_scores_codex":[0.9981109,0.0009366471,0.0002548131,0.0000731047,0.0003402152,0.0002843055],"domain_scores_gemma":[0.9890963,0.008793597,0.000314201,0.001341194,0.0003982954,0.00005644837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007003573,0.0002141064,0.001818817,0.0002252989,0.000619537,0.000001850024,0.002217463,0.01607211,0.06833603,0.01749843,0.001632194,0.8906638],"study_design_scores_gemma":[0.002739088,0.001598482,0.06103181,0.0006116288,0.0001923686,0.000806862,0.0004184754,0.1139773,0.2942013,0.3731492,0.1508024,0.0004710596],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002811858,0.001630431,0.9904679,0.003328712,0.00133549,0.0003329964,4.655925e-7,0.00000654514,0.0000856203],"genre_scores_gemma":[0.1206992,0.0001136707,0.8784853,0.00005848765,0.0003220989,0.00001652715,2.715249e-8,0.00001548812,0.0002891894],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8901927,"threshold_uncertainty_score":0.9982988,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2096879261","doi":"","title":"Measures of Clustering Quality: A Working Set of Axioms for Clustering","year":2008,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":141,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Axiom; Impossibility; Constrained clustering; Computer science; Correlation clustering; Theoretical computer science; Fuzzy clustering; Data mining; Mathematics; Set (abstract data type); CURE data clustering algorithm; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1776089612055428,"gpt":0.3598316936246269,"spread":0.182222732419084,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008386247,0.0001734521,0.0003984811,0.0003319068,0.0002493149,0.0001660767,0.0007375107,0.00008530613,4.279428e-7],"category_scores_gemma":[0.0002271104,0.0001636487,0.00008593741,0.00060126,0.00009067095,0.002898641,0.0002819751,0.0001393282,0.000001922514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008111746,"about_ca_system_score_gemma":0.0001247538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007649262,"about_ca_topic_score_gemma":0.000008416559,"domain_scores_codex":[0.9974428,0.00007975425,0.001168286,0.0001965296,0.0007552009,0.0003574742],"domain_scores_gemma":[0.9978505,0.0001560175,0.0008673548,0.0003889989,0.0006587805,0.00007828181],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001488576,0.00003145933,0.0004628917,0.006787437,0.00004601148,0.000003248139,0.02657915,0.4381305,0.006244717,0.00076103,0.0000431736,0.5207615],"study_design_scores_gemma":[0.0005459254,0.00009163097,0.0002116209,0.0004234742,0.000002806586,0.00009897262,0.0007702357,0.9947432,0.002077488,0.00002247688,0.0008380746,0.000174065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01525176,0.0002266406,0.9830521,0.00007737976,0.0003999258,0.0004916431,0.000008060041,0.0001553961,0.0003370792],"genre_scores_gemma":[0.9776586,0.000009333461,0.02206568,0.00003010738,0.00007761201,0.00007759826,0.000007171937,0.00001254985,0.00006136399],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9624068,"threshold_uncertainty_score":0.6673401,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1999646319","doi":"10.1016/j.patrec.2006.01.015","title":"An objective approach to cluster validation","year":2006,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":122,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Cluster analysis; Covariance; Cluster (spacecraft); Data mining; Computer science; Measure (data warehouse); Separable space; Fuzzy clustering; Index (typography); Mathematics; Rand index; Artificial intelligence; Pattern recognition (psychology); Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02420805172161281,"gpt":0.2761375682142507,"spread":0.2519295164926379,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002770436,0.0001732537,0.0001327196,0.0002804483,0.0001390382,0.0003029487,0.0005811747,0.000051024,0.00001477373],"category_scores_gemma":[0.0000180201,0.0001823902,0.00005052974,0.0004331701,0.00003000201,0.001045746,0.0001493141,0.0001749459,0.0004631963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001425801,"about_ca_system_score_gemma":0.00001446373,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001578647,"about_ca_topic_score_gemma":0.000006434047,"domain_scores_codex":[0.9980767,0.0001898518,0.0002319519,0.0006445961,0.000439649,0.0004171883],"domain_scores_gemma":[0.9991221,0.00006407392,0.00006904483,0.0004852886,0.0001284825,0.0001310261],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003062141,0.0005212883,0.001828813,0.00006111953,0.00003070724,0.00002900765,0.001478395,0.02848956,0.04441971,0.00006005062,0.00357845,0.9194723],"study_design_scores_gemma":[0.003569779,0.0006125583,0.05179996,0.0001525931,0.00003052678,0.0002531681,0.000267672,0.7774859,0.1555884,0.005772802,0.001799218,0.002667402],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.150254,0.000002125497,0.8460864,0.001750576,0.0001804906,0.0003707692,0.00001250295,0.0002478599,0.001095305],"genre_scores_gemma":[0.8016335,6.753821e-7,0.1918566,0.005679352,0.0003928071,0.0002112671,0.0001464446,0.00003007197,0.00004927477],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9168049,"threshold_uncertainty_score":0.7437658,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.123293934676361,"gpt":0.3420131434182264,"spread":0.2187192087418655,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005271394,0.00007322695,0.0001999888,0.0002220578,0.0000363423,0.00003353446,0.0003234625,0.00004326966,0.00000244033],"category_scores_gemma":[0.00004389069,0.00005700595,0.00005477055,0.0003471972,0.00005931115,0.0006330556,0.0000241345,0.0001077193,0.000001044358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008086822,"about_ca_system_score_gemma":0.0001153233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007405482,"about_ca_topic_score_gemma":0.000009717539,"domain_scores_codex":[0.9985024,0.00009657811,0.000603921,0.0001159253,0.0005807628,0.0001004392],"domain_scores_gemma":[0.9981604,0.00009120929,0.0007175154,0.0002574192,0.000738736,0.00003478672],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005829028,0.0002497289,0.0006657574,0.00006340298,0.00004816011,0.000007459881,0.0004534812,0.06372184,0.8272604,0.007668094,0.0006943919,0.09858439],"study_design_scores_gemma":[0.002772119,0.0006378008,0.04304248,0.0000885496,0.00002247675,0.00009263968,0.00009039294,0.6862508,0.2654493,0.0009384516,0.0004725476,0.0001424225],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1257267,0.00006448136,0.8730288,0.0003530684,0.0001018978,0.0001061873,7.50785e-7,0.000006781293,0.0006113782],"genre_scores_gemma":[0.8926737,0.00002259089,0.1070485,0.000004877477,0.0001479275,0.000002254894,0.000002833118,0.000005484029,0.00009178695],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.766947,"threshold_uncertainty_score":0.2324635,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2022201359","doi":"10.1016/j.eswa.2013.07.002","title":"Cluster center initialization algorithm for K-modes clustering","year":2013,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":120,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Initialization; Computer science; Cluster analysis; Cluster (spacecraft); Center (category theory); Algorithm; Data mining; Artificial intelligence; Pattern recognition (psychology); Computer network","retraction":null,"screen_n_in":null,"score":{"opus":0.02231767915479643,"gpt":0.304274552149248,"spread":0.2819568729944515,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000155345,0.0002124929,0.0002145211,0.0001549212,0.0003543449,0.0004921066,0.0008134524,0.00008135871,0.00000820796],"category_scores_gemma":[0.00001191316,0.0001776397,0.00004719726,0.0004126471,0.00006078443,0.0009471851,0.0002426906,0.000100144,0.0001339131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001343804,"about_ca_system_score_gemma":0.00005580847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001520068,"about_ca_topic_score_gemma":0.000007808228,"domain_scores_codex":[0.9981759,0.0000573641,0.0003466212,0.0005887427,0.0003551376,0.0004762739],"domain_scores_gemma":[0.9982127,0.000151693,0.0001274914,0.0008752447,0.0004538294,0.0001790308],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002159753,0.00050677,0.0001187116,0.0003320665,0.0001755053,0.000004243628,0.003030563,0.02020861,0.004388544,0.02428313,0.01190787,0.9350224],"study_design_scores_gemma":[0.0006848031,0.00007032254,0.00002574925,0.00005298708,0.000001847474,0.00005541477,0.0002058217,0.9483508,0.0003931898,0.0002782925,0.04962541,0.000255284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002765104,0.0001864452,0.9942246,0.0006397185,0.0001473908,0.003454682,0.00001565384,0.0003656149,0.000938253],"genre_scores_gemma":[0.05583839,0.00002524153,0.9125229,0.0003823673,0.0005707791,0.02924604,0.00006342767,0.00006812521,0.001282736],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9347671,"threshold_uncertainty_score":0.7243936,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2163097311","doi":"","title":"Proximity Graphs for Clustering and Manifold Learning","year":2004,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":120,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Cluster analysis; Lattice graph; Dimensionality reduction; Computer science; Line graph; Mathematics; Graph; Pattern recognition (psychology); Voltage graph; Theoretical computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.02268826032061569,"gpt":0.2818249507256548,"spread":0.2591366904050392,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003493266,0.0001342787,0.0001456435,0.0001785849,0.0004471399,0.001061691,0.0003265833,0.00005998795,1.816347e-7],"category_scores_gemma":[0.00009078638,0.0001237195,0.00002794758,0.000298571,0.00002687774,0.00641197,0.0001803769,0.00018373,0.000005738258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000833964,"about_ca_system_score_gemma":0.00005685315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002690486,"about_ca_topic_score_gemma":0.000002185014,"domain_scores_codex":[0.9988008,0.00002386275,0.0003595758,0.0001900142,0.00030548,0.0003202414],"domain_scores_gemma":[0.9992769,0.0000367033,0.0002022141,0.0001629717,0.000230502,0.00009075604],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003994585,0.00002742818,0.000267574,0.003547616,0.00001678365,0.000005346623,0.007381186,0.4327811,0.0008751774,0.02505668,0.00002451578,0.5299767],"study_design_scores_gemma":[0.0006390283,0.0001092776,0.0001814589,0.000141773,0.000001856805,0.0001294433,0.0002708816,0.9956893,0.0002519228,0.0008621284,0.001555904,0.0001670463],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01233472,0.0001402219,0.9858267,0.0002813896,0.0002473138,0.0005218023,0.000001375167,0.0003720966,0.0002743618],"genre_scores_gemma":[0.9677492,0.000006619242,0.03187799,0.00008369782,0.00004384931,0.000133897,0.000005556685,0.000009353646,0.00008986994],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9554144,"threshold_uncertainty_score":0.9999753,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2103991913","doi":"10.1093/bioinformatics/btg030","title":"<i>K</i>-ary clustering with optimal leaf ordering for gene expression data","year":2003,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":118,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Wilfrid Laurier University","funders":"Leverhulme Trust; Florida State University; Natural Sciences and Engineering Research Council of Canada; Burroughs Wellcome Fund","keywords":"Cluster analysis; Hierarchical clustering; Computer science; Tree (set theory); Binary tree; Pairwise comparison; Hierarchical clustering of networks; Single-linkage clustering; Robustness (evolution); CURE data clustering algorithm; Data mining; Algorithm; Nearest-neighbor chain algorithm; Correlation clustering; Canopy clustering algorithm; Tree structure; Mathematics; Artificial intelligence; Gene; Biology; Combinatorics; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.0550618501563367,"gpt":0.306350724116407,"spread":0.2512888739600703,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004352963,0.000183532,0.0001763087,0.0001025016,0.0002421556,0.0002511642,0.001585623,0.0000593692,0.000004228434],"category_scores_gemma":[0.0001802609,0.0001499872,0.00002537266,0.0002830002,0.0000460651,0.002003104,0.001133139,0.0001461407,0.00001721414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005156801,"about_ca_system_score_gemma":0.0001529818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002000756,"about_ca_topic_score_gemma":0.000001940493,"domain_scores_codex":[0.9984377,0.00002174524,0.0003223815,0.0003071792,0.0003949802,0.0005159879],"domain_scores_gemma":[0.9979311,0.0001148015,0.0001195792,0.001555635,0.0001027633,0.0001761741],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003343166,0.0004214087,0.0002406022,0.00278609,0.0002267104,0.0001238494,0.01016453,0.4575956,0.02336447,0.005136206,0.006969645,0.4926365],"study_design_scores_gemma":[0.0007020261,0.0001400371,0.000006820253,0.00006884495,0.000003430689,0.0001008807,0.0001614093,0.9643651,0.01651857,0.00004907758,0.01763409,0.0002497676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007065247,0.00006439203,0.997188,0.00005917369,0.0001720068,0.0003796126,0.00002038311,0.0001837565,0.001226172],"genre_scores_gemma":[0.005356442,0.00002357149,0.9941798,0.00009599646,0.00004178732,0.00003505057,0.00002943534,0.00002211996,0.0002158279],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5067694,"threshold_uncertainty_score":0.6116299,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4285781363","doi":"10.1002/widm.1343","title":"Density‐based clustering","year":2019,"lang":"en","type":"article","venue":"Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":116,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Cluster analysis; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.06673601290054507,"gpt":0.3667671650858934,"spread":0.3000311521853484,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.001261477,0.0003697553,0.0006410782,0.0002182963,0.0002668971,0.000580901,0.002815674,0.00008894339,0.00002057156],"category_scores_gemma":[0.0001291936,0.0003118947,0.0001062721,0.0004833117,0.0001161213,0.003279311,0.01598723,0.0002975141,0.0003936179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008435822,"about_ca_system_score_gemma":0.0001362927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003631454,"about_ca_topic_score_gemma":0.00004505294,"domain_scores_codex":[0.9969705,0.0002585065,0.0005830735,0.001359028,0.0002530659,0.0005758305],"domain_scores_gemma":[0.9961056,0.0003084517,0.0001807822,0.003144393,0.00006590065,0.0001949177],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006454901,0.0002250115,0.002030886,0.001373886,0.00005409072,0.0000754631,0.002631999,0.00009062741,0.001014678,0.000236424,0.01032604,0.9818764],"study_design_scores_gemma":[0.0009126164,0.0003685543,0.000762623,0.004225052,0.0000287296,0.0001698976,0.0004327928,0.9436858,0.0001775301,0.0001889779,0.04817912,0.0008683577],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04260752,0.02562562,0.9220114,0.0006030828,0.001862473,0.001012064,0.00008291951,0.0002765287,0.005918353],"genre_scores_gemma":[0.6197993,0.005663145,0.3584121,0.0005886046,0.0009509553,0.0002115989,0.0007197741,0.0001829479,0.01347155],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.981008,"threshold_uncertainty_score":0.9999333,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2111253950","doi":"10.1109/dexa.2002.1045928","title":"Clustering Web sessions by sequence alignment","year":2004,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":114,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Cluster analysis; Sequence (biology); World Wide Web; Information retrieval; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.03441255174344665,"gpt":0.3268487722889999,"spread":0.2924362205455533,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001530219,0.0001260445,0.0001044925,0.00006403239,0.0001727981,0.000140599,0.000995017,0.00004135429,0.0000334414],"category_scores_gemma":[0.00002537599,0.0001092602,0.00003421429,0.0003393121,0.00004974077,0.0005596329,0.0008851156,0.0001476931,0.0001860824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002636959,"about_ca_system_score_gemma":0.0001231091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005738287,"about_ca_topic_score_gemma":0.00001220136,"domain_scores_codex":[0.9984955,0.00002612993,0.0001654941,0.0004172812,0.0004464309,0.0004492016],"domain_scores_gemma":[0.9990956,0.00003989315,0.00003114447,0.0005970558,0.00004530078,0.0001910048],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001029024,0.00035246,0.00006922535,0.00006180156,0.00005868528,0.0003143681,0.001296416,0.09830733,0.6608332,0.03029235,0.005221001,0.2031829],"study_design_scores_gemma":[0.00192169,0.000297407,0.00007380982,0.0001570168,0.000004143608,0.0002416426,0.0001759664,0.8324533,0.1298522,0.01184681,0.02208252,0.0008935275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00265123,0.00004558471,0.9896187,0.00276182,0.0001671157,0.0001339081,0.000003533821,0.0003612401,0.004256937],"genre_scores_gemma":[0.4597847,0.00004730597,0.5365685,0.0005643026,0.00003823236,0.00003954777,0.000002125237,0.00001467566,0.00294061],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7341459,"threshold_uncertainty_score":0.4455501,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2032084149","doi":"10.1016/j.ins.2013.11.004","title":"Relative entropy fuzzy c-means clustering","year":2013,"lang":"en","type":"article","venue":"Information Sciences","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":113,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Cluster analysis; Fuzzy clustering; Pattern recognition (psychology); Artificial intelligence; Fuzzy logic; Data mining; Entropy (arrow of time); Computer science; FLAME clustering; Mathematics; Machine learning; CURE data clustering algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.02682990070830507,"gpt":0.3006563985874651,"spread":0.27382649787916,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004729774,0.00009658231,0.00008825291,0.0002587706,0.0003939242,0.0009278813,0.001189153,0.0000345091,0.0000579351],"category_scores_gemma":[0.0001692729,0.00007789387,0.00003157453,0.0008909593,0.0001939391,0.01764342,0.0004738909,0.000127994,0.001989241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006863215,"about_ca_system_score_gemma":0.00008250203,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000099121,"about_ca_topic_score_gemma":0.000003373871,"domain_scores_codex":[0.9984282,0.00003861287,0.000291791,0.0001737483,0.0006980307,0.0003696064],"domain_scores_gemma":[0.9991651,0.0001250195,0.0001216551,0.0002775748,0.0002032833,0.0001073797],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003077483,0.00002447545,0.0005227732,0.00003302432,0.00001443284,0.000002417601,0.01184593,0.04984032,0.0007568835,0.1294008,0.001912986,0.8056429],"study_design_scores_gemma":[0.0001531562,0.00007613323,0.002028119,0.00001450936,4.4528e-7,0.00001606469,0.000420535,0.9758576,0.0004115299,0.01425645,0.006621932,0.0001435088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00329873,0.0000122718,0.9607177,0.001863375,0.000276533,0.0002191789,9.509018e-7,0.0001871111,0.03342419],"genre_scores_gemma":[0.5765584,0.00001566858,0.4219863,0.0007807184,0.00005361892,0.0000806997,0.000001999373,0.000003796888,0.0005188165],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9260173,"threshold_uncertainty_score":0.9987878,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2089055054","doi":"10.1145/1401890.1401956","title":"Finding non-redundant, statistically significant regions in high dimensional data","year":2008,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Disjoint sets; Computer science; Cluster (spacecraft); Outlier; Data mining; Single-linkage clustering; Clustering high-dimensional data; Subspace topology; Complete-linkage clustering; Data point; Correlation clustering; Determining the number of clusters in a data set; CURE data clustering algorithm; Pattern recognition (psychology); Artificial intelligence; Mathematics; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.1047099670015588,"gpt":0.3439923630461722,"spread":0.2392823960446134,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003107999,0.0001271416,0.0001712153,0.0001754543,0.0001912596,0.00005962105,0.001887831,0.00004190151,0.00004308532],"category_scores_gemma":[0.0002266414,0.0001134627,0.00001575646,0.0005454281,0.000148681,0.0006289182,0.001916132,0.0002620393,0.0001214472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008419678,"about_ca_system_score_gemma":0.0002575786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000312938,"about_ca_topic_score_gemma":0.00004386804,"domain_scores_codex":[0.9979486,0.00005902998,0.0002691845,0.0006784492,0.0005536832,0.0004910497],"domain_scores_gemma":[0.9979619,0.0004239273,0.00003965025,0.001338189,0.00006814266,0.0001681949],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001859811,0.002341949,0.008631247,0.000161801,0.0001694143,0.01974997,0.003218761,0.0560712,0.02791096,0.541252,0.1038724,0.2364343],"study_design_scores_gemma":[0.0005204628,0.00007631245,0.01849069,0.00002964708,0.000001093695,0.0001300865,0.00001297317,0.9751111,0.0003769333,0.004364144,0.0006429841,0.0002435287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0119481,0.0000101387,0.9857756,0.001253216,0.0001435971,0.0001472607,0.00002665894,0.00009735882,0.0005980128],"genre_scores_gemma":[0.4299299,0.00001654303,0.5685577,0.0001134737,0.00003267332,0.000009066357,0.00002646466,0.000009960856,0.001304283],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.91904,"threshold_uncertainty_score":0.4626873,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2170896428","doi":"10.1109/icdm.2009.143","title":"Semi-supervised Density-Based Clustering","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":100,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Computer science; Artificial intelligence; Set (abstract data type); Pattern recognition (psychology); Cluster (spacecraft); Data mining; Noise (video); Feature (linguistics); Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.02295595446776774,"gpt":0.2907169793540355,"spread":0.2677610248862677,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002080427,0.0001360228,0.0001394579,0.000131225,0.0001342993,0.0001784211,0.0009627696,0.0000506901,0.0000286106],"category_scores_gemma":[0.00004193115,0.0001257582,0.00005555868,0.0004450472,0.00002377241,0.0004218846,0.0002386886,0.0001700632,0.0001334382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007586672,"about_ca_system_score_gemma":0.00006337599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001150047,"about_ca_topic_score_gemma":0.000006597969,"domain_scores_codex":[0.9985363,0.00004473261,0.0001630922,0.0004112407,0.0003966676,0.0004479337],"domain_scores_gemma":[0.998902,0.00007271633,0.0000246446,0.0007400979,0.00009579815,0.0001647583],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003074701,0.00018643,0.0001995538,0.00003394332,0.00001339803,0.0002809607,0.0003561787,0.04402509,0.03550113,0.007360909,0.0008423575,0.9111693],"study_design_scores_gemma":[0.0003961722,0.000114675,0.001093117,0.00001378962,8.029883e-7,0.00001849331,0.000007257279,0.980961,0.01507957,0.00133141,0.0008034578,0.0001802005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005311262,0.0000184569,0.986061,0.002632782,0.0001102441,0.0001201687,2.705982e-7,0.0005634868,0.005182354],"genre_scores_gemma":[0.5140666,0.000002126769,0.483197,0.001858742,0.00004939893,0.000004227219,9.578881e-7,0.000007218209,0.0008137434],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.936936,"threshold_uncertainty_score":0.5128269,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2080476941","doi":"10.1016/j.patcog.2007.11.011","title":"A convergence theorem for the fuzzy subspace clustering (FSC) algorithm","year":2007,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":100,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Subsequence; Convergence (economics); Cluster analysis; Subspace topology; Sequence (biology); Algorithm; Mathematics; Fuzzy logic; Set (abstract data type); Computer science; Mathematical optimization; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.04476244813819463,"gpt":0.3136870178531478,"spread":0.2689245697149532,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001352228,0.0001828196,0.0001436868,0.0001162323,0.0003330797,0.0001739575,0.0008542779,0.0000746499,0.00002208314],"category_scores_gemma":[0.0001167379,0.0001453462,0.00009620807,0.000355531,0.0000819913,0.0004570821,0.0003369825,0.0002301486,0.0001557895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009806257,"about_ca_system_score_gemma":0.00002972589,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005797153,"about_ca_topic_score_gemma":0.00008339334,"domain_scores_codex":[0.9981452,0.00006059738,0.000275079,0.0004829695,0.0004026649,0.0006335068],"domain_scores_gemma":[0.9980325,0.000953038,0.0001147665,0.0005239593,0.0002557712,0.0001199338],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001265823,0.00002188516,0.00004865005,0.00002551865,0.00001692384,0.0000130858,0.0003906297,0.00005769281,0.0003949201,0.00004526122,0.00005016199,0.9989226],"study_design_scores_gemma":[0.0009963847,0.0002069901,0.002587585,0.0001007253,0.0000162649,0.000133955,0.0003798326,0.9658268,0.01546098,0.01157858,0.002230746,0.0004811582],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002079559,0.0001162958,0.9947789,0.0007976635,0.0009081074,0.0006305964,0.00002298191,0.0002063434,0.000459581],"genre_scores_gemma":[0.580035,0.0001715432,0.4167953,0.001154191,0.0009201943,0.0003598182,0.00003916786,0.00007116888,0.0004536176],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9984415,"threshold_uncertainty_score":0.5927048,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2170006979","doi":"10.1007/s10107-010-0349-7","title":"An improved column generation algorithm for minimum sum-of-squares clustering","year":2010,"lang":"en","type":"article","venue":"Mathematical Programming","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":99,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Group for Research in Decision Analysis; HEC Montréal","funders":"","keywords":"Mathematics; Column (typography); Cluster analysis; Explained sum of squares; Bottleneck; Algorithm; Column generation; Set (abstract data type); Centroid; Point (geometry); Combinatorics; Square (algebra); Euclidean space; Mathematical optimization; Computer science; Statistics; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.03302216249232391,"gpt":0.335101045809392,"spread":0.3020788833170681,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007982343,0.0001830071,0.0002846081,0.0001103113,0.0001941197,0.0003413293,0.0008900949,0.0001254233,0.00001133519],"category_scores_gemma":[0.0002824005,0.0001732182,0.00009593284,0.000259758,0.0001207644,0.0005819192,0.0002733115,0.000253938,0.000007288833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003067869,"about_ca_system_score_gemma":0.00005622868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009879556,"about_ca_topic_score_gemma":0.00002223739,"domain_scores_codex":[0.9981113,0.00004290709,0.0004613242,0.0004794059,0.0003579977,0.0005470617],"domain_scores_gemma":[0.9983954,0.0002665358,0.0001320264,0.0007561165,0.0002455004,0.0002043828],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002374328,0.0001681135,0.000002708311,0.0001265005,0.00001060646,0.000002329481,0.0004142698,0.00004901692,0.09746256,0.0021291,0.000006235071,0.8996262],"study_design_scores_gemma":[0.0003709161,0.0003609812,0.000006560077,0.00002221,0.000006081903,0.00001985896,0.00005962951,0.9743242,0.02008656,0.004070641,0.0004745788,0.0001977582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01208412,0.00001377127,0.9863195,0.0001072954,0.0002807694,0.0009175584,0.000004337287,0.0002283322,0.00004427244],"genre_scores_gemma":[0.1070602,5.661294e-7,0.8922771,0.00001644231,0.0002230279,0.0002939165,0.000007821333,0.000029252,0.00009175244],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9742752,"threshold_uncertainty_score":0.7063631,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2020287868","doi":"10.1016/j.eswa.2007.11.045","title":"A genetic fuzzy <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" altimg=\"si218.gif\" overflow=\"scroll\"><mml:mrow><mml:mi>k</mml:mi></mml:mrow></mml:math>-Modes algorithm for clustering categorical data","year":2007,"lang":"lv","type":"article","venue":"Expert Systems with Applications","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Algorithm; Fuzzy logic; Crossover; Categorical variable; Computer science; Genetic algorithm; Operator (biology); Cluster analysis; Mathematics; Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.03440380589158171,"gpt":0.2949587150331948,"spread":0.2605549091416131,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001312681,0.0005209107,0.0003134588,0.0002670316,0.001260533,0.001034924,0.002982226,0.0006432917,0.0002564242],"category_scores_gemma":[0.0001928778,0.0007159947,0.000288761,0.0009701645,0.000523322,0.0009458872,0.002320052,0.0006552302,0.00067312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006366064,"about_ca_system_score_gemma":0.0008229521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00151568,"about_ca_topic_score_gemma":0.0002721815,"domain_scores_codex":[0.993938,0.0001293564,0.001112525,0.001739031,0.001492098,0.001588948],"domain_scores_gemma":[0.9939603,0.0008886759,0.0007240746,0.003504548,0.0002253246,0.0006970828],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002305374,0.0003902637,0.000005329672,0.0009708445,0.0005914618,0.0003413811,0.002879855,0.009681406,0.001965685,0.9068717,0.01026526,0.06580625],"study_design_scores_gemma":[0.0009030353,0.0004810371,0.00003036001,0.0003521093,0.0001014071,0.001061666,0.001189944,0.9684522,0.01257798,0.00008170414,0.01407721,0.0006913575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02456071,0.002504152,0.9617415,0.0003319232,0.0008417988,0.0003401249,0.0001965187,0.0002826203,0.00920066],"genre_scores_gemma":[0.802465,0.0003816008,0.1886521,0.0003093408,0.002367247,0.004811464,0.0003333307,0.0003183155,0.0003615327],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9587708,"threshold_uncertainty_score":0.9995291,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05001129746715327,"gpt":0.3724863672266711,"spread":0.3224750697595178,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009789171,0.00008107231,0.0001591357,0.0002152878,0.0001748815,0.0001931946,0.0001389653,0.00004785697,0.000002292691],"category_scores_gemma":[0.001156013,0.00006697453,0.00002186401,0.0003489734,0.00006757401,0.0007619719,0.00005215023,0.0001476553,1.79293e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004287973,"about_ca_system_score_gemma":0.00004823581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001826992,"about_ca_topic_score_gemma":6.026139e-7,"domain_scores_codex":[0.9991181,0.0001004399,0.0002651138,0.0001848446,0.0001705402,0.0001609743],"domain_scores_gemma":[0.9980493,0.001163131,0.0002613934,0.0001089113,0.000306051,0.000111225],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004464425,0.00004370182,0.001216569,0.00003070544,0.00003550225,0.000005272551,0.0005676752,0.0009850807,0.007113399,0.004193003,0.00008686008,0.9856776],"study_design_scores_gemma":[0.001031161,0.0005498572,0.03813516,0.0001009783,0.00002960197,0.0006520379,0.0004249333,0.9371274,0.002392045,0.008861195,0.01051681,0.0001788022],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0158059,0.0004760361,0.9828693,0.0006046038,0.00006293168,0.0001003016,0.000003035528,0.00001671729,0.000061149],"genre_scores_gemma":[0.05076816,0.0004936525,0.9485192,0.00002119276,0.00009047117,0.000009946366,0.00000117563,0.000006772673,0.00008941432],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9854988,"threshold_uncertainty_score":0.2731142,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4237407686","doi":"10.1007/3-540-36175-8_8","title":"Automatic Extraction of Clusters from Hierarchical Clustering Representations","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Hierarchical clustering; Hierarchical clustering of networks; Cluster analysis; Single-linkage clustering; Reachability; Brown clustering; Data mining; Dendrogram; Complete-linkage clustering; Correlation clustering; Set (abstract data type); Representation (politics); Cluster (spacecraft); Canopy clustering algorithm; Artificial intelligence; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.02616198335077822,"gpt":0.315371024856876,"spread":0.2892090415060977,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007286563,0.000456022,0.0005996617,0.001053051,0.0002322486,0.0003242792,0.002811644,0.0003020854,0.00005203185],"category_scores_gemma":[0.0002676345,0.0004606328,0.0001534375,0.0007846955,0.000818199,0.0008884198,0.00163444,0.001122475,0.00002449703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004660099,"about_ca_system_score_gemma":0.0004074495,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008239441,"about_ca_topic_score_gemma":0.00008084536,"domain_scores_codex":[0.9953334,0.0001004655,0.0008131487,0.001572853,0.001505216,0.0006748796],"domain_scores_gemma":[0.9959306,0.001304684,0.0004151277,0.001867666,0.000261255,0.0002207232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006466782,0.00003929216,0.00002072352,0.00006538563,0.00002207453,0.00009622853,0.0008742849,0.1684939,0.0008483694,0.001224422,0.00001211264,0.8282967],"study_design_scores_gemma":[0.0002840169,0.00009909974,0.0001644526,0.0003773059,0.000006783099,0.00007715957,5.24834e-7,0.9220613,0.001656792,0.0746761,0.0001930552,0.0004034753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002858869,0.0001800395,0.9952002,0.0006672175,0.001468729,0.0004385687,0.00001029075,0.0001614382,0.001587585],"genre_scores_gemma":[0.03861023,0.00004466335,0.9604045,0.0003730589,0.000213548,0.00001724083,0.000008433371,0.00004621835,0.0002821273],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8278933,"threshold_uncertainty_score":0.9997845,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1516498690","doi":"10.1007/3-540-44938-8_17","title":"Finding Natural Clusters Using Multi-clusterer Combiner Based on Shared Nearest Neighbors","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Graph; Computer science; k-nearest neighbors algorithm; Set (abstract data type); Pattern recognition (psychology); Data mining; Artificial intelligence; Theoretical computer science; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04392408286800724,"gpt":0.3073721529406045,"spread":0.2634480700725972,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001040488,0.00104355,0.0008395393,0.001894159,0.0006725676,0.001302347,0.004890142,0.0004880449,0.00003492588],"category_scores_gemma":[0.0003126174,0.000977465,0.0002552207,0.00134741,0.0008974215,0.001075767,0.002119418,0.002274675,0.00005371438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001511206,"about_ca_system_score_gemma":0.0007613241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004187629,"about_ca_topic_score_gemma":0.00005744427,"domain_scores_codex":[0.99252,0.0001367543,0.0007703581,0.002740918,0.002199193,0.001632713],"domain_scores_gemma":[0.9955398,0.0008877774,0.0003551367,0.002397681,0.0004123699,0.000407228],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002354775,0.00007221013,0.00005281364,0.00007299842,0.00001535422,0.0003320523,0.0003341579,0.8762456,0.0002026221,0.0004732453,0.00001718995,0.1221582],"study_design_scores_gemma":[0.001128615,0.0002042878,0.00009149145,0.000819847,0.000007111475,0.0000796301,3.326728e-7,0.9936935,0.0005548589,0.001955896,0.0003903822,0.001074076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001646331,0.0001729191,0.9938387,0.0007404762,0.00348954,0.0007765289,0.00001333949,0.0002435025,0.0005603457],"genre_scores_gemma":[0.08842174,0.000008119106,0.9055854,0.004749665,0.0003025127,0.00001640847,0.00001510762,0.0001370168,0.0007639947],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1210842,"threshold_uncertainty_score":0.9997344,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2286286503","doi":"10.1007/978-3-319-49487-6_3","title":"Theoretical Analysis of the k-Means Algorithm – A Survey","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Heuristics; Algorithm; Cluster analysis; Extension (predicate logic); Simplicity; k-means clustering; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01866825659025128,"gpt":0.2867864487581152,"spread":0.2681181921678639,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.002305734,0.0004525155,0.0007807244,0.001313883,0.0002168533,0.0002279525,0.007265948,0.0002785395,0.00007152547],"category_scores_gemma":[0.0004329725,0.0002774313,0.0003432321,0.003044621,0.003197153,0.0003200391,0.004021185,0.0007809637,0.00001595546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000327894,"about_ca_system_score_gemma":0.0006153568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003086884,"about_ca_topic_score_gemma":0.0001359805,"domain_scores_codex":[0.9949561,0.0001891508,0.0006062053,0.00150819,0.00195774,0.0007826383],"domain_scores_gemma":[0.9939972,0.002075308,0.0003242854,0.002853552,0.0005726646,0.0001770267],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004074634,0.00002083707,0.0001271386,0.00001018778,0.0001110895,0.00002015215,0.0002241561,0.02238777,0.00004141741,0.08096424,0.000002246064,0.8960867],"study_design_scores_gemma":[0.0001346075,0.00006755628,0.001731543,0.0001455696,0.00003200969,0.00001255567,4.230552e-8,0.8422289,0.000517906,0.1547139,0.00008060535,0.0003348078],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002265177,0.000115815,0.9960999,0.0006088878,0.000855158,0.0002916886,0.00006117363,0.00006434925,0.001880386],"genre_scores_gemma":[0.1493492,0.00006115323,0.848594,0.0006258923,0.000299805,0.00001435274,0.000006254364,0.00006404743,0.0009852847],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8957519,"threshold_uncertainty_score":0.9999678,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1891514807","doi":"10.1007/3-540-47887-6_4","title":"On Data Clustering Analysis: Scalability, Constraints, and Validation","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Computer science; Scalability; Data mining; Correlation clustering; Similarity (geometry); Consensus clustering; CURE data clustering algorithm; Artificial intelligence; Machine learning; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.05015855301203107,"gpt":0.3133047514182548,"spread":0.2631461984062237,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001473719,0.00047918,0.0005944345,0.001476316,0.0002767109,0.0008942328,0.004985479,0.0002483513,0.00004663227],"category_scores_gemma":[0.0003003922,0.0004573952,0.00007914552,0.001280373,0.001366011,0.0009869543,0.006368254,0.0009094601,0.00003076098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003089427,"about_ca_system_score_gemma":0.0001807532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001513202,"about_ca_topic_score_gemma":0.00004342763,"domain_scores_codex":[0.9947337,0.00006789001,0.0005239446,0.002634657,0.001365127,0.0006746691],"domain_scores_gemma":[0.9948068,0.0009426485,0.0002187642,0.003598001,0.0001992116,0.0002345904],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003564562,0.00002410485,0.00004850675,0.0000386523,0.00004830076,0.00006142483,0.0001913529,0.1299207,0.0000171538,0.00325827,0.000005178348,0.8663828],"study_design_scores_gemma":[0.0001884802,0.0001105055,0.0001526066,0.0001703098,0.00002470471,0.00004702064,1.036904e-7,0.9595024,0.0001190791,0.03912485,0.0001164614,0.0004434672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00007679317,0.0001562616,0.9965968,0.0005485945,0.0004617385,0.0003517018,0.0000261206,0.0001480985,0.001633891],"genre_scores_gemma":[0.2281184,0.0001178483,0.7705205,0.0005433609,0.0002644728,0.000008942415,0.0000380953,0.00004319167,0.0003451783],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8659393,"threshold_uncertainty_score":0.9997878,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3097529996","doi":"10.1016/j.patcog.2020.107748","title":"Projected fuzzy C-means clustering with locality preservation","year":2020,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":83,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Locality; Cluster analysis; Fuzzy clustering; Computer science; Fuzzy logic; Data mining; Curse of dimensionality; Clustering high-dimensional data; Partition (number theory); Benchmark (surveying); Pattern recognition (psychology); Artificial intelligence; Projection (relational algebra); Mathematics; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.07571112933585794,"gpt":0.2826266310745564,"spread":0.2069155017386985,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001575815,0.0001490573,0.0001389922,0.0000653215,0.0001070366,0.0001721411,0.0004526101,0.00005281398,0.00002293202],"category_scores_gemma":[0.00008133744,0.0001358521,0.00002979964,0.0005377101,0.00003267021,0.00114952,0.0002915154,0.000233845,0.0001599383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006456055,"about_ca_system_score_gemma":0.0000443272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000777817,"about_ca_topic_score_gemma":0.00005281412,"domain_scores_codex":[0.9983982,0.0001151934,0.0002090221,0.0005176757,0.000440322,0.000319565],"domain_scores_gemma":[0.9991795,0.00005954807,0.00008930621,0.0002997193,0.0002250319,0.0001468739],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006104759,0.00005820984,0.002055551,0.0002065014,0.00002638912,0.00004701458,0.001407719,0.001604542,0.001465494,0.000006572966,0.00007932073,0.9929816],"study_design_scores_gemma":[0.0008163888,0.0003757213,0.005133337,0.00009039596,0.00000655377,0.00002613006,0.00007468246,0.9879408,0.004305622,0.0005803211,0.0003388773,0.0003111971],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03235441,0.000007529086,0.9635194,0.002525269,0.00006356629,0.0004086087,0.00001309216,0.0004264688,0.0006816349],"genre_scores_gemma":[0.9030904,0.000009808156,0.09516636,0.001242761,0.0002124365,0.0001312138,0.00008106105,0.00003048995,0.00003546061],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9926704,"threshold_uncertainty_score":0.5539887,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2079040080","doi":"10.1007/s10618-013-0311-4","title":"A framework for semi-supervised and unsupervised optimal extraction of clusters from hierarchies","year":2013,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":83,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Computer science; Tree (set theory); Cluster (spacecraft); Variety (cybernetics); Data mining; Artificial intelligence; Extraction (chemistry); Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.06040773208466434,"gpt":0.3443362713711306,"spread":0.2839285392864663,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000238731,0.0001713157,0.0002562963,0.0001257743,0.0001670459,0.0003968435,0.0008133908,0.0000904069,0.000005448956],"category_scores_gemma":[0.000309196,0.0001568928,0.00002930959,0.0001910744,0.000170338,0.002814469,0.001429311,0.0001461741,0.000003625193],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001629306,"about_ca_system_score_gemma":0.00007075935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001211068,"about_ca_topic_score_gemma":0.00001440823,"domain_scores_codex":[0.9985679,0.00006793963,0.0002550842,0.000650616,0.0001550743,0.0003034252],"domain_scores_gemma":[0.9975732,0.001254727,0.00007298899,0.0008985171,0.00008317818,0.0001173893],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001359583,0.0002143146,0.001263114,0.0004137513,0.0001542915,0.000005941819,0.01339554,0.00009913054,0.008588029,0.001692562,0.001731571,0.9723058],"study_design_scores_gemma":[0.000935589,0.0001868791,0.002974103,0.0003260024,0.00002023509,0.00001071441,0.002441457,0.9881946,0.001106362,0.002765259,0.0007243263,0.0003145053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.369871,0.001067455,0.6282195,0.0001400122,0.000153844,0.0002140402,0.0002439981,0.00003692462,0.00005319574],"genre_scores_gemma":[0.3225427,0.0002250962,0.6765233,0.00003517904,0.0001407261,0.00006279472,0.0002316286,0.00002083375,0.0002177321],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9880955,"threshold_uncertainty_score":0.6397903,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2117544284","doi":"10.1145/375663.375672","title":"Data bubbles","year":2001,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Cluster analysis; Computer science; CURE data clustering algorithm; Canopy clustering algorithm; Data mining; Data stream clustering; Correlation clustering; Hierarchical clustering; Data compression; Data set; Set (abstract data type); Fuzzy clustering; Constrained clustering; Determining the number of clusters in a data set; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1292531724393648,"gpt":0.3804818146787029,"spread":0.2512286422393381,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001604899,0.00004580012,0.00004682371,0.00004036701,0.0000530497,0.00009837045,0.002573192,0.0000147703,0.00005990527],"category_scores_gemma":[0.00004622868,0.00003801651,0.000007165939,0.0002762656,0.00001982035,0.0007834401,0.002074871,0.00006208274,0.0003076753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001349511,"about_ca_system_score_gemma":0.00002551133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002199578,"about_ca_topic_score_gemma":0.00001557858,"domain_scores_codex":[0.999198,0.00001491111,0.00006794193,0.0002975801,0.0002112424,0.00021035],"domain_scores_gemma":[0.998311,0.00004799094,0.00001001966,0.00153517,0.00003029715,0.00006547646],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002218734,0.00003896054,0.0002857262,0.000003807809,0.000007256102,0.0001215928,0.0000457364,0.0002603219,0.00045551,0.02319794,0.008227439,0.9673535],"study_design_scores_gemma":[0.0001224593,0.00002022082,0.0005414826,0.000003145689,3.39351e-7,0.0000781798,0.00001122782,0.7263163,0.0002884318,0.003639622,0.2688806,0.0000978971],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004195057,0.00004835657,0.9748729,0.00149477,0.00008277842,0.00003670061,0.000001688152,0.000224812,0.02281851],"genre_scores_gemma":[0.04098022,0.00008687309,0.9430274,0.00033569,0.0001020689,0.000004337301,0.000007214235,0.00000793113,0.01544825],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9672556,"threshold_uncertainty_score":0.4781673,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2086829791","doi":"10.1007/s10618-011-0221-2","title":"DHCC: Divisive hierarchical clustering of categorical data","year":2011,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Categorical variable; Cluster analysis; Computer science; Data mining; Initialization; Similarity (geometry); Linear subspace; Single-linkage clustering; Hierarchical clustering; Artificial intelligence; Pattern recognition (psychology); CURE data clustering algorithm; Correlation clustering; Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1924145629485619,"gpt":0.3565834104161071,"spread":0.1641688474675453,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0006449376,0.0001822839,0.0002886598,0.0001442714,0.0001294541,0.0001568875,0.004612544,0.00006916543,0.000005830776],"category_scores_gemma":[0.0003771349,0.0001615467,0.00002204101,0.0003431668,0.000234049,0.002905003,0.01748029,0.0002213244,0.00001294279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002023781,"about_ca_system_score_gemma":0.0001600794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009914489,"about_ca_topic_score_gemma":0.00007402569,"domain_scores_codex":[0.9978786,0.0001133532,0.0003270568,0.001004776,0.0002610635,0.000415215],"domain_scores_gemma":[0.9959918,0.0003258905,0.00009042482,0.003367582,0.00006336138,0.0001609281],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009589503,0.0004998183,0.00218884,0.0003101905,0.0001349226,0.0001715096,0.01152958,0.00001170807,0.0004464381,0.005399827,0.003187992,0.9760233],"study_design_scores_gemma":[0.0007619996,0.0002582925,0.005229628,0.0001585501,0.00002653518,0.0001248283,0.0007297426,0.9872235,0.0004315386,0.001016521,0.003525732,0.0005131421],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01382685,0.0009646261,0.981401,0.00005297152,0.0003861318,0.0001221459,0.0003998737,0.00007760885,0.00276877],"genre_scores_gemma":[0.7519178,0.0001932975,0.2464058,0.0000258155,0.0001923682,0.000009209494,0.0005461478,0.00003009534,0.0006793858],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9872118,"threshold_uncertainty_score":0.9904661,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2072732320","doi":"10.1007/s10618-005-0019-1","title":"Data Clustering with Partial Supervision","year":2006,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Computer science; Artificial intelligence; Classifier (UML); Pattern recognition (psychology); Fuzzy clustering; Machine learning; Support vector machine; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.07186957610495115,"gpt":0.3322306622859221,"spread":0.260361086180971,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00049023,0.000178341,0.0001851581,0.00009239249,0.0002292482,0.0007158904,0.002913614,0.00004533082,0.000002409113],"category_scores_gemma":[0.00006487053,0.0001437177,0.000009930117,0.0003011455,0.0001064767,0.004600593,0.008966632,0.0001318614,0.00001554204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002082783,"about_ca_system_score_gemma":0.0001192684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001279364,"about_ca_topic_score_gemma":0.0005803453,"domain_scores_codex":[0.9980063,0.00006479952,0.0002096762,0.001044509,0.0002608342,0.0004138588],"domain_scores_gemma":[0.996532,0.0001714681,0.00004756732,0.003121869,0.00004051541,0.00008657637],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001302603,0.000413185,0.004966421,0.0002755834,0.00007413044,0.0002829958,0.001348295,0.0005931273,0.001118478,0.001369053,0.01762249,0.971806],"study_design_scores_gemma":[0.0006023248,0.0000972605,0.001134228,0.0001531405,0.00001020993,0.00008068766,0.0001850097,0.9664958,0.0001651092,0.00004569874,0.03072195,0.0003086045],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04754636,0.001228566,0.9485965,0.0001599947,0.0002542332,0.0001182578,0.0005409045,0.0001489676,0.001406255],"genre_scores_gemma":[0.6104358,0.0001391495,0.3819658,0.00005243966,0.0008981257,0.00001681079,0.003573437,0.00006011574,0.002858275],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9714974,"threshold_uncertainty_score":0.9990487,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2952461389","doi":"10.1016/j.ins.2018.01.013","title":"RECOME: A new density-based clustering algorithm using relative KNN kernel density","year":2018,"lang":"en","type":"article","venue":"Information Sciences","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Beijing Municipal Natural Science Foundation; National Natural Science Foundation of China","keywords":"Cluster analysis; Computer science; Pattern recognition (psychology); Jump; Single-linkage clustering; Merge (version control); Nearest-neighbor chain algorithm; Kernel density estimation; Algorithm; Graph; Kernel (algebra); Discontinuity (linguistics); k-nearest neighbors algorithm; Data mining; Artificial intelligence; Mathematics; Correlation clustering; CURE data clustering algorithm; Canopy clustering algorithm; Theoretical computer science; Combinatorics; Statistics; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.06083948764184269,"gpt":0.3449632069298229,"spread":0.2841237192879802,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001216548,0.0001749955,0.000178913,0.0004645857,0.0009404984,0.0008019665,0.001229044,0.00007858034,0.00002067436],"category_scores_gemma":[0.0003053697,0.0001596744,0.00005702528,0.001777117,0.000476779,0.008486692,0.0006549364,0.0002058577,0.0003189331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002176973,"about_ca_system_score_gemma":0.0006214693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003748323,"about_ca_topic_score_gemma":0.00004577764,"domain_scores_codex":[0.9976272,0.00008413636,0.00043199,0.0003431853,0.000985797,0.0005277165],"domain_scores_gemma":[0.9984131,0.0001753821,0.0002621241,0.0004462803,0.0004834885,0.0002195691],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001928607,0.00002585894,0.0006004699,0.00002681724,0.00001807004,0.000009958166,0.007014753,0.01670499,0.0004829939,0.003542519,0.0003518059,0.9712025],"study_design_scores_gemma":[0.0003044291,0.0001366624,0.0009605016,0.00004430742,0.000002156897,0.00004707626,0.0001431749,0.9905484,0.002971367,0.003377693,0.001251042,0.0002131832],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01135174,0.000007526458,0.9850947,0.0006202098,0.0006271563,0.0002014382,0.000002010236,0.0002250314,0.001870222],"genre_scores_gemma":[0.126109,0.000002182972,0.8729237,0.0006773551,0.000147021,0.000003986434,0.000001823465,0.000005023437,0.0001298881],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9738434,"threshold_uncertainty_score":0.7733381,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1972132022","doi":"10.1145/1046456.1046468","title":"Subspace clustering for high dimensional categorical data","year":2004,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Computer science; Clustering high-dimensional data; Categorical variable; Correlation clustering; CURE data clustering algorithm; Data mining; Subspace topology; Canopy clustering algorithm; Data stream clustering; Focus (optics); Algorithm; Pattern recognition (psychology); Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.1123055424811128,"gpt":0.3448912619355348,"spread":0.232585719454422,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002888907,0.0002237184,0.0002080637,0.0001738008,0.0004106516,0.0003026644,0.003262907,0.00008812359,0.00001300624],"category_scores_gemma":[0.0004711494,0.0002156771,0.00005059941,0.0005390499,0.0000772248,0.002463814,0.003044442,0.0002583137,0.0002306217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001766332,"about_ca_system_score_gemma":0.0001602932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008112521,"about_ca_topic_score_gemma":0.00007934668,"domain_scores_codex":[0.9976661,0.00005096177,0.0003247646,0.0008815498,0.0004971441,0.000579497],"domain_scores_gemma":[0.9959775,0.0003470546,0.00007833023,0.003250398,0.0001798864,0.000166896],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001931697,0.00113489,0.0001282362,0.0001860862,0.0003356656,0.0004963474,0.004846421,0.5114476,0.06080486,0.1426964,0.1548861,0.1228442],"study_design_scores_gemma":[0.006744563,0.0006695507,0.0006657018,0.0000906792,0.00004962123,0.0002637311,0.0001640765,0.7211635,0.01955274,0.1915259,0.05702209,0.002087855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002734174,0.0000377446,0.9214948,0.07449408,0.0005146203,0.0004209795,0.00002487672,0.0002542343,0.00002443746],"genre_scores_gemma":[0.2055515,0.000007963334,0.7900522,0.003010029,0.0005358455,0.0002541639,0.000236514,0.00004121936,0.0003105326],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2097159,"threshold_uncertainty_score":0.8795058,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4294311511","doi":"10.1109/tetci.2022.3201620","title":"Viewpoint-Based Kernel Fuzzy Clustering With Weight Information Granules","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Emerging Topics in Computational Intelligence","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Anhui Provincial Key Research and Development Plan; Natural Science Foundation of Anhui Province; Central University Basic Research Fund of China; National Natural Science Foundation of China","keywords":"Cluster analysis; Fuzzy clustering; Mathematics; Artificial intelligence; Data mining; Pattern recognition (psychology); FLAME clustering; Correlation clustering; CURE data clustering algorithm; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.02503364515159577,"gpt":0.2962129579615027,"spread":0.2711793128099069,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003353922,0.0001883066,0.0001605984,0.0005909022,0.0005051771,0.0001112932,0.0008206969,0.0000344977,0.0000599798],"category_scores_gemma":[0.000008386002,0.0001998527,0.00006285319,0.001116357,0.00007084729,0.0009696419,0.00002616928,0.0006197058,0.00002714664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003720142,"about_ca_system_score_gemma":0.0001723759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005970981,"about_ca_topic_score_gemma":0.00003105044,"domain_scores_codex":[0.9978727,0.0001269061,0.0004365275,0.0003625549,0.0008663341,0.0003350015],"domain_scores_gemma":[0.999045,0.0002691995,0.0001076139,0.0003501435,0.0001505186,0.00007757283],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003208557,0.00008202843,0.000005935116,0.00002231239,0.000008546014,0.00001263431,0.0004520409,0.8441563,0.000003701302,0.005422325,0.000005860921,0.1497962],"study_design_scores_gemma":[0.0002514929,0.0001880647,0.00007269561,0.0000428814,0.000002557208,0.00002832672,0.0001248767,0.9858555,0.0008717747,0.0112588,0.001072344,0.0002307409],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000630437,0.00002193244,0.994786,0.003292782,0.0005831601,0.0002535157,0.0000120204,0.0001641631,0.0002559883],"genre_scores_gemma":[0.6831065,0.00001350929,0.3154348,0.001089907,0.00002724071,0.0002153843,0.000008785523,0.00001566192,0.00008828114],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.682476,"threshold_uncertainty_score":0.8149755,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2972986690","doi":"10.1016/j.ijar.2019.09.001","title":"A three-way cluster ensemble approach for large-scale data","year":2019,"lang":"en","type":"article","venue":"International Journal of Approximate Reasoning","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Saint Mary's University","funders":"National Natural Science Foundation of China","keywords":"Cluster analysis; Computer science; Data mining; Correlation clustering; SPARK (programming language); CURE data clustering algorithm; Cluster (spacecraft); k-medians clustering; Granularity; Fuzzy clustering; Single-linkage clustering; Data stream clustering; Scale (ratio); Constrained clustering; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.03398508273410222,"gpt":0.3263792715860228,"spread":0.2923941888519206,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001671958,0.0001677403,0.000288852,0.000251322,0.00007568358,0.0003796734,0.004314702,0.00007246916,0.00001330835],"category_scores_gemma":[0.0002253553,0.000144174,0.0001253328,0.0001865772,0.0000229937,0.001733984,0.0016109,0.0003347292,0.00001626845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001501998,"about_ca_system_score_gemma":0.0001346135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005613222,"about_ca_topic_score_gemma":0.000002924072,"domain_scores_codex":[0.9975538,0.00004122896,0.0005010313,0.0004453024,0.00103162,0.0004270482],"domain_scores_gemma":[0.9976526,0.0002245162,0.0004405277,0.0007778872,0.0007726045,0.0001318406],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002686101,0.002939784,0.01170587,0.0007873567,0.002945073,0.0003929902,0.007500231,0.0827898,0.01779786,0.1448557,0.01168735,0.7139119],"study_design_scores_gemma":[0.001667704,0.0001085786,0.0001583303,0.0001228146,0.000007584243,0.0005105122,0.0001266944,0.9891623,0.0007522861,0.002508941,0.004708506,0.0001657451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007233102,0.000154621,0.9894122,0.0006010856,0.0008510061,0.000288127,0.00003091699,0.00004154568,0.001387429],"genre_scores_gemma":[0.08309245,0.00002691095,0.9160165,0.0001268305,0.0004435007,0.00001102472,0.00003367294,0.00002825517,0.0002208137],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9063725,"threshold_uncertainty_score":0.8017862,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2161806858","doi":"10.1109/icsmc.2006.384571","title":"GRIDBSCAN: GRId Density-Based Spatial Clustering of Applications with Noise","year":2006,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"BC Innovation Council; National Research Council Canada; Simon Fraser University","funders":"","keywords":"DBSCAN; Cluster analysis; Computer science; Noise (video); Grid; Data mining; Benchmark (surveying); Set (abstract data type); Data set; Artificial intelligence; Pattern recognition (psychology); Correlation clustering; CURE data clustering algorithm; Image (mathematics); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.00793827355241549,"gpt":0.2418846435667457,"spread":0.2339463700143302,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011579,0.0001177244,0.000148222,0.000127948,0.00009699158,0.00005646394,0.0006213441,0.00003386359,0.00001061936],"category_scores_gemma":[0.000005608034,0.00009879068,0.00003479129,0.0004536553,0.00008690418,0.0001933488,0.00024293,0.0001071837,0.00001875783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000548508,"about_ca_system_score_gemma":0.0001034468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001025549,"about_ca_topic_score_gemma":0.0006826423,"domain_scores_codex":[0.9987535,0.00002617621,0.0002006811,0.0003405542,0.0004003602,0.0002786548],"domain_scores_gemma":[0.9989389,0.0000796558,0.00007564387,0.0006515,0.0001827251,0.00007153205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001399175,0.0007142473,0.008275398,0.0003420579,0.00004717282,0.00008836956,0.0001381653,0.7306626,0.02788933,0.01735824,0.0006072085,0.2137373],"study_design_scores_gemma":[0.0006867762,0.0001414385,0.006692708,0.00002377188,0.000004112678,0.0000221038,0.000007652277,0.9453893,0.04434348,0.000472136,0.001988128,0.0002283364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003033558,0.00001079257,0.9941753,0.0003222046,0.00005010486,0.0002798615,0.000003642504,0.0001774491,0.00194712],"genre_scores_gemma":[0.4804248,7.280643e-7,0.5190085,0.00005411808,0.000123574,0.00006854152,0.000006022134,0.00001235749,0.0003013676],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4773912,"threshold_uncertainty_score":0.4028567,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2086478515","doi":"10.1126/science.1151268","title":"Response to Comment on \"Clustering by Passing Messages Between Data Points\"","year":2008,"lang":"en","type":"article","venue":"Science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Generalization; Heuristic; Cluster analysis; Vertex (graph theory); Affinity propagation; Probabilistic logic; Substitution (logic); Computer science; Algorithm; Combinatorics; Graph; Chemistry; Mathematics; Theoretical computer science; Artificial intelligence; Correlation clustering; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.1064152909560008,"gpt":0.3787788033895297,"spread":0.272363512433529,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.002861994,0.0001607116,0.0001688232,0.0003024408,0.0009512442,0.0003281676,0.006452911,0.00002944588,0.000006483497],"category_scores_gemma":[0.0008376518,0.0001494867,0.00001818048,0.001327804,0.0004413865,0.001515351,0.00576511,0.0002231655,0.000142287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002884321,"about_ca_system_score_gemma":0.0002586966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002687638,"about_ca_topic_score_gemma":0.000001331817,"domain_scores_codex":[0.996334,0.0001631787,0.0002259941,0.001088407,0.00142898,0.000759495],"domain_scores_gemma":[0.9965191,0.0004706793,0.00005809323,0.002447975,0.0001000328,0.0004041071],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003584542,0.0003616942,0.002953075,0.00004066689,0.00003138461,0.0005307179,0.01011681,0.004764364,0.1945636,0.0005873723,0.1004098,0.6852821],"study_design_scores_gemma":[0.001439073,0.001381563,0.03294069,0.0003420684,0.000004798402,0.0001719656,0.0002160842,0.3398672,0.1192378,0.001179719,0.5016673,0.00155179],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03766717,0.00003211507,0.9215111,0.03980799,0.000238125,0.000216559,0.00002726273,0.0001868333,0.0003129006],"genre_scores_gemma":[0.6142645,0.00001187948,0.3795638,0.005312406,0.00007262412,0.00001773169,0.000004818887,0.00002073456,0.0007314468],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6837302,"threshold_uncertainty_score":0.9989226,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2755594639","doi":"10.1109/trustcom/bigdatase/icess.2017.332","title":"A Data Science and Engineering Solution for Fast K-Means Clustering of Big Data","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Big data; Scalability; Computer science; Cluster analysis; Data mining; Science and engineering; Heuristic; Task (project management); Variety (cybernetics); Centroid; Data science; Database; Artificial intelligence; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.192390620466613,"gpt":0.3746471718461937,"spread":0.1822565513795807,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00144097,0.00008841442,0.0001219861,0.0001287427,0.0004708431,0.000459219,0.008214709,0.00002386034,4.744439e-7],"category_scores_gemma":[0.001348787,0.00008319418,0.000007418833,0.0001560074,0.0002667851,0.003743516,0.01696884,0.00007600075,0.000001075829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003645338,"about_ca_system_score_gemma":0.0001513935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008996149,"about_ca_topic_score_gemma":0.00008417168,"domain_scores_codex":[0.9983594,0.000005726879,0.000157113,0.0006992225,0.0004208098,0.0003577597],"domain_scores_gemma":[0.994667,0.00008882165,0.00008609359,0.004874242,0.0001829537,0.0001008717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007094402,0.00002209238,0.00005914275,0.0001444598,0.00001103985,0.000002976371,0.0001304874,0.00111313,0.0335121,0.00186404,0.0001312533,0.9630022],"study_design_scores_gemma":[0.0002282959,0.00003256884,0.0009100693,0.00003509601,0.000001876568,0.00001189667,0.000009732321,0.9954348,0.000933462,0.00005516647,0.002250067,0.00009693076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003967523,0.00003091391,0.9981433,0.0004846639,0.0003326189,0.0001849902,0.00008464579,0.00005717278,0.0002849881],"genre_scores_gemma":[0.176021,0.00002349058,0.8237185,0.00001175742,0.0001022301,0.000006808843,0.000009848374,0.000009218367,0.00009716055],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9943217,"threshold_uncertainty_score":0.9971513,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2011191813","doi":"10.1007/s10115-009-0226-y","title":"Subspace and projected clustering: experimental evaluation and analysis","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Subspace topology; Computer science; Data mining; Range (aeronautics); Clustering high-dimensional data; Consensus clustering; Artificial intelligence; Correlation clustering; CURE data clustering algorithm; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.0260607623732046,"gpt":0.3356089740219756,"spread":0.3095482116487711,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005176085,0.0001021088,0.0001579597,0.0003600104,0.0001496524,0.0004440716,0.0001109668,0.0000484272,0.000001253382],"category_scores_gemma":[0.00003357389,0.00009121774,0.00001611855,0.0005872467,0.00002743947,0.00295401,0.0001303302,0.00006182487,0.000007393433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005729397,"about_ca_system_score_gemma":0.00003156954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001380966,"about_ca_topic_score_gemma":0.000003917117,"domain_scores_codex":[0.9991026,0.00007900471,0.0002449848,0.000165154,0.0002540741,0.0001541702],"domain_scores_gemma":[0.999377,0.00003089116,0.0000859172,0.0001892623,0.0002238265,0.00009315759],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000589572,0.0001258657,0.002683405,0.0003834464,0.0002763455,0.000002794536,0.07744251,0.003161081,0.002335601,0.01343488,0.0004292368,0.8996659],"study_design_scores_gemma":[0.0004594934,0.0001109788,0.01138207,0.00001990161,0.00001532061,0.00002718644,0.0006025216,0.9844515,0.0002112004,0.00001500964,0.00259089,0.0001139543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1953805,0.005606333,0.7869529,0.0002187823,0.0002381475,0.001139852,0.00000442101,0.0002142725,0.01024476],"genre_scores_gemma":[0.9974134,0.00005203333,0.002330999,0.00002324634,0.00002621905,0.00003501795,0.00001071217,0.000002013009,0.000106333],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9812904,"threshold_uncertainty_score":0.4282193,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2129500661","doi":"10.1109/tkde.2008.162","title":"Mining Projected Clusters in High-Dimensional Spaces","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Cluster analysis; Computer science; Curse of dimensionality; Linear subspace; Outlier; Clustering high-dimensional data; Data mining; CURE data clustering algorithm; Data point; Correlation clustering; Computation; Pattern recognition (psychology); Canopy clustering algorithm; Single-linkage clustering; Algorithm; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03923416376241975,"gpt":0.2902071390881266,"spread":0.2509729753257069,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001470902,0.0001490361,0.0001529528,0.0003615766,0.0001305117,0.00004451277,0.0005477946,0.000054011,0.000003708798],"category_scores_gemma":[0.00001167857,0.0001519289,0.00001649736,0.0005637464,0.00003442713,0.0007464144,0.00003680541,0.0002589603,0.00001544827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005529967,"about_ca_system_score_gemma":0.00006496651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003081904,"about_ca_topic_score_gemma":0.00004048389,"domain_scores_codex":[0.9988579,0.00002510862,0.0001678302,0.0004770953,0.0001720259,0.000300053],"domain_scores_gemma":[0.9990692,0.0001697037,0.00001703606,0.000610294,0.00003472555,0.00009900614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005205935,0.0004295947,0.00007480193,0.0001740253,0.00007519741,0.0003074731,0.003033961,0.8233709,0.005062124,0.0001236625,0.0004251665,0.166871],"study_design_scores_gemma":[0.000505304,0.00005658673,0.0003523895,0.00007545039,0.000002484583,0.00009525517,0.00001517613,0.996149,0.002101911,0.000003042303,0.0004613504,0.0001820326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07835083,0.0001686478,0.9207112,0.00007827223,0.0003583954,0.0001182878,0.00001671544,0.00016878,0.0000288964],"genre_scores_gemma":[0.8648399,0.00007677724,0.1347946,0.00001285725,0.00003863903,0.00002413629,0.000008119606,0.00001836168,0.0001866567],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.786489,"threshold_uncertainty_score":0.619548,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2783873704","doi":"10.1186/s12859-017-1996-y","title":"diceR: an R package for class discovery using an ensemble driven approach","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"BC Cancer Foundation","keywords":"Computer science; Dicer; Cluster analysis; Context (archaeology); Data mining; Set (abstract data type); Class (philosophy); Permutation (music); Generalization; Cluster (spacecraft); Machine learning; Artificial intelligence; Data science; Biology; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.08579926171176273,"gpt":0.3410082939630839,"spread":0.2552090322513211,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004269402,0.0002005488,0.0002134319,0.0001569222,0.0003710826,0.0006900774,0.001321786,0.0001084937,0.00000137835],"category_scores_gemma":[0.0000757523,0.0001784927,0.00006904593,0.0003691603,0.0001726537,0.005290051,0.0005214868,0.0001450506,0.00002633266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001196499,"about_ca_system_score_gemma":0.0002002299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001549824,"about_ca_topic_score_gemma":0.00002727495,"domain_scores_codex":[0.9981972,0.000053307,0.0003840437,0.0003080463,0.0004424533,0.0006149227],"domain_scores_gemma":[0.9981145,0.000092479,0.0001591216,0.001200646,0.000203638,0.000229651],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004607723,0.003197095,0.001674655,0.004161801,0.0002703121,0.00002035516,0.06685312,0.1652574,0.01470022,0.1356119,0.001893724,0.6058986],"study_design_scores_gemma":[0.0004738097,0.0004285909,0.00007738776,0.00001871423,0.000005614143,0.0000286026,0.0005543471,0.9946892,0.001674172,0.001102141,0.0006831681,0.0002642801],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00971716,0.000007251685,0.9875722,0.00001577666,0.0002389072,0.0004676436,0.00002297247,0.0001967637,0.00176136],"genre_scores_gemma":[0.04167516,0.000002579183,0.9576384,0.0001053491,0.0002821751,0.0000255351,0.00003068943,0.00002479652,0.0002152412],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8294318,"threshold_uncertainty_score":0.7278723,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2801522993","doi":"10.1155/2018/6164534","title":"Application of Data Clustering to Railway Delay Pattern Recognition","year":2018,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Danmarks Tekniske Universitet","keywords":"Cluster analysis; Computer science; Data mining; Pattern recognition (psychology); Artificial intelligence; Transport engineering; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.04256832023106765,"gpt":0.3383466030776369,"spread":0.2957782828465692,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004718271,0.0001050836,0.0001975176,0.0002407641,0.00005760726,0.00002561866,0.001006808,0.00004210799,0.000006036499],"category_scores_gemma":[0.00004933917,0.0001027204,0.00004338712,0.0005034835,0.00003789511,0.002003643,0.00004620008,0.0001462373,0.00001354277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005214904,"about_ca_system_score_gemma":0.00005511986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000131831,"about_ca_topic_score_gemma":0.0001031707,"domain_scores_codex":[0.9983737,0.00003531544,0.0006387835,0.0002742162,0.0004905822,0.0001873609],"domain_scores_gemma":[0.9980052,0.00007285692,0.0004816013,0.000551096,0.0007726773,0.0001166291],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000816126,0.00004309903,0.0001459849,0.00003635746,0.00001619692,0.000009632479,0.00119368,0.01495059,0.02342048,0.00001253698,0.0000144536,0.9600754],"study_design_scores_gemma":[0.008045354,0.006238796,0.1978953,0.001512679,0.0001481258,0.0003545219,0.001275744,0.6024303,0.1569096,0.008602299,0.01503251,0.001554706],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08095312,0.00002934228,0.9182538,0.0002643802,0.0002557854,0.0001770453,0.00002425669,0.00002265129,0.00001962951],"genre_scores_gemma":[0.5911117,0.00002230034,0.4086344,0.0000513235,0.0001375084,0.000004385772,0.00002410393,0.000009766884,0.000004570926],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9585207,"threshold_uncertainty_score":0.4188817,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2010971425","doi":"10.1007/s10618-011-0212-3","title":"Measuring the component overlapping in the Gaussian mixture model","year":2011,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Cluster analysis; Gaussian; Computer science; Algorithm; Set (abstract data type); Component (thermodynamics); Multivariate normal distribution; Mixture model; Measure (data warehouse); Mathematics; Data mining; Multivariate statistics; Pattern recognition (psychology); Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.1637535893682168,"gpt":0.3177989488666944,"spread":0.1540453594984776,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001148349,0.0001519425,0.0001429513,0.00008335234,0.0002863971,0.0003568064,0.002941236,0.00004208538,8.785165e-7],"category_scores_gemma":[0.0001021624,0.00008779957,0.00002419719,0.0003220991,0.0001157562,0.001407272,0.002284872,0.0002834517,0.000006538445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002744577,"about_ca_system_score_gemma":0.00008664483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006620838,"about_ca_topic_score_gemma":0.0001617985,"domain_scores_codex":[0.9984991,0.000169605,0.0001943948,0.0005080145,0.0002608994,0.0003679634],"domain_scores_gemma":[0.9980503,0.0002316294,0.00005128475,0.001592203,0.00002517228,0.0000494324],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001195772,0.0009155978,0.004440024,0.0003540575,0.0001607817,0.0002805145,0.2990175,0.001566644,0.001898838,0.03504369,0.006414784,0.649788],"study_design_scores_gemma":[0.0002830366,0.00002738603,0.005578158,0.0001536824,0.000006515913,0.00004568974,0.002464745,0.9894086,0.00007875131,0.0007904441,0.000957433,0.0002055284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1429817,0.003371938,0.8390664,0.0007894944,0.0004231759,0.000421632,0.00009029728,0.0001052813,0.01275003],"genre_scores_gemma":[0.9748136,0.00008413412,0.02456645,0.0001173951,0.0000833452,0.00002290721,0.0000254923,0.00001271937,0.0002739531],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.987842,"threshold_uncertainty_score":0.5465598,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385232475","doi":"10.1109/tpami.2023.3298629","title":"Knowledge-Induced Multiple Kernel Fuzzy Clustering","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Cluster analysis; Fuzzy clustering; Computer science; Data mining; Artificial intelligence; Fuzzy logic; Knowledge extraction; Kernel (algebra); Domain knowledge; Correlation clustering; Data stream clustering; Pattern recognition (psychology); CURE data clustering algorithm; Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.05038867321862579,"gpt":0.3325815652432935,"spread":0.2821928920246677,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000365874,0.0002622293,0.0003392578,0.001097114,0.0003415727,0.0001947926,0.0007602882,0.00007904584,0.00003886373],"category_scores_gemma":[0.00001504118,0.0002445687,0.0002367664,0.003231499,0.00005532481,0.0004070583,0.00004007398,0.000403095,0.0003132196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006739905,"about_ca_system_score_gemma":0.00002655134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007286051,"about_ca_topic_score_gemma":0.001532236,"domain_scores_codex":[0.9978995,0.000108429,0.0003787125,0.0007634001,0.0003652181,0.0004847268],"domain_scores_gemma":[0.9985111,0.00035035,0.00007017523,0.0007461117,0.00010361,0.0002186208],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006830305,0.00008163256,0.0001441244,0.00002303703,0.0002419721,0.00002579441,0.0005831296,0.08465973,0.001240341,0.00001157966,0.000004169471,0.9129776],"study_design_scores_gemma":[0.0001139291,0.00009196986,0.0009270209,0.00002297233,0.00006721761,0.00001075226,0.00006883255,0.9382775,0.05994895,0.000148445,0.00006202668,0.0002603573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005459157,0.00004653858,0.9931574,0.00031557,0.0003222977,0.0001475799,0.00001646228,0.0003951564,0.0001398425],"genre_scores_gemma":[0.9953569,0.0002632869,0.003313513,0.0001078612,0.00002915195,0.00005370545,0.000004027328,0.00002209608,0.0008494717],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9898977,"threshold_uncertainty_score":0.9973223,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2512875827","doi":"10.18637/jss.v072.i05","title":"<b>RSKC</b>: An<i>R</i>Package for a Robust and Sparse K-Means Clustering Algorithm","year":2016,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Outlier; Cluster analysis; Computer science; Data mining; R package; Identification (biology); Algorithm; Monte Carlo method; Artificial intelligence; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.03384400660344562,"gpt":0.3084657004614797,"spread":0.2746216938580341,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006244439,0.000182414,0.0003427081,0.000141366,0.0001508966,0.0001784562,0.0006844442,0.0000749302,0.00002321097],"category_scores_gemma":[0.001237894,0.0001224104,0.0000640147,0.0001495949,0.0001553385,0.001029629,0.0003165031,0.0002142476,0.00000690521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001175814,"about_ca_system_score_gemma":0.0001111303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005034848,"about_ca_topic_score_gemma":0.000005809253,"domain_scores_codex":[0.9980499,0.00008658684,0.0004928761,0.0003364101,0.0005329926,0.0005012915],"domain_scores_gemma":[0.9970955,0.001440562,0.0002082896,0.0003288623,0.0004284634,0.0004983586],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005437817,0.00006938931,0.0001064223,0.00004848534,0.00002692322,0.0002227733,0.0001412652,0.0002375269,0.0004097314,0.001164303,0.0004286783,0.9970901],"study_design_scores_gemma":[0.009139725,0.006150754,0.008910947,0.0008803841,0.0000845441,0.003483956,0.0001779072,0.8703783,0.001593894,0.0860487,0.01179213,0.001358808],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003336116,0.00009500085,0.9982871,0.0006310376,0.0002733649,0.0001585039,0.0001530954,0.00006111642,0.000007142326],"genre_scores_gemma":[0.003934018,0.00006315737,0.9954907,0.0001040445,0.0002405308,0.000009092897,0.000001463921,0.0000276785,0.0001293165],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9957313,"threshold_uncertainty_score":0.499175,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2074553505","doi":"10.1080/02664760903186049","title":"Clustering probability distributions","year":2010,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Joint probability distribution; Probability distribution; Computer science; Mathematics; Probability density function; Algorithm; Statistical physics; Data mining; Statistics; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.01810154605205502,"gpt":0.2980051897073426,"spread":0.2799036436552876,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005406892,0.00009418598,0.0001705937,0.00007590694,0.0001212984,0.0001241808,0.0007747958,0.00004824127,0.00001769687],"category_scores_gemma":[0.0002556088,0.00008269557,0.00003453574,0.0002251452,0.000094889,0.0001900746,0.0002704581,0.000662657,0.00001341278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000677081,"about_ca_system_score_gemma":0.0001650124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001377389,"about_ca_topic_score_gemma":0.0000100289,"domain_scores_codex":[0.9987537,0.00001628212,0.0003965488,0.0001455499,0.000436216,0.0002516821],"domain_scores_gemma":[0.9986377,0.0002359448,0.0002365498,0.0003641839,0.0003513375,0.0001742923],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006610142,0.0002725481,0.00009429708,0.00008764456,0.00005187433,0.0001428147,0.0006333105,0.005167013,0.02938543,0.5154784,0.002041152,0.4465795],"study_design_scores_gemma":[0.001448865,0.0003601963,0.005233863,0.00002853661,0.00002300777,0.0005918498,0.00006089952,0.3738429,0.008041549,0.5925037,0.01736545,0.0004991783],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003660396,0.000004023816,0.9947535,0.0001840712,0.0004735366,0.00009128189,0.0000387758,0.00002610347,0.0007683356],"genre_scores_gemma":[0.2152928,0.000003966753,0.7845392,0.00001813165,0.0001133931,0.000003017556,0.000001530154,0.000005978397,0.00002204144],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4460803,"threshold_uncertainty_score":0.3372227,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1584777468","doi":"10.1007/11811305_30","title":"A Fuzzy Subspace Algorithm for Clustering High Dimensional Data","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Cluster analysis; Fuzzy clustering; Computer science; FLAME clustering; Subspace topology; Dimension (graph theory); k-medians clustering; Cluster (spacecraft); Fuzzy logic; Clustering high-dimensional data; Data mining; Correlation clustering; Pattern recognition (psychology); Single-linkage clustering; Algorithm; CURE data clustering algorithm; Artificial intelligence; Mathematics; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.03486772328265359,"gpt":0.3000635860296849,"spread":0.2651958627470313,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001434832,0.0007634051,0.0007542716,0.0009719799,0.000496323,0.0008079393,0.00928976,0.0003954783,0.000006993034],"category_scores_gemma":[0.0001454488,0.0007416059,0.0001306593,0.0007356648,0.0007755291,0.001344033,0.01000525,0.001046057,0.00003278238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005727097,"about_ca_system_score_gemma":0.0008169544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001134338,"about_ca_topic_score_gemma":0.0001713354,"domain_scores_codex":[0.9927568,0.00004093887,0.0006801395,0.003281576,0.001856443,0.001384111],"domain_scores_gemma":[0.9937458,0.001088285,0.000325514,0.004079757,0.0004799419,0.0002806962],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005639467,0.00002654929,0.000001394312,0.00004277524,0.00001260188,0.0001058013,0.00005405139,0.1368811,0.00005668212,0.001196517,0.0001708595,0.8614461],"study_design_scores_gemma":[0.000519793,0.0001669882,0.00002068821,0.0002812272,0.000007137302,0.0001235209,5.493044e-8,0.9191976,0.0002703518,0.07646069,0.002187226,0.0007647794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000005414817,0.0004445168,0.9943777,0.0009590042,0.002323972,0.0008796587,0.0001353316,0.0002771875,0.0005972101],"genre_scores_gemma":[0.001389545,0.00001835718,0.9952558,0.0004858904,0.001088575,0.00003196629,0.0001148282,0.00008476637,0.001530225],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8606813,"threshold_uncertainty_score":0.9995035,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}