{"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","author_layer_release":"2026-06-26"},"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","authors":[{"name":"Ricardo J. G. B. Campello","is_ca":true},{"name":"Davoud Moulavi","is_ca":true},{"name":"Jörg Sander","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00235469,0.001062691,0.002130456,0.002873365,0.001340266,0.001956776,0.004076336,0.001901906,0.003457947],"category_scores_gemma":[0.01379243,0.001400019,0.001855318,0.003861698,0.001140234,0.002660276,0.003054774,0.002179965,0.002614533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001542108,"about_ca_system_score_gemma":0.001348675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008361296,"about_ca_topic_score_gemma":0.008475352,"domain_scores_codex":[0.9979941,0.0006995166,0.0001069309,0.0003470925,0.0007352688,0.0001171251],"domain_scores_gemma":[0.994879,0.002598081,0.0002801873,0.0008395088,0.00127337,0.000129813],"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":[0.0001735492,0.00008608483,0.001244467,0.0003624383,0.0002175851,0.0001121298,0.0004156418,0.5959615,0.005542593,0.1122119,0.009358329,0.2743138],"study_design_scores_gemma":[0.000007395335,0.00001371658,0.0002926247,0.00001900788,0.00002044219,0.00006084052,0.00002294824,0.970121,0.000895777,0.02696976,0.001550295,0.00002616668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001937725,0.000247074,0.9964374,0.00005330732,0.00002978933,0.00003585385,0.00005055499,0.000279234,0.000929093],"genre_scores_gemma":[0.1431885,0.001018495,0.8486137,0.0001329824,0.0001534605,0.0002684171,0.0009074202,0.0004453143,0.005271695],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008361296,"threshold_uncertainty_score":0.01662529,"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","authors":[{"name":"Feng Cao","is_ca":false},{"name":"Martin Estert","is_ca":true},{"name":"Weining Qian","is_ca":false},{"name":"Aoying Zhou","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002345751,0.0006300164,0.001302698,0.002154591,0.0008180217,0.00110675,0.001957842,0.0009710949,0.0003552637],"category_scores_gemma":[0.01122344,0.0004607879,0.000642432,0.002295985,0.0007807803,0.00191336,0.001325731,0.0009131291,0.0002049035],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001394078,"about_ca_system_score_gemma":0.0008709253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006717699,"about_ca_topic_score_gemma":0.005122504,"domain_scores_codex":[0.9989274,0.0002255006,0.00007843198,0.0002365646,0.0004588785,0.00007326269],"domain_scores_gemma":[0.9957184,0.002272008,0.0004194022,0.0004647808,0.001000083,0.0001254197],"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":[0.000219837,0.00004742228,0.004229107,0.0001058894,0.000074908,0.0001496884,0.0003125675,0.8321775,0.005949399,0.01226975,0.001159984,0.1433039],"study_design_scores_gemma":[0.000003513441,0.00000842825,0.0002771838,0.000002612749,0.000003519457,0.00002276383,0.00001333284,0.9961361,0.00100051,0.002316302,0.0002103437,0.000005294796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03437565,0.0001806806,0.9645568,0.0001059189,0.0000178309,0.00004141738,0.00005160315,0.0003962387,0.0002737429],"genre_scores_gemma":[0.4814362,0.0005842888,0.5158734,0.0000833756,0.00006920748,0.0001325212,0.0004731573,0.0001108756,0.001236893],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006717699,"threshold_uncertainty_score":0.01335722,"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","authors":[{"name":"Hans‐Peter Kriegel","is_ca":false},{"name":"Peer Kröger","is_ca":false},{"name":"Jörg Sander","is_ca":true},{"name":"Arthur Zimek","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00340053,0.001490543,0.002054716,0.008395691,0.002071257,0.004955584,0.003101084,0.002351815,0.008533414],"category_scores_gemma":[0.01720308,0.0009357687,0.001820197,0.009168972,0.001702363,0.003516115,0.0035317,0.001822484,0.006697941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002795575,"about_ca_system_score_gemma":0.002694284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008082308,"about_ca_topic_score_gemma":0.004981634,"domain_scores_codex":[0.9950125,0.001133185,0.0002726587,0.001141866,0.002168474,0.0002712706],"domain_scores_gemma":[0.9942855,0.001876517,0.0004751302,0.001232438,0.001974573,0.0001558221],"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":[0.0002393312,0.0001253394,0.007886333,0.001176343,0.0005308698,0.0003195677,0.0009416512,0.2643835,0.004868445,0.2815238,0.06140286,0.376602],"study_design_scores_gemma":[0.00003969035,0.00006405476,0.003796205,0.000299132,0.0001236625,0.0006647286,0.0003861445,0.6702391,0.006034456,0.222713,0.09544726,0.0001926038],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006066402,0.002601064,0.9721345,0.000663111,0.0002246034,0.0003432082,0.001502978,0.001607541,0.01485662],"genre_scores_gemma":[0.3066771,0.005878679,0.6572748,0.0006545893,0.0004974403,0.0007769049,0.009142983,0.001007373,0.01809016],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008533414,"threshold_uncertainty_score":0.02854711,"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","authors":[{"name":"Ali Seyed Shirkhorshidi","is_ca":false},{"name":"Saeed Aghabozorgi","is_ca":true},{"name":"Teh Ying Wah","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01797167,0.0008908915,0.001196288,0.008430123,0.001010342,0.00304046,0.001397586,0.001454617,0.00111979],"category_scores_gemma":[0.09682115,0.0003037016,0.001241274,0.01063203,0.00148808,0.005809433,0.001706723,0.001202843,0.0003054438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001719355,"about_ca_system_score_gemma":0.001092045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001772873,"about_ca_topic_score_gemma":0.001528104,"domain_scores_codex":[0.9803352,0.008104173,0.002093108,0.002380759,0.006695054,0.0003917561],"domain_scores_gemma":[0.9195517,0.05883326,0.003292621,0.00502971,0.01228326,0.001009439],"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":[0.002176227,0.0005716927,0.08183413,0.004355904,0.002192463,0.0004226052,0.002494975,0.0566669,0.01142934,0.06501206,0.005745935,0.7670978],"study_design_scores_gemma":[0.0003522889,0.006583017,0.1498175,0.001585221,0.00168044,0.003230102,0.006019058,0.6854444,0.03097709,0.0716337,0.04213445,0.0005427367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4486104,0.04321476,0.4883186,0.001639057,0.0009752794,0.0005503662,0.0009025484,0.0005570646,0.01523191],"genre_scores_gemma":[0.7592854,0.005580308,0.2324036,0.0001403576,0.0002876577,0.0002409717,0.001088006,0.0001050228,0.0008685301],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01797167,"threshold_uncertainty_score":0.09504437,"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","authors":[{"name":"Witold Pedrycz","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002601201,0.001208615,0.002554999,0.003077448,0.002853816,0.003092807,0.003314419,0.003005857,0.008628493],"category_scores_gemma":[0.005671072,0.0008526702,0.002492042,0.002821573,0.001322939,0.00218887,0.003219757,0.001385295,0.003731318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0015132,"about_ca_system_score_gemma":0.001803208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005578012,"about_ca_topic_score_gemma":0.007124184,"domain_scores_codex":[0.9965055,0.0006565198,0.0001902982,0.001091193,0.001311335,0.0002450983],"domain_scores_gemma":[0.9968076,0.0006081671,0.0001545073,0.001130276,0.001148895,0.0001506928],"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":[0.0005755255,0.000196886,0.00154022,0.0003009603,0.0004705848,0.0002820445,0.000351867,0.2879498,0.01531722,0.09350444,0.01808115,0.5814293],"study_design_scores_gemma":[0.00003312653,0.00007774737,0.0005726445,0.0000243579,0.00008061058,0.0002370353,0.0001024321,0.9371347,0.008283947,0.04225315,0.01114771,0.0000525016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006103071,0.0004410164,0.984561,0.0001724108,0.0001383837,0.00009449061,0.0001168141,0.0004595972,0.0079133],"genre_scores_gemma":[0.3200683,0.000595285,0.6516533,0.0002322746,0.0002435722,0.0002819571,0.0009802406,0.0002291414,0.02571604],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008628493,"threshold_uncertainty_score":0.02886516,"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","authors":[{"name":"Davoud Moulavi","is_ca":true},{"name":"Pablo Andretta Jaskowiak","is_ca":true},{"name":"Ricardo J. G. B. Campello","is_ca":false},{"name":"Arthur Zimek","is_ca":false},{"name":"Jörg Sander","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02763772,0.001680771,0.002156772,0.007147281,0.00207713,0.003911127,0.00367745,0.002695333,0.002111681],"category_scores_gemma":[0.1135745,0.0006569583,0.001856002,0.004519029,0.002170359,0.004201065,0.004340978,0.002017509,0.001371072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002412501,"about_ca_system_score_gemma":0.002496772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004832457,"about_ca_topic_score_gemma":0.003334382,"domain_scores_codex":[0.9777729,0.008688192,0.001815522,0.002564231,0.008373225,0.000786015],"domain_scores_gemma":[0.9445189,0.02176011,0.0034373,0.009269884,0.02043717,0.0005765925],"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":[0.001016501,0.0003363781,0.03747839,0.001339697,0.0008505393,0.0003457896,0.001440629,0.5274352,0.02150648,0.05739074,0.009205127,0.3416544],"study_design_scores_gemma":[0.00003130325,0.0001159218,0.005931363,0.0001325509,0.00006843181,0.0003390955,0.0002593182,0.9592006,0.01567653,0.01483622,0.003319049,0.00008967082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05479322,0.000657799,0.9378679,0.0001906955,0.0001100685,0.0004186437,0.0005272026,0.001825156,0.003609295],"genre_scores_gemma":[0.5693581,0.0004179595,0.4243027,0.0001879687,0.00005441792,0.000550926,0.002824562,0.0006287472,0.001674542],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02763772,"threshold_uncertainty_score":0.146164,"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","authors":[{"name":"Periklis Andritsos","is_ca":true},{"name":"Panayiotis Tsaparas","is_ca":true},{"name":"Renée J. Miller","is_ca":true},{"name":"Kenneth C. Sevcik","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001481647,0.00144688,0.002048129,0.003256861,0.001583504,0.002625802,0.004145035,0.0009237397,0.01694855],"category_scores_gemma":[0.006111883,0.001379541,0.002395253,0.006372483,0.000685823,0.002928334,0.004924891,0.002147383,0.01129535],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001009359,"about_ca_system_score_gemma":0.002159623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0073229,"about_ca_topic_score_gemma":0.01413778,"domain_scores_codex":[0.9983224,0.0003099332,0.0001215514,0.000272689,0.0008174219,0.000155941],"domain_scores_gemma":[0.9978982,0.0004453268,0.00009649377,0.0009617906,0.000429305,0.0001689065],"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":[0.0006807392,0.0002201192,0.001464615,0.0006858487,0.000254577,0.0001931238,0.0002366523,0.02278141,0.01076154,0.01564228,0.2437471,0.7033319],"study_design_scores_gemma":[0.0004898231,0.0002014556,0.002855616,0.0001521482,0.0001868822,0.0005725932,0.0002563499,0.7180532,0.01863345,0.1480262,0.1104236,0.0001486605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004928685,0.0005555298,0.9234459,0.000268353,0.0002638773,0.0002975948,0.005706437,0.06098786,0.003545901],"genre_scores_gemma":[0.0305278,0.0003678072,0.9360351,0.0002391435,0.00009973413,0.0006086082,0.02082241,0.003933636,0.007365793],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01694855,"threshold_uncertainty_score":0.05669856,"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","authors":[{"name":"Hanan Ayad","is_ca":true},{"name":"Mohamed S. Kamel","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00409771,0.0009726681,0.001738732,0.001964199,0.001224103,0.001420137,0.002856963,0.001804594,0.00375009],"category_scores_gemma":[0.01111305,0.0004836399,0.001121823,0.002070851,0.001150807,0.002594985,0.001735975,0.001416606,0.001254139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00157404,"about_ca_system_score_gemma":0.001905193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004630226,"about_ca_topic_score_gemma":0.004506739,"domain_scores_codex":[0.9972192,0.0008593307,0.0001455347,0.0006256073,0.0009676598,0.0001826871],"domain_scores_gemma":[0.9969081,0.001157105,0.0002106704,0.0004854033,0.001110457,0.0001281966],"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":[0.000351115,0.00006643172,0.0008239607,0.0001737787,0.0001224978,0.0001181425,0.0003937367,0.5128079,0.00761568,0.1019542,0.005127124,0.3704454],"study_design_scores_gemma":[0.00002285496,0.00003007826,0.0001081892,0.000009946358,0.00001340854,0.00003085407,0.00002506918,0.9717997,0.001964138,0.02362669,0.00235442,0.00001472133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00269997,0.00007996673,0.9963361,0.00004373095,0.00002656988,0.00003662076,0.00002080869,0.0002149034,0.0005414262],"genre_scores_gemma":[0.1402124,0.0001581997,0.8545263,0.0001070104,0.00009081423,0.0003191469,0.0003295926,0.0002319009,0.004024473],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004630226,"threshold_uncertainty_score":0.02167106,"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","authors":[{"name":"Vincent Cohen-Addad","is_ca":false},{"name":"Varun Kanade","is_ca":false},{"name":"Frederik Mallmann-Trenn","is_ca":true},{"name":"Claire Mathieu","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003429312,0.002612446,0.002875324,0.006708002,0.002982405,0.006115853,0.006056515,0.00269493,0.0275878],"category_scores_gemma":[0.01273325,0.001073756,0.003972859,0.008202929,0.001456734,0.005095282,0.005589416,0.002389646,0.02362363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003343682,"about_ca_system_score_gemma":0.004433169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009738219,"about_ca_topic_score_gemma":0.01697514,"domain_scores_codex":[0.9924628,0.001624363,0.0004931904,0.002461773,0.002420144,0.0005377101],"domain_scores_gemma":[0.9938301,0.001216544,0.0003931941,0.002348131,0.001975198,0.0002367984],"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":[0.0002992357,0.0001673954,0.004265345,0.0017766,0.0008212059,0.0002866961,0.0007755331,0.07483504,0.004662727,0.1340771,0.2317518,0.5462813],"study_design_scores_gemma":[0.00008430688,0.0001190639,0.002808784,0.0005067384,0.0002821847,0.000586517,0.0007320257,0.3119563,0.00611871,0.2863572,0.3902747,0.0001735428],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002632773,0.002177528,0.9594924,0.0007473163,0.0002957739,0.000735456,0.008067493,0.006840693,0.01901047],"genre_scores_gemma":[0.06916197,0.002484805,0.8647962,0.001100556,0.0003414628,0.001035596,0.03783154,0.00233954,0.02090835],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0275878,"threshold_uncertainty_score":0.0922904,"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","authors":[{"name":"Rafail Ostrovsky","is_ca":false},{"name":"Yuval Rabani","is_ca":false},{"name":"Leonard J. Schulman","is_ca":false},{"name":"Chaitanya Swamy","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01032908,0.002069911,0.002452144,0.002573962,0.002165751,0.00394617,0.004857445,0.004114964,0.003192442],"category_scores_gemma":[0.04864528,0.001500118,0.001993753,0.002356225,0.003405437,0.00596827,0.004166868,0.003744483,0.001633201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002944557,"about_ca_system_score_gemma":0.003421683,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006553896,"about_ca_topic_score_gemma":0.005160035,"domain_scores_codex":[0.9943504,0.002783767,0.0002949133,0.0008053196,0.001435943,0.000329735],"domain_scores_gemma":[0.9825193,0.01268532,0.0008956263,0.001714365,0.001682381,0.0005029521],"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":[0.0003159616,0.0002196324,0.001842413,0.0003823439,0.0001578658,0.00009448543,0.0004428424,0.6936516,0.002059206,0.1723914,0.006618295,0.1218239],"study_design_scores_gemma":[0.00004710043,0.00007158265,0.0001399601,0.00004711022,0.0000143134,0.00004112081,0.00003869989,0.9356908,0.001112874,0.06030454,0.002467051,0.00002484417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005754602,0.0004963841,0.9902521,0.0003245521,0.00005870776,0.0000826612,0.00002901537,0.0002895258,0.002712403],"genre_scores_gemma":[0.1298261,0.0006841094,0.8651003,0.0003424932,0.0001593765,0.0003676894,0.0001872255,0.0003585848,0.002974262],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01032908,"threshold_uncertainty_score":0.05462605,"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","authors":[{"name":"Shai Ben-David","is_ca":true},{"name":"Margareta Ackerman","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02813102,0.001914843,0.002549851,0.008247268,0.003566847,0.009385272,0.007253961,0.005496571,0.002826716],"category_scores_gemma":[0.0516832,0.001360351,0.003657168,0.008383105,0.01772659,0.01819721,0.005802618,0.00820783,0.001111885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004895412,"about_ca_system_score_gemma":0.003450758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002243713,"about_ca_topic_score_gemma":0.001323467,"domain_scores_codex":[0.9734018,0.009433039,0.003766489,0.004429996,0.008156549,0.0008121577],"domain_scores_gemma":[0.9396952,0.03007066,0.006609267,0.01223302,0.01009488,0.00129703],"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":[0.00002268387,0.00002909058,0.0008153968,0.0002726815,0.00005407136,0.00003668056,0.0003048441,0.007677815,0.0005794693,0.9724894,0.001541748,0.01617609],"study_design_scores_gemma":[0.00002122353,0.00006400797,0.0005191172,0.0001366716,0.00004051674,0.0001569815,0.0001379918,0.03699968,0.001149011,0.9529071,0.007808596,0.00005904941],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003741741,0.0006511424,0.9909189,0.001618608,0.00009125115,0.0001038731,0.000229441,0.0001943502,0.002450815],"genre_scores_gemma":[0.0880386,0.0008861738,0.9074914,0.000851861,0.0003902321,0.0007049525,0.0006577589,0.0001321829,0.0008468429],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02813102,"threshold_uncertainty_score":0.1487728,"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","authors":[{"name":"Mohamed Bouguessa","is_ca":true},{"name":"Shengrui Wang","is_ca":true},{"name":"Haojun Sun","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02032488,0.001852251,0.002238298,0.004240494,0.00226538,0.005087934,0.004059223,0.002913462,0.002601517],"category_scores_gemma":[0.03390421,0.001191085,0.001999421,0.002349674,0.002441775,0.003051358,0.00461418,0.003120034,0.0007548357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001861981,"about_ca_system_score_gemma":0.003900993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003223551,"about_ca_topic_score_gemma":0.004326259,"domain_scores_codex":[0.9848262,0.008336063,0.0008555701,0.001533478,0.003811049,0.0006375671],"domain_scores_gemma":[0.9777974,0.01088308,0.001160113,0.002514569,0.007188568,0.0004562779],"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":[0.0004585573,0.0004095005,0.007378248,0.0006439066,0.0008962281,0.0001389379,0.0007204088,0.3765125,0.007123979,0.1833513,0.008523396,0.413843],"study_design_scores_gemma":[0.00003725158,0.0001301676,0.001054266,0.00007089828,0.00006329097,0.00007011942,0.0001431278,0.9453444,0.004084229,0.04628874,0.002673652,0.00003984899],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002047797,0.00005056924,0.9970946,0.0000903353,0.00001817202,0.00005725875,0.000042158,0.0001292091,0.0004698944],"genre_scores_gemma":[0.1157748,0.0001444678,0.8789771,0.0002679957,0.00009279756,0.0006121332,0.0006621641,0.0003894935,0.003079112],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02032488,"threshold_uncertainty_score":0.1074895,"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","authors":[{"name":"Weiliang Qiu","is_ca":false},{"name":"Harry Joe","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003183891,0.0006837457,0.0009940829,0.001431462,0.001038028,0.001154957,0.00216747,0.00158606,0.004110915],"category_scores_gemma":[0.01729624,0.0007514936,0.0009582366,0.001111555,0.0009323521,0.001260992,0.001976277,0.001174063,0.001058527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001193983,"about_ca_system_score_gemma":0.001007016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00099074,"about_ca_topic_score_gemma":0.001303082,"domain_scores_codex":[0.9983619,0.0005692735,0.00008852066,0.0003755484,0.000387411,0.0002173352],"domain_scores_gemma":[0.9900542,0.004264994,0.0003669363,0.002380955,0.002556013,0.0003768146],"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":[0.003326708,0.0007874038,0.007430605,0.0004927553,0.0002525996,0.0006750757,0.001339301,0.6671242,0.05402616,0.06855782,0.01284317,0.1831443],"study_design_scores_gemma":[0.0003044734,0.0001599705,0.0006485223,0.00002081339,0.00004629567,0.0001428325,0.0001219566,0.9611378,0.01980486,0.01570577,0.001861402,0.00004533317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2549108,0.0001671757,0.7369395,0.0004868512,0.0002448337,0.0009672235,0.0003602703,0.001461728,0.004461527],"genre_scores_gemma":[0.7322626,0.00007461704,0.2621889,0.0001849774,0.00003261123,0.0008232982,0.0007136718,0.0003253823,0.003393946],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004110915,"threshold_uncertainty_score":0.01683819,"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","authors":[{"name":"Shehroz S. Khan","is_ca":true},{"name":"Amir Ahmad","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001262775,0.001035586,0.001137247,0.001645635,0.001858366,0.001449107,0.002592851,0.001476532,0.006314137],"category_scores_gemma":[0.00413323,0.000676921,0.001027221,0.002037435,0.0006528165,0.001280901,0.001608813,0.002192117,0.004742485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001132249,"about_ca_system_score_gemma":0.002779763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01117003,"about_ca_topic_score_gemma":0.01301561,"domain_scores_codex":[0.9988613,0.0002556399,0.00006858325,0.0002930375,0.0003914158,0.0001300878],"domain_scores_gemma":[0.9986067,0.000259615,0.00006609828,0.0002390339,0.0007589253,0.0000696179],"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":[0.0008200851,0.000148942,0.001514862,0.0002758791,0.0001855982,0.0001137025,0.0004173579,0.1712034,0.01851998,0.02760586,0.03079143,0.7484029],"study_design_scores_gemma":[0.00006263667,0.00005237019,0.0008768007,0.00003691161,0.00004077988,0.0001317103,0.00009240861,0.9612038,0.01309927,0.01381938,0.0105216,0.0000623698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002550045,0.0001486374,0.9949216,0.00005938262,0.00008269643,0.00006701612,0.0001076167,0.000990444,0.001072557],"genre_scores_gemma":[0.07133662,0.0001695929,0.9226873,0.00007712089,0.00005278,0.000245731,0.0007641893,0.0004059235,0.004260613],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01117003,"threshold_uncertainty_score":0.02221,"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","authors":[{"name":"Richard S. Zemel","is_ca":true},{"name":"Miguel Á. Carreira-Perpiñán","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001739079,0.001482463,0.001724175,0.004793873,0.001432387,0.00254424,0.002152406,0.002227537,0.006908115],"category_scores_gemma":[0.01028299,0.0006651608,0.00151673,0.006542258,0.002750549,0.004406353,0.003418194,0.003401941,0.003370516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001790984,"about_ca_system_score_gemma":0.0008452652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003361639,"about_ca_topic_score_gemma":0.002466742,"domain_scores_codex":[0.997566,0.001100298,0.0001153402,0.000594673,0.0005298595,0.00009381171],"domain_scores_gemma":[0.9962965,0.001942961,0.0003947627,0.0007670574,0.0004853928,0.0001133578],"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":[0.00003696386,0.0000270325,0.0003855949,0.0003673674,0.00008100349,0.0001231954,0.0002504989,0.05199132,0.0007312233,0.8337422,0.01369481,0.09856872],"study_design_scores_gemma":[0.000008880733,0.00001506217,0.000225693,0.00005404506,0.00001509022,0.0001292093,0.00006400668,0.08582034,0.000333235,0.879816,0.03349651,0.00002199772],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002691486,0.005706999,0.9813973,0.001258717,0.0002403929,0.00009105352,0.0006579313,0.0008136816,0.007142448],"genre_scores_gemma":[0.165273,0.01162367,0.8044259,0.001083295,0.001437319,0.0009134352,0.003709492,0.000789062,0.01074476],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006908115,"threshold_uncertainty_score":0.02310997,"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","authors":[{"name":"Ziv Bar‐Joseph","is_ca":false},{"name":"Erik D. Demaine","is_ca":false},{"name":"David K. Gifford","is_ca":false},{"name":"Nathan Srebro","is_ca":false},{"name":"Angèle M. Hamel","is_ca":true},{"name":"Tommi Jaakkola","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002115394,0.001072253,0.001203182,0.002406828,0.001857343,0.001616001,0.002739578,0.001859837,0.004141501],"category_scores_gemma":[0.01025134,0.0008082603,0.001219742,0.004193914,0.00123501,0.00193353,0.002185735,0.001972206,0.00544974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001550411,"about_ca_system_score_gemma":0.002454538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006121623,"about_ca_topic_score_gemma":0.008840216,"domain_scores_codex":[0.9979377,0.0004461702,0.0001885449,0.0005006033,0.0007726861,0.0001542805],"domain_scores_gemma":[0.9969487,0.0009310616,0.0003253991,0.0009291266,0.0006864117,0.0001793366],"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":[0.0006282751,0.000357411,0.004625145,0.0006794899,0.0001286519,0.0002718981,0.0008622683,0.1810596,0.04641232,0.02183096,0.03661605,0.7065279],"study_design_scores_gemma":[0.00008747509,0.00008242814,0.001317839,0.00003989337,0.00002166478,0.000216292,0.00008967266,0.9379001,0.0194751,0.03069058,0.01002718,0.00005176188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006297597,0.0001145863,0.9838688,0.0001713091,0.00003039016,0.000114093,0.0004208825,0.008386512,0.0005958102],"genre_scores_gemma":[0.02429341,0.00006083597,0.9731079,0.00005941912,0.0000144548,0.0001536757,0.001178359,0.0005686024,0.0005633194],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006121623,"threshold_uncertainty_score":0.01385474,"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","authors":[{"name":"Ricardo J. G. B. Campello","is_ca":false},{"name":"Peer Kröger","is_ca":false},{"name":"Jörg Sander","is_ca":true},{"name":"Arthur Zimek","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003838481,0.00129238,0.00220873,0.007239121,0.00193558,0.005234365,0.00326446,0.002048587,0.005479062],"category_scores_gemma":[0.01620496,0.0009715724,0.001876872,0.008456771,0.002068645,0.004136845,0.003505504,0.002225565,0.004590356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003100173,"about_ca_system_score_gemma":0.002988806,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008484232,"about_ca_topic_score_gemma":0.006032702,"domain_scores_codex":[0.9949263,0.001283402,0.0003007831,0.001261996,0.00197574,0.0002517191],"domain_scores_gemma":[0.9935732,0.002282191,0.0005390351,0.001218934,0.002226437,0.0001600937],"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":[0.0001408121,0.00009933129,0.007816515,0.001292713,0.0005144815,0.0002478856,0.001063313,0.1986971,0.004724952,0.3514377,0.05352438,0.380441],"study_design_scores_gemma":[0.00002663183,0.00004443609,0.004098123,0.0003759955,0.0001059325,0.0004559251,0.0004699687,0.5812464,0.004608578,0.314015,0.09439316,0.0001597448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.004099802,0.002668845,0.982375,0.0007011472,0.0001699624,0.0001955536,0.001005308,0.0009771847,0.007807297],"genre_scores_gemma":[0.2004357,0.007931127,0.7709983,0.0007484067,0.0005505387,0.0006167406,0.006550762,0.0009230143,0.01124531],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.008484232,"threshold_uncertainty_score":0.02249342,"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","authors":[{"name":"Weinan Wang","is_ca":true},{"name":"Osmar R. Zai͏̈ane","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001672749,0.001078672,0.001358076,0.007600408,0.001223942,0.001683478,0.001366801,0.001419997,0.001599083],"category_scores_gemma":[0.008339362,0.0005270716,0.001310138,0.008935637,0.0005480593,0.002312163,0.001253053,0.001068057,0.002125849],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007149776,"about_ca_system_score_gemma":0.001937704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003778943,"about_ca_topic_score_gemma":0.004673411,"domain_scores_codex":[0.9967626,0.000978131,0.0002885479,0.0008471042,0.0008628016,0.0002607992],"domain_scores_gemma":[0.9953029,0.001496531,0.0007011553,0.0007544787,0.001468053,0.0002769858],"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":[0.001257317,0.0009573512,0.02999244,0.0008217816,0.0004394475,0.0004095223,0.00154077,0.06173344,0.04213545,0.01394479,0.01149562,0.835272],"study_design_scores_gemma":[0.0001077555,0.0005845633,0.02501392,0.0001333897,0.0002602407,0.001225043,0.001255829,0.8282697,0.03359766,0.06915231,0.04018997,0.0002096948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08892272,0.0007211943,0.9019054,0.0002129059,0.0001202576,0.0006695137,0.001712858,0.003575767,0.002159411],"genre_scores_gemma":[0.220144,0.0007073527,0.7663388,0.0001070359,0.000118651,0.0006952269,0.007876202,0.0005681537,0.003444471],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007600408,"threshold_uncertainty_score":0.008846402,"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","authors":[{"name":"Marzieh Zarinbal","is_ca":false},{"name":"M.H. Fazel Zarandi","is_ca":false},{"name":"İ.B. Türkşen","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002814036,0.0006994788,0.001290921,0.00383024,0.001882582,0.002466691,0.001514512,0.001329943,0.003072008],"category_scores_gemma":[0.009360615,0.0003807458,0.001140955,0.003037703,0.001028592,0.001863631,0.001149554,0.0009153704,0.0008260474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001664267,"about_ca_system_score_gemma":0.001694352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004722872,"about_ca_topic_score_gemma":0.003823781,"domain_scores_codex":[0.9966486,0.0007106448,0.000245924,0.0005395438,0.001707837,0.0001473386],"domain_scores_gemma":[0.9972562,0.000877328,0.0001792445,0.0004112612,0.001221461,0.00005445414],"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":[0.0005813787,0.0001313387,0.002551575,0.0005589018,0.0002673267,0.0001526077,0.0003792745,0.3873131,0.01447393,0.1259692,0.007329117,0.4602922],"study_design_scores_gemma":[0.0000176077,0.00005858805,0.001759251,0.00003441488,0.0000613569,0.0001477805,0.00006914468,0.9534481,0.008317977,0.03180262,0.004224219,0.00005895337],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02317604,0.0006823519,0.9707427,0.0001846228,0.0001021937,0.00009029652,0.000221954,0.0003715697,0.004428224],"genre_scores_gemma":[0.4191081,0.0005321566,0.5741214,0.0001030233,0.0001508407,0.0001845197,0.0008396092,0.0001699667,0.004790389],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004722872,"threshold_uncertainty_score":0.01488227,"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","authors":[{"name":"Gabriela Moise","is_ca":true},{"name":"Jörg Sander","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004778348,0.001431431,0.002888379,0.006813501,0.00144491,0.002659874,0.002212033,0.00223667,0.0007417048],"category_scores_gemma":[0.01412346,0.0009785583,0.001629969,0.006830544,0.002443931,0.002358523,0.002162053,0.001312854,0.000916635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006174619,"about_ca_system_score_gemma":0.002478775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001836301,"about_ca_topic_score_gemma":0.002234164,"domain_scores_codex":[0.995773,0.000988354,0.0003646212,0.0009911594,0.001570388,0.0003124692],"domain_scores_gemma":[0.9897725,0.00529696,0.002031566,0.001378428,0.001288413,0.0002320755],"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":[0.001269622,0.0007136622,0.05130379,0.002320428,0.001098372,0.003236082,0.002850415,0.1468328,0.09589059,0.02324325,0.01020964,0.6610314],"study_design_scores_gemma":[0.0001276654,0.000659034,0.04528477,0.0003032188,0.0007328783,0.003986267,0.003171764,0.7972945,0.05557269,0.08063266,0.01195546,0.0002791392],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1353906,0.003208513,0.8577666,0.0006410141,0.00009281497,0.0001667993,0.0005835518,0.001438478,0.0007115689],"genre_scores_gemma":[0.4636392,0.001560361,0.5313199,0.0001852293,0.0002306065,0.0002429874,0.001798503,0.0002205968,0.0008025866],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006813501,"threshold_uncertainty_score":0.02527058,"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)","authors":[{"name":"Levi H. S. Lelis","is_ca":true},{"name":"Jörg Sander","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003218754,0.001153958,0.001733784,0.003777371,0.001316392,0.002040047,0.003162093,0.00153009,0.003035133],"category_scores_gemma":[0.01267168,0.0007026571,0.001324631,0.002335255,0.001388357,0.002159248,0.002112059,0.001093264,0.002587748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001154399,"about_ca_system_score_gemma":0.001866604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004789297,"about_ca_topic_score_gemma":0.006232175,"domain_scores_codex":[0.9959282,0.001230485,0.000237686,0.0009117886,0.001509989,0.0001818497],"domain_scores_gemma":[0.99172,0.002759011,0.0006683707,0.001437004,0.00325702,0.0001585946],"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":[0.0004288065,0.0002715062,0.007311764,0.0007989884,0.0003162665,0.0002418182,0.001115664,0.3379282,0.01527271,0.0271291,0.01172442,0.5974607],"study_design_scores_gemma":[0.00001443563,0.00002754936,0.001071216,0.00003769795,0.00001671729,0.0001782687,0.0001219021,0.978977,0.004680795,0.01208008,0.002762967,0.00003136188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01033242,0.0001560897,0.9858776,0.00006387182,0.00001872162,0.0001444422,0.0001614142,0.001251539,0.001993891],"genre_scores_gemma":[0.3055422,0.00027365,0.688697,0.0001070478,0.00006422061,0.0003966527,0.001585128,0.0003533977,0.002980835],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004789297,"threshold_uncertainty_score":0.01702261,"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","authors":[{"name":"Guojun Gan","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005407882,0.001105404,0.00142213,0.0023312,0.001498289,0.002218453,0.002264584,0.002033511,0.006014173],"category_scores_gemma":[0.02015055,0.0004568423,0.001131368,0.002184802,0.002509939,0.002690815,0.002907023,0.003245411,0.002524649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001375741,"about_ca_system_score_gemma":0.002180382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005302574,"about_ca_topic_score_gemma":0.00313066,"domain_scores_codex":[0.9975094,0.0006884316,0.0001038601,0.0003374474,0.001208539,0.0001524255],"domain_scores_gemma":[0.9928807,0.003204921,0.0001782057,0.0004965369,0.003026871,0.0002127177],"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":[0.0001729563,0.00006516273,0.0008265642,0.0003086181,0.0001001061,0.00009283271,0.0003505111,0.1821584,0.006747125,0.575193,0.01398475,0.22],"study_design_scores_gemma":[0.00002279233,0.00006042833,0.0003197922,0.00005051008,0.00001912249,0.0001802784,0.00005704252,0.8382527,0.002547755,0.149192,0.009259198,0.00003843455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002317301,0.0002927364,0.9932142,0.0002627338,0.0001127977,0.00004582816,0.00007166185,0.0001248293,0.003557849],"genre_scores_gemma":[0.1386958,0.001306635,0.8432359,0.0005422693,0.0004774946,0.000546206,0.0005608484,0.0004845273,0.01415032],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006014173,"threshold_uncertainty_score":0.02859998,"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","authors":[{"name":"Daniel Aloise","is_ca":false},{"name":"Pierre Hansen","is_ca":true},{"name":"Leo Liberti","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001159601,0.0013974,0.00162508,0.001464652,0.001007512,0.001197399,0.002356344,0.001482266,0.006680382],"category_scores_gemma":[0.004282257,0.0007582605,0.001121118,0.002248078,0.0005750618,0.001305334,0.00165254,0.001946191,0.003642429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005814551,"about_ca_system_score_gemma":0.00183452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004198098,"about_ca_topic_score_gemma":0.006472728,"domain_scores_codex":[0.998771,0.0003660323,0.00006949514,0.0002040674,0.0004929037,0.00009645069],"domain_scores_gemma":[0.9978067,0.000796723,0.00008672343,0.0003054456,0.0009109185,0.00009346567],"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":[0.0004176755,0.0002183435,0.0005699699,0.0002733566,0.0001323848,0.000136743,0.0001518879,0.2388581,0.01886011,0.01491297,0.021307,0.7041615],"study_design_scores_gemma":[0.00005099477,0.00005515674,0.0001721725,0.000008438884,0.00002013929,0.00008388034,0.00001731992,0.9870062,0.004079745,0.005413801,0.00306755,0.00002456686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002446406,0.0001028646,0.9956158,0.00008537916,0.00008953609,0.00005068462,0.00007600191,0.0009261004,0.0006072658],"genre_scores_gemma":[0.02419648,0.00007065656,0.9729873,0.0001225087,0.00006430586,0.0001556695,0.0004321508,0.0002736644,0.001697276],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006680382,"threshold_uncertainty_score":0.02234805,"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","authors":[{"name":"Guojun Gan","is_ca":true},{"name":"Junzheng Wu","is_ca":true},{"name":"Zhijing Yang","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001223863,0.0004290872,0.0006065027,0.001519586,0.001139924,0.00144051,0.002129828,0.001320394,0.006803934],"category_scores_gemma":[0.004124444,0.00035092,0.0010874,0.001649818,0.0007008978,0.0007040647,0.0008425842,0.001157946,0.002395255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001912308,"about_ca_system_score_gemma":0.002484758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02485346,"about_ca_topic_score_gemma":0.02555266,"domain_scores_codex":[0.9990734,0.0001482301,0.00004404081,0.0002589134,0.0004216585,0.0000537694],"domain_scores_gemma":[0.9991124,0.0002662407,0.00004191049,0.0001384516,0.0003944465,0.00004645674],"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":[0.000205394,0.0001891132,0.002304127,0.0001863163,0.0001334223,0.0001714688,0.0003514629,0.216504,0.0158596,0.08961814,0.01764373,0.6568332],"study_design_scores_gemma":[0.00004292267,0.00007471246,0.0006493525,0.00004807624,0.0000525729,0.0001478668,0.0000673916,0.9505681,0.007548164,0.02914919,0.01161047,0.00004110689],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008415041,0.00007960118,0.9840109,0.0002324942,0.00007005004,0.00009829771,0.0003482506,0.0008099753,0.005935405],"genre_scores_gemma":[0.0777313,0.000104123,0.9109325,0.0001855394,0.00004074275,0.0001903005,0.0007285099,0.0001582689,0.009928742],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02485346,"threshold_uncertainty_score":0.04941761,"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","authors":[{"name":"Vladimir Makarenkov","is_ca":true},{"name":"Pierre Legendre","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008898418,0.001273041,0.002567802,0.002367392,0.001412633,0.002838928,0.003776597,0.002133588,0.003188486],"category_scores_gemma":[0.02399229,0.001667014,0.002083973,0.003573044,0.001523377,0.00471918,0.003360583,0.003349282,0.001196817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00172326,"about_ca_system_score_gemma":0.002596236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00549187,"about_ca_topic_score_gemma":0.007748777,"domain_scores_codex":[0.9947295,0.002558931,0.0003978141,0.0008245994,0.001262679,0.000226507],"domain_scores_gemma":[0.9892697,0.006981115,0.0004912786,0.001297311,0.001704729,0.0002559207],"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":[0.0002089806,0.0001350421,0.0008346335,0.0002713739,0.0001294154,0.00002811904,0.0003352667,0.2004033,0.002558238,0.0916884,0.003254909,0.7001524],"study_design_scores_gemma":[0.00002730405,0.0000349376,0.0002297849,0.00002303432,0.00003860382,0.00003680491,0.00003747292,0.9256083,0.001525011,0.07050094,0.001911402,0.00002642744],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002044137,0.000146213,0.9974004,0.00003842065,0.00002250704,0.00001649559,0.00001324044,0.0001973489,0.0001212863],"genre_scores_gemma":[0.02586521,0.0001517262,0.9728602,0.00002412751,0.00004354012,0.0001108666,0.00008319924,0.0001966107,0.0006644399],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008898418,"threshold_uncertainty_score":0.04705989,"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","authors":[{"name":"Jörg Sander","is_ca":true},{"name":"Xuejie Qin","is_ca":true},{"name":"Zhiyong Lu","is_ca":true},{"name":"Nan Niu","is_ca":true},{"name":"Alex Kovarsky","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00109371,0.001776646,0.001974748,0.006144172,0.00153611,0.003588075,0.002714472,0.001498051,0.005610983],"category_scores_gemma":[0.006291488,0.001197649,0.001945893,0.006445002,0.0007731344,0.00216581,0.002530694,0.002104534,0.007067174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001010971,"about_ca_system_score_gemma":0.002049777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005519561,"about_ca_topic_score_gemma":0.009911517,"domain_scores_codex":[0.9985739,0.0002100516,0.00009631181,0.000392345,0.0005233362,0.0002041047],"domain_scores_gemma":[0.997476,0.000709982,0.0001892826,0.0004916275,0.001027602,0.0001054025],"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":[0.0004636483,0.0001628868,0.002185713,0.0006868641,0.000186856,0.0003447466,0.0007283212,0.01707251,0.03608197,0.01569556,0.04748762,0.8789033],"study_design_scores_gemma":[0.0001806206,0.0001908707,0.006979705,0.0002989761,0.0004986206,0.001140241,0.001277015,0.7715062,0.04717517,0.108243,0.06231719,0.0001924283],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01741643,0.0006932954,0.9639372,0.0002440693,0.0001605114,0.0003642707,0.002255136,0.01072631,0.004202748],"genre_scores_gemma":[0.07926261,0.0004991587,0.9065908,0.00008752153,0.00008003434,0.0002818222,0.008277352,0.001381641,0.003539172],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006144172,"threshold_uncertainty_score":0.01877058,"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","authors":[{"name":"Hanan Ayad","is_ca":true},{"name":"Mohamed S. Kamel","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001221259,0.001046225,0.002534721,0.003744995,0.002130649,0.002081462,0.003191246,0.001683287,0.004064528],"category_scores_gemma":[0.002756516,0.0007760948,0.001718405,0.004458682,0.0009724633,0.003303631,0.003262778,0.0008765737,0.001535721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008891238,"about_ca_system_score_gemma":0.0008293514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003024099,"about_ca_topic_score_gemma":0.007287414,"domain_scores_codex":[0.9983191,0.0001734653,0.00008595851,0.0005132315,0.00072398,0.0001843311],"domain_scores_gemma":[0.9980077,0.0004705544,0.00016575,0.0004443144,0.0007704149,0.0001412741],"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":[0.001250268,0.0004588368,0.007624807,0.0003632749,0.0004569203,0.0005066408,0.00096353,0.04578444,0.09395356,0.01071392,0.005193194,0.8327307],"study_design_scores_gemma":[0.0001140703,0.0003269617,0.004646148,0.00002259675,0.0002601449,0.0005894152,0.0007507246,0.9307965,0.04205712,0.01626648,0.004057369,0.0001124317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05451648,0.0002288268,0.9406791,0.00007684666,0.00005338391,0.0001603012,0.0001483816,0.001916179,0.002220484],"genre_scores_gemma":[0.1887957,0.00009087661,0.8065794,0.00005543671,0.00003992758,0.0001684246,0.0005078985,0.0002989019,0.003463416],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004064528,"threshold_uncertainty_score":0.01359719,"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","authors":[{"name":"Johannes Blömer","is_ca":false},{"name":"Christiane Lammersen","is_ca":true},{"name":"Melanie Schmidt","is_ca":false},{"name":"Christian Sohler","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003223583,0.001791805,0.002645235,0.003869693,0.001672133,0.005658661,0.00467318,0.003010663,0.007463112],"category_scores_gemma":[0.01241545,0.001530437,0.001854287,0.01002584,0.003334873,0.00754407,0.002990144,0.005484617,0.004534878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003634467,"about_ca_system_score_gemma":0.003259694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00324567,"about_ca_topic_score_gemma":0.002310704,"domain_scores_codex":[0.9966772,0.0008558225,0.0002123944,0.000634407,0.001441541,0.0001786106],"domain_scores_gemma":[0.9941472,0.004110338,0.0001961345,0.0005489387,0.0008835017,0.0001138806],"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":[0.00006667871,0.0001413233,0.0007995942,0.00248561,0.000118087,0.00007988294,0.0002229414,0.04233618,0.0007343618,0.6250097,0.02587339,0.3021324],"study_design_scores_gemma":[0.00001715081,0.00005349837,0.0005122126,0.0005109495,0.00005350613,0.0003290774,0.0001040065,0.1274345,0.0007870167,0.7822189,0.08792611,0.00005299212],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.003564567,0.1635648,0.7916152,0.004567097,0.001208053,0.00006718446,0.0004296143,0.000339356,0.0346441],"genre_scores_gemma":[0.1065228,0.3079455,0.5542457,0.003666569,0.0102948,0.0004136501,0.001720964,0.0008169499,0.01437299],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.007463112,"threshold_uncertainty_score":0.02637005,"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","authors":[{"name":"Osmar R. Zai͏̈ane","is_ca":true},{"name":"Andrew Foss","is_ca":true},{"name":"Chi-Hoon Lee","is_ca":true},{"name":"Weinan Wang","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09286975,0.003180394,0.00496768,0.005025295,0.00366681,0.007899754,0.008711525,0.005999687,0.003603831],"category_scores_gemma":[0.3498641,0.002624653,0.003295851,0.009786966,0.00758834,0.02164654,0.01261559,0.007990186,0.001515226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004350682,"about_ca_system_score_gemma":0.008509657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01005519,"about_ca_topic_score_gemma":0.009102168,"domain_scores_codex":[0.9064413,0.05417688,0.006022006,0.006326301,0.02502504,0.00200856],"domain_scores_gemma":[0.5357109,0.3510808,0.008944332,0.06862209,0.03327026,0.00237163],"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":[0.001767132,0.0006070916,0.01816363,0.001301904,0.0007371357,0.00031021,0.0009414972,0.2598436,0.005876109,0.1025189,0.01982845,0.5881044],"study_design_scores_gemma":[0.0001069672,0.00009245071,0.001267191,0.0001977312,0.00009199145,0.000226076,0.0001577269,0.8876345,0.003979114,0.1044671,0.00172984,0.00004937829],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01546109,0.002090272,0.9720865,0.002543507,0.0001700555,0.000554643,0.0003631346,0.00284984,0.003880897],"genre_scores_gemma":[0.1610958,0.001342199,0.8317899,0.0008916941,0.000411779,0.0007241092,0.001038828,0.001037214,0.001668363],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.09286975,"threshold_uncertainty_score":0.4911481,"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","authors":[{"name":"Jie Zhou","is_ca":false},{"name":"Witold Pedrycz","is_ca":true},{"name":"Xiaodong Yue","is_ca":false},{"name":"Can Gao","is_ca":false},{"name":"Zhihui Lai","is_ca":false},{"name":"Jun Wan","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001468846,0.0007130155,0.001289094,0.001744729,0.001840966,0.001701442,0.001962731,0.001274185,0.002483817],"category_scores_gemma":[0.004638128,0.0006481008,0.001534543,0.00267725,0.001051925,0.00159703,0.002154785,0.001069723,0.001265086],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001039956,"about_ca_system_score_gemma":0.002841204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01400609,"about_ca_topic_score_gemma":0.012242,"domain_scores_codex":[0.9980478,0.0003915573,0.0001126559,0.0004342086,0.0008618634,0.0001518825],"domain_scores_gemma":[0.9978647,0.0003031564,0.0001153915,0.0005530377,0.001093808,0.00006993508],"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":[0.0006908567,0.000185759,0.002036143,0.0002908717,0.0002559791,0.0001233729,0.0003593336,0.2450081,0.03039898,0.01865161,0.005811721,0.6961873],"study_design_scores_gemma":[0.00002210569,0.00007656703,0.0007597833,0.00001168748,0.00003618572,0.0001329319,0.00006193377,0.9755491,0.01303374,0.008571078,0.001709431,0.00003546396],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0142943,0.0001297808,0.9836881,0.00007366709,0.00003294603,0.00005862268,0.0001036946,0.000702869,0.0009160375],"genre_scores_gemma":[0.2188656,0.0001340659,0.7776355,0.00007197234,0.00005232131,0.0001752906,0.0005319187,0.0002133219,0.002320049],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01400609,"threshold_uncertainty_score":0.02784908,"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","authors":[{"name":"Ricardo J. G. B. Campello","is_ca":true},{"name":"Davoud Moulavi","is_ca":true},{"name":"Arthur Zimek","is_ca":true},{"name":"Jörg Sander","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004712904,0.00117388,0.002136,0.003472786,0.001937464,0.003710632,0.004754857,0.001975002,0.002734884],"category_scores_gemma":[0.01164817,0.001068743,0.002507082,0.004050041,0.002121405,0.003801972,0.004615476,0.002957153,0.001830198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001660069,"about_ca_system_score_gemma":0.003871193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008027991,"about_ca_topic_score_gemma":0.01518997,"domain_scores_codex":[0.9961482,0.001162313,0.0003094972,0.0008732014,0.001257979,0.0002488778],"domain_scores_gemma":[0.9951792,0.001775514,0.0003824513,0.001027828,0.001393923,0.0002410205],"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":[0.0002108904,0.0002091988,0.001290277,0.0005154728,0.0002858337,0.0002536786,0.0008870711,0.1577751,0.01065595,0.2780117,0.01594564,0.5339591],"study_design_scores_gemma":[0.00003342421,0.00004685997,0.0003688262,0.00006355796,0.00005094475,0.0001592612,0.0001190532,0.7681822,0.002756648,0.2180263,0.01014296,0.00005003229],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003578806,0.00006508255,0.999009,0.00004375724,0.000009231741,0.00002323801,0.0000526012,0.0002874676,0.0001516203],"genre_scores_gemma":[0.01760601,0.0001191692,0.9808699,0.00005842078,0.00004026802,0.0001329232,0.0003835343,0.0001414221,0.0006483616],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008027991,"threshold_uncertainty_score":0.02492452,"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","authors":[{"name":"Markus Breunig","is_ca":false},{"name":"Hans‐Peter Kriegel","is_ca":false},{"name":"Peer Kröger","is_ca":false},{"name":"Jörg Sander","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004271393,0.000717883,0.001015422,0.002230354,0.001585356,0.003580371,0.002917317,0.001906889,0.02160664],"category_scores_gemma":[0.02874354,0.0005578107,0.001041123,0.002926084,0.001866302,0.01051364,0.006357067,0.002424677,0.007120849],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001190537,"about_ca_system_score_gemma":0.001185502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001490794,"about_ca_topic_score_gemma":0.001056572,"domain_scores_codex":[0.9951416,0.001068352,0.0003799366,0.001106916,0.00206573,0.0002374713],"domain_scores_gemma":[0.9858145,0.006481198,0.0006928246,0.004297899,0.002199639,0.000514006],"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":[0.0005966222,0.00013087,0.003386099,0.0009590957,0.00009543943,0.0007352084,0.001355408,0.01140886,0.006778263,0.5116902,0.06766343,0.3952005],"study_design_scores_gemma":[0.00008394467,0.0002045245,0.001039186,0.0002506467,0.00005381997,0.001624107,0.0008639693,0.05318266,0.01080382,0.3285155,0.6032785,0.00009935022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01599324,0.004075348,0.9381399,0.006197358,0.001712561,0.0006598126,0.0034109,0.0034226,0.02638833],"genre_scores_gemma":[0.1833804,0.003671493,0.767874,0.004676725,0.0009755068,0.001301112,0.008454241,0.001591,0.02807548],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02160664,"threshold_uncertainty_score":0.07228148,"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","authors":[{"name":"Tengke Xiong","is_ca":true},{"name":"Shengrui Wang","is_ca":true},{"name":"André Mayers","is_ca":true},{"name":"Ernest Monga","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003186143,0.001350303,0.001641656,0.005162863,0.001626792,0.002618825,0.003455608,0.001392419,0.006119874],"category_scores_gemma":[0.01450486,0.0008620228,0.00202511,0.007430254,0.0006719409,0.001627894,0.00278945,0.002248004,0.004251963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001201059,"about_ca_system_score_gemma":0.003998428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01226791,"about_ca_topic_score_gemma":0.01728992,"domain_scores_codex":[0.9966754,0.001123483,0.000236967,0.0005648898,0.001192503,0.0002068261],"domain_scores_gemma":[0.9951391,0.001474113,0.0002268712,0.00158372,0.001367019,0.0002092161],"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":[0.000424089,0.0002477535,0.003628014,0.0007672905,0.0004126163,0.0001602235,0.000566676,0.04784878,0.005984741,0.02416062,0.06596284,0.8498363],"study_design_scores_gemma":[0.0001696962,0.0001659042,0.003628456,0.000129551,0.0001926012,0.0003882017,0.0002982659,0.839159,0.0140065,0.07377815,0.06792869,0.0001550078],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003337046,0.0003346055,0.9810245,0.0001645491,0.0001614567,0.0004255908,0.002433635,0.01115917,0.0009594607],"genre_scores_gemma":[0.02977494,0.000206044,0.961478,0.0001240128,0.00007489182,0.0005166616,0.00520127,0.0008726419,0.001751508],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01226791,"threshold_uncertainty_score":0.02439302,"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","authors":[{"name":"Abdelhamid Bouchachia","is_ca":false},{"name":"Witold Pedrycz","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004555407,0.0008085172,0.002184588,0.001374606,0.001302216,0.002090327,0.002616422,0.001203297,0.002848036],"category_scores_gemma":[0.0220838,0.001122146,0.001975679,0.002114159,0.001751276,0.004056206,0.003653304,0.001552107,0.001392676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008077853,"about_ca_system_score_gemma":0.00264174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00240993,"about_ca_topic_score_gemma":0.003934134,"domain_scores_codex":[0.9943514,0.002137703,0.0004170933,0.001361777,0.00155833,0.0001736776],"domain_scores_gemma":[0.9855563,0.00413865,0.0007965696,0.007122415,0.002040097,0.0003459355],"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":[0.0009985493,0.0002153772,0.008193932,0.0007827635,0.0006102683,0.0003059329,0.0005634647,0.2593059,0.007974184,0.06632493,0.01252527,0.6421995],"study_design_scores_gemma":[0.00003029683,0.00007733476,0.0007943041,0.00002196082,0.00005532573,0.0001578326,0.00003933338,0.9392262,0.003600049,0.05306476,0.002914346,0.0000183528],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00929492,0.0002416268,0.9879447,0.0002582112,0.00003962943,0.00007452391,0.0002601745,0.001052391,0.0008337929],"genre_scores_gemma":[0.3790835,0.0003808873,0.6139207,0.0001876275,0.0002165162,0.0003732599,0.002162853,0.0002577119,0.003416892],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004555407,"threshold_uncertainty_score":0.02409154,"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","authors":[{"name":"Yangli-ao Geng","is_ca":false},{"name":"Qingyong Li","is_ca":false},{"name":"Rong Zheng","is_ca":true},{"name":"Fuzhen Zhuang","is_ca":false},{"name":"Ruisi He","is_ca":false},{"name":"Naixue Xiong","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002125233,0.001316472,0.002584667,0.003130736,0.001805811,0.002062543,0.00508545,0.002270476,0.00391226],"category_scores_gemma":[0.007451648,0.001144015,0.001632878,0.003159042,0.001011503,0.003522913,0.003751785,0.002453981,0.003497426],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00136386,"about_ca_system_score_gemma":0.002091153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00878654,"about_ca_topic_score_gemma":0.01080776,"domain_scores_codex":[0.9975365,0.0004896289,0.0001232486,0.0004897926,0.001218686,0.0001421348],"domain_scores_gemma":[0.9977344,0.0004996515,0.0001279131,0.0004885895,0.001041668,0.0001078239],"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":[0.0003551366,0.0002431226,0.001465305,0.0002781906,0.0002404281,0.0001086009,0.0002428218,0.1121417,0.01017277,0.0201129,0.01393112,0.8407078],"study_design_scores_gemma":[0.00003546243,0.00004371945,0.0005465161,0.00001748637,0.00002727034,0.0001781291,0.00005172677,0.9789385,0.00531612,0.006792321,0.007997538,0.00005526114],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002624894,0.0002332514,0.9949233,0.00007512803,0.00007461251,0.0000724016,0.00007931401,0.001407882,0.0005092454],"genre_scores_gemma":[0.04235242,0.0002206182,0.953111,0.0001248295,0.00005980209,0.0002035519,0.0005270432,0.0004007516,0.002999933],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00878654,"threshold_uncertainty_score":0.01747078,"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","authors":[{"name":"Guojun Gan","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003667024,0.0007325431,0.0013952,0.003133809,0.001615953,0.001524821,0.001362129,0.001086037,0.001365948],"category_scores_gemma":[0.01125367,0.0003534379,0.001386236,0.004813941,0.001364131,0.001934973,0.00186994,0.001586164,0.000713491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001175548,"about_ca_system_score_gemma":0.001714046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003713113,"about_ca_topic_score_gemma":0.004320384,"domain_scores_codex":[0.9958442,0.001840004,0.0002245165,0.0005922827,0.00133916,0.000159775],"domain_scores_gemma":[0.9945497,0.00251713,0.0004290871,0.0009376222,0.001399775,0.0001666127],"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":[0.0001577147,0.00009320082,0.003772436,0.0005072683,0.0001755037,0.0002328453,0.0008529113,0.3639867,0.009032694,0.1766486,0.007019468,0.4375206],"study_design_scores_gemma":[0.000009494041,0.00005123314,0.0009633853,0.00002273448,0.00001552045,0.0001524013,0.0001588011,0.8882079,0.003188365,0.101581,0.005601386,0.00004775618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002977177,0.0001891443,0.9962111,0.00008878906,0.00001316635,0.0000216117,0.00006211713,0.0001968504,0.0002400615],"genre_scores_gemma":[0.08437975,0.00045641,0.9132391,0.00006756825,0.00006028299,0.0001528903,0.0006502906,0.0001009036,0.0008928911],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003713113,"threshold_uncertainty_score":0.01939332,"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","authors":[{"name":"Yiming Tang","is_ca":true},{"name":"Zhifu Pan","is_ca":false},{"name":"Witold Pedrycz","is_ca":true},{"name":"Fuji Ren","is_ca":false},{"name":"Xiaocheng Song","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000880613,0.0008190622,0.001078946,0.001431293,0.0005362485,0.001415189,0.001275414,0.0008182704,0.0007562274],"category_scores_gemma":[0.003564575,0.0003646038,0.001238624,0.001504179,0.0007452093,0.002006944,0.001290533,0.0007566023,0.0002787811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001098319,"about_ca_system_score_gemma":0.0009318774,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005582873,"about_ca_topic_score_gemma":0.003117785,"domain_scores_codex":[0.9990783,0.0001515581,0.00006148429,0.0002577139,0.0003676947,0.00008333952],"domain_scores_gemma":[0.9991061,0.0002291012,0.0001040102,0.0001373346,0.0003809089,0.00004250458],"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":[0.0002953576,0.00007597348,0.002905173,0.0002636316,0.0001670919,0.0001847041,0.0005725664,0.5872093,0.01810704,0.05886737,0.002322981,0.3290289],"study_design_scores_gemma":[0.00001095815,0.00002914742,0.0005152081,0.000008778075,0.00001781833,0.00004651358,0.000035759,0.9869528,0.002364258,0.009279856,0.0007185021,0.00002052768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01970222,0.0001693813,0.9789505,0.00004861241,0.00001763796,0.00003276363,0.00003455127,0.0001618912,0.0008824912],"genre_scores_gemma":[0.5978384,0.0004597622,0.399384,0.00005568407,0.00005228889,0.0001485933,0.0003904661,0.00009684626,0.001573963],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005582873,"threshold_uncertainty_score":0.01110077,"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","authors":[{"name":"Hong Yu","is_ca":false},{"name":"Yun Chen","is_ca":false},{"name":"Pawan Lingras","is_ca":true},{"name":"Guoyin Wang","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003291747,0.001091379,0.002516867,0.00252998,0.002423282,0.00230096,0.003713401,0.001842272,0.002508954],"category_scores_gemma":[0.00769264,0.00063834,0.002654906,0.004153103,0.0005987986,0.002750737,0.003005779,0.002481263,0.001245956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008389937,"about_ca_system_score_gemma":0.00192213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01596693,"about_ca_topic_score_gemma":0.02824194,"domain_scores_codex":[0.9973776,0.0006553183,0.0001713706,0.0005195985,0.001026028,0.0002501106],"domain_scores_gemma":[0.9955456,0.001145765,0.0001782367,0.0009914915,0.00188148,0.0002572939],"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":[0.0004140161,0.0003300303,0.005409164,0.0001786993,0.0009726165,0.0001865724,0.000544352,0.3126215,0.005953684,0.01385435,0.01261641,0.6469186],"study_design_scores_gemma":[0.000008613836,0.00002763321,0.000459768,0.000009950687,0.00005722808,0.00003985612,0.00008548503,0.9895542,0.0008846401,0.007399626,0.001454883,0.00001814528],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005731296,0.0001997259,0.9925722,0.0001096006,0.00008060716,0.00005861086,0.0001385265,0.0006653697,0.000443955],"genre_scores_gemma":[0.1429332,0.0003114429,0.8519794,0.0001859902,0.0001902562,0.0002257771,0.001421441,0.0003039986,0.002448434],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01596693,"threshold_uncertainty_score":0.031748,"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","authors":[{"name":"O. Uncu","is_ca":true},{"name":"W.A. Gruver","is_ca":true},{"name":"Dilip Kotak","is_ca":true},{"name":"Dorian Sabaz","is_ca":false},{"name":"Z. Alibhai","is_ca":true},{"name":"Colin Ng","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001387837,0.001763612,0.001579889,0.002783326,0.001397837,0.002126826,0.003697721,0.001234042,0.003654566],"category_scores_gemma":[0.006118607,0.0009039565,0.001586525,0.003827059,0.0008563678,0.00169028,0.002594014,0.001351905,0.002345431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001728502,"about_ca_system_score_gemma":0.003369121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03165635,"about_ca_topic_score_gemma":0.0296796,"domain_scores_codex":[0.9980322,0.0003540194,0.0001381337,0.0003337018,0.0009813373,0.0001607359],"domain_scores_gemma":[0.9983765,0.0003530166,0.0001437739,0.0003291066,0.0007136996,0.00008391022],"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":[0.0005289267,0.0001813194,0.005912362,0.0006153556,0.0002871242,0.0003819999,0.0005874755,0.4421397,0.007836781,0.01989974,0.04841431,0.4732149],"study_design_scores_gemma":[0.00002868823,0.0000340484,0.0006908529,0.00001864059,0.00001905681,0.00007961607,0.00007339873,0.9733998,0.005395636,0.006360181,0.01386548,0.00003458947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008476779,0.0003026589,0.9651187,0.0002051876,0.00007515899,0.000255123,0.0008317244,0.02242809,0.002306537],"genre_scores_gemma":[0.1461775,0.0004887774,0.8422052,0.0002212234,0.00004749948,0.0006785296,0.004869296,0.001695817,0.003616077],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03165635,"threshold_uncertainty_score":0.06294417,"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","authors":[{"name":"Brendan J. Frey","is_ca":true},{"name":"Delbert Dueck","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007798056,0.001833999,0.001784018,0.001585438,0.003846627,0.003671047,0.004372071,0.04037102,0.02125883],"category_scores_gemma":[0.06216367,0.001128891,0.002123105,0.001731543,0.004018871,0.003845166,0.002874129,0.04474756,0.02488409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006216642,"about_ca_system_score_gemma":0.004589908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02146091,"about_ca_topic_score_gemma":0.01775002,"domain_scores_codex":[0.9939535,0.00136389,0.0008157606,0.0009819712,0.00233179,0.0005530901],"domain_scores_gemma":[0.9616578,0.01955434,0.002065921,0.001219823,0.01341915,0.002082986],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004011359,0.00001189085,0.0001290429,0.0000571995,0.00001459314,0.00007483864,0.000051911,0.00006188552,0.00009115791,0.0006976354,0.9965701,0.00219961],"study_design_scores_gemma":[0.0001636553,0.00006706645,0.002424501,0.0004161841,0.00005022394,0.0002977011,0.0003808906,0.0006263172,0.0006001433,0.003673518,0.991199,0.0001007357],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.0001699091,0.0007461957,0.0006025409,0.9255188,0.07112769,0.00003560802,0.0003063031,0.0001903507,0.001302688],"genre_scores_gemma":[0.00103106,0.0004670742,0.0003756727,0.9608483,0.03245177,0.00008184592,0.00007552277,0.00007000906,0.004598791],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.04037102,"threshold_uncertainty_score":0.07111788,"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","authors":[{"name":"Karl E. Dierckens","is_ca":true},{"name":"A.B. Harrison","is_ca":true},{"name":"Carson K. Leung","is_ca":true},{"name":"Adrienne V. Pind","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001213429,0.0009381813,0.001013327,0.001675505,0.001737968,0.001579116,0.002551228,0.002754147,0.004297047],"category_scores_gemma":[0.005562311,0.0006937099,0.001274626,0.002898339,0.0008775573,0.002361111,0.001881612,0.001808346,0.002892403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009470125,"about_ca_system_score_gemma":0.002505592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00395345,"about_ca_topic_score_gemma":0.005228013,"domain_scores_codex":[0.9984863,0.0002274639,0.00009318033,0.0003643201,0.0007191102,0.0001096744],"domain_scores_gemma":[0.9987603,0.0002215996,0.00009991288,0.0002938673,0.0005410349,0.00008330196],"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":[0.0002764737,0.000262875,0.001329481,0.0005471038,0.0001474491,0.0003176426,0.0003263994,0.1934347,0.01409881,0.07095242,0.03114658,0.6871601],"study_design_scores_gemma":[0.00008419108,0.0001246817,0.0004232535,0.00003921257,0.00003125795,0.0005390411,0.0001617193,0.9117599,0.007050514,0.05015309,0.02958726,0.00004600312],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001940948,0.0001647272,0.9952489,0.0002931552,0.0001113085,0.0000827675,0.00006964979,0.0009806826,0.001107973],"genre_scores_gemma":[0.02715077,0.0001558642,0.9703569,0.0001106573,0.00005752513,0.0001775558,0.0002749169,0.0001178641,0.001597957],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004297047,"threshold_uncertainty_score":0.01437503,"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","authors":[{"name":"Gabriela Moise","is_ca":true},{"name":"Arthur Zimek","is_ca":false},{"name":"Peer Kröger","is_ca":false},{"name":"Hans‐Peter Kriegel","is_ca":false},{"name":"Jörg Sander","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01322983,0.001851313,0.001863671,0.003206553,0.001857989,0.00259302,0.002214892,0.001770928,0.00357361],"category_scores_gemma":[0.03895741,0.0005320774,0.001126727,0.004688549,0.00124831,0.003248808,0.002650267,0.0009089446,0.001577457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009447859,"about_ca_system_score_gemma":0.001399791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008395977,"about_ca_topic_score_gemma":0.01012129,"domain_scores_codex":[0.9872727,0.006476497,0.0007481424,0.001550948,0.003612913,0.0003387835],"domain_scores_gemma":[0.971338,0.01462847,0.0008990652,0.004903384,0.007769272,0.0004618798],"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":[0.00834869,0.002163913,0.01079401,0.003018155,0.002095722,0.0001225434,0.0008504087,0.1563409,0.01938897,0.006058128,0.0169387,0.7738798],"study_design_scores_gemma":[0.0007027799,0.002335805,0.01284615,0.0001265392,0.0007356569,0.0005277541,0.000969531,0.9347551,0.03266923,0.008646244,0.005505955,0.0001793288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4080405,0.006439429,0.5602527,0.0006380794,0.0008176843,0.001438588,0.00501834,0.008960683,0.008393994],"genre_scores_gemma":[0.5216079,0.001716121,0.4629073,0.0001690846,0.0001356158,0.0006875365,0.008576652,0.001096651,0.003103146],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01322983,"threshold_uncertainty_score":0.06996685,"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","authors":[{"name":"Mohamed Bouguessa","is_ca":true},{"name":"Shengrui Wang","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003843067,0.001458915,0.002320229,0.005876507,0.002084518,0.003404848,0.002761962,0.002166633,0.0009169714],"category_scores_gemma":[0.01857025,0.001056979,0.001927939,0.005983123,0.001610611,0.003401351,0.00403104,0.001920173,0.00085037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009341603,"about_ca_system_score_gemma":0.001622829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003376128,"about_ca_topic_score_gemma":0.003143603,"domain_scores_codex":[0.9943976,0.001717083,0.0003905838,0.001161525,0.001996562,0.0003366333],"domain_scores_gemma":[0.9909,0.003748921,0.0009833293,0.001255505,0.002773721,0.0003384296],"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":[0.0007366231,0.0005352815,0.02626669,0.0008861371,0.000890365,0.001501383,0.002813942,0.515168,0.009665623,0.06391372,0.01102143,0.3666008],"study_design_scores_gemma":[0.00003637567,0.00007805529,0.002673762,0.00004689402,0.00004192767,0.0002743098,0.0006276823,0.919227,0.002476842,0.0724598,0.002007036,0.00005036467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06225463,0.0003778762,0.9349715,0.000251377,0.00004252632,0.0001841339,0.0004301528,0.0006967588,0.0007910997],"genre_scores_gemma":[0.3365365,0.0005125635,0.6580942,0.0001014015,0.00009495959,0.0004147555,0.002869759,0.0001330442,0.001242849],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005876507,"threshold_uncertainty_score":0.02032435,"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","authors":[{"name":"Derek S. Chiu","is_ca":true},{"name":"Aline Talhouk","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02315324,0.003914279,0.004704414,0.009180763,0.002275164,0.00632269,0.007729058,0.002847473,0.06165078],"category_scores_gemma":[0.1075756,0.003794423,0.005900973,0.006671592,0.002340676,0.004112719,0.00638744,0.007684025,0.03254007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001686317,"about_ca_system_score_gemma":0.007401756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004472909,"about_ca_topic_score_gemma":0.00654537,"domain_scores_codex":[0.9837514,0.007529731,0.001727452,0.003400197,0.003158304,0.0004330793],"domain_scores_gemma":[0.9297916,0.04856842,0.004834617,0.008724692,0.007000038,0.001080582],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001074285,0.0001467254,0.007428849,0.006614684,0.004286401,0.000597728,0.001129893,0.02779114,0.004328352,0.04227517,0.6374006,0.2669263],"study_design_scores_gemma":[0.0009468817,0.0002310705,0.005912778,0.001066447,0.001400438,0.001232554,0.0003029339,0.1583235,0.01158805,0.1955446,0.6228955,0.0005551748],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.001370723,0.001063031,0.8547183,0.0006726391,0.0005547235,0.0008160069,0.03219429,0.1061607,0.002449653],"genre_scores_gemma":[0.01364631,0.0006818832,0.9248242,0.0007313746,0.0002745494,0.004755282,0.02133904,0.03176516,0.001982178],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.06165078,"threshold_uncertainty_score":0.2062424,"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","authors":[{"name":"Fabrizio Cerreto","is_ca":false},{"name":"Bo Friis Nielsen","is_ca":false},{"name":"Otto Anker Nielsen","is_ca":false},{"name":"Steven Harrod","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00109448,0.0008472541,0.0008398856,0.003007455,0.0008556642,0.001188616,0.0009553541,0.0008918246,0.0006225767],"category_scores_gemma":[0.004331325,0.0003753375,0.0008586572,0.003439186,0.0004221476,0.0005639884,0.0009907802,0.0006010311,0.0004085581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00108693,"about_ca_system_score_gemma":0.001260529,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01253332,"about_ca_topic_score_gemma":0.007798023,"domain_scores_codex":[0.9986493,0.0003273748,0.0001407804,0.0003804716,0.0004035407,0.00009847044],"domain_scores_gemma":[0.99812,0.0006815052,0.000183233,0.0003203602,0.0006308588,0.00006398172],"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":[0.0002884677,0.0002427238,0.01336166,0.0003456182,0.0003404998,0.0004102938,0.0006798027,0.4840815,0.02239933,0.007782089,0.004783569,0.4652844],"study_design_scores_gemma":[0.00001033275,0.00004084345,0.004166407,0.00001460666,0.00002869899,0.0001143779,0.000184182,0.9774335,0.01024112,0.004968081,0.002763409,0.00003446382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08641633,0.0003686188,0.9080159,0.0002589633,0.0000894606,0.0002062095,0.0007486559,0.002412456,0.001483402],"genre_scores_gemma":[0.5536823,0.0002076123,0.443703,0.00004029933,0.00002768341,0.0001302068,0.001039051,0.0001347667,0.001035038],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01253332,"threshold_uncertainty_score":0.02492076,"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","authors":[{"name":"Haojun Sun","is_ca":false},{"name":"Shengrui Wang","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007576704,0.001149678,0.001711906,0.003760576,0.001233904,0.003047348,0.002140683,0.002754769,0.001137866],"category_scores_gemma":[0.04215915,0.0008143449,0.001245828,0.00376109,0.00202863,0.005212673,0.002972289,0.001793928,0.0005117311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001167714,"about_ca_system_score_gemma":0.001254622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004889307,"about_ca_topic_score_gemma":0.002713131,"domain_scores_codex":[0.9936507,0.002371164,0.0003064643,0.001168198,0.002032174,0.0004713232],"domain_scores_gemma":[0.9801658,0.01353327,0.001174364,0.002590504,0.002015208,0.0005207778],"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":[0.001772096,0.0003880253,0.05562976,0.0005531026,0.001034749,0.0004554652,0.001660801,0.5435554,0.02667048,0.1018234,0.002965267,0.2634914],"study_design_scores_gemma":[0.00001513588,0.00007522311,0.008059748,0.00002831405,0.0001262048,0.0003239846,0.0001385213,0.9529648,0.004293298,0.0329752,0.0009392739,0.00006025826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.104692,0.0005797641,0.8925421,0.0001676184,0.00004299302,0.00004140039,0.00009155746,0.0003448396,0.001497724],"genre_scores_gemma":[0.7774403,0.0006471138,0.2202113,0.0001028953,0.00009189534,0.00009057267,0.0004989449,0.0001937566,0.0007231524],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007576704,"threshold_uncertainty_score":0.04006994,"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","authors":[{"name":"Yiming Tang","is_ca":true},{"name":"Zhifu Pan","is_ca":false},{"name":"Xianghui Hu","is_ca":false},{"name":"Witold Pedrycz","is_ca":true},{"name":"Renhao Chen","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00153061,0.0006788656,0.001157239,0.001811947,0.0009125568,0.001540015,0.001745036,0.001215577,0.001134853],"category_scores_gemma":[0.006612902,0.0003363576,0.001228087,0.001918411,0.0009212322,0.002408542,0.001700474,0.001024823,0.000461731],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001616918,"about_ca_system_score_gemma":0.001908754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008070629,"about_ca_topic_score_gemma":0.004910387,"domain_scores_codex":[0.9979107,0.0003848372,0.0001579081,0.0004833894,0.0008943893,0.0001688875],"domain_scores_gemma":[0.9976044,0.000636738,0.0002084531,0.0003699892,0.001116632,0.00006382974],"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":[0.000184443,0.0001011944,0.001742727,0.0002596659,0.0001525029,0.0001408063,0.0003571865,0.5833345,0.008695056,0.03991163,0.002372526,0.3627478],"study_design_scores_gemma":[0.000006143562,0.0000194407,0.000388583,0.000007919849,0.00001097244,0.00003827016,0.00002528558,0.9878061,0.002924289,0.007873156,0.0008810901,0.00001870695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01168263,0.0001968431,0.9865493,0.0000744117,0.00002063562,0.000036359,0.00004402571,0.0002910339,0.001104858],"genre_scores_gemma":[0.6136193,0.0003838775,0.3824227,0.00008537403,0.00004623222,0.0001438695,0.000481325,0.00009286417,0.002724565],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008070629,"threshold_uncertainty_score":0.0160473,"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","authors":[{"name":"Yumi Kondo","is_ca":true},{"name":"Matías Salibián‐Barrera","is_ca":true},{"name":"Ruben H. Zamar","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00448584,0.004450302,0.002675449,0.003618174,0.001387486,0.002729005,0.005171321,0.00230444,0.1019357],"category_scores_gemma":[0.02994602,0.002582627,0.002965581,0.003984427,0.001233026,0.003420288,0.003600611,0.004842449,0.09441852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001057591,"about_ca_system_score_gemma":0.003386945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006139835,"about_ca_topic_score_gemma":0.007782201,"domain_scores_codex":[0.9974026,0.0008536855,0.0002624399,0.0005392933,0.0007564641,0.0001855647],"domain_scores_gemma":[0.9885315,0.006294433,0.001022668,0.001828981,0.002079226,0.0002432822],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006202791,0.0001971778,0.002595966,0.002871234,0.0008549531,0.0003623073,0.0006157177,0.02128648,0.009308229,0.02113414,0.7948718,0.1452817],"study_design_scores_gemma":[0.0006913306,0.0002138728,0.005582566,0.0007064519,0.0003892487,0.001110804,0.0001905334,0.2275456,0.02982458,0.06633011,0.6668005,0.0006144092],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.001935271,0.0003964116,0.7657343,0.0005254048,0.0003999677,0.0003077066,0.03339776,0.1938272,0.003475976],"genre_scores_gemma":[0.01170143,0.0003384122,0.865818,0.0005724712,0.0001126756,0.001982902,0.02790916,0.0869103,0.004654733],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.1019357,"threshold_uncertainty_score":0.3410088,"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","authors":[{"name":"Tai Vovan","is_ca":false},{"name":"T. Pham‐Gia","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005053262,0.001262352,0.001642335,0.006348693,0.001877559,0.004015893,0.003249857,0.002657877,0.005400025],"category_scores_gemma":[0.02532385,0.0007523635,0.001499452,0.004046832,0.002653157,0.005260281,0.002527011,0.002211621,0.002545337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002493379,"about_ca_system_score_gemma":0.000962411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001361453,"about_ca_topic_score_gemma":0.001032174,"domain_scores_codex":[0.9957515,0.001203183,0.0002268991,0.001198551,0.001268013,0.0003519065],"domain_scores_gemma":[0.9895739,0.005960399,0.0007304146,0.001338979,0.002034365,0.0003619986],"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":[0.00008072009,0.00004298548,0.002263245,0.0002265332,0.00008972787,0.0001999446,0.0004730977,0.1683348,0.002177608,0.7651075,0.004379124,0.05662471],"study_design_scores_gemma":[0.00001646759,0.00004699074,0.001321554,0.000118815,0.00004403112,0.0004508309,0.0002402422,0.4858696,0.002322339,0.4980909,0.0113984,0.00007998671],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01127562,0.0006525295,0.9811172,0.0003869126,0.00005377672,0.00009080359,0.0003097905,0.0002976435,0.005815604],"genre_scores_gemma":[0.5199983,0.003733321,0.4572355,0.0004856377,0.0005050068,0.000759783,0.002084305,0.0005971636,0.01460103],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006348693,"threshold_uncertainty_score":0.02672458,"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","authors":[{"name":"Guojun Gan","is_ca":true},{"name":"Zijiang Yang","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001516815,0.0008224557,0.001783229,0.001547891,0.001243726,0.001276059,0.001773273,0.001173011,0.003706497],"category_scores_gemma":[0.002618373,0.0004793171,0.001261804,0.003580524,0.0008781232,0.001842513,0.001635731,0.001400528,0.001953927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004441468,"about_ca_system_score_gemma":0.001204203,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004351097,"about_ca_topic_score_gemma":0.004302245,"domain_scores_codex":[0.9984861,0.0003523396,0.00008681053,0.0002278193,0.0007704712,0.00007650796],"domain_scores_gemma":[0.9991311,0.0002363052,0.00004011705,0.0001759037,0.0003698357,0.00004675567],"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":[0.0002025711,0.00008207828,0.0003235185,0.000162434,0.0001358277,0.00005614708,0.0001432103,0.07365577,0.01387736,0.02515305,0.005893388,0.8803146],"study_design_scores_gemma":[0.00003758726,0.000140929,0.0005516906,0.00002378874,0.000047112,0.0002765245,0.00008000887,0.9454631,0.007377995,0.03461016,0.01131779,0.00007335797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001767504,0.0002128158,0.9972517,0.00003175078,0.00003998572,0.00002471475,0.00004288311,0.0002628761,0.0003658338],"genre_scores_gemma":[0.01973988,0.0002666209,0.9778641,0.00004130456,0.00005801071,0.00009612182,0.0002081985,0.00006894937,0.001656809],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004351097,"threshold_uncertainty_score":0.01239944,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}