{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":123,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":123,"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":"962ff7d3bf67","filters":{"venue":"Knowledge and Information Systems"}},"results":[{"id":"W3195438473","doi":"10.1007/s10115-021-01605-0","title":"Model complexity of deep learning: a survey","year":2021,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":388,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Deep learning; Artificial intelligence; Generalization; Machine learning; Model selection; Game complexity; Process (computing); Computational complexity theory; Worst-case complexity; Algorithm; Mathematics","authors":[{"name":"Xia Hu","is_ca":true},{"name":"Lingyang Chu","is_ca":true},{"name":"Jian Pei","is_ca":true},{"name":"Weiqing Liu","is_ca":false},{"name":"Jiang Bian","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04158325762783575,"gpt":0.2735118115492377,"spread":0.2319285539214019,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004316606,0.001624215,0.002834076,0.001899191,0.0006552453,0.004785905,0.003301958,0.00230685,0.004022646],"category_scores_gemma":[0.02343692,0.001209669,0.001400076,0.002821492,0.001907154,0.01075548,0.003146238,0.004528206,0.0008751925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003635771,"about_ca_system_score_gemma":0.002586847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003919233,"about_ca_topic_score_gemma":0.003194188,"domain_scores_codex":[0.9976375,0.0007653854,0.0001987967,0.0004365774,0.0008244429,0.0001372847],"domain_scores_gemma":[0.9797282,0.01683488,0.000619177,0.001276113,0.001278175,0.000263439],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001870128,0.0002114612,0.003924327,0.002181076,0.0002691566,0.0001103814,0.0001261386,0.2328888,0.0005905586,0.4925283,0.01610288,0.2508798],"study_design_scores_gemma":[0.00001389993,0.00004529257,0.0004391911,0.0002021849,0.00004001289,0.00008750469,0.00003961769,0.3804627,0.000447263,0.6098202,0.008378144,0.0000240263],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.01982539,0.1345303,0.8135599,0.01596766,0.0006585559,0.000075305,0.001326505,0.0005445912,0.01351179],"genre_scores_gemma":[0.5074816,0.2361419,0.2332387,0.003686212,0.005305241,0.0005302477,0.003537014,0.0006843341,0.009394791],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.004785905,"threshold_uncertainty_score":0.02637947,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2126734246","doi":"10.1007/s10115-009-0198-y","title":"Boosting support vector machines for imbalanced data sets","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":279,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"National Institutes of Health","keywords":"Support vector machine; Boosting (machine learning); Classifier (UML); Machine learning; Artificial intelligence; Computer science; Margin classifier; Data mining; Structured support vector machine; Relevance vector machine; Pattern recognition (psychology)","authors":[{"name":"Benjamin Wang","is_ca":false},{"name":"Nathalie Japkowicz","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03635550629993588,"gpt":0.3092264469905259,"spread":0.27287094069059,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008011001,0.0009689268,0.002682338,0.002403769,0.0007545329,0.001490138,0.001701568,0.001207216,0.00100659],"category_scores_gemma":[0.02421632,0.0006982004,0.0008906369,0.002278053,0.0007072627,0.002535664,0.001753574,0.002273642,0.0006797113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000646519,"about_ca_system_score_gemma":0.0008980531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00152806,"about_ca_topic_score_gemma":0.001288506,"domain_scores_codex":[0.996557,0.001210911,0.0002647609,0.0004861411,0.001259009,0.0002221163],"domain_scores_gemma":[0.9889899,0.006535327,0.0006749143,0.001445471,0.002089565,0.0002646903],"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":[0.0005129984,0.0003408183,0.004731841,0.000348443,0.0002255754,0.0001331977,0.0001660846,0.2980393,0.004411284,0.0138503,0.009289028,0.6679512],"study_design_scores_gemma":[0.00001363062,0.00003460746,0.0004371813,0.000011616,0.00002235099,0.00002701982,0.00001385033,0.9864187,0.0009436852,0.01130033,0.0007718347,0.000005257896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03903639,0.002098255,0.9563919,0.000492308,0.0002368158,0.0000759656,0.0001500282,0.0007503307,0.0007679068],"genre_scores_gemma":[0.6567967,0.001560552,0.3365908,0.0002157345,0.0007992375,0.000216737,0.001187565,0.000146811,0.002485865],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008011001,"threshold_uncertainty_score":0.04236674,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2513061279","doi":"10.1007/s10115-016-0986-0","title":"EFIM: a fast and memory efficient algorithm for high-utility itemset mining","year":2016,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":239,"is_retracted":false,"has_abstract":false,"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; Government of Canada","keywords":"Computer science; Key (lock); Data mining; Projection (relational algebra); Database transaction; Task (project management); Tree (set theory); Algorithm; High memory; Database; Mathematics; Parallel computing","authors":[{"name":"Souleymane Zida","is_ca":true},{"name":"Philippe Fournier‐Viger","is_ca":false},{"name":"Jerry Chun‐Wei Lin","is_ca":false},{"name":"Chengwei Wu","is_ca":false},{"name":"Vincent S. Tseng","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01286533636610831,"gpt":0.2381222319819108,"spread":0.2252568956158025,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002128504,0.001848496,0.002000174,0.005484755,0.001302347,0.001932655,0.004423071,0.001950544,0.008165998],"category_scores_gemma":[0.01012878,0.0009413406,0.001424512,0.007221487,0.0004804058,0.003943192,0.002838069,0.001691584,0.004507513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007999422,"about_ca_system_score_gemma":0.002295863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003248723,"about_ca_topic_score_gemma":0.005698227,"domain_scores_codex":[0.9985874,0.0002644389,0.0002229209,0.0002816058,0.0004789818,0.0001646483],"domain_scores_gemma":[0.9972329,0.001373022,0.0001545134,0.0005448204,0.0005814935,0.0001133296],"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":[0.0008522374,0.0003128728,0.002929007,0.0004685944,0.0001886996,0.0002351143,0.0001192448,0.01661964,0.003935123,0.004598603,0.03019193,0.939549],"study_design_scores_gemma":[0.0004705612,0.0004178163,0.002324692,0.0002041119,0.0001981563,0.001326218,0.0002057489,0.893647,0.01904894,0.04372665,0.03832556,0.0001045901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01899075,0.001886892,0.9525266,0.0004182133,0.0002427152,0.0004443645,0.003413398,0.01990284,0.002174239],"genre_scores_gemma":[0.04341999,0.0003351131,0.948034,0.0001868907,0.00007432727,0.000337082,0.004750748,0.0004298192,0.002431891],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008165998,"threshold_uncertainty_score":0.02731794,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2153689444","doi":"10.1007/s10115-010-0311-2","title":"The k-anonymity and l-diversity approaches for privacy preservation in social networks against neighborhood attacks","year":2010,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":229,"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":"Data publishing; Social network (sociolinguistics); Computer science; Anonymity; k-anonymity; Adversary; Internet privacy; Computer security; Information privacy; Identity (music); Diversity (politics); Data science; Publishing; Social media; World Wide Web; Sociology","authors":[{"name":"Bin Zhou","is_ca":true},{"name":"Jian Pei","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04483096747457849,"gpt":0.2595111551553161,"spread":0.2146801876807377,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007183415,0.0006698808,0.002091828,0.0024258,0.005329462,0.005900607,0.003309782,0.003846413,0.002055099],"category_scores_gemma":[0.02520445,0.0006682564,0.001985017,0.002698116,0.00696681,0.01614317,0.008561075,0.005128773,0.0006123416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002466723,"about_ca_system_score_gemma":0.002216656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009202299,"about_ca_topic_score_gemma":0.0007327708,"domain_scores_codex":[0.9854506,0.007172006,0.0006218514,0.001881471,0.003593889,0.001280252],"domain_scores_gemma":[0.9667051,0.0179253,0.002763965,0.008933272,0.002679997,0.0009923275],"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":[0.0005584576,0.0001238252,0.001863664,0.0003326756,0.0002248663,0.0002842419,0.001927786,0.06564105,0.003831368,0.8249918,0.004104984,0.09611527],"study_design_scores_gemma":[0.00006293385,0.0001588116,0.0005718829,0.00008273919,0.000104361,0.0005973472,0.0007766874,0.2186712,0.005839653,0.7648522,0.008163278,0.0001189461],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0484931,0.001524255,0.9311755,0.004477323,0.000149121,0.0001245249,0.0002499437,0.0001674877,0.01363871],"genre_scores_gemma":[0.9125812,0.0008794064,0.08064794,0.0005910388,0.0004269644,0.0002146408,0.0001102689,0.00004837058,0.004500086],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007183415,"threshold_uncertainty_score":0.03798997,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2145373745","doi":"10.1007/s10115-003-0135-4","title":"Ontologies for Knowledge Management: An Information Systems Perspective","year":2004,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":201,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Ontology; Computer science; Knowledge management; Perspective (graphical); Data science; Interdependence; Representation (politics); Knowledge representation and reasoning; Management science; Epistemology; Artificial intelligence; Sociology; Engineering","authors":[{"name":"Igor Jurišica","is_ca":true},{"name":"John Mylopoulos","is_ca":true},{"name":"Eric Yu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02185879408285468,"gpt":0.2725057675742664,"spread":0.2506469734914117,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00768812,0.001449665,0.002580661,0.01055112,0.003309427,0.01999174,0.004548378,0.007125156,0.005406705],"category_scores_gemma":[0.008595577,0.001541071,0.00205043,0.01262337,0.02065001,0.04507128,0.005714162,0.006999721,0.001475792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006116792,"about_ca_system_score_gemma":0.003939179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00768079,"about_ca_topic_score_gemma":0.005122691,"domain_scores_codex":[0.9948031,0.002308344,0.0005815489,0.0005644877,0.001367306,0.0003751387],"domain_scores_gemma":[0.9928331,0.004816303,0.000478902,0.0007974415,0.0006370759,0.0004371124],"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":[0.000004110328,0.00001238683,0.00004020432,0.00008915177,0.00001672592,0.00004007776,0.0002343348,0.0005832532,0.00004968256,0.9927511,0.001558622,0.00462024],"study_design_scores_gemma":[0.000005151367,0.000004092967,0.00004495496,0.0001271902,0.00001587635,0.00005184296,0.0002429445,0.001621469,0.0001013037,0.9708356,0.0269401,0.000009526494],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00634148,0.09259059,0.6831421,0.07201799,0.002382085,0.0001464553,0.0005913618,0.0005481984,0.1422398],"genre_scores_gemma":[0.3681436,0.1151584,0.4707858,0.01158107,0.008474478,0.000705742,0.001516032,0.0003700849,0.02326474],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01999174,"threshold_uncertainty_score":0.04438066,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2087414729","doi":"10.1007/s10115-006-0020-z","title":"Detecting outlying subspaces for high-dimensional data: the new task, algorithms, and performance","year":2006,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":143,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Saint Mary's University; Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Linear subspace; Outlier; Subspace topology; Pruning; Computer science; Dimension (graph theory); Heuristic; Anomaly detection; Task (project management); Algorithm; Pattern recognition (psychology); Clustering high-dimensional data; Measure (data warehouse); Point (geometry); Process (computing); Artificial intelligence; Data point; Mathematics; Data mining; Cluster analysis; Combinatorics","authors":[{"name":"Ji Zhang","is_ca":true},{"name":"Hai Wang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0196734787435495,"gpt":0.2493453736811592,"spread":0.2296718949376097,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01184391,0.001541212,0.004350826,0.003174828,0.001462598,0.006851447,0.003087921,0.004166258,0.001681659],"category_scores_gemma":[0.05218237,0.001030454,0.001173473,0.004943903,0.003372387,0.01105235,0.004154882,0.005085617,0.001168707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008323551,"about_ca_system_score_gemma":0.001370588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002922441,"about_ca_topic_score_gemma":0.002151246,"domain_scores_codex":[0.9914305,0.003333409,0.000658816,0.001376471,0.002931431,0.0002695228],"domain_scores_gemma":[0.9328982,0.04842728,0.003099086,0.009165387,0.005311021,0.001098988],"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":[0.0006335271,0.0003106968,0.01610615,0.0005342786,0.0002904817,0.000164056,0.0005113992,0.05490437,0.008648601,0.0247037,0.0104033,0.8827895],"study_design_scores_gemma":[0.0000536512,0.0001765719,0.004166026,0.0000535115,0.00007739431,0.0006601958,0.0003619523,0.8724295,0.004798899,0.1129695,0.004155114,0.00009775443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0272557,0.004847516,0.9634069,0.002748321,0.0001321631,0.00004250123,0.000149221,0.0009463711,0.000471437],"genre_scores_gemma":[0.2787491,0.004514429,0.7126281,0.0004374923,0.001092566,0.000120354,0.0007359012,0.0003316473,0.001390429],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01184391,"threshold_uncertainty_score":0.06263733,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2032469362","doi":"10.1007/s10115-006-0032-8","title":"CanTree: a canonical-order tree for incremental frequent-pattern mining","year":2006,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":140,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Data mining; Tree (set theory); GSP Algorithm; Database transaction; Tree structure; A priori and a posteriori; Association rule learning; Apriori algorithm; Database; Mathematics; Algorithm; Binary tree","authors":[{"name":"Carson K. Leung","is_ca":true},{"name":"Quamrul Khan","is_ca":true},{"name":"Zhan Li","is_ca":true},{"name":"Tariqul Hoque","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01329467542214002,"gpt":0.2450617536862699,"spread":0.2317670782641299,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001515917,0.001060664,0.001507573,0.004260251,0.001009946,0.002600781,0.002450834,0.001064657,0.008621993],"category_scores_gemma":[0.01106732,0.0008973642,0.001435983,0.005473205,0.0005227218,0.003007544,0.001535109,0.001647342,0.003742522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006007674,"about_ca_system_score_gemma":0.002887062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006871248,"about_ca_topic_score_gemma":0.01683791,"domain_scores_codex":[0.9986927,0.0002501215,0.0001691348,0.0001909783,0.0005937807,0.0001032536],"domain_scores_gemma":[0.9958216,0.001742498,0.0002051335,0.0009794168,0.001007629,0.000243681],"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":[0.001130326,0.0003617201,0.003866584,0.001379936,0.000273181,0.0006747421,0.0004561777,0.0217341,0.008582065,0.02837995,0.1013327,0.8318286],"study_design_scores_gemma":[0.0006083248,0.0004746486,0.002462396,0.0003597173,0.0003877381,0.00158242,0.0003367146,0.7047969,0.01561137,0.1211034,0.1520473,0.0002290226],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01109918,0.001114215,0.9371065,0.0003608908,0.0002484014,0.0005986546,0.0114221,0.03531371,0.002736395],"genre_scores_gemma":[0.04933676,0.0006688891,0.9275955,0.0001566743,0.00007818708,0.0003773109,0.01749674,0.001608038,0.00268185],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008621993,"threshold_uncertainty_score":0.0288434,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2078765398","doi":"10.1007/s10115-011-0400-x","title":"Early classification on time series","year":2011,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":123,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Beijing Institute of Technology; University of Windsor; Simon Fraser University; National Science Foundation","keywords":"Series (stratigraphy); Classifier (UML); Time series; Computer science; k-nearest neighbors algorithm; Benchmark (surveying); Data mining; Artificial intelligence; Pattern recognition (psychology); Machine learning; Geography","authors":[{"name":"Zhengzheng Xing","is_ca":false},{"name":"Jian Pei","is_ca":true},{"name":"Philip S. Yu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02641227350953722,"gpt":0.2078618429014923,"spread":0.1814495693919551,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002923914,0.0007860246,0.0009662483,0.004905713,0.0008344337,0.003055407,0.0009911422,0.001203533,0.004669551],"category_scores_gemma":[0.01508437,0.0003736748,0.0007932195,0.003334575,0.001048191,0.004689715,0.001179925,0.002497486,0.002316077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001375491,"about_ca_system_score_gemma":0.0006484394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001755871,"about_ca_topic_score_gemma":0.001279443,"domain_scores_codex":[0.9985178,0.000380751,0.0001191975,0.0002865187,0.0005424714,0.0001533336],"domain_scores_gemma":[0.9886628,0.005780545,0.0006920673,0.001657982,0.00285152,0.0003550258],"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":[0.0005437552,0.0001883913,0.01347488,0.0004787052,0.0001176809,0.0002621318,0.0003735698,0.02752961,0.009754282,0.1895827,0.01782446,0.7398698],"study_design_scores_gemma":[0.00003508567,0.0002412476,0.01267101,0.0002089332,0.0001245218,0.0003598573,0.0002292125,0.5777108,0.01333039,0.3599247,0.03509586,0.00006838021],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.148766,0.01166999,0.8106495,0.004044154,0.002429274,0.0001132743,0.000693086,0.001010444,0.02062434],"genre_scores_gemma":[0.8127771,0.00822032,0.1259059,0.0006020581,0.004298452,0.0001272254,0.002147187,0.0002543029,0.04566752],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004905713,"threshold_uncertainty_score":0.01562119,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2077179394","doi":"10.1007/s10115-006-0035-5","title":"Handicapping attacker's confidence: an alternative to k-anonymization","year":2006,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Privacy-Preserving Technologies in Data","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":"Simon Fraser University","funders":"","keywords":"Property (philosophy); Computer science; Data mining; Limit (mathematics); Domain (mathematical analysis); Set (abstract data type); Monotonic function; Limiting; Dual (grammatical number); Data set; Information sensitivity; Transformation (genetics); Information retrieval; Artificial intelligence; Computer security; Mathematics","authors":[{"name":"Ke Wang","is_ca":true},{"name":"Benjamin C. M. Fung","is_ca":true},{"name":"Philip S. Yu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02149667981623806,"gpt":0.2771397648339458,"spread":0.2556430850177077,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005304991,0.0008138818,0.002087191,0.001335026,0.002748956,0.003694285,0.002830693,0.004499556,0.004015748],"category_scores_gemma":[0.02995597,0.0006370934,0.001327636,0.001975135,0.005403352,0.01107,0.009334718,0.003976621,0.001182148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008499459,"about_ca_system_score_gemma":0.001452044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000624957,"about_ca_topic_score_gemma":0.0005172882,"domain_scores_codex":[0.988303,0.005256792,0.0005436804,0.001597933,0.003109925,0.00118865],"domain_scores_gemma":[0.9559052,0.01566399,0.002451063,0.02320593,0.002157151,0.0006167286],"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":[0.001090408,0.0001562447,0.001565144,0.0001853122,0.0002030559,0.0008306211,0.001895748,0.04151156,0.00950708,0.7664293,0.006079119,0.1705464],"study_design_scores_gemma":[0.0001094879,0.0001694623,0.0004194932,0.00007708288,0.0001449246,0.001554279,0.0005524227,0.2631156,0.01722026,0.7039043,0.01260009,0.000132515],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04191501,0.0003326784,0.9360014,0.002763531,0.0001932335,0.0001440232,0.0001366234,0.0008307443,0.01768279],"genre_scores_gemma":[0.9169798,0.0001656113,0.07635539,0.0004640956,0.0001513581,0.00006409027,0.00005303924,0.00008561026,0.005680927],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005304991,"threshold_uncertainty_score":0.02805579,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2026962484","doi":"10.1007/s10115-006-0002-1","title":"A collaborative filtering framework based on fuzzy association rules and multiple-level similarity","year":2006,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":114,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Research Council Canada; Hong Kong Polytechnic University; University of Rochester","keywords":"Collaborative filtering; Recommender system; Computer science; Association rule learning; Similarity (geometry); Popularity; Fuzzy logic; Data mining; Product (mathematics); Information retrieval; Quality (philosophy); The Internet; Machine learning; Artificial intelligence; World Wide Web; Mathematics","authors":[{"name":"Cane Wing-ki Leung","is_ca":false},{"name":"Stephen Chan","is_ca":false},{"name":"Fu-Lai Chung","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01406702293136997,"gpt":0.2411199238886861,"spread":0.2270529009573161,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005764916,0.0008993491,0.003073223,0.004016074,0.001923085,0.003711778,0.004292514,0.003196993,0.002752561],"category_scores_gemma":[0.01106684,0.0008810489,0.00248067,0.004648945,0.001254803,0.00596575,0.002096414,0.0021061,0.001280918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001095916,"about_ca_system_score_gemma":0.001777428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01105787,"about_ca_topic_score_gemma":0.01103358,"domain_scores_codex":[0.9943494,0.00163193,0.0004199911,0.001158028,0.002213355,0.0002273281],"domain_scores_gemma":[0.9936243,0.003177907,0.0003299385,0.0008814778,0.001763565,0.0002228238],"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":[0.0003013008,0.0005448804,0.002800656,0.0005228191,0.001022064,0.0004599663,0.000981222,0.2260992,0.006553807,0.2760389,0.006257436,0.4784178],"study_design_scores_gemma":[0.00004196502,0.0001159643,0.0005234499,0.00004495908,0.0002050982,0.0003105053,0.00005683815,0.9217408,0.001562546,0.06991953,0.005394578,0.00008384184],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002150224,0.0003092919,0.9964676,0.0001056407,0.00003941719,0.00003515701,0.00003302104,0.0001287119,0.0007309041],"genre_scores_gemma":[0.1225132,0.0006923485,0.8723636,0.0001445071,0.000213196,0.000142239,0.0002262991,0.00004633029,0.003658395],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01105787,"threshold_uncertainty_score":0.03048813,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2025568499","doi":"10.1007/s10115-012-0538-1","title":"Efficient greedy feature selection for unsupervised learning","year":2012,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Face and Expression Recognition","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 Waterloo","funders":"","keywords":"Feature selection; Dimensionality reduction; Computer science; Artificial intelligence; Greedy algorithm; Machine learning; Pattern recognition (psychology); Curse of dimensionality; Feature (linguistics); Feature learning; Unsupervised learning; Selection (genetic algorithm); Dimension (graph theory); Data mining; Algorithm; Mathematics","authors":[{"name":"Ahmed Farahat","is_ca":true},{"name":"Ali Ghodsi","is_ca":true},{"name":"Mohamed S. Kamel","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01308683905805496,"gpt":0.237677893728842,"spread":0.224591054670787,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001504255,0.001378011,0.002566203,0.001282719,0.000960951,0.001131053,0.002829985,0.001508051,0.003741584],"category_scores_gemma":[0.004929672,0.000917985,0.001421511,0.00188014,0.001006509,0.001612012,0.001885452,0.001634189,0.001844391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009909511,"about_ca_system_score_gemma":0.002496041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007707199,"about_ca_topic_score_gemma":0.01124916,"domain_scores_codex":[0.9985158,0.0004636955,0.0001096835,0.0003250369,0.0003692086,0.0002166476],"domain_scores_gemma":[0.9977502,0.001355593,0.0001105612,0.0003338003,0.0003651651,0.00008458199],"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":[0.0005921476,0.0003047773,0.001295262,0.0001642782,0.0001777237,0.0001600365,0.00008150204,0.1767653,0.0134836,0.009667578,0.01463947,0.7826682],"study_design_scores_gemma":[0.00005362348,0.00005540741,0.0004023163,0.00000613026,0.0000251257,0.00005966133,0.00001874268,0.9837252,0.002868221,0.01190797,0.0008634177,0.00001420874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008496701,0.0002046547,0.9889966,0.0001216876,0.00003069316,0.00005926217,0.0001475665,0.001523113,0.0004196588],"genre_scores_gemma":[0.3055759,0.0002747072,0.68502,0.0003004976,0.0001360404,0.0006072868,0.002322823,0.0004956709,0.005267175],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007707199,"threshold_uncertainty_score":0.01532471,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2126966660","doi":"10.1007/s10115-005-0233-6","title":"Capabilities of outlier detection schemes in large datasets, framework and methodologies","year":2006,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":86,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Outlier; Computer science; Anomaly detection; Data mining; Scheme (mathematics); Credit card fraud; Matching (statistics); Artificial intelligence; Machine learning; Pattern recognition (psychology); Credit card; Mathematics; Statistics","authors":[{"name":"Jian Tang","is_ca":true},{"name":"Zhixiang Chen","is_ca":false},{"name":"Ada Wai-Chee Fu","is_ca":false},{"name":"David W. Cheung","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01661910464544925,"gpt":0.2830376010041942,"spread":0.266418496358745,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02346593,0.001010752,0.001525185,0.003758194,0.001399023,0.005631189,0.002525873,0.00235548,0.001668287],"category_scores_gemma":[0.08315993,0.0006009713,0.001029276,0.003589117,0.001824268,0.009106221,0.004438931,0.002482416,0.000672808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001343926,"about_ca_system_score_gemma":0.001818289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002109724,"about_ca_topic_score_gemma":0.001638978,"domain_scores_codex":[0.9898568,0.004410428,0.000862802,0.001514671,0.003001199,0.0003540853],"domain_scores_gemma":[0.9298368,0.04826687,0.003745627,0.01156252,0.005616658,0.000971498],"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":[0.001075286,0.0004771872,0.02511466,0.0007794263,0.0005804109,0.000318813,0.0008515539,0.2709495,0.0128624,0.1074985,0.007124438,0.5723678],"study_design_scores_gemma":[0.00003814613,0.0001612358,0.00201674,0.00006107907,0.00007445203,0.0002885987,0.0002012839,0.875465,0.006912788,0.1117749,0.00296069,0.00004509],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04848084,0.0009675084,0.9454159,0.001418673,0.00006323633,0.00009411418,0.0003962542,0.001726408,0.001437043],"genre_scores_gemma":[0.5292632,0.000826155,0.4674322,0.0002241384,0.0001683897,0.0001485084,0.0008248018,0.0001968021,0.0009157824],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02346593,"threshold_uncertainty_score":0.1241012,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2029902517","doi":"10.1007/s10115-012-0511-z","title":"How you move reveals who you are: understanding human behavior by analyzing trajectory data","year":2012,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Process (computing); Inference; Field (mathematics); Human behavior; Data science; Trajectory; Artificial intelligence; Knowledge extraction; Business process discovery; Human–computer interaction; Work in process; Business process; Engineering","authors":[{"name":"Chiara Renso","is_ca":false},{"name":"Miriam Baglioni","is_ca":false},{"name":"José Antônio Fernandes de Macêdo","is_ca":false},{"name":"Roberto Trasarti","is_ca":false},{"name":"Mónica Wachowicz","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07373967419833824,"gpt":0.2829743150121176,"spread":0.2092346408137793,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004530261,0.0003359424,0.0002754017,0.001589513,0.0004420284,0.001080058,0.0003502307,0.0006866451,0.001016667],"category_scores_gemma":[0.005807994,0.0001606803,0.0001961177,0.00216585,0.0004174779,0.001553057,0.0004616578,0.000502735,0.000554823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003945993,"about_ca_system_score_gemma":0.000599633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02486583,"about_ca_topic_score_gemma":0.03165158,"domain_scores_codex":[0.999747,0.0001062282,0.00001665212,0.00006217154,0.00004000873,0.0000279126],"domain_scores_gemma":[0.9976271,0.001306716,0.0004388817,0.0002352465,0.0002755587,0.0001166286],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000555159,0.0002617264,0.7475089,0.0002614675,0.0002230177,0.0004978544,0.011638,0.02090652,0.008871657,0.00384757,0.006051277,0.1993768],"study_design_scores_gemma":[0.00002650469,0.0003781372,0.5899519,0.0002358457,0.0002147703,0.000865067,0.03413604,0.3237942,0.006643747,0.02725133,0.01636626,0.000136213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9468104,0.0004726883,0.04586838,0.0008855085,0.00002215691,0.00006524283,0.003136613,0.0003240146,0.002415119],"genre_scores_gemma":[0.9856839,0.0002679703,0.01249106,0.00003146369,0.000008575304,0.00002330371,0.001017836,0.00002759105,0.0004482237],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02486583,"threshold_uncertainty_score":0.04944217,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2009423697","doi":"10.1007/s10115-013-0658-2","title":"Email mining: tasks, common techniques, and tools","year":2013,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":73,"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; Categorization; World Wide Web; Data science; Visualization; Information retrieval; Data mining; Artificial intelligence","authors":[{"name":"Guanting Tang","is_ca":true},{"name":"Jian Pei","is_ca":true},{"name":"Wo-Shun Luk","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01539316849572635,"gpt":0.2287722311190385,"spread":0.2133790626233122,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009927617,0.002324489,0.002752721,0.01454405,0.002490113,0.007769799,0.003619723,0.003849448,0.001779404],"category_scores_gemma":[0.02434436,0.001162136,0.001958015,0.0162762,0.00176431,0.01004421,0.004155178,0.002900436,0.002587523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001155683,"about_ca_system_score_gemma":0.002504646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001199823,"about_ca_topic_score_gemma":0.001602099,"domain_scores_codex":[0.9870652,0.004455486,0.001852212,0.001936981,0.004121812,0.0005684348],"domain_scores_gemma":[0.9783638,0.012121,0.001603125,0.004175346,0.002947624,0.0007892702],"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":[0.0002506389,0.0005257511,0.01262045,0.003089922,0.000250043,0.0001944724,0.001049569,0.004089974,0.005254285,0.02611569,0.02167418,0.924885],"study_design_scores_gemma":[0.0001349604,0.0005337095,0.02943647,0.002633886,0.0006597433,0.005985161,0.004791792,0.2484223,0.04568275,0.4731155,0.1881957,0.0004081519],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.03655865,0.01923406,0.9237629,0.004986897,0.0003188959,0.0007993868,0.003449337,0.005123331,0.005766587],"genre_scores_gemma":[0.1756071,0.01434323,0.7970798,0.0008235562,0.0009404365,0.0007357559,0.00601661,0.000609273,0.003844228],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.01454405,"threshold_uncertainty_score":0.05250287,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2073825221","doi":"10.1007/s10115-007-0090-6","title":"Robust projected clustering","year":2007,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":70,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; University of Alberta","funders":"Yale University","keywords":"Cluster analysis; Categorical variable; Disjoint sets; Linear subspace; Outlier; Data mining; CURE data clustering algorithm; Cluster (spacecraft); Subspace topology; Set (abstract data type); Computer science; Data set; Correlation clustering; Clustering high-dimensional data; Single-linkage clustering; Algorithm; Pattern recognition (psychology); Mathematics; Artificial intelligence; Machine learning; Combinatorics","authors":[{"name":"Gabriela Moise","is_ca":true},{"name":"Jörg Sander","is_ca":true},{"name":"Martin Ester","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1299341584742713,"gpt":0.3893189388673293,"spread":0.259384780393058,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003004806,0.002183257,0.003138893,0.003160511,0.00166732,0.003524109,0.003524566,0.003103825,0.009476632],"category_scores_gemma":[0.01216205,0.001301326,0.003427071,0.002928799,0.001752965,0.003090538,0.004389039,0.002712828,0.007641758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001307331,"about_ca_system_score_gemma":0.002715041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004153752,"about_ca_topic_score_gemma":0.00433531,"domain_scores_codex":[0.9941738,0.001791817,0.0002755616,0.001946718,0.001520249,0.0002918363],"domain_scores_gemma":[0.9950842,0.001082262,0.0002815233,0.00187352,0.001496609,0.0001819811],"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":[0.0005996759,0.0001575263,0.0008816859,0.000494365,0.0005761574,0.0001310083,0.0001821717,0.3006151,0.01028872,0.1031293,0.02921272,0.5537316],"study_design_scores_gemma":[0.00002510893,0.00004919743,0.0004786802,0.00003260446,0.00005059741,0.0001085064,0.00004513581,0.9114035,0.00388268,0.07660711,0.007279193,0.00003754938],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003052884,0.0003623419,0.9921829,0.0001997578,0.00009930063,0.00007035005,0.0003887304,0.001068518,0.00257517],"genre_scores_gemma":[0.1651687,0.0007603678,0.8101547,0.0003957471,0.0003207678,0.0004189034,0.005527291,0.001208324,0.01604522],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009476632,"threshold_uncertainty_score":0.03170252,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2102549231","doi":"10.1007/s10115-006-0023-9","title":"Node similarity in the citation graph","year":2006,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":69,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; Dalhousie University","funders":"Southeast University; Dalhousie University","keywords":"Computer science; Graph; Complementarity (molecular biology); Theoretical computer science; Similarity (geometry); Citation; Random geometric graph; Similitude; Information retrieval; Data mining; Artificial intelligence; Line graph; Voltage graph; World Wide Web","authors":[{"name":"Wangzhong Lu","is_ca":true},{"name":"Jeannette Janssen","is_ca":true},{"name":"Evangelos Milios","is_ca":true},{"name":"Nathalie Japkowicz","is_ca":true},{"name":"Yongzheng Zhang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01017648760587226,"gpt":0.2432162399859891,"spread":0.2330397523801168,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.001813473,0.0003341897,0.001131658,0.0120919,0.001208837,0.002728873,0.001130044,0.002009824,0.00358949],"category_scores_gemma":[0.03197455,0.0003938176,0.0004660721,0.01272321,0.001220985,0.006174432,0.001189806,0.0007189678,0.000551267],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001097279,"about_ca_system_score_gemma":0.0007418505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002633516,"about_ca_topic_score_gemma":0.002973024,"domain_scores_codex":[0.9980393,0.0007626176,0.0001314494,0.0003918977,0.0005924597,0.00008229219],"domain_scores_gemma":[0.9749126,0.01917719,0.001965292,0.0009620233,0.002402098,0.00058083],"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":[0.0004481796,0.0002343542,0.04411734,0.001325079,0.000524707,0.0005778585,0.001359072,0.100222,0.006316209,0.6174456,0.01350913,0.2139205],"study_design_scores_gemma":[0.00004396064,0.00007224855,0.01572741,0.0001394337,0.0003069089,0.0005965765,0.0002807526,0.3006682,0.001819041,0.6700974,0.01018751,0.0000605908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.559788,0.00637731,0.4033404,0.003249412,0.0002562192,0.000149049,0.003078832,0.0006850169,0.02307579],"genre_scores_gemma":[0.9519441,0.002145666,0.03992207,0.0001259539,0.0002910499,0.0001039844,0.001176223,0.00007463888,0.004216377],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9879081,"threshold_uncertainty_score":0.01200801,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2027417703","doi":"10.1007/s10115-010-0287-y","title":"An information gain-based approach for recommending useful product reviews","year":2010,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Helpfulness; Computer science; Product (mathematics); Recommender system; Ranking (information retrieval); Quality (philosophy); Order (exchange); Task (project management); Information retrieval; Data science; Business; Engineering","authors":[{"name":"Richong Zhang","is_ca":true},{"name":"Thomas Tran","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03250743570292643,"gpt":0.2886427697291577,"spread":0.2561353340262313,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002384093,0.001117378,0.001898645,0.007053579,0.0008148514,0.001748455,0.00137035,0.001715071,0.001973832],"category_scores_gemma":[0.008329907,0.0004306571,0.001255554,0.003778921,0.0004709353,0.002564795,0.0007179801,0.001016123,0.0008293616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001101207,"about_ca_system_score_gemma":0.001061281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003749022,"about_ca_topic_score_gemma":0.007448062,"domain_scores_codex":[0.9974769,0.0004163119,0.0002097724,0.0003354637,0.001446271,0.0001153302],"domain_scores_gemma":[0.9956188,0.002036917,0.0002492666,0.0001620691,0.001839573,0.00009339726],"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":[0.001186967,0.001339551,0.01191481,0.0006854301,0.000900044,0.000337252,0.0002578143,0.02759868,0.01879237,0.005585945,0.01551356,0.9158876],"study_design_scores_gemma":[0.0001908849,0.0007892297,0.009662986,0.00007044531,0.0006330215,0.0005826137,0.0001069824,0.964583,0.009652946,0.008892618,0.004732787,0.0001024503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.147433,0.006187667,0.8279379,0.002145537,0.0005627064,0.001030626,0.001517107,0.002550171,0.01063531],"genre_scores_gemma":[0.7109576,0.001372178,0.2787635,0.0004048865,0.0007892257,0.0003927375,0.001148431,0.0000721033,0.006099379],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007053579,"threshold_uncertainty_score":0.01260847,"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":"W2007800125","doi":"10.1007/s10115-014-0801-8","title":"Greedy column subset selection for large-scale data sets","year":2014,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Face and Expression Recognition","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":"University of Waterloo","funders":"","keywords":"Computer science; Column (typography); Selection (genetic algorithm); Greedy algorithm; Algorithm; Representation (politics); Matrix (chemical analysis); Big data; Data mining; Artificial intelligence; Frame (networking)","authors":[{"name":"Ahmed Farahat","is_ca":true},{"name":"Ahmed Elgohary","is_ca":false},{"name":"Ali Ghodsi","is_ca":true},{"name":"Mohamed S. Kamel","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02411245776584549,"gpt":0.2674305953687463,"spread":0.2433181376029008,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002045721,0.001984775,0.003167829,0.002676265,0.001428328,0.001995054,0.002538315,0.001407676,0.004025536],"category_scores_gemma":[0.007130517,0.000928579,0.001990488,0.003800157,0.0008914231,0.001795366,0.001593214,0.001672889,0.002093735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005566605,"about_ca_system_score_gemma":0.002402544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00478381,"about_ca_topic_score_gemma":0.01049613,"domain_scores_codex":[0.9984737,0.0005299787,0.0001449562,0.0003221947,0.000338429,0.0001906912],"domain_scores_gemma":[0.9951853,0.003115656,0.000181202,0.0007955162,0.000499669,0.0002226656],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001439646,0.0008857434,0.007488468,0.0007926346,0.0006231323,0.0005404422,0.0002598451,0.1773816,0.01991207,0.004072769,0.05562621,0.7309775],"study_design_scores_gemma":[0.0001620147,0.0002283987,0.001935819,0.00003903989,0.0001580921,0.0002502178,0.0002400074,0.9735112,0.006154989,0.0138457,0.003440113,0.00003427849],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0808576,0.002150911,0.9026178,0.001302441,0.0002833099,0.0005031752,0.004837399,0.005789918,0.001657522],"genre_scores_gemma":[0.3958808,0.001054999,0.5665901,0.0008516598,0.0005967169,0.001084075,0.02807845,0.0007914052,0.005071898],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00478381,"threshold_uncertainty_score":0.01346678,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2028936054","doi":"10.1007/s101150050009","title":"An Index Structure for Data Mining and Clustering","year":2000,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Fudan University; National Science Foundation","keywords":"Cluster analysis; Euclidean distance; Data mining; Computer science; Metric (unit); Set (abstract data type); Index (typography); Visualization; Mathematics; Data set; Computation; Approximation error; Algorithm; Pattern recognition (psychology); Artificial intelligence","authors":[{"name":"Xiong Wang","is_ca":false},{"name":"Jason T. L. Wang","is_ca":false},{"name":"King-Ip Lin","is_ca":false},{"name":"Dennis Shasha","is_ca":false},{"name":"Bruce A. Shapiro","is_ca":false},{"name":"Kaizhong Zhang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02296360961186923,"gpt":0.2681822105133437,"spread":0.2452186009014745,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003293111,0.0007136749,0.001899149,0.005131128,0.002317026,0.004012326,0.0021302,0.001242124,0.004042132],"category_scores_gemma":[0.01536919,0.0006781723,0.001079907,0.009693438,0.001030113,0.007321326,0.003064326,0.002042048,0.003529952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001249892,"about_ca_system_score_gemma":0.002921402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002178858,"about_ca_topic_score_gemma":0.003615917,"domain_scores_codex":[0.9973655,0.0004352924,0.0004429263,0.0003427358,0.001288501,0.0001250671],"domain_scores_gemma":[0.9931471,0.001655556,0.0005890211,0.002357865,0.001861162,0.0003893021],"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":[0.0003853157,0.0002761069,0.002820111,0.0005930468,0.0001198641,0.0001752923,0.0005992815,0.01459231,0.007878007,0.1934887,0.05655429,0.7225177],"study_design_scores_gemma":[0.0001251722,0.000393815,0.002039717,0.0003050283,0.0001918053,0.0008816585,0.0002458033,0.2646913,0.01086266,0.5632091,0.1569248,0.0001290011],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005291731,0.001183088,0.9842395,0.0006764233,0.0002976216,0.0002046249,0.002556458,0.002642401,0.002908121],"genre_scores_gemma":[0.03962049,0.001027263,0.9479585,0.0002842285,0.0003074995,0.0003944876,0.005811334,0.0004454489,0.004150762],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005131128,"threshold_uncertainty_score":0.01741582,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2054765427","doi":"10.1007/s10115-011-0467-4","title":"A countably infinite mixture model for clustering and feature selection","year":2011,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke; Concordia University","funders":"","keywords":"Mixture model; Cluster analysis; Model selection; Computer science; Artificial intelligence; Feature selection; Dirichlet process; Dirichlet distribution; Machine learning; Bayesian inference; Inference; Pattern recognition (psychology); Data mining; Mathematics; Bayesian probability","authors":[{"name":"Nizar Bouguila","is_ca":true},{"name":"Djemel Ziou","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02864478443536663,"gpt":0.2546671348517391,"spread":0.2260223504163725,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008247054,0.001524198,0.003856428,0.003741367,0.002002191,0.004424692,0.008513694,0.004212843,0.005240204],"category_scores_gemma":[0.02975276,0.002046646,0.003454539,0.006218964,0.003559905,0.007841675,0.003938571,0.005627663,0.002222069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00303307,"about_ca_system_score_gemma":0.002081005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009596976,"about_ca_topic_score_gemma":0.009844458,"domain_scores_codex":[0.9933289,0.003547089,0.0003676968,0.001171602,0.001279784,0.0003049647],"domain_scores_gemma":[0.9853056,0.01111777,0.0006226068,0.001342307,0.001295963,0.0003157322],"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":[0.000151014,0.00009760749,0.0006613346,0.0002714892,0.0002430649,0.0001179351,0.0002921236,0.274262,0.0008596445,0.6372823,0.004785927,0.0809755],"study_design_scores_gemma":[0.00001483197,0.00001197374,0.0001203612,0.00002649153,0.00003148201,0.00004537527,0.00001375532,0.7168162,0.0001630967,0.2811109,0.001612263,0.00003313991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008769478,0.0003146155,0.9981573,0.0001685873,0.00001681386,0.00001489428,0.00005999161,0.00006813517,0.0003227085],"genre_scores_gemma":[0.120834,0.001724557,0.8660718,0.000483067,0.0003678806,0.0007573895,0.001223373,0.0002855387,0.008252461],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009596976,"threshold_uncertainty_score":0.0436151,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2054521721","doi":"10.1007/s10115-009-0245-8","title":"Mining incomplete survey data through classification","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Saint Mary's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Missing data; Data mining; Computer science; Classifier (UML); Complete information; Data set; Artificial intelligence; Machine learning; Mathematics","authors":[{"name":"Hai Wang","is_ca":true},{"name":"Shouhong Wang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1156448316538467,"gpt":0.3234492842129648,"spread":0.2078044525591181,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003440158,0.0007899865,0.00235631,0.007087081,0.001083543,0.003342159,0.002276636,0.001400022,0.002261367],"category_scores_gemma":[0.01486697,0.0005808569,0.001755656,0.008942463,0.0009063632,0.003880474,0.001962285,0.001418873,0.001828069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001003916,"about_ca_system_score_gemma":0.001838106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005739502,"about_ca_topic_score_gemma":0.007566735,"domain_scores_codex":[0.996483,0.001098482,0.0003177076,0.0007633005,0.0009849096,0.0003526021],"domain_scores_gemma":[0.9875729,0.006105102,0.001292381,0.002863755,0.001914943,0.0002508566],"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":[0.0003127668,0.0004290742,0.08690983,0.0004654329,0.0003228158,0.0002360258,0.0005261197,0.02553726,0.002790309,0.01435305,0.01278264,0.8553346],"study_design_scores_gemma":[0.00005105343,0.0001554727,0.01921575,0.0001962824,0.000346468,0.0005779616,0.0009903309,0.871932,0.006831903,0.08171186,0.01792961,0.00006118715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09135821,0.001761642,0.8978154,0.001083748,0.00014716,0.0003576363,0.002508975,0.001721293,0.003245887],"genre_scores_gemma":[0.6101188,0.001398525,0.3744561,0.0003393726,0.0003208993,0.0005120386,0.008116314,0.0001138893,0.004624099],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007087081,"threshold_uncertainty_score":0.01819348,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2077378918","doi":"10.1007/s10115-009-0252-9","title":"A binary decision diagram based approach for mining frequent subsequences","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":48,"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; Bottleneck; Data mining; Prefix; Sequence (biology); Binary decision diagram; Representation (politics); Theoretical computer science","authors":[{"name":"Elsa Loekito","is_ca":false},{"name":"James Bailey","is_ca":false},{"name":"Jian Pei","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02221211123180673,"gpt":0.2688086613249732,"spread":0.2465965500931665,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002849782,0.0007054725,0.001148151,0.004950769,0.0009336949,0.002582649,0.001343712,0.001276723,0.005750876],"category_scores_gemma":[0.01289001,0.0005311655,0.001171111,0.003805598,0.0006068251,0.002735511,0.0009251632,0.001080808,0.001577723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007939913,"about_ca_system_score_gemma":0.001980868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00379519,"about_ca_topic_score_gemma":0.004158495,"domain_scores_codex":[0.9966801,0.0008990314,0.0005351149,0.0006359203,0.001126369,0.0001234661],"domain_scores_gemma":[0.9915455,0.005728547,0.0004682552,0.0003976678,0.001649246,0.000210712],"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":[0.001668813,0.0007975425,0.01639756,0.002348413,0.00040133,0.001088264,0.0007028333,0.05776659,0.02440337,0.08915106,0.01115201,0.7941223],"study_design_scores_gemma":[0.0003275767,0.000701722,0.003866563,0.0003394565,0.0004982288,0.001500509,0.000299961,0.8452305,0.02122974,0.08970056,0.03615619,0.0001490663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008779426,0.0002639309,0.9865739,0.0001983837,0.0000783022,0.0004062239,0.00114076,0.001290515,0.001268515],"genre_scores_gemma":[0.08722176,0.0002827185,0.9078753,0.0001079341,0.00004106845,0.0005440522,0.002225805,0.00006854393,0.00163277],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005750876,"threshold_uncertainty_score":0.01923853,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4406070280","doi":"10.1007/s10115-024-02321-1","title":"Fake news detection: comparative evaluation of BERT-like models and large language models with generative AI-annotated data","year":2025,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":43,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University; Vector Institute","funders":"","keywords":"Computer science; Generative grammar; Language model; Fake news; Artificial intelligence; Natural language processing; Generative model; Information retrieval","authors":[{"name":"Shaina Raza","is_ca":true},{"name":"Drai Paulen-Patterson","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1036317786528191,"gpt":0.3879677179702772,"spread":0.2843359393174581,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02314073,0.002669788,0.002119899,0.004082035,0.001654141,0.004608538,0.004659823,0.004596998,0.004127358],"category_scores_gemma":[0.07072268,0.001182483,0.00180768,0.002378218,0.00184868,0.008757744,0.002682497,0.004013559,0.002443053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003735532,"about_ca_system_score_gemma":0.003025491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03869615,"about_ca_topic_score_gemma":0.03139057,"domain_scores_codex":[0.988739,0.007384152,0.000699501,0.001665825,0.001121309,0.0003902461],"domain_scores_gemma":[0.8040937,0.179518,0.002450871,0.006114888,0.00570482,0.002117758],"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":[0.01129777,0.004307502,0.0269958,0.002233483,0.002369637,0.0005777514,0.001710602,0.6459736,0.002761446,0.01000018,0.0185307,0.2732415],"study_design_scores_gemma":[0.0001222335,0.0001778089,0.0008871219,0.00003980775,0.0001265264,0.00005569824,0.0001292367,0.9947038,0.0007170009,0.002536715,0.0004690857,0.00003489913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7562237,0.00705089,0.1855296,0.008416146,0.001103988,0.0009776815,0.006865086,0.01887406,0.01495866],"genre_scores_gemma":[0.9308776,0.0008616416,0.05618494,0.0005697434,0.0002324105,0.000231988,0.007903374,0.0007026882,0.002435714],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03869615,"threshold_uncertainty_score":0.1223813,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2762595523","doi":"10.1007/s10115-017-1110-9","title":"Subspace multi-clustering: a review","year":2017,"lang":"en","type":"review","venue":"Knowledge and Information Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":41,"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":"Cluster analysis; Computer science; Clustering high-dimensional data; Correlation clustering; CURE data clustering algorithm; Data mining; Consensus clustering; Canopy clustering algorithm; Data stream clustering; Fuzzy clustering; Constrained clustering; Artificial intelligence; Brown clustering; Pattern recognition (psychology); Machine learning","authors":[{"name":"Juhua Hu","is_ca":true},{"name":"Jian Pei","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.165485976111518,"gpt":0.4314369205160333,"spread":0.2659509444045153,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001466736,0.001324991,0.00258246,0.003956627,0.0004321892,0.002189337,0.001762245,0.001647051,0.00374628],"category_scores_gemma":[0.003769251,0.0005089733,0.0009480345,0.007532904,0.0008527921,0.002803445,0.001205236,0.001360673,0.002315257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008517377,"about_ca_system_score_gemma":0.002631633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002363903,"about_ca_topic_score_gemma":0.003583429,"domain_scores_codex":[0.999483,0.0001005626,0.00007846512,0.0001300718,0.0001749493,0.00003286258],"domain_scores_gemma":[0.9982779,0.0008915665,0.0001667314,0.00006971641,0.0005021219,0.00009201267],"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":[0.00007994848,0.00007318317,0.0004866839,0.02612618,0.0002792771,0.0001106369,0.00005825163,0.0008640919,0.000543758,0.004970846,0.04801681,0.9183903],"study_design_scores_gemma":[0.00005853057,0.0001571706,0.002022639,0.01276547,0.000872759,0.00197224,0.0002035733,0.001365684,0.0007962504,0.01287257,0.9667932,0.0001199944],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00012459,0.9975314,0.00106982,0.0003835422,0.0002605077,0.000008283933,0.00004405498,0.00001564306,0.0005620815],"genre_scores_gemma":[0.001073189,0.9965216,0.00139631,0.0002771396,0.0003943999,0.00001254514,0.00008359187,0.000006058863,0.000235105],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.003956627,"threshold_uncertainty_score":0.01253253,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2151207331","doi":"10.1007/s10115-008-0127-5","title":"Multirelational classification: a multiple view approach","year":2008,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"Shanghai Jiao Tong University","keywords":"Computer science; Relational database; Construct (python library); Table (database); Set (abstract data type); Feature (linguistics); Data mining; Relevance (law); Artificial intelligence; Information retrieval","authors":[{"name":"Hongyu Guo","is_ca":true},{"name":"Herna L. Viktor","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04522474571286368,"gpt":0.2490703254591846,"spread":0.2038455797463209,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006538544,0.001136456,0.002195565,0.005617841,0.001539878,0.008194407,0.003586456,0.002225814,0.005128782],"category_scores_gemma":[0.0149124,0.0008368774,0.003628632,0.005194607,0.001246381,0.008015023,0.003057084,0.002801332,0.001742419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001178368,"about_ca_system_score_gemma":0.00155674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002696005,"about_ca_topic_score_gemma":0.003048436,"domain_scores_codex":[0.991873,0.003228932,0.000484297,0.001407689,0.002538481,0.0004675781],"domain_scores_gemma":[0.9912418,0.004168655,0.0006740282,0.001708748,0.00183981,0.0003669517],"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":[0.0005662011,0.000517417,0.01009609,0.0007786528,0.001317937,0.0005707039,0.001053694,0.02499255,0.01051559,0.1669971,0.0212525,0.7613415],"study_design_scores_gemma":[0.00005881278,0.0001827757,0.003764621,0.0002542338,0.0007292874,0.0007526894,0.0008893063,0.6755484,0.005668349,0.2910421,0.02098092,0.0001284378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007803008,0.001585827,0.9851151,0.001056134,0.0002016011,0.00009105446,0.0003116381,0.000482496,0.003353151],"genre_scores_gemma":[0.314514,0.001873411,0.6765507,0.00062722,0.0006351438,0.0002506631,0.001577491,0.0003008519,0.003670512],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008194407,"threshold_uncertainty_score":0.03457952,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1981679236","doi":"10.1007/s10115-004-0150-0","title":"Multiknowledge for decision making","year":2004,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Reduct; Rough set; Computer science; Data mining; Artificial intelligence; Decision system; Naive Bayes classifier; Machine learning; Classifier (UML); Decision table; Mathematics; Support vector machine","authors":[{"name":"Qingxiang Wu","is_ca":false},{"name":"David Bell","is_ca":true},{"name":"T.M. McGinnity","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01815329828864976,"gpt":0.2729560177640058,"spread":0.254802719475356,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002127454,0.0008582024,0.001503047,0.002256387,0.0009997969,0.004874372,0.001158934,0.002883919,0.01018908],"category_scores_gemma":[0.005397165,0.0004380103,0.0009819714,0.002402778,0.003662078,0.00931182,0.00221907,0.003148008,0.001781609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001781545,"about_ca_system_score_gemma":0.0008480193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001148321,"about_ca_topic_score_gemma":0.0008628746,"domain_scores_codex":[0.9984471,0.0006389344,0.0001096843,0.0002659569,0.0004601286,0.00007817723],"domain_scores_gemma":[0.9967615,0.002287805,0.0001742172,0.0004407364,0.0002379296,0.00009791485],"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":[0.00001513327,0.000014692,0.00004481789,0.0001452147,0.00003327056,0.00006362894,0.00008805733,0.002667963,0.00009746072,0.9655845,0.002354271,0.02889085],"study_design_scores_gemma":[0.000002016533,0.000002272999,0.00001853697,0.00002907966,0.000006417034,0.00001523731,0.00001161457,0.00278646,0.00004176172,0.993448,0.003635418,0.000003226832],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01264454,0.06249536,0.7528563,0.01928128,0.002024239,0.00006379221,0.0003359769,0.000295072,0.1500034],"genre_scores_gemma":[0.6958783,0.02924612,0.2245041,0.002345065,0.003103659,0.0002280124,0.0004436492,0.0001384444,0.04411268],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01018908,"threshold_uncertainty_score":0.03408587,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2883420210","doi":"10.1007/s10115-018-1235-5","title":"Overview of the crowdsourcing process","year":2018,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Mobile Crowdsensing and Crowdsourcing","field":"Computer Science","cited_by":37,"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":"Crowdsourcing; Computer science; Process (computing); Task (project management); Quality (philosophy); Data science; Human intelligence; Incentive; Artificial intelligence; Machine learning; World Wide Web; Engineering","authors":[{"name":"Lobna Nassar","is_ca":true},{"name":"Fakhri Karray","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02053653358225349,"gpt":0.2674521754395504,"spread":0.2469156418572969,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005813695,0.001707607,0.001864276,0.005876833,0.003424972,0.009762814,0.003526879,0.00523236,0.01632053],"category_scores_gemma":[0.01155777,0.001919746,0.002048744,0.007299447,0.003190617,0.006882859,0.007223922,0.003967068,0.0109312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004133658,"about_ca_system_score_gemma":0.006896369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01603959,"about_ca_topic_score_gemma":0.009058144,"domain_scores_codex":[0.9932942,0.001873412,0.0005109904,0.001444005,0.002433365,0.0004441176],"domain_scores_gemma":[0.9934828,0.003027584,0.0003199346,0.001212857,0.001618381,0.0003385098],"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":[0.0001213275,0.0001525527,0.001184897,0.002195492,0.0001110994,0.0002946908,0.001150285,0.02342018,0.003242262,0.707544,0.03064657,0.2299365],"study_design_scores_gemma":[0.00003444837,0.00005548305,0.001033155,0.0006560921,0.00006169404,0.0003673113,0.0003086292,0.06058326,0.002595883,0.4374002,0.4967839,0.0001199738],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003125776,0.0192296,0.895905,0.007920758,0.001040963,0.00120645,0.002257576,0.001567609,0.06774631],"genre_scores_gemma":[0.147669,0.05269965,0.7069905,0.002631483,0.004800797,0.002636677,0.005234147,0.001090257,0.07624749],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01632053,"threshold_uncertainty_score":0.05459762,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2127408419","doi":"10.1007/s10115-009-0202-6","title":"Integrating multiple document features in language models for expert finding","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Expert finding and Q&A systems","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"Engineering and Physical Sciences Research Council; Commonwealth Scientific and Industrial Research Organisation","keywords":"Computer science; Information retrieval; Language model; Paragraph; Document retrieval; Document management system; Question answering; PageRank; Intranet; Key (lock); Subject-matter expert; Expert system; Artificial intelligence; Natural language processing; World Wide Web; The Internet","authors":[{"name":"Jianhan Zhu","is_ca":false},{"name":"Dawei Song","is_ca":false},{"name":"Stefan Rüger","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0164611288398977,"gpt":0.2821247681681098,"spread":0.2656636393282121,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004282814,0.0009947096,0.001275544,0.002706536,0.0009497906,0.003126006,0.002216532,0.002011712,0.003965814],"category_scores_gemma":[0.01987546,0.0008447961,0.002230196,0.002360844,0.0007333153,0.006504217,0.001273844,0.002765212,0.002215315],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001581425,"about_ca_system_score_gemma":0.001638766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008427418,"about_ca_topic_score_gemma":0.0124046,"domain_scores_codex":[0.9978505,0.0008852026,0.0002520218,0.0004015041,0.000478549,0.000132144],"domain_scores_gemma":[0.9836922,0.01264315,0.000625264,0.00110482,0.001675106,0.0002594715],"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":[0.001527261,0.0008296387,0.01052381,0.000787719,0.0006222136,0.0005094036,0.0007563306,0.415453,0.01120002,0.02930829,0.01244904,0.5160333],"study_design_scores_gemma":[0.0000331689,0.00006438082,0.0004826155,0.00002547016,0.000115352,0.00008082993,0.00004654114,0.9729768,0.001947454,0.02276626,0.001427531,0.00003371894],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04821385,0.0007381566,0.9417662,0.0009040574,0.0001684053,0.0001645625,0.001687367,0.00428161,0.002075834],"genre_scores_gemma":[0.6081293,0.0005258964,0.3834569,0.0002703084,0.0002089604,0.0003669549,0.002624501,0.0007805098,0.003636634],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008427418,"threshold_uncertainty_score":0.02264994,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2118013824","doi":"10.1007/s10115-010-0367-z","title":"Statistical semantics for enhancing document clustering","year":2010,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":35,"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":"Semantic similarity; Computer science; Cluster analysis; Document clustering; Similarity (geometry); Vector space model; Explicit semantic analysis; Semantics (computer science); Representation (politics); Benchmark (surveying); Context (archaeology); Artificial intelligence; Information retrieval; Distributional semantics; Data mining; Natural language processing; Semantic computing; Semantic technology; Semantic Web","authors":[{"name":"Ahmed Farahat","is_ca":true},{"name":"Mohamed S. Kamel","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01213181996842227,"gpt":0.3032534578081119,"spread":0.2911216378396896,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002960821,0.0006463801,0.001161857,0.004362243,0.0008966718,0.002245253,0.001252349,0.001040608,0.001609927],"category_scores_gemma":[0.01577654,0.0004870039,0.001138414,0.005239945,0.001095302,0.005560641,0.001895596,0.001319833,0.0008123124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000973848,"about_ca_system_score_gemma":0.00143989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001326323,"about_ca_topic_score_gemma":0.002523746,"domain_scores_codex":[0.997378,0.0008933295,0.0002572096,0.000406694,0.0009632908,0.0001015251],"domain_scores_gemma":[0.9923922,0.00365748,0.0005811307,0.001400499,0.001771549,0.0001970906],"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":[0.0005998366,0.0003936489,0.00399971,0.000673744,0.0002233608,0.000157171,0.0005300961,0.07697785,0.02591924,0.2264632,0.006540974,0.6575211],"study_design_scores_gemma":[0.00007092633,0.0001998829,0.00166419,0.00007945563,0.0001587853,0.0003144453,0.0001980679,0.6094691,0.01632606,0.3584957,0.01295867,0.00006491266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01615167,0.0005797925,0.980714,0.0002327464,0.0000763006,0.0000451606,0.0002453669,0.0009297875,0.001025146],"genre_scores_gemma":[0.3014457,0.0009334723,0.6934118,0.0002364247,0.0002657629,0.0001867938,0.001332327,0.0003702497,0.001817442],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004362243,"threshold_uncertainty_score":0.0156585,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1991959600","doi":"10.1007/s10115-008-0145-3","title":"Resolution-based outlier factor: detecting the top-n most outlying data points in engineering data","year":2008,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":35,"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":"Outlier; Anomaly detection; Data mining; Computer science; Identification (biology); Local outlier factor; Rank (graph theory); Nonparametric statistics; Domain (mathematical analysis); Artificial intelligence; Mathematics; Statistics","authors":[{"name":"Hongqin Fan","is_ca":false},{"name":"Osmar R. Zai͏̈ane","is_ca":true},{"name":"Andrew Foss","is_ca":true},{"name":"Junfeng Wu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05467301865057345,"gpt":0.2702243801443387,"spread":0.2155513614937653,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002886757,0.001127344,0.001996749,0.005049569,0.001003877,0.001458451,0.00224532,0.001549629,0.0007261144],"category_scores_gemma":[0.01508348,0.0003945634,0.001128133,0.004167891,0.0008650235,0.001979316,0.001333132,0.001341523,0.0006459638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003716892,"about_ca_system_score_gemma":0.001103068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003811692,"about_ca_topic_score_gemma":0.003451219,"domain_scores_codex":[0.9970118,0.0003314115,0.0002755453,0.0006600805,0.001411098,0.0003101087],"domain_scores_gemma":[0.9953213,0.001774671,0.0008881156,0.0005616969,0.001232677,0.0002215806],"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":[0.001445135,0.0006498828,0.07668196,0.0004957546,0.0004980443,0.0009299132,0.0005803658,0.0763917,0.05055019,0.004093175,0.007899131,0.7797847],"study_design_scores_gemma":[0.00007340296,0.0002596964,0.01967377,0.0000362633,0.0001985289,0.00113597,0.0003088279,0.9387363,0.03105311,0.005598107,0.00285415,0.00007188108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1788077,0.000796887,0.8163911,0.0003026839,0.0001195198,0.0001599761,0.0005144753,0.002226069,0.0006815177],"genre_scores_gemma":[0.5551718,0.0002848117,0.4421778,0.00007637945,0.0001177781,0.00007122981,0.001389892,0.000133151,0.0005769672],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005049569,"threshold_uncertainty_score":0.01526684,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W632121358","doi":"10.1007/s10115-015-0851-6","title":"On strategies for building effective ensembles of relative clustering validity criteria","year":2015,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Cluster analysis; Computer science; Measure (data warehouse); Data mining; Set (abstract data type); Partition (number theory); Complementarity (molecular biology); Consensus clustering; Stability (learning theory); Variety (cybernetics); Machine learning; Artificial intelligence; Mathematics; Fuzzy clustering; CURE data clustering algorithm","authors":[{"name":"Pablo Andretta Jaskowiak","is_ca":false},{"name":"Davoud Moulavi","is_ca":true},{"name":"Antonio Carlos Furtado","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":0.06181771647573652,"gpt":0.357017140401257,"spread":0.2951994239255205,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01329189,0.001576327,0.002427132,0.00390209,0.001749407,0.00358481,0.004255763,0.002844117,0.00395895],"category_scores_gemma":[0.06355019,0.00117805,0.001705107,0.003577403,0.002044486,0.006333203,0.00576961,0.003459866,0.001057818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001726141,"about_ca_system_score_gemma":0.002640627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00435276,"about_ca_topic_score_gemma":0.006689926,"domain_scores_codex":[0.9912582,0.004617597,0.0006788023,0.0009492334,0.002085842,0.0004102742],"domain_scores_gemma":[0.9621264,0.02761735,0.001143959,0.003088451,0.005495066,0.0005287752],"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":[0.000207627,0.0003177333,0.002727721,0.0003312458,0.0003216684,0.0001195261,0.0007637503,0.3698556,0.00376267,0.186913,0.005755852,0.4289237],"study_design_scores_gemma":[0.00002515719,0.00007503813,0.0003319236,0.00007078653,0.00004981532,0.00005339753,0.0001299178,0.8874778,0.001808409,0.1084192,0.001529638,0.00002886956],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004002503,0.0001425275,0.9947311,0.0001097637,0.00001648281,0.00007049635,0.00003377578,0.0001381584,0.0007552388],"genre_scores_gemma":[0.1128389,0.000204695,0.8846509,0.0001796808,0.00008452885,0.0004177625,0.0003489716,0.0002080956,0.00106652],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01329189,"threshold_uncertainty_score":0.07029504,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1991278297","doi":"10.1007/pl00011645","title":"Intentions in the Coordinated Generation of Graphics and Text from Tabular Data","year":2000,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Graphics; Computer science; Wizard; Chart; Set (abstract data type); Table (database); Declaration; ASCII; Computer graphics (images); Information retrieval; Focus (optics); Plotter; Programming language; Data mining; World Wide Web","authors":[{"name":"Massimo Fasciano","is_ca":false},{"name":"Guy Lapalme","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05029146975346122,"gpt":0.2904555233044631,"spread":0.2401640535510019,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006883529,0.0006061347,0.0005239013,0.001479825,0.001370883,0.007866529,0.001777236,0.001977116,0.007870173],"category_scores_gemma":[0.04182001,0.001336214,0.0009829369,0.001579105,0.002781905,0.005471137,0.004609504,0.002099295,0.003291975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006529426,"about_ca_system_score_gemma":0.0018405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005553439,"about_ca_topic_score_gemma":0.004345655,"domain_scores_codex":[0.9938005,0.003081115,0.0003491043,0.0008311779,0.001534124,0.0004040471],"domain_scores_gemma":[0.9822302,0.01023974,0.001279975,0.00255845,0.002943674,0.0007479931],"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":[0.002566313,0.0005049019,0.01872144,0.0008685074,0.0001553446,0.001160684,0.03836594,0.02243179,0.06619407,0.3926397,0.02057676,0.4358145],"study_design_scores_gemma":[0.0003781844,0.0005618103,0.009250482,0.0003852199,0.0002869947,0.0004728955,0.01465519,0.5111555,0.07576867,0.3343944,0.05236094,0.0003297277],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08037866,0.0001738734,0.8928779,0.001150226,0.0001552312,0.0002950055,0.0002868807,0.004877598,0.01980455],"genre_scores_gemma":[0.4967621,0.0002098459,0.4907249,0.0003865707,0.00004742288,0.0003835165,0.00086567,0.002196723,0.00842331],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007870173,"threshold_uncertainty_score":0.03640401,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2043301550","doi":"10.1007/s10115-003-0101-1","title":"Data Mining: How Research Meets Practical Development?","year":2003,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Data science; Computer science; Data mining; Panel discussion; Development (topology); Business","authors":[{"name":"Xindong Wu","is_ca":false},{"name":"Philip S. Yu","is_ca":false},{"name":"Gregory Piatetsky-Shapiro","is_ca":false},{"name":"Nick Cercone","is_ca":true},{"name":"Tzu-Yu Lin","is_ca":false},{"name":"Kotagiri Ramamohanarao","is_ca":false},{"name":"Benjamin W. Wah","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1924554065942589,"gpt":0.3901175826814103,"spread":0.1976621760871514,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1347235,0.003167832,0.005327099,0.008756171,0.003780332,0.02202194,0.007917255,0.01532635,0.01066808],"category_scores_gemma":[0.2447363,0.002357063,0.00146199,0.00889241,0.03702589,0.07013687,0.01091011,0.01548575,0.005318611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005938333,"about_ca_system_score_gemma":0.02502849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003501137,"about_ca_topic_score_gemma":0.002666916,"domain_scores_codex":[0.9474573,0.03334611,0.004461061,0.002660342,0.01101732,0.001057911],"domain_scores_gemma":[0.5589017,0.3357632,0.01010663,0.02942055,0.05494438,0.01086364],"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":[0.0001927551,0.0003940949,0.004852294,0.004807663,0.0002354541,0.0002277237,0.001162152,0.001505003,0.0004100919,0.5731629,0.133825,0.2792249],"study_design_scores_gemma":[0.0001404143,0.0001254681,0.0009150158,0.004077683,0.0001127128,0.000349997,0.003174749,0.004298895,0.0004595472,0.8291125,0.1571601,0.00007293135],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.001960856,0.1511461,0.08948012,0.7347131,0.005779936,0.0002055743,0.0003033827,0.0005099943,0.01590085],"genre_scores_gemma":[0.1670647,0.3342386,0.3697121,0.08712785,0.02937904,0.001502189,0.0008729019,0.0007580621,0.009344655],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1347235,"threshold_uncertainty_score":0.7124944,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2050175694","doi":"10.1007/s10115-012-0527-4","title":"A new approach for maximizing bichromatic reverse nearest neighbor search","year":2012,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":33,"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":"National Natural Science Foundation of China; National Science Foundation","keywords":"k-nearest neighbors algorithm; Best bin first; Nearest neighbor search; Large margin nearest neighbor; Nearest-neighbor chain algorithm; Computer science; Nearest neighbor graph; Metric space; Metric (unit); Fixed-radius near neighbors; Algorithm; Space (punctuation); Mathematics; Data mining; Artificial intelligence; Discrete mathematics; Cluster analysis","authors":[{"name":"Yubao Liu","is_ca":false},{"name":"Raymond Chi-Wing Wong","is_ca":false},{"name":"Ke Wang","is_ca":true},{"name":"Zhijie Li","is_ca":false},{"name":"Cheng Chen","is_ca":false},{"name":"Zhitong Chen","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03640221889120267,"gpt":0.2651786546214523,"spread":0.2287764357302497,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002978646,0.001176783,0.001841746,0.002090102,0.0009710832,0.001483731,0.00370422,0.00171887,0.003589894],"category_scores_gemma":[0.009467943,0.0007315173,0.0008486923,0.002613329,0.000979381,0.00306077,0.00315451,0.001633478,0.001395549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009600619,"about_ca_system_score_gemma":0.001587944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002810193,"about_ca_topic_score_gemma":0.005510249,"domain_scores_codex":[0.9969015,0.001004565,0.0001759183,0.0004786539,0.001254892,0.0001844934],"domain_scores_gemma":[0.9973215,0.0008063291,0.0001754953,0.0006057321,0.0009966777,0.00009427691],"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":[0.0004042449,0.0002763226,0.00158168,0.0004139434,0.0001499922,0.0001160941,0.00023406,0.2356356,0.01911618,0.1319232,0.01184392,0.5983048],"study_design_scores_gemma":[0.00002593849,0.00006748514,0.0002767387,0.00002345108,0.00003541843,0.0001692446,0.00003399861,0.9572448,0.004143518,0.0326926,0.005260457,0.00002646198],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002720377,0.0002165323,0.9951918,0.00008013338,0.00004214847,0.00003721796,0.00003434721,0.0001966922,0.001480764],"genre_scores_gemma":[0.07147072,0.0002901081,0.9240741,0.0001671926,0.00009664541,0.0001415077,0.0001821685,0.0002052339,0.003372228],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00370422,"threshold_uncertainty_score":0.01575279,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1971324060","doi":"10.1007/pl00011676","title":"Parallel and Sequential Algorithms for Data Mining Using Inductive Logic","year":2001,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"IBM (Canada); Queen's University","funders":"","keywords":"Computer science; Inductive logic programming; Algorithm; Data mining; Artificial intelligence","authors":[{"name":"David B. Skillicorn","is_ca":true},{"name":"Yu Wang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09966565189006675,"gpt":0.3377073262655644,"spread":0.2380416743754977,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006658421,0.001257689,0.001628465,0.003292845,0.001895482,0.002954239,0.003302695,0.001157355,0.007881403],"category_scores_gemma":[0.0197977,0.001118846,0.002203899,0.004046678,0.002299009,0.006034729,0.003203933,0.003043554,0.002506607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001607419,"about_ca_system_score_gemma":0.003308904,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002989838,"about_ca_topic_score_gemma":0.005381451,"domain_scores_codex":[0.9953488,0.001401923,0.0004384223,0.0009614877,0.001609272,0.0002401158],"domain_scores_gemma":[0.9850864,0.01046018,0.0004107839,0.002330694,0.001497497,0.0002144246],"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":[0.0005970395,0.0003777491,0.002591735,0.0005831955,0.0002699584,0.0001737859,0.0003038859,0.07629567,0.003475694,0.1613281,0.008006992,0.7459961],"study_design_scores_gemma":[0.0001356523,0.00009630648,0.0004027607,0.00005178773,0.0001251695,0.0002285492,0.00007631966,0.439181,0.004065546,0.5461702,0.009438873,0.00002777494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002970175,0.0003751414,0.9938308,0.000234148,0.00005884591,0.0001081541,0.00008015616,0.0007683515,0.001574165],"genre_scores_gemma":[0.0631979,0.0005197497,0.9312381,0.0002214606,0.0002381226,0.0003741758,0.0005130369,0.0001878922,0.003509694],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007881403,"threshold_uncertainty_score":0.03521353,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2127392028","doi":"10.1007/s10115-010-0298-8","title":"User-centric query refinement and processing using granularity-based strategies","year":2010,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Granularity; Unification; Ontology; Context (archaeology); Information retrieval; Data mining; Data science","authors":[{"name":"Yi Zeng","is_ca":false},{"name":"Ning Zhong","is_ca":false},{"name":"Yan Wang","is_ca":false},{"name":"Yulin Qin","is_ca":false},{"name":"Zhisheng Huang","is_ca":false},{"name":"Haiyan Zhou","is_ca":false},{"name":"Yiyu Yao","is_ca":true},{"name":"Frank van Harmelen","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01529202025100286,"gpt":0.2504373584232618,"spread":0.2351453381722589,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009965888,0.001092042,0.002279399,0.003309837,0.001447669,0.00475855,0.002795878,0.001406615,0.003901547],"category_scores_gemma":[0.02447969,0.0009549882,0.001431385,0.003226784,0.001368255,0.005482695,0.004261415,0.001938954,0.000996827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001204229,"about_ca_system_score_gemma":0.002205497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005038487,"about_ca_topic_score_gemma":0.005476571,"domain_scores_codex":[0.9876862,0.004613327,0.001101551,0.001324797,0.004457181,0.0008169746],"domain_scores_gemma":[0.980877,0.009472259,0.0008688848,0.005647324,0.002643204,0.0004912899],"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":[0.003588033,0.0006866741,0.008438812,0.0009386907,0.0007454907,0.0007533825,0.006192423,0.04379813,0.1399239,0.1049119,0.01272658,0.677296],"study_design_scores_gemma":[0.0003109262,0.0004665208,0.00338868,0.0001453276,0.0006251562,0.0009562934,0.002244154,0.7698781,0.114896,0.08495924,0.02189633,0.0002331934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02527218,0.0003986423,0.9685348,0.0003617057,0.00003478226,0.000253701,0.0001078369,0.002785395,0.002250985],"genre_scores_gemma":[0.4317797,0.0002670707,0.5648986,0.0002452403,0.00006408945,0.0002028337,0.0003860235,0.0003752569,0.001781303],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009965888,"threshold_uncertainty_score":0.05270523,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2031366103","doi":"10.1007/s10115-002-8192-7","title":"Knowledge Discovery Through Self-Organizing Maps: Data Visualization and Query Processing","year":2002,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":29,"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":"Computer science; Knowledge extraction; Visualization; Data mining; Set (abstract data type); Information retrieval; Heuristic; Premise; Data visualization; Information visualization; Data science; Artificial intelligence","authors":[{"name":"Shouhong Wang","is_ca":false},{"name":"Hai Wang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04714598115889816,"gpt":0.3028134019006688,"spread":0.2556674207417706,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003234598,0.0008284166,0.0009413622,0.00608657,0.001046246,0.006537509,0.001265429,0.001090137,0.003126432],"category_scores_gemma":[0.01111563,0.0005867595,0.0008446951,0.007684327,0.001112437,0.005718411,0.002404532,0.001013162,0.0008773102],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009627545,"about_ca_system_score_gemma":0.001888764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00485451,"about_ca_topic_score_gemma":0.004842831,"domain_scores_codex":[0.9979317,0.0007632367,0.0001245036,0.0002532849,0.0008172108,0.0001100823],"domain_scores_gemma":[0.9951494,0.002845012,0.000278793,0.0007516456,0.0007719217,0.0002032165],"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":[0.0005752888,0.0003844813,0.007883566,0.001133147,0.0003294168,0.0003587412,0.003068978,0.04686737,0.01023592,0.1034315,0.02637996,0.7993516],"study_design_scores_gemma":[0.00008294633,0.0000982123,0.003520109,0.0001356909,0.0001903307,0.0004154201,0.00184674,0.6693265,0.03077017,0.2531922,0.04029699,0.000124786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03805707,0.002284454,0.9440732,0.001755565,0.0001329127,0.0001755873,0.001265947,0.006840509,0.0054146],"genre_scores_gemma":[0.365652,0.002379931,0.627491,0.0001520131,0.0001161811,0.0002477629,0.001324672,0.0005537653,0.002082688],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006537509,"threshold_uncertainty_score":0.01710635,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2017760966","doi":"10.1007/s10115-009-0214-2","title":"Fuzzy clustering-based discretization for gene expression classification","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Artificial intelligence; Classifier (UML); Computer science; Data mining; Fuzzy logic; Machine learning; Cluster analysis; Fuzzy classification; Pattern recognition (psychology); Association rule learning; Margin classifier; Support vector machine; Fuzzy rule; Fuzzy set; Feature vector; Fuzzy clustering","authors":[{"name":"Keivan Kianmehr","is_ca":true},{"name":"Mohammed Alshalalfa","is_ca":true},{"name":"Reda Alhajj","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01610687294180848,"gpt":0.269217612532778,"spread":0.2531107395909696,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001004516,0.0003106911,0.001107269,0.001039366,0.0005827962,0.0009716538,0.001024164,0.0005994707,0.001314112],"category_scores_gemma":[0.002437877,0.0002634635,0.0008008861,0.001868859,0.0004349424,0.0006884551,0.0004459739,0.0008604325,0.0003776046],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001184026,"about_ca_system_score_gemma":0.0008601304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01041095,"about_ca_topic_score_gemma":0.008158467,"domain_scores_codex":[0.9993494,0.0001680007,0.00006220155,0.000113631,0.0002529636,0.00005383573],"domain_scores_gemma":[0.9989666,0.0005651909,0.00004628855,0.0001308098,0.0002610674,0.00003005448],"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":[0.0003461016,0.0001257129,0.001392592,0.0002156651,0.0001357227,0.00008971366,0.0002288054,0.4824861,0.01570649,0.02444584,0.003372908,0.4714544],"study_design_scores_gemma":[0.000009240508,0.00001729934,0.0004247042,0.0000121483,0.0000145454,0.00002704861,0.00001976408,0.9871191,0.001792228,0.009736509,0.000817002,0.00001044125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01633378,0.0003279563,0.9815709,0.00007851292,0.00003842515,0.00004028143,0.0002357191,0.0003241039,0.001050355],"genre_scores_gemma":[0.336327,0.0003465824,0.6601575,0.00007892359,0.00004535149,0.0001867621,0.0009506688,0.00006365228,0.001843527],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01041095,"threshold_uncertainty_score":0.02070075,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2034485749","doi":"10.1007/s10115-008-0190-y","title":"Effectiveness of NAQ-tree as index structure for similarity search in high-dimensional metric space","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Nearest neighbor search; Metric space; Tree (set theory); Tree traversal; Mathematics; Computer science; Cover tree; Data mining; Metric (unit); Disjoint sets; Algorithm; Pattern recognition (psychology); Artificial intelligence; Combinatorics; Cluster analysis; Discrete mathematics","authors":[{"name":"Ming Zhang","is_ca":true},{"name":"Reda Alhajj","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.009903275750799953,"gpt":0.2899844482842681,"spread":0.2800811725334681,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003052235,0.0004066774,0.00201349,0.003415406,0.001095737,0.00200328,0.001547606,0.001620752,0.002852324],"category_scores_gemma":[0.02069985,0.0002379098,0.000461464,0.005180234,0.0006495985,0.005933608,0.001373965,0.0005739086,0.001056812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001053498,"about_ca_system_score_gemma":0.00216285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007471449,"about_ca_topic_score_gemma":0.005127252,"domain_scores_codex":[0.9955676,0.001550411,0.0003298249,0.0003295595,0.002009417,0.0002132068],"domain_scores_gemma":[0.9883754,0.006844673,0.0004919906,0.001538946,0.002364268,0.0003846915],"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":[0.0028984,0.001001153,0.01016796,0.00111274,0.0002438095,0.000241305,0.0005847433,0.09116068,0.02041942,0.05022824,0.02492069,0.7970208],"study_design_scores_gemma":[0.0002299957,0.0007612457,0.002822898,0.00006342991,0.0001202944,0.0006471159,0.0002987277,0.9476881,0.007318309,0.03331283,0.006682797,0.00005433485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4494004,0.01656079,0.5051788,0.001955615,0.0005977934,0.0004153872,0.002581719,0.003823934,0.0194855],"genre_scores_gemma":[0.7393671,0.002310429,0.2524615,0.0002079238,0.0001910659,0.0001423542,0.002275547,0.0001695504,0.002874598],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007471449,"threshold_uncertainty_score":0.01614195,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2292231671","doi":"10.1007/s10115-015-0906-8","title":"Managing dimensionality in data privacy anonymization","year":2015,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Curse of dimensionality; Computer science; Data mining; Closeness; Process (computing); Cluster analysis; Variety (cybernetics); Machine learning; Mathematics; Artificial intelligence","authors":[{"name":"Hessam Zakerzadeh","is_ca":true},{"name":"Charų C. Aggarwal","is_ca":false},{"name":"Ken Barker","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07068525535148379,"gpt":0.3013851363574971,"spread":0.2306998810060134,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01564143,0.000640392,0.002217445,0.002186804,0.004085601,0.009264796,0.002298712,0.002609704,0.001630698],"category_scores_gemma":[0.06057881,0.0009735006,0.001506044,0.004840464,0.007638927,0.02364261,0.01131511,0.005955392,0.0004783524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002830898,"about_ca_system_score_gemma":0.004192434,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001435431,"about_ca_topic_score_gemma":0.001185717,"domain_scores_codex":[0.9721124,0.01505653,0.001847505,0.002780304,0.006862339,0.001340824],"domain_scores_gemma":[0.9323665,0.0266008,0.003880511,0.03289529,0.003467994,0.0007889242],"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":[0.0002902078,0.0001481972,0.002821769,0.0002662113,0.0001410163,0.0002136536,0.001487285,0.05890441,0.001943897,0.8255437,0.005608246,0.1026314],"study_design_scores_gemma":[0.00002289621,0.00003771003,0.000400183,0.00007066378,0.00006223562,0.0002737582,0.0006079162,0.1403836,0.00473957,0.842837,0.01052421,0.00004020706],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02792364,0.001589029,0.956005,0.007636402,0.000223205,0.0001374794,0.0003700867,0.0003257009,0.005789569],"genre_scores_gemma":[0.7464541,0.002123264,0.2458334,0.0009601437,0.0004976075,0.0002221665,0.0004610342,0.0001123453,0.003336011],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01564143,"threshold_uncertainty_score":0.08272082,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2081471536","doi":"10.1007/s10115-007-0097-z","title":"A compact multi-resolution index for variable length queries in time series databases","year":2007,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Search engine indexing; Scalability; Computer science; Ranging; Series (stratigraphy); Piecewise; Data mining; Algorithm; Univariate; Variable (mathematics); Database; Mathematics; Artificial intelligence; Multivariate statistics; Machine learning","authors":[{"name":"Srividya Kadiyala","is_ca":true},{"name":"Nematollaah Shiri","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02291554355587029,"gpt":0.2587146255682038,"spread":0.2357990820123336,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002925488,0.0007970466,0.003163126,0.004040785,0.001126011,0.004679446,0.002693051,0.001316308,0.00505406],"category_scores_gemma":[0.01882737,0.0007156507,0.0006328709,0.006486262,0.0007737616,0.0081626,0.003787057,0.001765603,0.003167021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008617378,"about_ca_system_score_gemma":0.001585307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001576939,"about_ca_topic_score_gemma":0.001495789,"domain_scores_codex":[0.9963257,0.0006120293,0.0007404373,0.0004168838,0.001662826,0.0002421543],"domain_scores_gemma":[0.9892135,0.003981391,0.000716152,0.003871136,0.001732763,0.0004850283],"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":[0.002457277,0.0005386628,0.00263994,0.0006987418,0.0001720631,0.000557343,0.0005687116,0.03872767,0.03613842,0.05531668,0.04282402,0.8193604],"study_design_scores_gemma":[0.0003862927,0.0005872097,0.001398157,0.0001389935,0.0001504827,0.001387539,0.0002827327,0.8526937,0.02240906,0.08033068,0.04006733,0.0001678513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02832227,0.003605576,0.9563262,0.0006449189,0.0004151489,0.000231839,0.002171273,0.006049642,0.002233131],"genre_scores_gemma":[0.2627348,0.0017429,0.7234119,0.0004443427,0.0006852656,0.0003927104,0.005991371,0.000675197,0.003921642],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00505406,"threshold_uncertainty_score":0.01690751,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3096565974","doi":"10.1007/s10115-020-01521-9","title":"CANE: community-aware network embedding via adversarial training","year":2020,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Novelis (Canada)","funders":"","keywords":"Computer science; Node (physics); Discriminative model; Pairwise comparison; Embedding; Adversarial system; Machine learning; Representation (politics); Feature learning; Data mining; Artificial intelligence; Community structure; Theoretical computer science; Mathematics","authors":[{"name":"Jia Wang","is_ca":false},{"name":"Jiannong Cao","is_ca":false},{"name":"Wei Li","is_ca":false},{"name":"Senzhang Wang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0314213780843983,"gpt":0.2559193188299602,"spread":0.2244979407455619,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001344089,0.001875419,0.001387966,0.001333416,0.0008016598,0.0009579289,0.003555262,0.003343785,0.009324199],"category_scores_gemma":[0.006385839,0.000754594,0.001041911,0.001303993,0.001070118,0.00280823,0.003476032,0.004111093,0.003838959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008890697,"about_ca_system_score_gemma":0.001094218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00683907,"about_ca_topic_score_gemma":0.01355735,"domain_scores_codex":[0.9992988,0.0002476155,0.00001767821,0.0001844413,0.0001695189,0.00008192426],"domain_scores_gemma":[0.9978848,0.001017063,0.0001026612,0.000571942,0.0002824718,0.0001409462],"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":[0.0003759533,0.0003687874,0.0008961227,0.0002804911,0.0002292055,0.0002497818,0.0001178687,0.6152396,0.004554525,0.03283675,0.05879717,0.2860537],"study_design_scores_gemma":[0.0000155944,0.00001869482,0.00004987378,0.00001030606,0.000007528077,0.00002817543,0.000008088256,0.9857538,0.0006550082,0.01185607,0.001590587,0.000006298671],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008892289,0.0004938703,0.9784291,0.0006705748,0.000296603,0.0001772742,0.0008907954,0.006499246,0.003650283],"genre_scores_gemma":[0.3871111,0.0006046887,0.576538,0.001300102,0.0003367198,0.0007096621,0.006148761,0.002013223,0.02523783],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009324199,"threshold_uncertainty_score":0.03119254,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2081778498","doi":"10.1007/s10115-008-0188-5","title":"Protecting buying agents in e-marketplaces by direct experience trust modelling","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Blockchain Technology Applications and Security","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Quality (philosophy); Context (archaeology); Computer science; Trustworthiness; Value (mathematics); Business; Risk analysis (engineering); Marketing; Internet privacy; Computer security; Microeconomics; Economics","authors":[{"name":"Thomas Tran","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01795719709441475,"gpt":0.2543770988064091,"spread":0.2364199017119944,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046418,0.0005139509,0.0008642586,0.0005799021,0.0007937488,0.003139633,0.001668167,0.002177326,0.004529694],"category_scores_gemma":[0.02323419,0.0006221807,0.0007772941,0.0006243301,0.00249228,0.009737631,0.002925179,0.001770378,0.0006050025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001251984,"about_ca_system_score_gemma":0.001405891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003757725,"about_ca_topic_score_gemma":0.002803311,"domain_scores_codex":[0.9962199,0.001877709,0.0002455891,0.0003798998,0.0007951724,0.0004816696],"domain_scores_gemma":[0.9805241,0.0115057,0.001776716,0.003801469,0.00182272,0.0005693056],"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":[0.0007516601,0.0002466136,0.004504094,0.0001866768,0.0001103405,0.0004803752,0.001403224,0.5627456,0.003578002,0.3770983,0.00124158,0.04765359],"study_design_scores_gemma":[0.0000343969,0.00007746613,0.0002942012,0.00001686756,0.00002180357,0.00005428723,0.0001541586,0.866014,0.001104838,0.1313768,0.000830422,0.00002086412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1781613,0.0001729294,0.8079571,0.0009348687,0.00004382195,0.0001287045,0.00008159372,0.0002819743,0.01223769],"genre_scores_gemma":[0.9824211,0.00006056861,0.01467032,0.00003087118,0.000009473993,0.00003664679,0.00003410759,0.00001731731,0.002719495],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0046418,"threshold_uncertainty_score":0.02454847,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2529045002","doi":"10.1007/s10115-016-0998-9","title":"Finding multiple stable clusterings","year":2016,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":23,"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":"Office of Naval Research; National Science Foundation","keywords":"Cluster analysis; Computer science; Data mining; Constrained clustering; Clustering high-dimensional data; Spectral clustering; Fuzzy clustering; Correlation clustering; Consensus clustering; Partition (number theory); CURE data clustering algorithm; Stability (learning theory); Machine learning; Artificial intelligence; Mathematics","authors":[{"name":"Juhua Hu","is_ca":true},{"name":"Qi Qian","is_ca":false},{"name":"Jian Pei","is_ca":true},{"name":"Rong Jin","is_ca":false},{"name":"Shenghuo Zhu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02254849331534967,"gpt":0.2736265916603705,"spread":0.2510780983450208,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002512912,0.001375433,0.002053639,0.005706573,0.002981475,0.003087394,0.003752621,0.002941398,0.006927431],"category_scores_gemma":[0.02120949,0.001615843,0.002482848,0.004445926,0.001546869,0.004206941,0.003524964,0.00195933,0.002490098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001496785,"about_ca_system_score_gemma":0.001204108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001993116,"about_ca_topic_score_gemma":0.003676966,"domain_scores_codex":[0.9975905,0.0004935985,0.0001660715,0.0009756435,0.0005511167,0.0002231256],"domain_scores_gemma":[0.9901957,0.004585199,0.0008073159,0.001748061,0.002191603,0.0004720765],"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":[0.001998094,0.0004292422,0.01437215,0.001176912,0.001545148,0.001001504,0.001648919,0.2389616,0.03605173,0.1283021,0.0234632,0.5510494],"study_design_scores_gemma":[0.0001490798,0.0002196445,0.003276098,0.00006886735,0.00025073,0.0005280762,0.0007723849,0.8088738,0.00887589,0.1720855,0.004813977,0.00008601944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09634908,0.0008335551,0.8959324,0.0006974693,0.0001546099,0.0002480769,0.0004746266,0.0008234699,0.004486712],"genre_scores_gemma":[0.5212867,0.000399002,0.4676853,0.000192489,0.0001568616,0.0003221954,0.002068403,0.0004952815,0.00739385],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006927431,"threshold_uncertainty_score":0.02317458,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2017217509","doi":"10.1007/s10115-011-0397-1","title":"Scalable clustering methods for the name disambiguation problem","year":2011,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"University of Illinois at Urbana-Champaign; University of British Columbia; Advanced Digital Sciences Center; Pennsylvania State University; National Science Foundation","keywords":"Cluster analysis; Computer science; Scalability; Artificial intelligence; Natural language processing; Entity linking; Data mining; Database","authors":[{"name":"Byung-Won On","is_ca":false},{"name":"Ingyu Lee","is_ca":false},{"name":"Dongwon Lee","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2257578615555757,"gpt":0.4321284819533481,"spread":0.2063706203977725,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004422265,0.001548225,0.002923498,0.003684261,0.00202741,0.002369818,0.004323401,0.002242126,0.003866598],"category_scores_gemma":[0.0160442,0.001087826,0.001705097,0.006425919,0.001191119,0.005085086,0.00421585,0.002713499,0.001422555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001728211,"about_ca_system_score_gemma":0.003514505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01063374,"about_ca_topic_score_gemma":0.01596277,"domain_scores_codex":[0.9958887,0.001417325,0.0003206194,0.0009394631,0.001154528,0.0002793235],"domain_scores_gemma":[0.9902293,0.005135311,0.000702271,0.002248099,0.001363667,0.0003213358],"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":[0.0004587182,0.0003763997,0.001870492,0.0004820086,0.0004074992,0.0001243349,0.0002579805,0.3377997,0.004516144,0.04367876,0.02886019,0.5811678],"study_design_scores_gemma":[0.0000804997,0.00003216534,0.000441965,0.00002021127,0.00004263174,0.0000474908,0.00005459541,0.9029911,0.0008989739,0.09293938,0.002428419,0.00002256098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009259845,0.001336226,0.9852647,0.000619024,0.0001600165,0.00009745931,0.0005225118,0.001625756,0.001114329],"genre_scores_gemma":[0.1552874,0.0009935036,0.8358585,0.0003072194,0.0005553812,0.0003063303,0.003019715,0.0005716212,0.003100267],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01063374,"threshold_uncertainty_score":0.02338743,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2906685695","doi":"10.1007/s10115-018-1278-7","title":"Combining semantic and term frequency similarities for text clustering","year":2019,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Natural Sciences and Engineering Research Council of Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Cluster analysis; Semantic similarity; Computer science; Document clustering; Similarity (geometry); Measure (data warehouse); Information retrieval; Similarity measure; Natural language processing; Term (time); Artificial intelligence; Word (group theory); Data mining; Mathematics","authors":[{"name":"Victor Hugo Andrade Soares","is_ca":false},{"name":"Ricardo J. G. B. Campello","is_ca":false},{"name":"Seyednaser Nourashrafeddin","is_ca":true},{"name":"Evangelos Milios","is_ca":true},{"name":"Murilo Coelho Naldi","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01570786528100131,"gpt":0.2428618567949933,"spread":0.227153991513992,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00211578,0.0006341282,0.001262585,0.01437788,0.001130186,0.002137496,0.001045712,0.001225269,0.002666824],"category_scores_gemma":[0.009617088,0.0002898363,0.001536634,0.01171675,0.0005454635,0.003095946,0.00118344,0.0006619652,0.00218431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006573049,"about_ca_system_score_gemma":0.001343273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003248692,"about_ca_topic_score_gemma":0.005441156,"domain_scores_codex":[0.9970804,0.0005349146,0.0003549845,0.0005263233,0.001317149,0.0001862606],"domain_scores_gemma":[0.9957747,0.001754288,0.0003476068,0.0004820694,0.001505379,0.0001360321],"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":[0.000933483,0.0004256205,0.01097661,0.000657147,0.0006392734,0.0001525617,0.0003585493,0.01542342,0.03027804,0.007473375,0.006437035,0.9262449],"study_design_scores_gemma":[0.0002191065,0.0006747313,0.03179697,0.0002195308,0.001267676,0.001348452,0.0008799106,0.8438234,0.03290542,0.06828828,0.01831172,0.0002647747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1238826,0.003607151,0.8606651,0.0003190131,0.0004058735,0.0003209196,0.002177426,0.003327159,0.005294564],"genre_scores_gemma":[0.5690671,0.001371774,0.418795,0.0001126642,0.0006654824,0.0003299161,0.005411552,0.0004216472,0.003824939],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01437788,"threshold_uncertainty_score":0.01118946,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2121566986","doi":"10.1007/s10115-008-0179-6","title":"PADS: a simple yet effective pattern-aware dynamic search method for fast maximal frequent pattern mining","year":2008,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":21,"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; Executable; Data mining; Benchmark (surveying); Pattern search; Simple (philosophy); Linear subspace; Tree (set theory); Algorithm; Mathematics; Programming language","authors":[{"name":"Xinghuo Zeng","is_ca":true},{"name":"Jian Pei","is_ca":true},{"name":"Ke Wang","is_ca":true},{"name":"Jinyan Li","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01972505674650053,"gpt":0.2976702125706421,"spread":0.2779451558241415,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001031408,0.00114048,0.001669606,0.004487724,0.0007601981,0.001772317,0.002399455,0.0009681152,0.00789005],"category_scores_gemma":[0.005779328,0.0008565799,0.001042352,0.004902567,0.0004583492,0.003068113,0.002471954,0.001162372,0.003725333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003044397,"about_ca_system_score_gemma":0.001524507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001015176,"about_ca_topic_score_gemma":0.002299341,"domain_scores_codex":[0.9987141,0.0002449017,0.0001583321,0.0002562068,0.0005508912,0.0000755943],"domain_scores_gemma":[0.9978886,0.001138008,0.0001392076,0.0004538924,0.000289117,0.00009127304],"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":[0.001041709,0.0002331876,0.00268048,0.0006447144,0.0002740172,0.0003076522,0.0001306791,0.008301948,0.01563848,0.005302595,0.02852453,0.93692],"study_design_scores_gemma":[0.0008975322,0.0007380916,0.002754177,0.0001233003,0.0005138077,0.002203855,0.0003142006,0.8152127,0.04202738,0.06030845,0.07475117,0.0001553133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01438856,0.0008810688,0.9580609,0.0002512757,0.0001759569,0.0002345753,0.002067958,0.02228221,0.001657408],"genre_scores_gemma":[0.08911966,0.0004525259,0.9009691,0.0002353697,0.0001262923,0.0004458659,0.004239587,0.0007699828,0.003641618],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00789005,"threshold_uncertainty_score":0.02639484,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1981324119","doi":"10.1007/s10115-010-0292-1","title":"Architecturing large integrated complex information systems: an application to healthcare","year":2010,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":20,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Knowledge management; Enterprise architecture; Information system; Schema (genetic algorithms); Key (lock); Enterprise information system; Multitude; Data science; Enterprise integration; Health care; Architecture; Process management; Enterprise software; Business; Engineering; Computer security","authors":[{"name":"Daniel Pascot","is_ca":true},{"name":"Faouzi Bouslama","is_ca":true},{"name":"Sehl Mellouli","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03302324811347194,"gpt":0.3880023965570019,"spread":0.3549791484435299,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001748268,0.0006067802,0.0004038471,0.0006583676,0.001581868,0.003069135,0.0008364681,0.001458344,0.004006657],"category_scores_gemma":[0.005701656,0.0005807528,0.0005118616,0.001425561,0.001013775,0.00206971,0.001894874,0.0009980472,0.0007460063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009163639,"about_ca_system_score_gemma":0.002050343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00593515,"about_ca_topic_score_gemma":0.008582097,"domain_scores_codex":[0.9990548,0.0003509255,0.0000784618,0.0001469294,0.0002931511,0.00007570285],"domain_scores_gemma":[0.9963418,0.002159109,0.0002039675,0.0006107879,0.000409194,0.0002752362],"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":[0.0004039096,0.000637971,0.01284719,0.000864596,0.00009440077,0.001691744,0.005166403,0.1535731,0.0475004,0.04279849,0.009691349,0.7247305],"study_design_scores_gemma":[0.0001796976,0.0004028694,0.005921331,0.0001936149,0.0001998935,0.001580713,0.0038576,0.816568,0.03736756,0.07252799,0.06110544,0.00009525692],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2040347,0.001047303,0.7777877,0.002426147,0.000127391,0.0005329145,0.0002235209,0.004023068,0.009797285],"genre_scores_gemma":[0.2712701,0.0006417045,0.7246078,0.0001285081,0.00004109418,0.00009134896,0.0001813278,0.0001757523,0.002862471],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00593515,"threshold_uncertainty_score":0.01340359,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2016772176","doi":"10.1007/s10115-009-0279-y","title":"A knowledge encapsulation approach to ontology modularization","year":2010,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Ontology; Ontology components; Modular design; Modular programming; Encapsulation (networking); Process ontology; Upper ontology; Modularity (biology); Ontology-based data integration; Web Ontology Language; Formalism (music); Software engineering; Information retrieval; Suggested Upper Merged Ontology; Domain knowledge; Semantic Web; Programming language","authors":[{"name":"Faezeh Ensan","is_ca":true},{"name":"Weichang Du","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01550687693980566,"gpt":0.2454834538018327,"spread":0.2299765768620271,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005885118,0.0005514007,0.0007727366,0.002336682,0.001567648,0.004504972,0.00250593,0.001478753,0.00287137],"category_scores_gemma":[0.01115851,0.0009765024,0.002690608,0.002472539,0.003946451,0.0135602,0.004677565,0.003809685,0.001075758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001235336,"about_ca_system_score_gemma":0.002038163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002733333,"about_ca_topic_score_gemma":0.002693985,"domain_scores_codex":[0.9971564,0.001007358,0.000364085,0.0004143823,0.0008292595,0.0002284863],"domain_scores_gemma":[0.9932111,0.002310833,0.0003485373,0.002852504,0.001070661,0.0002063602],"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":[0.00001973834,0.00004062028,0.0002332703,0.00006898116,0.00003423815,0.00008753888,0.0008401469,0.002860924,0.001368279,0.9516941,0.002288126,0.04046404],"study_design_scores_gemma":[0.00001756005,0.00001951005,0.0002454473,0.000118936,0.0001134761,0.0001908442,0.0002132703,0.03517246,0.003671011,0.9272414,0.03295921,0.00003670164],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003159553,0.0001863241,0.9907538,0.0007830599,0.00005335532,0.00004962314,0.00005164214,0.0003906099,0.004572141],"genre_scores_gemma":[0.1181892,0.0006551289,0.8730823,0.0005374193,0.0002023554,0.0002489318,0.0004415567,0.0004107439,0.006232443],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005885118,"threshold_uncertainty_score":0.03112388,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}