{"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"},"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005991665,0.00007211404,0.0001636633,0.00007419771,0.0001006047,0.000142088,0.0001582609,0.00004130724,0.000003398053],"category_scores_gemma":[0.0001253672,0.00006492138,0.00002676885,0.0002758492,0.00003075425,0.001070598,0.0001320175,0.0001134388,0.00004922884],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001013606,"about_ca_system_score_gemma":0.00005646752,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006306011,"about_ca_topic_score_gemma":0.00001521194,"domain_scores_codex":[0.9991813,0.0001823727,0.0003109242,0.00009015535,0.0001292952,0.0001060054],"domain_scores_gemma":[0.9991612,0.00006477844,0.0001422934,0.0001814776,0.0003945134,0.00005568634],"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":[0.00001365936,0.0001501156,0.02834709,0.001179396,0.00008054642,0.000002432376,0.03528959,0.05226162,0.0001498796,0.6317839,0.002073729,0.2486681],"study_design_scores_gemma":[0.0001868465,0.00002085397,0.008182041,0.00002110583,0.000001361786,0.00001474394,0.0001117068,0.9789101,0.00005589762,0.00009591159,0.01232306,0.0000763204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01263126,0.0009045778,0.9428683,0.00004752743,0.0002997088,0.00007268301,0.00000530989,0.00008948745,0.04308116],"genre_scores_gemma":[0.99685,0.00003055525,0.002403842,0.00002074509,0.00002209132,0.00000392475,0.00003615395,0.000002155658,0.0006305463],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9842187,"threshold_uncertainty_score":0.2647417,"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)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005966123,0.0001187576,0.0001665566,0.00012892,0.0001536226,0.0004052713,0.0008417442,0.00006325058,0.000001474214],"category_scores_gemma":[0.0001389793,0.0001043766,0.00001824412,0.0002018749,0.00001457913,0.006741441,0.0001657871,0.00005913844,0.00006596997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002859385,"about_ca_system_score_gemma":0.00006388925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004030068,"about_ca_topic_score_gemma":8.231892e-7,"domain_scores_codex":[0.9990044,0.00002704536,0.0004564001,0.0001999501,0.0001263576,0.0001858298],"domain_scores_gemma":[0.9985817,0.00006994687,0.000227254,0.0008392452,0.0002161107,0.00006570998],"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":[0.00001407183,0.00004768093,0.0004486191,0.0003374548,0.00001696981,4.414367e-7,0.002476966,0.000004635871,0.001087167,0.3098598,0.1801419,0.5055643],"study_design_scores_gemma":[0.0004115945,0.0001109259,0.004568014,0.00005826338,0.000004503831,0.0000294131,0.00004517331,0.3933702,0.0006587317,0.0003552405,0.6001729,0.000215015],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003040078,0.0002586794,0.9745212,0.0005168449,0.0005639926,0.0007288966,0.0002305308,0.0005936896,0.02228214],"genre_scores_gemma":[0.968823,0.00005544183,0.02850256,0.0005063423,0.0001770562,0.00009187179,0.001496064,0.000006733002,0.0003409789],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.968519,"threshold_uncertainty_score":0.4887382,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000548853,0.0001143918,0.0001602475,0.0001092999,0.0002194931,0.0002770021,0.000214128,0.00005614005,0.000001484387],"category_scores_gemma":[0.00003823084,0.00007865322,0.00002025423,0.000163047,0.00004770574,0.001459292,0.0001527072,0.00002957216,0.00004823738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002252444,"about_ca_system_score_gemma":0.00003956776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001762827,"about_ca_topic_score_gemma":0.000001267471,"domain_scores_codex":[0.9991227,0.00002595643,0.0003644195,0.0001936656,0.0001101053,0.0001831537],"domain_scores_gemma":[0.999092,0.00017271,0.0001378472,0.0003033266,0.0001906559,0.0001034221],"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":[0.000001081535,0.00001394249,0.00002219216,0.00005725368,0.000006597157,6.281721e-8,0.00161845,0.000001581604,0.00001966127,0.00993299,0.003538189,0.984788],"study_design_scores_gemma":[0.0009723359,0.00007488783,0.001319578,0.0001437574,0.000008045311,0.00002787545,0.000555233,0.7896622,0.000267569,0.00005650237,0.2066921,0.0002198322],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006712245,0.0003578088,0.9895452,0.0001816323,0.00042066,0.0004128819,0.0002185038,0.0001046645,0.002046431],"genre_scores_gemma":[0.9233494,0.00008428992,0.07429645,0.0001218442,0.0003272239,0.0005772162,0.0001028264,0.00001280115,0.001127884],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9845682,"threshold_uncertainty_score":0.3207385,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.001099126,0.0001096495,0.0001337496,0.00009472611,0.0008130556,0.000500117,0.003555681,0.0001788514,1.593308e-7],"category_scores_gemma":[0.001904213,0.00008466261,0.0000223203,0.0002655176,0.00008964199,0.004731442,0.01616205,0.0002409964,0.000003000764],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000304004,"about_ca_system_score_gemma":0.00003330702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001318517,"about_ca_topic_score_gemma":0.00003182545,"domain_scores_codex":[0.9991304,0.00005017011,0.0003161929,0.0001634763,0.0001234036,0.0002164102],"domain_scores_gemma":[0.9983408,0.0002415982,0.0001824298,0.001074134,0.0001250628,0.00003592702],"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":[0.00004861716,0.00007402392,0.05060839,0.0004445985,0.00005402822,4.163671e-7,0.008412228,0.00008624888,0.00002388584,0.320327,0.1618932,0.4580274],"study_design_scores_gemma":[0.0005066087,0.00001916915,0.01616073,0.0000156703,0.000002684003,0.000002166546,0.0002392491,0.9243014,0.00001359274,0.005806982,0.05280739,0.0001243477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1525268,0.0008744709,0.8183422,0.00816566,0.00193734,0.002422933,0.00003991831,0.0005629575,0.01512776],"genre_scores_gemma":[0.9974788,0.00009874496,0.0021458,0.00003594028,0.0001093595,0.00007754281,0.00002961336,0.000003080778,0.00002115488],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9242151,"threshold_uncertainty_score":0.9917951,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0005542017,0.0002189421,0.0002962999,0.0004304116,0.0003248976,0.001057961,0.0005472283,0.0001389604,4.093224e-7],"category_scores_gemma":[0.00007538579,0.0001834233,0.0000596203,0.0003406534,0.00005698109,0.01403682,0.0001615934,0.00008217286,0.0002478033],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002125229,"about_ca_system_score_gemma":0.00009565656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001339261,"about_ca_topic_score_gemma":0.00002520978,"domain_scores_codex":[0.998628,0.00005460436,0.0006265561,0.0001891029,0.0001760818,0.0003256451],"domain_scores_gemma":[0.9984395,0.00008624583,0.0002628038,0.0004344813,0.0006748024,0.0001021944],"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":[0.00001091602,0.000033113,0.00003768224,0.0005235082,0.0000359287,3.802089e-7,0.02317351,0.0003252654,0.000001774659,0.9631323,0.0008931991,0.01183244],"study_design_scores_gemma":[0.004705667,0.0007412161,0.002933558,0.0005067647,0.00006002443,0.0001610658,0.1336578,0.1162499,0.0001669444,0.004576325,0.7352293,0.001011355],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003142358,0.004501152,0.7184632,0.0001760305,0.00324066,0.001921141,0.0000223145,0.0007733841,0.2677598],"genre_scores_gemma":[0.9965332,0.0001718695,0.002484834,0.00006720329,0.000129193,0.0003421325,0.00004078769,0.00000558318,0.0002251688],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9933909,"threshold_uncertainty_score":0.999979,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004209719,0.00008859661,0.00009739203,0.00007186781,0.0005302755,0.0003613794,0.0002788234,0.00004564808,4.213679e-7],"category_scores_gemma":[0.00001241388,0.00006308322,0.00001240741,0.0001782208,0.00002597897,0.002572989,0.0001485814,0.0000634231,0.00001177616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001480159,"about_ca_system_score_gemma":0.00003904602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000163025,"about_ca_topic_score_gemma":0.00001474463,"domain_scores_codex":[0.9993365,0.00001542048,0.0002844697,0.0001444941,0.00009272856,0.0001263779],"domain_scores_gemma":[0.9992995,0.00008638251,0.0001504242,0.000317427,0.0001074421,0.00003885365],"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":[0.00001336025,0.00002573659,0.000723471,0.000305325,0.00002764486,1.198611e-7,0.001662151,0.0003028005,0.0004635198,0.233482,0.0423804,0.7206135],"study_design_scores_gemma":[0.0002596738,0.0000632115,0.001898043,0.00003551926,0.000007241032,0.00003766852,0.000112038,0.7220818,0.0009080998,0.0002753256,0.2741825,0.0001389207],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01659608,0.001124521,0.9797473,0.0003844314,0.0002547158,0.000509483,0.00001473029,0.000176118,0.001192617],"genre_scores_gemma":[0.9860743,0.00004699631,0.01305284,0.00005373231,0.0001995789,0.00008487619,0.00003112161,0.000004005439,0.000452508],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9694782,"threshold_uncertainty_score":0.4078504,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002289257,0.0001017177,0.0001268355,0.00009636548,0.0001920595,0.0003639731,0.0002646018,0.00004684648,0.000002124256],"category_scores_gemma":[0.00001319359,0.0000911038,0.00002537921,0.0002130593,0.00002064592,0.001855865,0.00009218301,0.00003752891,0.00005495962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004409355,"about_ca_system_score_gemma":0.00008177441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008626219,"about_ca_topic_score_gemma":0.0002328012,"domain_scores_codex":[0.9991714,0.00001540575,0.0003846003,0.0001368479,0.000108579,0.0001831038],"domain_scores_gemma":[0.9993578,0.00005801074,0.0001303031,0.0002377715,0.0001589832,0.00005708275],"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":[0.000004244461,0.0001015958,0.002701929,0.0002825884,0.00003966493,6.97018e-7,0.003894152,0.0000601961,0.0002606819,0.1270139,0.09229397,0.7733464],"study_design_scores_gemma":[0.0007268995,0.00005013138,0.001974117,0.00005602384,0.000007778801,0.00002173418,0.0003484063,0.4438933,0.0001436961,0.00004010799,0.5525398,0.0001980751],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01007841,0.0005016748,0.9589057,0.0002564671,0.0004609165,0.0005374212,0.0001284529,0.0001396263,0.02899131],"genre_scores_gemma":[0.9777804,0.00001669211,0.0198578,0.0001914855,0.0003567098,0.0004578465,0.0003961672,0.000009487901,0.0009334019],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.967702,"threshold_uncertainty_score":0.3715105,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002177614,0.00007778206,0.0001068562,0.0001244434,0.0001336065,0.0002297351,0.0001725462,0.00004304254,0.00001436893],"category_scores_gemma":[0.00001233543,0.00006245097,0.00002711031,0.0002182346,0.0000193571,0.004105042,0.00005016286,0.00004393714,0.001388933],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000145977,"about_ca_system_score_gemma":0.00001462829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000181536,"about_ca_topic_score_gemma":6.189991e-7,"domain_scores_codex":[0.9994039,0.00002712684,0.0002779236,0.00008883696,0.00009516923,0.0001070509],"domain_scores_gemma":[0.9994541,0.00001283248,0.0001371619,0.0002142957,0.0001298184,0.00005183763],"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":[0.00001484863,0.00002933751,0.0006827807,0.00006500819,0.00002983995,4.153806e-7,0.02148048,0.000007705678,0.00007328449,0.883163,0.002809539,0.09164381],"study_design_scores_gemma":[0.0005245428,0.0006407677,0.07129269,0.0001565602,0.00001974761,0.0000454733,0.001349457,0.3524329,0.0005753417,0.0004205637,0.5719837,0.0005582616],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.02713969,0.0002445711,0.07118143,0.00007411138,0.0005241648,0.0002521628,0.000004677662,0.000267035,0.9003122],"genre_scores_gemma":[0.997309,0.00001565883,0.00069103,0.00002905851,0.00005042021,0.00001474099,0.000006827684,0.000002682526,0.001880609],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9701693,"threshold_uncertainty_score":0.9993886,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000457818,0.0001182865,0.0001430678,0.0003084528,0.0001712832,0.0006589549,0.003891758,0.00008400677,0.000003043725],"category_scores_gemma":[0.00094621,0.0001094072,0.00001492863,0.0004719485,0.00003500073,0.007391031,0.005672321,0.00008162848,0.00027278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006427825,"about_ca_system_score_gemma":0.00004215418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001568651,"about_ca_topic_score_gemma":0.00001407968,"domain_scores_codex":[0.9989408,0.00005584085,0.000403825,0.0001955793,0.0002091459,0.0001948424],"domain_scores_gemma":[0.9978014,0.00004842056,0.0001664053,0.001665173,0.0002478079,0.00007076657],"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":[0.00001058592,0.00007158263,0.002237012,0.000238466,0.00003053182,0.000002957355,0.004733173,0.0009992184,0.0004388496,0.5698376,0.371885,0.04951509],"study_design_scores_gemma":[0.0004035831,0.0001028236,0.001976676,0.0001522076,0.000003681787,0.00002198887,0.0003233264,0.7930243,0.001442296,0.009981899,0.1922595,0.0003077202],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00928923,0.0002682455,0.9686565,0.0009735858,0.0006726133,0.0003710242,0.00001411842,0.0005120419,0.01924266],"genre_scores_gemma":[0.9854147,0.00002795603,0.01404741,0.0001272442,0.0001375289,0.00005878948,0.00007041431,0.000004951655,0.0001109608],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9761255,"threshold_uncertainty_score":0.723192,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005894859,0.0001404383,0.0002032603,0.0001769199,0.0002048301,0.0006418438,0.0001381891,0.0001576058,7.623974e-7],"category_scores_gemma":[0.00009788845,0.0001226631,0.00002474956,0.000239998,0.00001166154,0.001881669,0.00006741824,0.0001173629,0.00002267226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001100249,"about_ca_system_score_gemma":0.00004066246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001060563,"about_ca_topic_score_gemma":0.0000157375,"domain_scores_codex":[0.9989806,0.0001114799,0.000407671,0.0001463523,0.0001904017,0.0001634694],"domain_scores_gemma":[0.9988968,0.0003116482,0.0002783056,0.0002030985,0.0002585449,0.00005164027],"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":[0.00004577099,0.0002593312,0.07623462,0.001452958,0.00009548508,0.000003642796,0.01488003,0.0005873842,0.0002171973,0.7797562,0.06515287,0.06131452],"study_design_scores_gemma":[0.001198706,0.0002291977,0.05016796,0.0007479326,0.00001028901,0.00001079068,0.0004445316,0.6016515,0.001166686,0.002185689,0.3415724,0.0006142493],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01235709,0.0005545839,0.9167571,0.000465684,0.0008995661,0.0008234725,0.0000950465,0.000410949,0.06763653],"genre_scores_gemma":[0.9915185,0.00002116002,0.008037348,0.0001222787,0.0001100017,0.00005363478,0.00002217122,0.000004434363,0.0001104562],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9791614,"threshold_uncertainty_score":0.6189315,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003802798,0.00008246046,0.00009450594,0.0001307653,0.0002434827,0.0001821149,0.00008628201,0.00008056567,0.000002489187],"category_scores_gemma":[0.00003358276,0.0000674449,0.0000301008,0.0002029109,0.000006949208,0.001792415,0.00003831559,0.00007961185,0.0001817209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002530797,"about_ca_system_score_gemma":0.00001801488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000054599,"about_ca_topic_score_gemma":4.470164e-7,"domain_scores_codex":[0.9994179,0.00004218736,0.0001783099,0.00007273553,0.00009977439,0.0001891053],"domain_scores_gemma":[0.9995151,0.00004539057,0.00008623075,0.00007556179,0.0001939462,0.00008376093],"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":[0.0001116444,0.0003846562,0.01977193,0.002906447,0.0001217074,1.581867e-7,0.09824891,0.01079778,0.006056101,0.1486726,0.1457438,0.5671843],"study_design_scores_gemma":[0.0003911652,0.00005058342,0.0009833355,0.00005899123,0.000004224927,0.00001433144,0.0004657196,0.5982829,0.0005626663,0.000005969938,0.3990671,0.0001129906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09279111,0.001926925,0.8805411,0.0001763476,0.002294862,0.0008842178,0.000005366993,0.0003736144,0.0210064],"genre_scores_gemma":[0.9979131,0.00001483775,0.001148742,0.00005282871,0.000184878,0.0000859169,0.00002529707,0.000003366648,0.0005710715],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9051219,"threshold_uncertainty_score":0.2750323,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004866998,0.00006728902,0.0001284961,0.0001717147,0.00007489952,0.0000853056,0.0001051593,0.00007986715,0.000001078443],"category_scores_gemma":[0.00004879308,0.00005913479,0.00001429847,0.0002475183,0.0000380123,0.001427921,0.000090606,0.00006999655,0.0000051799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001651222,"about_ca_system_score_gemma":0.00001194611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001203423,"about_ca_topic_score_gemma":0.00002346285,"domain_scores_codex":[0.9993566,0.00005273377,0.0003435951,0.00009200653,0.0000616324,0.00009338761],"domain_scores_gemma":[0.9994852,0.0001130442,0.0001229879,0.0001941004,0.00006690444,0.00001779296],"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":[0.000005558164,0.00003665255,0.003550639,0.0003739675,0.000007245886,9.920094e-8,0.002497462,0.00002845128,0.0003878931,0.9295632,0.0007257841,0.06282304],"study_design_scores_gemma":[0.0007882681,0.0002087126,0.04302689,0.0002532284,0.00001324126,0.00004708263,0.004335439,0.09365165,0.02997079,0.02495447,0.8021916,0.0005585772],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02474757,0.0008766822,0.9720842,0.00002954391,0.00008447139,0.0002111449,0.00002978972,0.00009607807,0.001840466],"genre_scores_gemma":[0.9841559,0.00007455394,0.01561494,0.00001230431,0.00002242128,0.00006869684,0.00001299997,0.000001717474,0.0000364496],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9594083,"threshold_uncertainty_score":0.2411447,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0009921666,0.0001608961,0.0002166598,0.0002278518,0.0003101774,0.001402991,0.0008291722,0.00006423355,0.000002426064],"category_scores_gemma":[0.00002248572,0.0001443619,0.00002728354,0.0003307691,0.00003671293,0.02322539,0.0005329265,0.00009855857,0.00005109182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009220568,"about_ca_system_score_gemma":0.00001110323,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001680663,"about_ca_topic_score_gemma":0.000001700167,"domain_scores_codex":[0.9988152,0.00006362271,0.0003741601,0.0001968409,0.0002325152,0.0003177081],"domain_scores_gemma":[0.998701,0.00002490526,0.0002931913,0.0007829323,0.00006035511,0.0001376411],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005746575,0.0002750265,0.04695866,0.001334495,0.000198052,0.000003469901,0.02033293,0.000006278407,0.0004521225,0.2720436,0.5895072,0.06888239],"study_design_scores_gemma":[0.001117328,0.00006573282,0.008126792,0.0003174477,0.00009809782,0.00002027413,0.0123051,0.04662163,0.0001092439,0.00006744514,0.9302734,0.0008775232],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01211377,0.004857827,0.956411,0.0002644265,0.002349176,0.0009025019,0.0003208819,0.0003400543,0.02244038],"genre_scores_gemma":[0.9960933,0.00009461978,0.0003862013,0.00005444676,0.0002891152,0.0000301614,0.0005264111,0.000008269855,0.00251751],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9839795,"threshold_uncertainty_score":0.9996337,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000269684,0.00008651211,0.0001182465,0.0001241055,0.0001370568,0.001125468,0.0001475569,0.00007648922,0.000003222534],"category_scores_gemma":[0.00001774483,0.00007361711,0.00001386274,0.00016643,0.00002031368,0.007821758,0.00009426787,0.0000626214,0.0001517724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001846667,"about_ca_system_score_gemma":0.00001565341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001233378,"about_ca_topic_score_gemma":0.0000041162,"domain_scores_codex":[0.9993973,0.00003775317,0.0002678625,0.00009093162,0.00009219969,0.0001139831],"domain_scores_gemma":[0.9994678,0.00005265635,0.0001025156,0.0001927405,0.0001129001,0.00007141756],"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":[0.000002228769,0.00001244349,0.001167536,0.0002013258,0.00001055204,4.747519e-7,0.007039928,0.000001448544,0.0001184494,0.03513667,0.02678557,0.9295233],"study_design_scores_gemma":[0.0003308432,0.0001528561,0.004331955,0.0001355436,0.000004368319,0.0001818838,0.000699776,0.04502887,0.001005423,0.0001732885,0.9476953,0.0002599056],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4495901,0.005807269,0.1189352,0.0008664399,0.003206076,0.002332732,0.00001075316,0.001700756,0.4175507],"genre_scores_gemma":[0.9985225,0.00006858673,0.0008617189,0.00007741179,0.0001014685,0.00007686704,0.000006866403,0.000002917044,0.0002816151],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9292635,"threshold_uncertainty_score":0.9999115,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008255133,0.00009139613,0.0001604401,0.0001005866,0.0000920442,0.00005518978,0.00004614014,0.00006430932,0.000005295443],"category_scores_gemma":[0.0003200011,0.00007347397,0.00001790527,0.0001215545,0.00002136575,0.0008334933,0.00003622701,0.00007563677,0.00003353994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003000185,"about_ca_system_score_gemma":0.00001490826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000588111,"about_ca_topic_score_gemma":0.000008509334,"domain_scores_codex":[0.9991851,0.000031124,0.0004419923,0.00006978751,0.00009700502,0.0001750225],"domain_scores_gemma":[0.9992146,0.0003182588,0.0001140823,0.0001098408,0.0001642522,0.00007892845],"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":[0.00004090311,0.00003689801,0.00007536812,0.001233038,0.00002332259,0.000001584472,0.00665426,0.00009137197,0.00009727305,0.8450027,0.00233829,0.1444051],"study_design_scores_gemma":[0.002441571,0.000256192,0.001112861,0.0006787335,0.00006310017,0.000175044,0.006964,0.3518253,0.0005484116,0.02908387,0.6059033,0.0009476296],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001789854,0.0001192062,0.9061499,0.000006040167,0.0002800014,0.0002830065,0.000007098544,0.0000863159,0.09127863],"genre_scores_gemma":[0.6925923,0.00004283055,0.3051424,0.00006464681,0.0002955481,0.0000502544,0.00002045289,0.00002148094,0.001770024],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8159187,"threshold_uncertainty_score":0.2996181,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003587136,0.00006564549,0.00009419722,0.000126648,0.00008327612,0.0001322373,0.00007610406,0.00002113797,0.000009745947],"category_scores_gemma":[0.000001758286,0.00004750259,0.00003333855,0.000312299,0.00001535171,0.0006746443,0.00001438668,0.00006594774,0.00003205523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009877157,"about_ca_system_score_gemma":0.000009138165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005513974,"about_ca_topic_score_gemma":0.00003798954,"domain_scores_codex":[0.9994363,0.00005984202,0.0002857473,0.00004813159,0.00008211446,0.00008782809],"domain_scores_gemma":[0.99967,0.00004590671,0.00009074342,0.0001121735,0.00007038453,0.00001079523],"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":[0.000005987396,0.00009833739,0.1457358,0.00007590455,0.00002420781,1.432082e-7,0.004603974,0.0007871956,0.00002373247,0.7829243,0.05171754,0.01400291],"study_design_scores_gemma":[0.0008893238,0.00003621028,0.1985846,0.0001078117,0.00004263535,0.000002894835,0.004843879,0.0868443,0.0001037474,0.0190291,0.6891016,0.0004139278],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.23801,0.000587826,0.07877822,0.0001729216,0.0001758754,0.0006864917,0.00002169198,0.00009549739,0.6814715],"genre_scores_gemma":[0.9995604,0.000002805976,0.00004592026,0.00002539411,0.0001481945,0.00005084126,0.0001079864,0.000001863888,0.00005659336],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7638952,"threshold_uncertainty_score":0.1937099,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00168109,0.0001323409,0.0002234488,0.0003236482,0.0002460031,0.0008321911,0.0003218188,0.00006106167,0.000004373206],"category_scores_gemma":[0.00007993868,0.0001075085,0.00006476539,0.0003359161,0.00001410168,0.008852879,0.00003562311,0.00009994797,0.0000749543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001891732,"about_ca_system_score_gemma":0.00004402726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005278066,"about_ca_topic_score_gemma":0.000001087375,"domain_scores_codex":[0.9988187,0.00006111907,0.0006787903,0.0001348822,0.0001315082,0.0001749824],"domain_scores_gemma":[0.9988196,0.00004340284,0.0003775078,0.0004100412,0.0002557923,0.00009362265],"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":[0.00002943703,0.0002029373,0.005209516,0.002400242,0.00007151206,6.50985e-8,0.02204784,0.001816758,0.0007490002,0.1468235,0.06088854,0.7597607],"study_design_scores_gemma":[0.000236451,0.00002821896,0.0001053559,0.00002157602,0.00000505607,0.000002004272,0.0001468684,0.5339448,0.0002090446,0.00000435077,0.4651918,0.0001044496],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001682211,0.0002859398,0.9844014,0.00009496605,0.001097213,0.0009095948,0.000005219923,0.0001101762,0.01141328],"genre_scores_gemma":[0.9344091,0.00007158634,0.06323349,0.0004750597,0.0005065442,0.0004473668,0.0007122741,0.000008457447,0.0001361284],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9327269,"threshold_uncertainty_score":0.8024838,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2011191813","doi":"10.1007/s10115-009-0226-y","title":"Subspace and projected clustering: experimental evaluation and analysis","year":2009,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Subspace topology; Computer science; Data mining; Range (aeronautics); Clustering high-dimensional data; Consensus clustering; Artificial intelligence; Correlation clustering; CURE data clustering algorithm; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.0260607623732046,"gpt":0.3356089740219756,"spread":0.3095482116487711,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005176085,0.0001021088,0.0001579597,0.0003600104,0.0001496524,0.0004440716,0.0001109668,0.0000484272,0.000001253382],"category_scores_gemma":[0.00003357389,0.00009121774,0.00001611855,0.0005872467,0.00002743947,0.00295401,0.0001303302,0.00006182487,0.000007393433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005729397,"about_ca_system_score_gemma":0.00003156954,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001380966,"about_ca_topic_score_gemma":0.000003917117,"domain_scores_codex":[0.9991026,0.00007900471,0.0002449848,0.000165154,0.0002540741,0.0001541702],"domain_scores_gemma":[0.999377,0.00003089116,0.0000859172,0.0001892623,0.0002238265,0.00009315759],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000589572,0.0001258657,0.002683405,0.0003834464,0.0002763455,0.000002794536,0.07744251,0.003161081,0.002335601,0.01343488,0.0004292368,0.8996659],"study_design_scores_gemma":[0.0004594934,0.0001109788,0.01138207,0.00001990161,0.00001532061,0.00002718644,0.0006025216,0.9844515,0.0002112004,0.00001500964,0.00259089,0.0001139543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1953805,0.005606333,0.7869529,0.0002187823,0.0002381475,0.001139852,0.00000442101,0.0002142725,0.01024476],"genre_scores_gemma":[0.9974134,0.00005203333,0.002330999,0.00002324634,0.00002621905,0.00003501795,0.00001071217,0.000002013009,0.000106333],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9812904,"threshold_uncertainty_score":0.4282193,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"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)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007320938,0.00008673998,0.0001266225,0.0001085761,0.0002348054,0.0003448351,0.000328499,0.00007902023,0.000003709845],"category_scores_gemma":[0.00004847067,0.00007744155,0.00001927135,0.0001844764,0.000007396207,0.004973713,0.0001557144,0.00005134826,0.0002549935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001499206,"about_ca_system_score_gemma":0.00002943726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001627208,"about_ca_topic_score_gemma":0.00003918016,"domain_scores_codex":[0.9992038,0.00005273776,0.0002957737,0.0001589344,0.0001164045,0.0001723701],"domain_scores_gemma":[0.9991722,0.00006418781,0.0001260481,0.0003340843,0.0002315723,0.00007186917],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003391548,0.0001196274,0.002830514,0.001084592,0.00003762953,7.303117e-8,0.008913418,0.00007722973,0.0003689968,0.03764538,0.7684908,0.1803978],"study_design_scores_gemma":[0.0003450435,0.00003966329,0.0002281483,0.00003488137,0.000002941352,0.000006588812,0.0001155451,0.5118001,0.0001191665,0.00005176305,0.4871836,0.00007257593],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006806211,0.0001437134,0.979907,0.0001332299,0.001066995,0.0005097776,0.00009775646,0.0001746528,0.01116068],"genre_scores_gemma":[0.9927744,0.00004809724,0.004756309,0.0003713118,0.0002722622,0.0001466582,0.0009694624,0.000008039655,0.0006534522],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9859682,"threshold_uncertainty_score":0.3605822,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002313983,0.00007206283,0.0000865042,0.00007765849,0.0001277901,0.0007807057,0.0004406526,0.00003223692,0.000004268629],"category_scores_gemma":[0.000005458377,0.0000619935,0.000005084823,0.00009635787,0.00001132945,0.01070403,0.0001905323,0.00002317434,0.000007243217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005090786,"about_ca_system_score_gemma":0.000009659576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001009094,"about_ca_topic_score_gemma":0.000009649344,"domain_scores_codex":[0.9994803,0.00001379266,0.0001943678,0.0001352727,0.0000675955,0.0001086791],"domain_scores_gemma":[0.9994371,0.00001719776,0.0000503524,0.0004099534,0.00003451353,0.00005087244],"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":[0.000003149779,0.00000375494,0.0002432576,0.0001533647,0.000007670604,1.170747e-7,0.00213129,0.00003450355,0.000003089254,0.00203041,0.003443012,0.9919464],"study_design_scores_gemma":[0.0002194739,0.00002227217,0.0004670079,0.00001968564,0.000002136306,0.000006005112,0.0001595405,0.7034905,0.00000193404,0.00001184623,0.2955329,0.00006676715],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02200378,0.0005894785,0.9631935,0.00006924679,0.0006421484,0.0005528611,0.000143457,0.0001545539,0.01265095],"genre_scores_gemma":[0.9863914,0.00007617244,0.01219571,0.0001198037,0.0002123818,0.00001528633,0.0004810638,0.000004885491,0.0005032803],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9918796,"threshold_uncertainty_score":0.7760165,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004031151,0.000118814,0.0001515694,0.000126446,0.000158266,0.0002236549,0.0001213337,0.0001288349,4.22812e-7],"category_scores_gemma":[0.00001484988,0.00009857066,0.00002465625,0.0001444443,0.00001456053,0.002750146,0.00006778618,0.00008676936,0.000004545022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000182719,"about_ca_system_score_gemma":0.00004115783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008812988,"about_ca_topic_score_gemma":0.000007460337,"domain_scores_codex":[0.9993963,0.00003087386,0.0002185469,0.0001297076,0.00007045898,0.0001541486],"domain_scores_gemma":[0.9994591,0.00002739257,0.0001065288,0.0001321803,0.0001980505,0.00007672417],"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":[0.00006700397,0.00003667004,0.0002848406,0.001493848,0.00005854954,3.388237e-7,0.09350681,0.0002370422,0.0003108859,0.6711775,0.01373329,0.2190932],"study_design_scores_gemma":[0.0003384,0.00004449866,0.0001425324,0.00005167727,0.000006953088,0.00004260056,0.00005797865,0.9687272,0.00006251068,0.001145852,0.02924774,0.0001320728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004484888,0.0006697313,0.983844,0.00003446662,0.0002879308,0.0003435014,0.000007453755,0.0000810636,0.01428341],"genre_scores_gemma":[0.5823224,0.0001579087,0.4155915,0.0003933853,0.0001491964,0.0001524996,0.00001226941,0.00001141436,0.001209377],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9684901,"threshold_uncertainty_score":0.4019595,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007624028,0.00009261708,0.0001238873,0.00007432222,0.0001999102,0.0005544264,0.000829316,0.00004717922,0.000001006363],"category_scores_gemma":[0.00006347284,0.00008305009,0.000009601961,0.0003940124,0.00001848562,0.007777039,0.0002056111,0.00005653798,0.0001853119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001802283,"about_ca_system_score_gemma":0.00004826876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006196569,"about_ca_topic_score_gemma":0.000006809192,"domain_scores_codex":[0.9990896,0.00006294285,0.0003867131,0.0001939751,0.0001305095,0.0001362891],"domain_scores_gemma":[0.9986237,0.00008506371,0.0001654651,0.000908927,0.0001625666,0.00005431762],"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":[0.000002803406,0.00005365647,0.0007877338,0.00004946192,0.00001433126,2.013147e-7,0.00693646,0.000009888283,0.00004569829,0.2516141,0.07221185,0.6682739],"study_design_scores_gemma":[0.0001501913,0.00002695558,0.03488784,0.00002730307,0.000002264198,0.00001111608,0.0002162296,0.5417486,0.000006978911,0.00006968384,0.4227348,0.0001180137],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001922861,0.0005102273,0.9511836,0.0003523874,0.0003901738,0.0002584386,0.0001457503,0.0001982892,0.04503833],"genre_scores_gemma":[0.9741927,0.0001107316,0.02353493,0.0002604011,0.0001259238,0.00002167201,0.001589936,0.000003533229,0.0001601601],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9722698,"threshold_uncertainty_score":0.5638165,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004467884,0.0001024722,0.0001341194,0.0001531867,0.0002186393,0.0004587353,0.0003355103,0.00005477107,4.845606e-7],"category_scores_gemma":[0.00003725226,0.0000833743,0.00003445015,0.0003084478,0.00001787585,0.002438879,0.00003456668,0.00003933417,0.00001785108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002534846,"about_ca_system_score_gemma":0.00005947292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006803069,"about_ca_topic_score_gemma":3.516828e-7,"domain_scores_codex":[0.9991885,0.00001864438,0.0003473122,0.0001583634,0.0001276819,0.0001594453],"domain_scores_gemma":[0.9992609,0.00009758542,0.000125579,0.0002830067,0.0001514703,0.00008147467],"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":[0.00000562999,0.00008091303,0.00008453787,0.00009213775,0.000006432008,2.04598e-7,0.002149888,0.0005966033,0.00004926039,0.07816522,0.01143092,0.9073383],"study_design_scores_gemma":[0.0003070518,0.0001203912,0.000554992,0.00005017618,0.000003285558,0.000007034547,0.0001866865,0.9163986,0.00004663195,0.0001009696,0.08210491,0.0001192462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002342703,0.0005378344,0.9894109,0.0001042227,0.0001808953,0.0004238867,0.00002169666,0.0001150338,0.006862813],"genre_scores_gemma":[0.7655048,0.00002605907,0.2337262,0.0001806326,0.00009135356,0.0002386715,0.0001558185,0.000003085912,0.00007336697],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.915802,"threshold_uncertainty_score":0.4423595,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001564973,0.0001186443,0.000230736,0.0002291479,0.0003844259,0.000235608,0.0001335461,0.00009229562,0.00001342326],"category_scores_gemma":[0.00006084869,0.00009491987,0.00001373393,0.0004591992,0.00009327559,0.00764628,0.00006590888,0.00008607855,0.00001022797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007114086,"about_ca_system_score_gemma":0.0003629762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006241133,"about_ca_topic_score_gemma":0.002479651,"domain_scores_codex":[0.9985892,0.0002679859,0.000457043,0.0001150184,0.0004094291,0.0001613891],"domain_scores_gemma":[0.9984338,0.00005632556,0.0002415698,0.0002314806,0.0009519738,0.0000848679],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001018245,0.00006054897,0.00008707841,0.0003083211,0.0001598504,1.043115e-7,0.8193449,0.008169045,0.00002971821,0.122927,0.01010598,0.0387056],"study_design_scores_gemma":[0.001151203,0.00003690513,0.0001333035,0.00011439,0.00005034362,0.000001558639,0.1116527,0.8543628,0.0000923136,0.0001899843,0.03209783,0.0001166195],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1731239,0.003618072,0.2474,0.0003202005,0.0006045795,0.002519645,0.000306707,0.0001258876,0.571981],"genre_scores_gemma":[0.9988016,0.00013548,0.00007013625,0.0001786714,0.0000378712,0.0000179741,0.0001871253,0.000002574368,0.000568554],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8461938,"threshold_uncertainty_score":0.5543369,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001033129,0.0004173023,0.001543763,0.0003587736,0.000339932,0.001010028,0.001688456,0.0002329658,0.000002446397],"category_scores_gemma":[0.0002388548,0.0003265181,0.0002061135,0.0003315342,0.00005668455,0.004637249,0.001235986,0.0003982791,0.001282563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001609359,"about_ca_system_score_gemma":0.0003334089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001007637,"about_ca_topic_score_gemma":0.000003061851,"domain_scores_codex":[0.9977045,0.0002070839,0.001026764,0.0003372593,0.0003290417,0.0003953597],"domain_scores_gemma":[0.9969624,0.0001157037,0.0008953467,0.001466984,0.0003456765,0.0002138429],"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":[1.508189e-7,0.000006299154,5.121484e-8,0.1200942,0.00002379865,0.000002162174,0.0002025027,9.005644e-7,3.107322e-9,0.0004092734,0.001270532,0.8779901],"study_design_scores_gemma":[0.0001424222,0.00002101625,3.623847e-7,0.07307363,0.0000332394,0.0002393896,0.000008027521,0.01967522,2.381212e-8,7.340371e-7,0.9064887,0.0003171988],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.374491e-9,0.7794117,0.2112981,0.00001850597,0.0007915598,0.001201701,0.00001250546,0.0001370238,0.007128883],"genre_scores_gemma":[3.057969e-7,0.9936709,0.002223097,0.00002487473,0.0001305864,0.0003933708,0.00003918504,0.00001878118,0.003498938],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9052182,"threshold_uncertainty_score":0.9999187,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002075644,0.00009071919,0.0001124725,0.0001044352,0.0003386078,0.0001576497,0.0002717509,0.00005466092,0.000001772706],"category_scores_gemma":[0.0000275958,0.00007946236,0.00002379653,0.000327204,0.00004205008,0.003237837,0.00008389833,0.00006986027,0.0004031425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002368892,"about_ca_system_score_gemma":0.00006290674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001246677,"about_ca_topic_score_gemma":3.174135e-7,"domain_scores_codex":[0.9992182,0.00002875533,0.000346208,0.0001423682,0.0001486371,0.000115823],"domain_scores_gemma":[0.9992481,0.00006123335,0.000122288,0.0003101201,0.0001783683,0.00007983527],"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":[0.000003118379,0.0001851688,0.003875611,0.0002203042,0.00003416803,5.360237e-7,0.01379098,0.0001797678,0.00003842888,0.7252459,0.03179258,0.2246335],"study_design_scores_gemma":[0.0001937703,0.0000073939,0.009855788,0.00001030686,0.000001220714,0.00006260054,0.000100323,0.607186,0.0000037165,0.000008492329,0.3824925,0.00007789089],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001356542,0.0008014348,0.9366615,0.0001124958,0.0002320396,0.0003186781,0.00002133182,0.000181943,0.060314],"genre_scores_gemma":[0.9511789,0.0001946861,0.04723531,0.00008643423,0.0001323371,0.0002602142,0.0002158058,0.000004674702,0.0006916388],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9498224,"threshold_uncertainty_score":0.5181715,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003391636,0.0001056725,0.0001417215,0.0001478355,0.0002059859,0.0003892679,0.000270607,0.00007176932,8.984603e-7],"category_scores_gemma":[0.00007956972,0.00008264155,0.00004285659,0.0002049952,0.00001562271,0.002786491,0.0001047649,0.00004659445,0.0002217891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005033603,"about_ca_system_score_gemma":0.00005774821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004574833,"about_ca_topic_score_gemma":0.000003256586,"domain_scores_codex":[0.9992212,0.00001276085,0.0003565307,0.0001250567,0.0001035592,0.000180897],"domain_scores_gemma":[0.9992919,0.0001152141,0.00010668,0.0002284043,0.0001977304,0.00006004514],"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":[0.00001131672,0.00003446008,0.00008014955,0.0001952763,0.00001027988,4.300385e-7,0.006956055,0.0005826049,0.000008333506,0.5241652,0.00326691,0.464689],"study_design_scores_gemma":[0.001763387,0.0001900786,0.001445397,0.00044603,0.000006393704,0.00005368319,0.0003465088,0.2381149,0.00005044837,0.00520918,0.7520192,0.0003548278],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001701923,0.001061601,0.9608043,0.00006200893,0.001230244,0.0004325931,0.000005162497,0.000125649,0.03457646],"genre_scores_gemma":[0.9670318,0.0000368824,0.03259183,0.00009946701,0.000128229,0.00006638327,0.000005026364,0.000003789162,0.00003654264],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9653299,"threshold_uncertainty_score":0.3753719,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004071188,0.00007702543,0.0001227142,0.00006917779,0.0002122411,0.0001775004,0.0003118912,0.00004285569,0.000001676127],"category_scores_gemma":[0.00004425329,0.00005041101,0.00003241693,0.0003882415,0.0000713316,0.001404242,0.0001227021,0.00005520125,0.00004854331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001291667,"about_ca_system_score_gemma":0.00005695907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001567329,"about_ca_topic_score_gemma":0.000002385696,"domain_scores_codex":[0.9992777,0.00004838581,0.0003252336,0.00008165953,0.000145417,0.0001216292],"domain_scores_gemma":[0.9990718,0.00003064059,0.000193435,0.0003349764,0.000331677,0.00003749607],"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":[0.00001733138,0.00009666149,0.0119154,0.00517382,0.00009393866,5.640011e-7,0.185591,0.0003746777,0.001506453,0.4972804,0.01415081,0.2837989],"study_design_scores_gemma":[0.0009817738,0.000186966,0.01313402,0.002182848,0.00002447149,0.0001831063,0.002849896,0.3853168,0.01990933,0.0004792247,0.5742147,0.0005368965],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5472501,0.005940554,0.1919339,0.000335771,0.004395103,0.0009605568,0.000005865993,0.0003416565,0.2488365],"genre_scores_gemma":[0.9995651,0.00001331417,0.00008301195,0.00007227178,0.0001006868,0.000006480708,4.131135e-7,0.000002421177,0.0001562721],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5600639,"threshold_uncertainty_score":0.2055701,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000528978,0.0001355566,0.0002048266,0.000259945,0.0001404174,0.0004474689,0.0002510221,0.00008759899,3.289034e-7],"category_scores_gemma":[0.00005965599,0.0001088115,0.00004167459,0.0002128033,0.000007313301,0.003373622,0.0000419241,0.00008505226,0.00001268685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008166504,"about_ca_system_score_gemma":0.00002938947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001350777,"about_ca_topic_score_gemma":0.00002449997,"domain_scores_codex":[0.9989958,0.00004565015,0.0004510571,0.0001491352,0.0001294689,0.0002288229],"domain_scores_gemma":[0.9994031,0.0001119286,0.0001343127,0.0002075612,0.00008109167,0.00006198976],"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":[0.00002363901,0.00006288664,0.0003253711,0.0003143984,0.0000193347,0.000002190296,0.3875514,0.001465955,0.001510756,0.4038297,0.01437988,0.1905145],"study_design_scores_gemma":[0.001572292,0.0001783234,0.0003864556,0.0007275147,0.000001901951,0.00004354706,0.01204932,0.9333828,0.001535453,0.000395465,0.04931827,0.0004086692],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02876982,0.009788663,0.9127027,0.0004090197,0.001882097,0.001592532,0.000009792342,0.0003754445,0.04446989],"genre_scores_gemma":[0.9962328,0.00003087949,0.003005077,0.0001329437,0.0001280436,0.0001037768,0.00001452687,0.000003558226,0.0003483838],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.967463,"threshold_uncertainty_score":0.4437204,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000537654,0.00009313502,0.0001294619,0.0001198911,0.0001735374,0.0004649937,0.0002491954,0.000056959,0.000002158636],"category_scores_gemma":[0.0001204792,0.00008362466,0.00001741457,0.000119601,0.00002646845,0.002474161,0.0002268613,0.0001339074,0.00007456307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000307707,"about_ca_system_score_gemma":0.00005157014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000824185,"about_ca_topic_score_gemma":0.00003039517,"domain_scores_codex":[0.9991048,0.00001972941,0.0003442348,0.0001237735,0.0001658347,0.0002416326],"domain_scores_gemma":[0.9991529,0.0001862439,0.00007727305,0.0002425785,0.0002299595,0.0001110593],"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":[0.00001982205,0.00003668342,0.0001139307,0.002016826,0.00003751753,0.000002200778,0.01072934,0.0009884767,0.003240237,0.53394,0.001474167,0.4474008],"study_design_scores_gemma":[0.0003916157,0.00006480171,0.0001588402,0.00004177726,0.000001951267,0.0000396754,0.0001718253,0.8243201,0.0005976501,0.0002712749,0.1738006,0.0001398048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001323863,0.00005416876,0.9943241,0.00007007845,0.00117393,0.0003706124,0.000006977087,0.00009341141,0.002582897],"genre_scores_gemma":[0.8967787,0.00001917109,0.1023552,0.00003892464,0.0002202224,0.0001390813,0.0000141388,0.000007988332,0.0004265874],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8954548,"threshold_uncertainty_score":0.4483945,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005481259,0.0001001587,0.0001114876,0.0001632107,0.00031505,0.000195402,0.001129862,0.00005829458,0.000001697028],"category_scores_gemma":[0.0001097415,0.0000785164,0.00001171509,0.0004821291,0.00002116653,0.003400248,0.0005724872,0.0001473191,0.00004179456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000426557,"about_ca_system_score_gemma":0.00006961913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009437228,"about_ca_topic_score_gemma":0.00001365129,"domain_scores_codex":[0.9990644,0.00003502484,0.0004040621,0.000199033,0.0001373653,0.0001601286],"domain_scores_gemma":[0.9982737,0.0001134154,0.0001273607,0.001360769,0.00007928891,0.00004541376],"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":[0.00005546916,0.0004765149,0.09279066,0.002064595,0.0002122056,0.00001244335,0.05867912,0.01977475,0.001036661,0.09381883,0.05334174,0.677737],"study_design_scores_gemma":[0.0001465762,0.000007522412,0.003655063,0.00003727855,0.000001453795,0.00001333346,0.000103935,0.8664418,0.00007154227,0.000003730047,0.129418,0.00009978095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007752168,0.0003638553,0.989426,0.000164834,0.0002358592,0.0003965798,0.00005506566,0.000240596,0.001365047],"genre_scores_gemma":[0.9966878,0.00002644181,0.003007786,0.00006665395,0.00006130207,0.00003903719,0.0000719672,0.000004710284,0.00003435278],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9889356,"threshold_uncertainty_score":0.3201806,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008216946,0.0001104577,0.0002008773,0.0001926438,0.00009577546,0.0002386203,0.0002158319,0.00005922846,2.556844e-7],"category_scores_gemma":[0.0002793185,0.00009582606,0.00003034765,0.0001945245,0.00003519703,0.00465257,0.0001684402,0.00007696984,0.00001175272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009050864,"about_ca_system_score_gemma":0.00008313302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001578304,"about_ca_topic_score_gemma":0.000001852736,"domain_scores_codex":[0.9990762,0.0001099645,0.0003242738,0.0001284557,0.0001878043,0.0001732589],"domain_scores_gemma":[0.9985195,0.0004888867,0.0001595837,0.0002022889,0.0005430822,0.00008668181],"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":[0.0002697253,0.00008882697,0.00007553841,0.003208955,0.0001033046,0.000001787542,0.07651583,0.02331647,0.00168732,0.7712,0.001982016,0.1215502],"study_design_scores_gemma":[0.001005972,0.0007093091,0.0001479564,0.0003211971,0.000003919751,0.00001573441,0.001806561,0.9790575,0.001718313,0.006533852,0.008501003,0.0001786745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0164925,0.0001648345,0.9745897,0.00001767473,0.0005558401,0.000598195,0.00001023227,0.00006760026,0.007503445],"genre_scores_gemma":[0.9863458,0.000006751727,0.01339382,0.000008417455,0.00005850579,0.0001229958,0.000003110354,0.000004969106,0.00005568428],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9698532,"threshold_uncertainty_score":0.3907674,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004228186,0.00005057245,0.00008281993,0.0001093115,0.00006764962,0.0002380663,0.0003338588,0.00003283951,0.000007424723],"category_scores_gemma":[0.00002958784,0.00003671588,0.000007322506,0.0003917736,0.00002786083,0.002689774,0.00007603112,0.00004088875,0.00001657671],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003936365,"about_ca_system_score_gemma":0.00002112452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001159011,"about_ca_topic_score_gemma":0.00006728024,"domain_scores_codex":[0.9993726,0.00006938519,0.0003112757,0.00008230656,0.0001103156,0.00005408677],"domain_scores_gemma":[0.9994304,0.00003348343,0.00007567388,0.0003449594,0.00009479986,0.00002072334],"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":[0.000006696634,0.0001771112,0.005406687,0.0001982677,0.00005880195,0.000001004331,0.02430638,0.0002904279,0.0002150565,0.7412269,0.0550792,0.1730334],"study_design_scores_gemma":[0.0001982424,0.00001182776,0.001604762,0.00002990321,0.00000457872,0.000002550176,0.0003550788,0.8326009,0.00001551544,0.00004629197,0.1650835,0.00004689384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1406749,0.00460981,0.8236321,0.0008896342,0.0006364168,0.0008952048,0.0004437387,0.0001156114,0.02810264],"genre_scores_gemma":[0.9986356,0.0004533094,0.0001315015,0.0001209484,0.00002574305,0.000004223161,0.0005665033,0.000001225577,0.00006095817],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8579607,"threshold_uncertainty_score":0.2295679,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002260996,0.00007971915,0.0001013042,0.0001656186,0.0003550011,0.001022781,0.0005974293,0.00005617317,0.000002241441],"category_scores_gemma":[0.0003808221,0.00006875124,0.000006674797,0.0004813038,0.00003848574,0.006693568,0.0004158828,0.0001157375,0.0003439436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002713653,"about_ca_system_score_gemma":0.0002971269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003171998,"about_ca_topic_score_gemma":0.000002604851,"domain_scores_codex":[0.9989066,0.0001220131,0.0002654204,0.0002039709,0.0002787178,0.0002233457],"domain_scores_gemma":[0.9985375,0.0001887953,0.00008404316,0.0007758656,0.0002970301,0.0001167645],"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":[0.000001122525,0.00006175315,0.0001217414,0.0001100818,0.00002234318,0.000001210752,0.00706811,7.346438e-7,0.0000150573,0.5449266,0.2612365,0.1864347],"study_design_scores_gemma":[0.0001287994,0.0000131936,0.0001322592,0.0000273623,0.000001239603,0.00004562604,0.0009234733,0.0511423,0.00006304999,0.00001453505,0.9474193,0.00008880736],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001899622,0.001131186,0.807824,0.002267054,0.0008733597,0.0006441115,0.00005539746,0.0002289598,0.1850763],"genre_scores_gemma":[0.5824712,0.0001618933,0.4123424,0.0001303936,0.0002114774,0.000252132,0.0004768486,0.00001468656,0.00393895],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6861829,"threshold_uncertainty_score":0.9862698,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007358426,0.00009976498,0.00013574,0.0001666826,0.0001478146,0.0005628632,0.0003369793,0.00004125321,0.000005026831],"category_scores_gemma":[0.00002485276,0.000083644,0.00003053297,0.0002835173,0.00001101791,0.008684679,0.0001998227,0.00004956236,0.0003199797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002713702,"about_ca_system_score_gemma":0.00003968754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003185462,"about_ca_topic_score_gemma":2.757121e-7,"domain_scores_codex":[0.9991646,0.0000319903,0.0002860371,0.0001009832,0.0001478466,0.0002685242],"domain_scores_gemma":[0.9993591,0.00004388034,0.00008331051,0.0002934078,0.00007390276,0.0001463463],"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":[0.000008618154,0.00007138297,0.0005260217,0.001907605,0.00006284449,2.12192e-7,0.01574341,0.00007254089,0.00001620002,0.4417636,0.1986962,0.3411314],"study_design_scores_gemma":[0.0004885456,0.00002341255,0.0003316111,0.0000403343,0.000007831654,0.000009412418,0.0006599497,0.4469224,0.00001875105,0.00001538208,0.5513446,0.0001377732],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001400381,0.0004719938,0.9495576,0.00007064566,0.0005907592,0.0005529718,0.000006686511,0.00009239161,0.04851689],"genre_scores_gemma":[0.5731216,0.0001684597,0.4081356,0.0005066012,0.002152187,0.000368729,0.0004834361,0.00003152593,0.01503183],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5729816,"threshold_uncertainty_score":0.6296183,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005356062,0.0001110167,0.00015687,0.0001251124,0.000246501,0.0004164954,0.0003015587,0.00006437734,9.032349e-7],"category_scores_gemma":[0.00005003278,0.000094148,0.00001514681,0.0001698041,0.00002857848,0.003693938,0.0002915363,0.00007628032,0.00000977358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001756509,"about_ca_system_score_gemma":0.00004428105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008292831,"about_ca_topic_score_gemma":0.000002223913,"domain_scores_codex":[0.999189,0.00005162134,0.0002924807,0.0001897822,0.0001009419,0.0001762227],"domain_scores_gemma":[0.9993036,0.00006271758,0.000150479,0.0002866342,0.0001241897,0.00007240928],"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":[0.00002632625,0.00005252366,0.002113991,0.0004669481,0.0001008853,0.000004379678,0.02022727,0.001253505,0.00004967396,0.06008751,0.002996197,0.9126208],"study_design_scores_gemma":[0.000436134,0.00004600847,0.0001632987,0.00003963679,0.000006452467,0.0001089235,0.0004081414,0.9037437,0.000002264335,0.00008082942,0.09484187,0.0001227187],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007391149,0.0007349274,0.9880199,0.00008325535,0.0006593048,0.000259443,0.00001115283,0.0000775071,0.002763373],"genre_scores_gemma":[0.6858633,0.0002329166,0.3114687,0.0002321271,0.001147605,0.00006144508,0.000215113,0.00001726151,0.0007615275],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9124981,"threshold_uncertainty_score":0.4016275,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004362858,0.0001092417,0.0001365239,0.0001620298,0.0002525853,0.001129428,0.0001506408,0.0000746011,0.00000125865],"category_scores_gemma":[0.00001324628,0.00008573317,0.00001655988,0.0002452315,0.00003540652,0.003556014,0.00007031581,0.0001168359,0.00001099742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001428685,"about_ca_system_score_gemma":0.000135848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005861298,"about_ca_topic_score_gemma":0.00001017604,"domain_scores_codex":[0.9992475,0.00003376869,0.000307538,0.0001177148,0.0001321047,0.000161367],"domain_scores_gemma":[0.9994456,0.00002372083,0.0001364122,0.0001733321,0.0001468883,0.00007411197],"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":[0.0000223851,0.0001879825,0.01176884,0.003677907,0.00003338692,0.000006588828,0.01562238,0.001006794,0.001284571,0.5489231,0.001788493,0.4156776],"study_design_scores_gemma":[0.0005600897,0.00004382379,0.003080997,0.00009464809,0.000007309812,0.0000381634,0.000514692,0.8470559,0.0000592911,0.0001613138,0.1481641,0.0002197193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2052786,0.002396124,0.7556437,0.0002345786,0.001577017,0.0006369964,0.000006888497,0.0002784306,0.03394764],"genre_scores_gemma":[0.9933032,0.00001853858,0.006489893,0.0000861472,0.00006961013,0.00001017891,0.000006781813,0.000002779534,0.00001284812],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8460491,"threshold_uncertainty_score":0.9999075,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0004002175,0.0001681894,0.0002002551,0.0001784791,0.0003156508,0.001921202,0.0004837319,0.00008373075,0.000004208941],"category_scores_gemma":[0.00006984765,0.0001501531,0.00001380078,0.0006752092,0.00003586432,0.02506938,0.0005709207,0.00007210863,0.0001576041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000366428,"about_ca_system_score_gemma":0.00005400334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001047511,"about_ca_topic_score_gemma":0.000004241099,"domain_scores_codex":[0.99875,0.0000783987,0.0005331711,0.0002655942,0.0001785079,0.0001942968],"domain_scores_gemma":[0.9989105,0.00004553165,0.0002304688,0.0004997357,0.0002321945,0.00008156337],"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":[0.000002809107,0.0002499405,0.001352895,0.002594813,0.00006417793,0.000001599066,0.06997391,0.00001712391,0.0000354188,0.7880519,0.08302036,0.05463508],"study_design_scores_gemma":[0.0002500681,0.00001727531,0.00006408594,0.0001398158,0.00001091207,0.00002471918,0.0006450296,0.5940569,0.00002576753,0.00003574858,0.4045628,0.0001669246],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009806429,0.007853058,0.9549496,0.00009662916,0.000616508,0.0003299608,0.00005575096,0.0004517989,0.03466608],"genre_scores_gemma":[0.993314,0.002166348,0.001897582,0.0003369972,0.0003044466,0.00001460923,0.0005873268,0.00002073432,0.001357924],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9923334,"threshold_uncertainty_score":0.9991149,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001892489,0.0001134778,0.00009716584,0.0001003177,0.0001433913,0.00009177317,0.00008290957,0.0001368671,0.000001466525],"category_scores_gemma":[0.00003901895,0.0001002319,0.00003973002,0.00009528693,0.00001727439,0.00006265334,0.00001436748,0.00003111175,0.0000107776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001970816,"about_ca_system_score_gemma":0.00005310532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.357685e-7,"about_ca_topic_score_gemma":0.000001262368,"domain_scores_codex":[0.999275,0.00003793165,0.000315011,0.0001609982,0.00008977889,0.0001213059],"domain_scores_gemma":[0.9993059,0.000007282781,0.000175541,0.0002208323,0.0002219958,0.00006842173],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002140714,0.00005984097,0.0003760182,0.0001655537,0.000008396943,2.483986e-8,0.0004149065,0.001084108,0.9557944,0.003106024,0.01638568,0.02239097],"study_design_scores_gemma":[0.002053753,0.0004649634,0.007869856,0.0001253858,0.00001816764,0.000005961577,0.0006763441,0.05623429,0.2038508,0.0000750714,0.7282239,0.0004015495],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03385708,0.001406373,0.9440359,0.000366497,0.0007306291,0.001224433,0.000046343,0.00007449427,0.01825824],"genre_scores_gemma":[0.9974228,0.00008969439,0.0005525279,0.0001930904,0.000233702,0.0001458195,0.001011145,0.000006921966,0.0003442912],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9635657,"threshold_uncertainty_score":0.4087337,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007234361,0.0001131885,0.0002517542,0.0004620289,0.00006113452,0.00007719929,0.0002179976,0.0001049853,7.546592e-7],"category_scores_gemma":[0.0001431662,0.00009503032,0.00003355059,0.0008389863,0.00002281652,0.002571238,0.00007239063,0.0001158129,0.000003697807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006019512,"about_ca_system_score_gemma":0.00007797482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000376219,"about_ca_topic_score_gemma":0.000002076478,"domain_scores_codex":[0.9990692,0.0001003961,0.0003301882,0.0001360678,0.0002012671,0.000162857],"domain_scores_gemma":[0.9989765,0.0002504324,0.0001160887,0.0002019257,0.0004024836,0.00005260393],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005094546,0.0002282216,0.006363624,0.003654141,0.00005457967,0.000004044006,0.003579268,0.00182877,0.007844221,0.5575461,0.00106366,0.4173239],"study_design_scores_gemma":[0.00672451,0.002742149,0.2784071,0.001529469,0.00002114149,0.00009373822,0.0002687488,0.2778988,0.3840469,0.03086307,0.01631086,0.001093525],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09559017,0.0009380045,0.9006771,0.00005010457,0.0002015963,0.0009534939,0.00001708833,0.0000826312,0.001489792],"genre_scores_gemma":[0.9971531,0.00002033735,0.002725569,0.00002648383,0.00002115915,0.00001324823,0.00001382745,0.000002505238,0.00002375717],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9015629,"threshold_uncertainty_score":0.3875224,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001332014,0.00009179235,0.000131019,0.000246678,0.00005432297,0.0002952095,0.007434627,0.00007164779,6.726069e-7],"category_scores_gemma":[0.004108274,0.00008371955,0.000006604195,0.0005245368,0.00002767148,0.01119479,0.03705124,0.00009846451,0.0001132977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007407393,"about_ca_system_score_gemma":0.00008423943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005447588,"about_ca_topic_score_gemma":0.000007070067,"domain_scores_codex":[0.9989586,0.0000741922,0.0003997584,0.0002020675,0.0002065282,0.0001588579],"domain_scores_gemma":[0.9953856,0.00005482613,0.0001340762,0.004218177,0.0001448784,0.00006247751],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001330906,0.00008477355,0.01020466,0.0003988386,0.00002261183,0.000004734227,0.004388955,0.0002485477,0.00001764948,0.09837068,0.7546239,0.1316213],"study_design_scores_gemma":[0.0003528074,0.00001039911,0.001143235,0.00006588812,0.000001219505,0.00001301867,0.0001628222,0.8252246,0.00002085715,0.007629868,0.1652644,0.0001108431],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008936398,0.002523785,0.9468613,0.008123039,0.001650438,0.0006483804,0.0000428528,0.000859349,0.03035446],"genre_scores_gemma":[0.9725661,0.0001534149,0.02666954,0.0001254221,0.00005556662,0.00002445269,0.0003330261,0.000005505066,0.00006700661],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9636297,"threshold_uncertainty_score":0.9979357,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001137714,0.0001170665,0.0002162514,0.0002593862,0.0001821114,0.0003035265,0.0001895364,0.00005042171,0.000004173969],"category_scores_gemma":[0.0000794374,0.0001020261,0.0000315794,0.000428461,0.00003113364,0.006123073,0.00008762014,0.0000602404,0.00003738745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000495457,"about_ca_system_score_gemma":0.0000457325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002287045,"about_ca_topic_score_gemma":0.0001089654,"domain_scores_codex":[0.998958,0.00002840088,0.0005226142,0.00012328,0.0001215095,0.0002462098],"domain_scores_gemma":[0.9992867,0.00009600252,0.0001812069,0.0001969014,0.0001750392,0.00006413378],"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":[0.0003850302,0.0003800368,0.05043552,0.002042133,0.0002127426,0.000003712715,0.03328161,0.01158588,0.000443677,0.8114147,0.01454207,0.07527294],"study_design_scores_gemma":[0.0005278733,0.00005575092,0.00566198,0.000101597,0.000004876508,0.00001593488,0.0006252577,0.7238325,0.00008964031,0.0000197348,0.2689055,0.0001592594],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003046213,0.0004742044,0.9894127,0.00002726473,0.000217572,0.0003137775,0.0000256579,0.00008217384,0.006400431],"genre_scores_gemma":[0.9796105,0.00003939858,0.01864587,0.00004840324,0.0001289147,0.00002428837,0.0001421869,0.00000825289,0.001352198],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9765643,"threshold_uncertainty_score":0.443908,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000340432,0.0001462736,0.0002215481,0.00006032041,0.0004741486,0.0002530967,0.000438285,0.00008170644,0.000001956337],"category_scores_gemma":[0.00003310089,0.0001385212,0.0000407252,0.000541997,0.00002997218,0.003942407,0.0002475841,0.0003428635,0.00007141838],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002637598,"about_ca_system_score_gemma":0.00003928293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002178371,"about_ca_topic_score_gemma":0.000006810562,"domain_scores_codex":[0.9988734,0.0001775151,0.0004207478,0.0001097366,0.0001448111,0.0002738013],"domain_scores_gemma":[0.9991271,0.0001502137,0.0001838919,0.0002395786,0.0001172564,0.0001819477],"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":[0.00007345241,0.00003456961,0.0009194394,0.0009027427,0.0001264099,0.000009327608,0.2576198,0.1834127,0.00007237815,0.1038934,0.04208701,0.4108487],"study_design_scores_gemma":[0.0004069096,0.00007666868,0.0000970982,0.00007345512,0.000004165573,0.00002432591,0.001324325,0.8611942,0.000007638696,0.0001076557,0.1365035,0.0001800733],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002005445,0.0004720958,0.9853281,0.0002080472,0.001447019,0.0002910593,0.000003749056,0.0003309035,0.009913518],"genre_scores_gemma":[0.9974542,0.00002290612,0.001272806,0.0006517619,0.0005322784,0.00001729019,0.00002201529,0.000006166883,0.0000205936],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9954487,"threshold_uncertainty_score":0.564873,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005350745,0.00009435334,0.0001323695,0.0001723069,0.0002249423,0.0001757868,0.0002901628,0.00009545238,7.680905e-7],"category_scores_gemma":[0.00002589546,0.00008828531,0.00001476796,0.0004295125,0.00001958469,0.001838112,0.00005646005,0.0001435428,0.00001621774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003678475,"about_ca_system_score_gemma":0.00001571647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003230391,"about_ca_topic_score_gemma":0.000001433711,"domain_scores_codex":[0.9991912,0.00004522115,0.0003514282,0.0001482231,0.00009327287,0.0001707032],"domain_scores_gemma":[0.9995236,0.00003509847,0.0001192644,0.0002213388,0.00006129899,0.00003934484],"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":[0.00003089672,0.0003673808,0.007089087,0.0005321924,0.00003041165,0.000003112365,0.1766911,0.0100124,0.0008885548,0.2089506,0.004865475,0.5905389],"study_design_scores_gemma":[0.0001873893,0.00002269417,0.0002435446,0.00007018548,6.577159e-7,0.000007766715,0.000729954,0.9538966,0.0005847533,0.0001297202,0.0440009,0.0001258479],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3029422,0.001483894,0.6590348,0.0001863181,0.000173146,0.0006964594,0.000002323193,0.0003374377,0.03514343],"genre_scores_gemma":[0.9988172,0.00007419413,0.0008809113,0.0000438356,0.00001321711,0.0001055606,0.000002384886,0.000001630649,0.00006105177],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9438842,"threshold_uncertainty_score":0.3600171,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003912775,0.00009507349,0.0001194652,0.0001793331,0.0001526374,0.0002857515,0.0003230508,0.00004843156,0.000003653846],"category_scores_gemma":[0.0001064019,0.00006444844,0.00001871903,0.0002230164,0.00002648801,0.006391293,0.0003625768,0.0000531164,0.0004843626],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008393385,"about_ca_system_score_gemma":0.00003732493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000136587,"about_ca_topic_score_gemma":0.000002231477,"domain_scores_codex":[0.9991032,0.00003738832,0.000285783,0.0001305761,0.0001810781,0.0002619663],"domain_scores_gemma":[0.9992027,0.0001558547,0.00008670562,0.000279698,0.0001703448,0.0001046479],"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":[0.0000179233,0.00002995419,0.002227983,0.000526317,0.00003035523,0.000002948287,0.008420843,0.0002413335,0.002865982,0.03969935,0.003499258,0.9424378],"study_design_scores_gemma":[0.001000575,0.00006843887,0.00125144,0.0002251104,0.000001120048,0.00005478034,0.00017828,0.3206545,0.001196703,0.00008074491,0.6750448,0.0002434579],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004734093,0.0002238498,0.9815965,0.0001215806,0.0005395984,0.0002080784,0.000005446291,0.0001803388,0.01239052],"genre_scores_gemma":[0.9928983,0.00007328569,0.004041505,0.00002866913,0.00008257851,0.00005321547,0.000001851187,0.000005841956,0.00281478],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9881642,"threshold_uncertainty_score":0.6225663,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008740007,0.00008212918,0.0001491528,0.0001302008,0.000302446,0.000546005,0.0003521977,0.00004326124,0.00004269716],"category_scores_gemma":[0.0005829246,0.00004699517,0.00004276058,0.0002524482,0.00004280791,0.003275534,0.0001721007,0.00004190734,0.0003713012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001980986,"about_ca_system_score_gemma":0.00001989503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008203866,"about_ca_topic_score_gemma":0.00002159074,"domain_scores_codex":[0.9986074,0.0001951491,0.0007045777,0.0001211589,0.0002313981,0.0001402942],"domain_scores_gemma":[0.9983549,0.000668644,0.0002670132,0.0003420416,0.0003204006,0.00004700798],"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":[0.00002038821,0.00001623201,0.00008231983,0.0001329863,0.00002104025,1.56923e-8,0.01572614,0.00005586748,0.000004409889,0.09761997,0.02069665,0.865624],"study_design_scores_gemma":[0.0002154554,0.000033797,0.0006820714,0.00002184191,0.00001163526,0.000001865895,0.005581904,0.1243545,0.00003541122,0.002260976,0.8667283,0.00007222288],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001293776,0.000703313,0.9004654,0.0001318237,0.0007820256,0.0007959562,0.00001585072,0.00003346075,0.09694281],"genre_scores_gemma":[0.9021753,0.0004080944,0.0719536,0.0008394708,0.0004590142,0.0016313,0.0001338732,0.00002423467,0.02237508],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.902046,"threshold_uncertainty_score":0.5265139,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002037002,0.00008688413,0.0001329152,0.0001565243,0.0001212954,0.000478067,0.000189652,0.00006488503,0.00000164935],"category_scores_gemma":[0.00002247297,0.00007590689,0.00001730354,0.000104048,0.00002688438,0.003214444,0.0001270655,0.00004718287,0.00005420994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001730461,"about_ca_system_score_gemma":0.00001856013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005474195,"about_ca_topic_score_gemma":0.000001559079,"domain_scores_codex":[0.9994033,0.00001202534,0.0002782558,0.0001083929,0.00007038647,0.0001276316],"domain_scores_gemma":[0.9994855,0.00007406912,0.0001155796,0.0002066783,0.00008834455,0.00002982253],"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":[0.00000482765,0.00001657308,0.01269581,0.00156468,0.00002436229,1.436937e-7,0.01122626,0.00001200933,0.0005755522,0.8524855,0.001452804,0.1199415],"study_design_scores_gemma":[0.00280395,0.0004499895,0.02152757,0.0006493693,0.00001723673,0.00006820701,0.008267388,0.757913,0.001084672,0.004126457,0.2022596,0.0008325913],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1304501,0.003670856,0.7936513,0.0008219174,0.002156708,0.001895438,0.00001355896,0.00107316,0.06626697],"genre_scores_gemma":[0.9980265,0.00007045909,0.001292695,0.00004641076,0.00001734803,0.00005807085,0.000006893855,0.000002890264,0.0004786649],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8675765,"threshold_uncertainty_score":0.4610011,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005285197,0.0001593769,0.0002238597,0.0001683332,0.0003701919,0.0002657086,0.0003682188,0.00007347024,0.000002525861],"category_scores_gemma":[0.00002340696,0.0001414897,0.0000529628,0.0002540808,0.00002939418,0.001975519,0.0001820145,0.00009278842,0.00009786879],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007016634,"about_ca_system_score_gemma":0.00006464611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001548608,"about_ca_topic_score_gemma":0.00001327673,"domain_scores_codex":[0.9988135,0.00008124654,0.0004150139,0.0002378359,0.00017729,0.0002750932],"domain_scores_gemma":[0.998871,0.0002547904,0.0001413245,0.0003564502,0.0002657365,0.0001106614],"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":[0.000002387997,0.00003171597,0.0007883478,0.0002445879,0.00002873267,0.000001107685,0.0123158,0.00006544156,0.00002638876,0.0006548791,0.003683462,0.9821572],"study_design_scores_gemma":[0.0005303204,0.0001210289,0.003682128,0.00007435391,0.0000061684,0.00008793639,0.0009557129,0.9571458,0.00009206307,0.00001495764,0.03709601,0.0001934957],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01013597,0.0001453342,0.9875056,0.00008023189,0.0002597088,0.0008198041,0.0002512285,0.0001145564,0.0006876058],"genre_scores_gemma":[0.9800624,0.00003208804,0.01827717,0.0001381136,0.00009954888,0.0008512819,0.0003804193,0.00001267233,0.0001463078],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9819636,"threshold_uncertainty_score":0.5769782,"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","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003172815,0.0003102436,0.0005368994,0.00070993,0.001251826,0.0001801576,0.0003070533,0.0004694366,0.00002321249],"category_scores_gemma":[0.0002268182,0.0002712682,0.00004011899,0.0006549482,0.00002749564,0.003680208,0.0001108332,0.001174223,0.00287176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004357975,"about_ca_system_score_gemma":0.0007793673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003859921,"about_ca_topic_score_gemma":0.002488595,"domain_scores_codex":[0.9955548,0.0007113949,0.002185568,0.0002332746,0.0003747145,0.0009402286],"domain_scores_gemma":[0.9963593,0.0002182127,0.0008152229,0.0006465563,0.001280111,0.0006805627],"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":[0.0003982173,0.0002126677,0.03731897,0.03251325,0.0001155194,7.43625e-7,0.2196239,0.0005065512,0.001843582,0.492197,0.03888719,0.1763824],"study_design_scores_gemma":[0.0008550823,0.0001662788,0.005920453,0.0003848965,0.000006776512,0.00002289416,0.01259948,0.04982029,0.00000796591,0.00001224945,0.929924,0.0002796594],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6287264,0.001055421,0.2043639,0.00221447,0.01676917,0.02723388,0.001140798,0.002515725,0.1159803],"genre_scores_gemma":[0.9948,0.00002587208,0.000159624,0.0008992504,0.0007763301,0.001966404,0.001079933,0.00002536976,0.0002672143],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8910368,"threshold_uncertainty_score":0.999974,"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","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004296723,0.000126299,0.0001806267,0.0002965161,0.0001549967,0.0003188763,0.0003382447,0.0001478806,0.000001516885],"category_scores_gemma":[0.0001094417,0.00010808,0.00002666714,0.0004078085,0.00002748362,0.002763446,0.0001388304,0.0001193366,0.0003227273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002012065,"about_ca_system_score_gemma":0.00006315553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002572256,"about_ca_topic_score_gemma":0.00002503685,"domain_scores_codex":[0.9990798,0.00005377729,0.0003808857,0.0001779513,0.000112719,0.0001948779],"domain_scores_gemma":[0.9991045,0.00004810051,0.0001082112,0.0003520748,0.0002813042,0.0001058241],"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":[0.000003739537,0.00005940826,0.001294196,0.0001319781,0.00001103502,1.426965e-7,0.01469135,0.0001205779,0.0007950289,0.9376719,0.002177275,0.04304336],"study_design_scores_gemma":[0.0005116257,0.00007368734,0.02481474,0.00002720434,0.000007320114,0.00008510149,0.0004876431,0.7066854,0.0004326471,0.0004784213,0.2660797,0.0003165774],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03061177,0.0002402758,0.7920762,0.0001102938,0.001866808,0.0004315135,0.000001589561,0.0002310248,0.1744305],"genre_scores_gemma":[0.9931383,0.000007401266,0.006256634,0.00007886726,0.0001302332,0.00006630927,0.00001859108,0.000003533372,0.000300113],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9625266,"threshold_uncertainty_score":0.4407376,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}