{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":120,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":120,"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":"3a9fca90f174","filters":{"venue":"IEEE Transactions on Knowledge and Data Engineering"}},"results":[{"id":"W2096451472","doi":"10.1109/tkde.2005.50","title":"Using AUC and accuracy in evaluating learning algorithms","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2141,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Machine learning; Computer science; Artificial intelligence; Naive Bayes classifier; Decision tree; Measure (data warehouse); Receiver operating characteristic; Algorithm; Bayes' theorem; Data mining; Support vector machine; Bayesian probability","retraction":null,"screen_n_in":null,"score":{"opus":0.09066818198011457,"gpt":0.3642777199882067,"spread":0.2736095380080922,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004324713,0.0001276593,0.0001235776,0.0002408607,0.000115294,0.0001156627,0.0004013286,0.00005380643,0.000003580371],"category_scores_gemma":[0.00003864769,0.0001392269,0.00001097022,0.0003086899,0.0000167689,0.001447589,0.0000255762,0.0002880872,0.00000661875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005457976,"about_ca_system_score_gemma":0.00003282005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001308241,"about_ca_topic_score_gemma":0.00001194664,"domain_scores_codex":[0.999059,0.0000338975,0.0002060342,0.0004149186,0.00009663967,0.0001895097],"domain_scores_gemma":[0.9991423,0.0001987749,0.00003604428,0.0005336754,0.0000283248,0.00006082984],"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":[0.000002809259,0.00006130484,0.00002767492,0.00004036618,0.00001028785,0.000001983083,0.0006082497,0.03106907,0.01580902,0.0003083105,0.00002559873,0.9520353],"study_design_scores_gemma":[0.0002095673,0.00002559086,0.0001845205,0.00007466973,0.000006041735,0.00001956216,0.00001525022,0.9869223,0.01009867,0.00001192378,0.002280105,0.0001517955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00894332,0.0003533961,0.9901127,0.00006803263,0.0001054274,0.0001086147,0.00001614932,0.0002427346,0.00004968545],"genre_scores_gemma":[0.6860757,0.000179386,0.3136319,0.00001385473,0.00004045405,0.00001263597,0.000007849952,0.0000120493,0.00002610507],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9558532,"threshold_uncertainty_score":0.5677507,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2151953639","doi":"10.1109/tkde.2005.166","title":"Fast algorithms for frequent itemset mining using FP-trees","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":552,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Data mining; Traverse; Association rule learning; Algorithm; Tree (set theory); Data structure; Tree structure; Trie; Prefix; Binary tree; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.05517782314487753,"gpt":0.3067297556925058,"spread":0.2515519325476283,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001941877,0.0001773885,0.0001578308,0.0001621162,0.0002377558,0.000176843,0.0007163907,0.00005733486,0.000004527164],"category_scores_gemma":[0.000005707857,0.0001836319,0.0000379477,0.0002658083,0.00001941717,0.0009323033,0.00002110892,0.0001193066,0.00001428661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004174819,"about_ca_system_score_gemma":0.00003867082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000153798,"about_ca_topic_score_gemma":0.00003306532,"domain_scores_codex":[0.9988756,0.000007874056,0.0002304932,0.0005226892,0.00009284649,0.000270515],"domain_scores_gemma":[0.9988046,0.0001390864,0.00003547944,0.0008561587,0.0000432712,0.0001214113],"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":[0.00000229816,0.0001532455,0.000002270808,0.00003794017,0.00005037117,0.000001234929,0.0005487343,0.0327771,0.00263042,0.0004759213,0.0008216894,0.9624988],"study_design_scores_gemma":[0.0002649273,0.00003324448,0.00001543196,0.00005872684,0.00002368727,0.00002060261,0.00002952387,0.9620176,0.003079309,0.000006797861,0.03423934,0.0002107866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001680434,0.0003745414,0.9963653,0.0001203766,0.0003658569,0.0001703619,0.0006825803,0.0001945859,0.0000459653],"genre_scores_gemma":[0.1133055,0.00007764086,0.8859453,0.00003875242,0.0002993993,0.00007474193,0.00008503442,0.00002955934,0.0001440631],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.962288,"threshold_uncertainty_score":0.7488291,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2170595610","doi":"10.1109/tkde.2004.1269594","title":"CAIM discretization algorithm","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":449,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Discretization; Discretization of continuous features; Algorithm; Computer science; Decision tree; Class (philosophy); Tree (set theory); ID3 algorithm; Decision tree learning; Artificial intelligence; Incremental decision tree; Mathematics; Discretization error","retraction":null,"screen_n_in":null,"score":{"opus":0.01997980423624899,"gpt":0.2493373957629373,"spread":0.2293575915266883,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008238421,0.0001110388,0.00008980783,0.00009643594,0.0001095878,0.00009593235,0.000430515,0.00004379451,0.000003741072],"category_scores_gemma":[0.000002060777,0.0001008455,0.00001906935,0.0002514163,0.00001250175,0.0006093589,0.00001012696,0.0001177165,0.00003622699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002568005,"about_ca_system_score_gemma":0.00002514163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001608122,"about_ca_topic_score_gemma":0.000010767,"domain_scores_codex":[0.9993352,0.000006462973,0.0001111867,0.0003137255,0.00007646952,0.0001569031],"domain_scores_gemma":[0.9992934,0.00002634264,0.00001275563,0.0005708373,0.00001795738,0.00007865595],"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":[0.00000273193,0.000229134,0.000002130127,0.00004578897,0.00004125589,0.00001803307,0.0009046309,0.1070795,0.0004470738,0.006167661,0.0001817095,0.8848804],"study_design_scores_gemma":[0.0004442349,0.00007185344,0.00009079916,0.00004781183,0.00001326432,0.00003114247,0.00001115708,0.9899884,0.001983302,0.0003001074,0.006777542,0.0002403583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002059428,0.0002697047,0.9982048,0.0001340667,0.0005470757,0.00006929399,0.00004589841,0.0001879981,0.000335196],"genre_scores_gemma":[0.7816358,0.0002981079,0.2178026,0.00004897859,0.00009864548,0.00001324652,0.00002947491,0.00001676625,0.00005638506],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.88464,"threshold_uncertainty_score":0.4112361,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2137763598","doi":"10.1109/tkde.2004.58","title":"Efficient phrase-based document indexing for Web document clustering","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":320,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Document clustering; Computer science; Cluster analysis; Vector space model; Search engine indexing; Phrase; Information retrieval; Document classification; Data mining; tf–idf; Artificial intelligence; Term (time)","retraction":null,"screen_n_in":null,"score":{"opus":0.02028388213544066,"gpt":0.2679597706680517,"spread":0.247675888532611,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003419823,0.0002049949,0.0001926514,0.0002855363,0.0002133799,0.0002177284,0.0006802019,0.00005285157,0.000004958067],"category_scores_gemma":[0.000008043313,0.0002021405,0.0000673313,0.0003431034,0.00001614486,0.0003144251,0.00002518323,0.0001446296,0.00001762712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001009411,"about_ca_system_score_gemma":0.00008974737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000186786,"about_ca_topic_score_gemma":0.00003339825,"domain_scores_codex":[0.9986981,0.00001259748,0.0002472124,0.0005792846,0.0001507878,0.0003120013],"domain_scores_gemma":[0.9987521,0.0001044905,0.00003679768,0.000934187,0.00003374653,0.0001387132],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000821009,0.000105566,0.000001027519,0.00008869779,0.00005468107,0.000003846004,0.0002296668,0.9700858,0.001920419,0.0003200825,0.00003901521,0.027143],"study_design_scores_gemma":[0.001064808,0.00007637138,0.000009209919,0.0001740748,0.00005016522,0.00000569945,0.00001882931,0.9885849,0.006719325,0.00001931992,0.003021014,0.0002562322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007419664,0.0001950593,0.9911999,0.0001820255,0.0004795745,0.0001662769,0.0001075544,0.0002164863,0.00003342925],"genre_scores_gemma":[0.9234667,0.00001709425,0.07628253,0.00003994777,0.00005907203,0.00005234398,0.00003098117,0.00001778425,0.00003357515],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.916047,"threshold_uncertainty_score":0.8243051,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2137525015","doi":"10.1109/tkde.2006.80","title":"Pattern discovery of fuzzy time series for financial prediction","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":179,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Research Council Canada; University of Illinois at Urbana-Champaign; National Science Council","keywords":"Fuzzy logic; Investment (military); Computer science; Fuzzy set; Time series; Data mining; Finance; Process (computing); Representation (politics); Artificial intelligence; Machine learning; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.05021834214437013,"gpt":0.3252064956071853,"spread":0.2749881534628152,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001104979,0.0001359446,0.0002311815,0.0002525208,0.0001039906,0.00007789517,0.0003406969,0.00007346839,0.00001739768],"category_scores_gemma":[0.0002523719,0.0001190444,0.00006439662,0.0003284275,0.00003908728,0.0007846606,0.000009209162,0.0001002892,0.00001063602],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001739807,"about_ca_system_score_gemma":0.00003960312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001486347,"about_ca_topic_score_gemma":0.00003868654,"domain_scores_codex":[0.9987673,0.00004082522,0.0004172678,0.0003863891,0.0002211696,0.0001670277],"domain_scores_gemma":[0.9980663,0.00115436,0.00007055332,0.0005746637,0.00009727045,0.0000368747],"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":[0.0003532162,0.0004303732,0.0006279076,0.0002435836,0.00007232557,0.000003205924,0.0004118286,0.04702095,0.02507468,0.000365841,0.01628241,0.9091137],"study_design_scores_gemma":[0.002577515,0.0009116956,0.02449855,0.0004271707,0.0002647133,0.00007337407,0.00009555326,0.8256016,0.08448612,0.004824019,0.0552382,0.001001521],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02964831,0.0001104008,0.9670722,0.00002355826,0.0008646747,0.0001743009,0.001669141,0.00005658152,0.0003808174],"genre_scores_gemma":[0.982339,0.00001318563,0.01508823,0.000005024991,0.000270364,0.00003656173,0.00005049837,0.0000245243,0.002172566],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9526907,"threshold_uncertainty_score":0.485449,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2142804492","doi":"10.1109/tkde.2011.138","title":"A Lightweight Algorithm for Message Type Extraction in System Application Logs","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":146,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Message passing; Partition (number theory); Event (particle physics); Algorithm; Data type; Web log analysis software; Task (project management); Data mining; Theoretical computer science; Distributed computing; Programming language; Operating system; The Internet","retraction":null,"screen_n_in":null,"score":{"opus":0.02653254209557903,"gpt":0.2630677020256542,"spread":0.2365351599300751,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003071773,0.0001190928,0.0001392375,0.0001600184,0.0000774049,0.00002736328,0.0003612571,0.0000873321,0.000001599725],"category_scores_gemma":[0.000002695902,0.0001085308,0.00002406362,0.000312328,0.000009232072,0.0006585125,0.000006669656,0.0001184824,0.00002550142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005841538,"about_ca_system_score_gemma":0.00002746673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003086907,"about_ca_topic_score_gemma":0.00001838259,"domain_scores_codex":[0.9991672,0.00001418253,0.000209795,0.0003829502,0.00006408944,0.0001617949],"domain_scores_gemma":[0.9991283,0.00007463609,0.00003126986,0.0006606614,0.00005039404,0.00005476346],"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":[0.00002773397,0.0003786199,0.00008710205,0.0006803393,0.00004863121,0.000003853639,0.001580599,0.001514595,0.0008519981,0.001398399,0.0001241131,0.993304],"study_design_scores_gemma":[0.0003295193,0.0000722859,0.0004599959,0.0001082205,0.0000142547,0.00002140499,0.00002906367,0.9893338,0.0070516,0.00001175781,0.002400467,0.0001676216],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001869113,0.0003628436,0.9961526,0.000006940484,0.0009098417,0.0003274452,0.00002792786,0.0002309558,0.0001122999],"genre_scores_gemma":[0.9460119,0.00007745639,0.05366471,0.000003820629,0.0000582603,0.0001275274,0.00001132561,0.00001264498,0.00003237456],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9931364,"threshold_uncertainty_score":0.4425758,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2157751754","doi":"10.1109/tkde.2006.131","title":"Test strategies for cost-sensitive decision trees","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":145,"is_retracted":false,"has_abstract":true,"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; Hong Kong University of Science and Technology","keywords":"Computer science; Medical diagnosis; Decision tree; Machine learning; Test (biology); Artificial intelligence; Test case; Process (computing); Medical costs; Data mining; Health care; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.02750885075641095,"gpt":0.2859938931044155,"spread":0.2584850423480046,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000150702,0.0001414718,0.0001266255,0.0001656278,0.0001238907,0.0001864817,0.0005170818,0.00005941732,0.000001495578],"category_scores_gemma":[0.00001378495,0.0001397748,0.00002550986,0.0002248815,0.00002306067,0.001118471,0.0000104551,0.0001033851,0.00001196586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003096646,"about_ca_system_score_gemma":0.00004309484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000127861,"about_ca_topic_score_gemma":0.00007561653,"domain_scores_codex":[0.9991253,0.000007476686,0.0001887185,0.0004169702,0.00008169304,0.000179832],"domain_scores_gemma":[0.9985084,0.0005348213,0.0000298615,0.000809367,0.00007151535,0.00004601159],"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":[0.00004069004,0.0007419148,0.00001592206,0.0001374785,0.00004983195,0.000009757272,0.0003729459,0.01906031,0.07036135,0.0450838,0.0155964,0.8485296],"study_design_scores_gemma":[0.0004426764,0.000104,0.0005472545,0.0000828764,0.00001694826,0.0000169346,0.00003084982,0.8973285,0.07337502,0.0008244778,0.02692505,0.0003054193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000287398,0.000094606,0.9978827,0.00005465498,0.0002334535,0.0002648158,0.0005355648,0.0004254546,0.000221413],"genre_scores_gemma":[0.8282907,0.00005557546,0.1713178,0.00001474395,0.00006024666,0.00008239884,0.0000799073,0.00001518114,0.00008349338],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8782682,"threshold_uncertainty_score":0.5699851,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2129546202","doi":"10.1109/tkde.2009.174","title":"An Efficient Concept-Based Mining Model for Enhancing Text Clustering","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":131,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Sentence; Natural language processing; Phrase; Term (time); Similarity (geometry); Semantics (computer science); Cluster analysis; Artificial intelligence; Document clustering; Meaning (existential); Word (group theory); Measure (data warehouse); Information retrieval; Similarity measure; Semantic similarity; Data mining; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02779020595604768,"gpt":0.2810140212831417,"spread":0.253223815327094,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000262825,0.0001803386,0.0001905087,0.0002198206,0.0002098036,0.0001705563,0.0007010057,0.00005614471,0.000001667858],"category_scores_gemma":[0.000006700024,0.0001856918,0.00004853342,0.0002611228,0.00001251327,0.0005065864,0.000007252913,0.0001152264,0.00000330278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000276966,"about_ca_system_score_gemma":0.00005162087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000271801,"about_ca_topic_score_gemma":0.00002273831,"domain_scores_codex":[0.9988211,0.00001339826,0.0002198609,0.0005637287,0.0001004537,0.0002814317],"domain_scores_gemma":[0.9987236,0.0001122982,0.00003214907,0.0009533399,0.00003945975,0.0001391547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004530902,0.00008491378,1.779571e-7,0.00001585297,0.00001214752,9.798123e-7,0.0005523343,0.9268813,0.003856711,0.00005512716,0.00005228357,0.06848367],"study_design_scores_gemma":[0.0003545949,0.0001017748,0.000004968153,0.00007302899,0.00003392881,0.000002615989,0.00003324074,0.9921582,0.006827439,0.00000272018,0.0001835741,0.0002238726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003891453,0.000129599,0.9952431,0.0000561388,0.0001894916,0.00009320914,0.000130284,0.0002380028,0.00002869334],"genre_scores_gemma":[0.8403625,0.000004060427,0.1594156,0.00006946542,0.00004538479,0.000009794446,0.00004544479,0.00001179664,0.0000359766],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8364711,"threshold_uncertainty_score":0.7572293,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1969381345","doi":"10.1109/tkde.2014.2320725","title":"Malware Propagation in Large-Scale Networks","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":123,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"National Natural Science Foundation of China","keywords":"Malware; Computer science; Pareto distribution; Scale (ratio); Scale-free network; Network security; Exponential function; Computer security; Exponential distribution; Complex network; Theoretical computer science; Data mining; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01172611878137981,"gpt":0.2281549863714376,"spread":0.2164288675900578,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000316724,0.0001067481,0.0001068569,0.0001512505,0.0001018569,0.00006943711,0.000338688,0.00007458323,0.000008375896],"category_scores_gemma":[0.000004331221,0.0001091844,0.00001793972,0.0003717266,0.000008089294,0.0006524643,0.00001357162,0.0002450508,0.00001770592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002112554,"about_ca_system_score_gemma":0.000008946151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005984046,"about_ca_topic_score_gemma":0.0001393966,"domain_scores_codex":[0.9992097,0.00003213925,0.0001536045,0.0003354847,0.00007139743,0.0001976459],"domain_scores_gemma":[0.9993138,0.00006526827,0.00001878911,0.0005193247,0.00002036069,0.00006246495],"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":[0.00002157431,0.0003247213,0.00006519006,0.0001066199,0.00001873934,0.000003490922,0.001116908,0.4471264,0.0005276478,0.002358262,0.0004401499,0.5478903],"study_design_scores_gemma":[0.0002496239,0.00004752382,0.0003158597,0.00005898292,0.000003819918,0.000006826274,0.000005659273,0.9907829,0.0008191997,0.00002832227,0.007556307,0.000125041],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004746902,0.0001579907,0.9939108,0.00005028458,0.0007211432,0.00009626423,0.000006781121,0.0001528463,0.0001570217],"genre_scores_gemma":[0.9952744,0.0001195628,0.004390751,0.00003132184,0.000108071,0.00001506297,0.00000888811,0.000009306713,0.00004261576],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9905275,"threshold_uncertainty_score":0.4452412,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2085909071","doi":"10.1109/tkde.2010.226","title":"Privacy Preserving Decision Tree Learning Using Unrealized Data Sets","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":112,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Decision tree; Incremental decision tree; Tree (set theory); Decision tree learning; Information privacy; Data mining; Artificial intelligence; Machine learning; Computer security; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.06209211290478007,"gpt":0.3253722159210252,"spread":0.2632801030162451,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0008289365,0.0003004261,0.0002733222,0.0003913953,0.0003473822,0.0003605883,0.02865805,0.0002056134,0.00002048727],"category_scores_gemma":[0.002694152,0.0003052232,0.00003223964,0.0006806769,0.000052975,0.003233462,0.009679719,0.001115755,0.00002396997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003693302,"about_ca_system_score_gemma":0.00008046273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005923727,"about_ca_topic_score_gemma":0.0001275432,"domain_scores_codex":[0.99768,0.000042442,0.0003627376,0.001190877,0.0002644911,0.0004594159],"domain_scores_gemma":[0.981989,0.0006485488,0.00007308756,0.01707724,0.00005788721,0.0001542219],"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":[0.00003694793,0.0003111935,0.0001264041,0.0002016348,0.0001568165,0.00004623686,0.0002980576,0.01194805,0.04296456,0.0002320826,0.0148754,0.9288026],"study_design_scores_gemma":[0.0004479336,0.00002872208,0.0001116835,0.0001353054,0.00002942512,0.00005905716,0.000008965685,0.9823125,0.003717231,0.000616886,0.01220363,0.0003286486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02380718,0.0002919365,0.972679,0.0003307918,0.001293812,0.0001813596,0.0002105176,0.0010991,0.0001063124],"genre_scores_gemma":[0.4240717,0.000198681,0.5754898,0.000009711624,0.00006308425,0.000008161234,0.00009955382,0.00003910035,0.0000201634],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9703645,"threshold_uncertainty_score":0.99994,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2142103633","doi":"10.1109/tkde.2006.172","title":"Discovering Frequent Closed Partial Orders from Strings","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"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; National Natural Science Foundation of China; National Science Foundation","keywords":"Computer science; Multiset; Data mining; String (physics); Pruning; Set (abstract data type); Knowledge extraction; Order (exchange); Theoretical computer science; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01726091384251803,"gpt":0.2454227689265866,"spread":0.2281618550840686,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008104604,0.0001492711,0.000122726,0.00008592279,0.0001420045,0.0001899458,0.0006378362,0.00004413474,0.000008920797],"category_scores_gemma":[0.000002348714,0.0001527701,0.00002621944,0.0002340124,0.00001832911,0.0007576906,0.00002214874,0.0001532406,0.00003306237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002516229,"about_ca_system_score_gemma":0.00002570348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004847812,"about_ca_topic_score_gemma":0.00008797783,"domain_scores_codex":[0.9990181,0.000007836794,0.0001836054,0.0004833777,0.00009854178,0.0002085265],"domain_scores_gemma":[0.9989446,0.00008500744,0.00002527378,0.0008537541,0.00001596807,0.00007543514],"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":[0.00001634502,0.0009825596,0.00007444298,0.00009596853,0.0002083218,0.00002896053,0.0008142356,0.08190013,0.02814152,0.01764404,0.003848367,0.8662451],"study_design_scores_gemma":[0.0003411898,0.00002322897,0.0003339497,0.00004581538,0.00002177482,0.000003886598,0.00001091036,0.9626608,0.01192566,0.00008028219,0.0243016,0.0002508315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0177417,0.000153687,0.980753,0.00007641144,0.0003722316,0.00008412961,0.0004548825,0.0002235896,0.0001403496],"genre_scores_gemma":[0.9338047,0.00004879589,0.06574257,0.00001367867,0.0001530315,0.00003123274,0.0001263956,0.00001734937,0.0000622417],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.916063,"threshold_uncertainty_score":0.6229783,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2142407957","doi":"10.1109/tkde.2010.152","title":"A Machine Learning Approach for Identifying Disease-Treatment Relations in Short Texts","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":88,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Domain (mathematical analysis); Field (mathematics); Set (abstract data type); Health care; Machine learning; Artificial intelligence; Dissemination; Information extraction; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.03615084399736213,"gpt":0.3036804357149973,"spread":0.2675295917176352,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001141546,0.0001141068,0.00009727784,0.00007957437,0.00009414869,0.00001993748,0.0001159061,0.00009597624,0.000003992708],"category_scores_gemma":[0.00002888675,0.0001043717,0.00003436522,0.00007109288,0.00002852391,0.000008167922,0.000006254895,0.0001654682,0.000001751987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009098444,"about_ca_system_score_gemma":0.0000266773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008721762,"about_ca_topic_score_gemma":0.0001094285,"domain_scores_codex":[0.9993793,0.00001001225,0.0001168654,0.0003087133,0.00003591632,0.000149185],"domain_scores_gemma":[0.9995773,0.00003745235,0.000007672468,0.0002800116,0.00001293153,0.00008457683],"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":[0.0003168347,0.001527187,0.004219961,0.0003936346,0.0003562684,0.00001163806,0.0007099883,0.05734234,0.3783905,0.0001262606,0.0004059272,0.5561994],"study_design_scores_gemma":[0.001498496,0.0003678424,0.002892682,0.00006796973,0.0001348297,0.00002198608,0.00007915618,0.865657,0.02265521,0.00001457635,0.10607,0.0005402422],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08613843,0.001364699,0.9117308,0.00002635339,0.0002365335,0.0001811428,0.0001808244,0.00004446999,0.00009674636],"genre_scores_gemma":[0.9873821,0.0001934219,0.01155891,0.00000421512,0.00007739292,0.00007907087,0.0003724264,0.00001688701,0.000315589],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9012437,"threshold_uncertainty_score":0.4256156,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3173856251","doi":"10.1109/tkde.2021.3090664","title":"Hierarchical Multi-View Graph Pooling with Structure Learning","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Pooling; Theoretical computer science; Graph; Upsampling; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01904280756439184,"gpt":0.2570408665654081,"spread":0.2379980590010163,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006299529,0.0001844163,0.0001786393,0.0001191377,0.0001883586,0.00009779711,0.0004188205,0.00006308717,0.000006090596],"category_scores_gemma":[0.000007490387,0.0001647212,0.00003089637,0.0006317936,0.00002572537,0.0005929618,0.00002067054,0.0006366213,0.000003522664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001188804,"about_ca_system_score_gemma":0.00003249869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001359171,"about_ca_topic_score_gemma":0.00003612683,"domain_scores_codex":[0.9989044,0.00003303893,0.0001431506,0.0005460316,0.0001113307,0.0002620336],"domain_scores_gemma":[0.9989986,0.0001429391,0.00002164683,0.0006604624,0.00004785588,0.0001285413],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001216634,0.0001080078,0.00004547948,0.0001375093,0.0001010179,0.0001289342,0.0005057104,0.7960659,0.005525045,0.001056878,0.00002537219,0.196288],"study_design_scores_gemma":[0.0005480915,0.00006780569,0.000233104,0.0002341144,0.00002887175,0.0002198717,0.00001487988,0.9883364,0.006607865,0.0000669059,0.003286783,0.0003553196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004413978,0.00168592,0.99318,0.00005616011,0.0003290222,0.00006331563,0.00002141247,0.0002352056,0.00001497586],"genre_scores_gemma":[0.8424382,0.0005158379,0.1568389,0.00003615573,0.00005313014,0.000005902796,0.0000187862,0.0000240918,0.00006908045],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8380241,"threshold_uncertainty_score":0.6717135,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2059054797","doi":"10.1109/tkde.2013.88","title":"Mining Statistically Significant Co-location and Segregation Patterns","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Data mining; Correlation; Artificial intelligence; Pattern recognition (psychology); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02346222270620061,"gpt":0.2662764905445469,"spread":0.2428142678383463,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001172729,0.0001149629,0.00009376403,0.00009814605,0.0001303333,0.0002239402,0.0003063648,0.00003731944,0.00001162727],"category_scores_gemma":[0.000008127247,0.0001140788,0.000007502587,0.0001695901,0.0000193416,0.0008171042,0.00001144191,0.0000997757,0.00003845317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001387817,"about_ca_system_score_gemma":0.00002222805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004929788,"about_ca_topic_score_gemma":0.000009099314,"domain_scores_codex":[0.9992233,0.00001222495,0.0001593712,0.0003763684,0.00008048425,0.0001482464],"domain_scores_gemma":[0.9991368,0.0001551785,0.00002493002,0.0005236433,0.00005117925,0.0001082559],"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":[9.605554e-7,0.00008008433,0.00003421058,0.00008493797,0.00002079143,0.000001176553,0.0005016862,0.0006227955,0.001621274,0.002625365,0.0005480857,0.9938586],"study_design_scores_gemma":[0.0001462528,0.00003791708,0.001961406,0.00004760027,0.0000119716,0.000007255225,0.00003968733,0.9955748,0.00115568,0.00004212369,0.0008224653,0.0001528004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007077262,0.00005133887,0.9921492,0.0001164814,0.0001131526,0.0001468264,0.0001604961,0.0001238907,0.00006138504],"genre_scores_gemma":[0.8807807,0.00007153591,0.1188743,0.00002271406,0.00002752175,0.00006996468,0.00008167647,0.00001136898,0.00006019584],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.994952,"threshold_uncertainty_score":0.4651997,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3185513611","doi":"10.1109/tkde.2022.3220948","title":"Rethinking Graph Auto-Encoder Models for Attributed Graph Clustering","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Randomness; Computer science; Adjacency matrix; Correlation clustering; Feature (linguistics); Graph; Clustering coefficient; Encoder; Data mining; Pattern recognition (psychology); Theoretical computer science; Artificial intelligence; Algorithm; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.05141376820259933,"gpt":0.2706461837856772,"spread":0.2192324155830779,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003528534,0.000233311,0.0002231956,0.0003506531,0.0006529049,0.00009500977,0.001091345,0.00005885577,0.000004616655],"category_scores_gemma":[0.000004540154,0.0002619003,0.00008619091,0.000832136,0.00002186541,0.001176553,0.00007943263,0.0004862723,0.000001239713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004772844,"about_ca_system_score_gemma":0.00002582185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005519607,"about_ca_topic_score_gemma":0.00001865789,"domain_scores_codex":[0.9984136,0.00003806743,0.0002618097,0.0007018227,0.0001804668,0.0004042282],"domain_scores_gemma":[0.9985359,0.0002682478,0.00004702292,0.0009876703,0.00004439318,0.0001168222],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001359659,0.00005254314,6.150192e-7,0.00004043485,0.00004012481,0.000005441871,0.0004926433,0.9754489,0.0005475667,0.001219682,0.0001978839,0.02194056],"study_design_scores_gemma":[0.0004471912,0.00009033839,0.000004075422,0.00003327492,0.00002352833,0.00004821858,0.0000146287,0.9925967,0.0004326911,0.00399357,0.002020407,0.0002953717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004127463,0.0006584151,0.9963865,0.00009538344,0.001355463,0.0003141962,0.0002332014,0.0005118487,0.00003226931],"genre_scores_gemma":[0.8858261,0.0001517802,0.1134845,0.00009370599,0.0000544348,0.0002174664,0.00005488359,0.00004628066,0.00007092352],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8854133,"threshold_uncertainty_score":0.9999833,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2091214390","doi":"10.1109/tkde.2012.220","title":"Bias Correction in a Small Sample from Big Data","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":71,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Sample size determination; Computer science; Sampling bias; Big data; Sample (material); Simple random sample; Population size; Sampling (signal processing); Statistics; Reciprocal; Population; Point estimation; Data mining; Mathematics; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.1054743786026927,"gpt":0.291973674795889,"spread":0.1864992961931962,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002017402,0.0001440873,0.0001715052,0.0001596882,0.00005942028,0.00003768162,0.0003455977,0.00003488257,0.0000842236],"category_scores_gemma":[0.000004628803,0.000151624,0.00002638959,0.0002796486,0.00001050491,0.0003379993,0.00002428931,0.0002190635,0.00001782021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002032066,"about_ca_system_score_gemma":0.00001469365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001771138,"about_ca_topic_score_gemma":0.000915329,"domain_scores_codex":[0.9992189,0.00002390862,0.0001851089,0.0003113101,0.00004351863,0.0002171944],"domain_scores_gemma":[0.9986143,0.0002844278,0.00002676073,0.0009817338,0.00001237402,0.00008040761],"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":[0.00001683013,0.0005624874,0.008457338,0.00001660068,0.0001850858,4.823119e-7,0.0005007351,0.003186948,0.0008408173,0.0001110594,0.002225028,0.9838966],"study_design_scores_gemma":[0.0005716198,0.00003060772,0.005730016,0.0001662203,0.0002216406,0.000001522991,0.000171401,0.9165331,0.004123494,0.0001389943,0.07173528,0.0005760954],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02976199,0.0003158721,0.9678766,0.000007196609,0.0007925911,0.00008691838,0.000843008,0.00009090141,0.0002249026],"genre_scores_gemma":[0.9943161,0.00003706256,0.004241915,0.000004113786,0.0004639294,0.00001668682,0.0008527008,0.00002041213,0.00004707208],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9833205,"threshold_uncertainty_score":0.6183048,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2076039115","doi":"10.1109/tkde.2009.25","title":"Evaluating the Generation of Domain Ontologies in the Knowledge Puzzle Project","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Ontology; Computer science; Ontology learning; Upper ontology; Information retrieval; Domain (mathematical analysis); Ontology-based data integration; Domain knowledge; Process ontology; Suggested Upper Merged Ontology; Set (abstract data type); Ontology alignment; Natural language processing; Data science; Artificial intelligence; Semantic Web","retraction":null,"screen_n_in":null,"score":{"opus":0.1546157879818343,"gpt":0.3661375498068649,"spread":0.2115217618250305,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008713633,0.0001018684,0.0001076029,0.0001129747,0.0001257354,0.00006575783,0.0008079504,0.00003912305,8.327247e-7],"category_scores_gemma":[0.00001938048,0.00006537016,0.00002253036,0.0003314563,0.00001537259,0.0003558696,0.000009762877,0.0001830198,0.000002031382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002041336,"about_ca_system_score_gemma":0.00004585782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001701011,"about_ca_topic_score_gemma":0.0001490721,"domain_scores_codex":[0.9991903,0.00008628238,0.0002069792,0.0002634568,0.0001069953,0.00014594],"domain_scores_gemma":[0.9989139,0.0002056959,0.00002836333,0.0008096169,0.00002879378,0.00001363319],"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":[0.00001085026,0.0003325545,0.000008578974,0.0000749032,0.0000278672,0.00000330159,0.0187463,0.1348446,0.01717996,0.009188426,0.0002256692,0.819357],"study_design_scores_gemma":[0.0001823841,0.00009058989,0.0001413696,0.00003537935,0.000008155248,0.000009739869,0.0001098417,0.997099,0.001590401,0.0001043822,0.0005468494,0.00008185361],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03891435,0.0008551374,0.959178,0.0002572009,0.0002491175,0.0002202991,0.000006400674,0.00004989064,0.0002695524],"genre_scores_gemma":[0.9748093,0.00005632752,0.02500234,0.00002070326,0.00006293332,0.00002127113,0.000002710038,0.000003847534,0.00002059968],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9358949,"threshold_uncertainty_score":0.2665718,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2131967083","doi":"10.1109/tkde.2010.262","title":"Resilient Identity Crime Detection","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Advantage Forensics (Canada)","funders":"Australian Research Council; University of Warwick","keywords":"Computer science; Identity (music); Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.03861372655258806,"gpt":0.271454297643489,"spread":0.2328405710909009,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001302225,0.0001049536,0.00008112096,0.0001537309,0.0001628192,0.00005608775,0.0005187141,0.00005301046,0.00001696169],"category_scores_gemma":[0.000002333257,0.0001092711,0.00002810042,0.0003197784,0.00001597481,0.0009551146,0.00001648774,0.0001488436,0.00005900265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002396316,"about_ca_system_score_gemma":0.00001187361,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003566016,"about_ca_topic_score_gemma":0.00003015273,"domain_scores_codex":[0.9992883,0.00001061858,0.0001411959,0.0003529917,0.00007089831,0.0001360549],"domain_scores_gemma":[0.999044,0.00002297818,0.00002246993,0.0007990946,0.00003204959,0.00007938431],"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":[0.00002956737,0.0009117267,0.00001831064,0.0001465603,0.0001213846,0.00001084777,0.001756719,0.0008294694,0.04583066,0.03273528,0.0006399393,0.9169695],"study_design_scores_gemma":[0.0003086627,0.000217241,0.002092998,0.00004775185,0.00004539606,0.00006636703,0.00003023129,0.4991866,0.4824637,0.0007846566,0.01424552,0.0005108661],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001979674,0.0001001196,0.9960957,0.000009815875,0.0002985413,0.0001091417,0.00001472344,0.0004789632,0.0009133256],"genre_scores_gemma":[0.9766067,0.00008955969,0.02309212,0.00001341491,0.00002786401,0.00004050105,0.000001488508,0.000009695036,0.0001186622],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.974627,"threshold_uncertainty_score":0.4455945,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2129500661","doi":"10.1109/tkde.2008.162","title":"Mining Projected Clusters in High-Dimensional Spaces","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Cluster analysis; Computer science; Curse of dimensionality; Linear subspace; Outlier; Clustering high-dimensional data; Data mining; CURE data clustering algorithm; Data point; Correlation clustering; Computation; Pattern recognition (psychology); Canopy clustering algorithm; Single-linkage clustering; Algorithm; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03923416376241975,"gpt":0.2902071390881266,"spread":0.2509729753257069,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001470902,0.0001490361,0.0001529528,0.0003615766,0.0001305117,0.00004451277,0.0005477946,0.000054011,0.000003708798],"category_scores_gemma":[0.00001167857,0.0001519289,0.00001649736,0.0005637464,0.00003442713,0.0007464144,0.00003680541,0.0002589603,0.00001544827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005529967,"about_ca_system_score_gemma":0.00006496651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003081904,"about_ca_topic_score_gemma":0.00004048389,"domain_scores_codex":[0.9988579,0.00002510862,0.0001678302,0.0004770953,0.0001720259,0.000300053],"domain_scores_gemma":[0.9990692,0.0001697037,0.00001703606,0.000610294,0.00003472555,0.00009900614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005205935,0.0004295947,0.00007480193,0.0001740253,0.00007519741,0.0003074731,0.003033961,0.8233709,0.005062124,0.0001236625,0.0004251665,0.166871],"study_design_scores_gemma":[0.000505304,0.00005658673,0.0003523895,0.00007545039,0.000002484583,0.00009525517,0.00001517613,0.996149,0.002101911,0.000003042303,0.0004613504,0.0001820326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07835083,0.0001686478,0.9207112,0.00007827223,0.0003583954,0.0001182878,0.00001671544,0.00016878,0.0000288964],"genre_scores_gemma":[0.8648399,0.00007677724,0.1347946,0.00001285725,0.00003863903,0.00002413629,0.000008119606,0.00001836168,0.0001866567],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.786489,"threshold_uncertainty_score":0.619548,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2543722153","doi":"10.1109/tkde.2017.2740284","title":"Activity Maximization by Effective Information Diffusion in Social Networks","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":63,"is_retracted":false,"has_abstract":true,"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; National Natural Science Foundation of China","keywords":"Computer science; Submodular set function; Scalability; Maximization; Polling; Approximation algorithm; Heuristic; Upper and lower bounds; Social network (sociolinguistics); Mathematical optimization; Algorithm; Artificial intelligence; Social media; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01055453571133445,"gpt":0.2678646365113213,"spread":0.2573101007999868,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001161536,0.0001159583,0.0001385004,0.00009488957,0.000331966,0.0001205777,0.0001973507,0.00004526682,0.0000180168],"category_scores_gemma":[0.000001689966,0.0001236162,0.00002959876,0.00008641387,0.0000171352,0.0009555359,0.0000132622,0.0001949726,0.000003702765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002781328,"about_ca_system_score_gemma":0.000006110868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001263162,"about_ca_topic_score_gemma":0.00002751637,"domain_scores_codex":[0.9995274,0.00001757317,0.0001169007,0.0001573162,0.00005091384,0.0001298728],"domain_scores_gemma":[0.9994955,0.00004334796,0.00005911151,0.0003506387,0.00001997548,0.00003140367],"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":[0.00003726341,0.0002204829,0.001416062,0.00002720965,0.0000726942,2.304941e-7,0.0002702161,0.02203332,0.0007527949,0.0002987296,0.0009528073,0.9739182],"study_design_scores_gemma":[0.0003804956,0.00001609255,0.007797851,0.00003439856,0.00003062632,1.631856e-7,0.00001061491,0.9885112,0.001205033,0.00003789301,0.001819265,0.0001563803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04848959,0.00001799199,0.9505302,0.00001838801,0.000100609,0.0001607683,0.00008438587,0.00004809547,0.0005499705],"genre_scores_gemma":[0.9995152,0.00001830846,0.0001840437,0.000002572402,0.0001012489,0.00003863819,0.000110365,0.000008816063,0.00002084893],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9737618,"threshold_uncertainty_score":0.5040921,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2766449686","doi":"10.1109/tkde.2017.2766059","title":"A Location-Query-Browse Graph for Contextual Recommendation","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":61,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Australian Research Council","keywords":"Computer science; Graph; Bipartite graph; Information retrieval; Graph database; Web search query; Web query classification; Homogeneous; Theoretical computer science; World Wide Web; Search engine; Mathematics; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.0619002510906548,"gpt":0.3532966062404341,"spread":0.2913963551497793,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0005916502,0.00009212331,0.0001173218,0.0001162691,0.0014635,0.0001836981,0.000329561,0.00006978256,0.00007681379],"category_scores_gemma":[0.0001121771,0.0001014449,0.00004239872,0.0001031339,0.00009595812,0.0005558295,0.000003043082,0.0001004962,0.0000190654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004194381,"about_ca_system_score_gemma":0.00009147827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001123959,"about_ca_topic_score_gemma":0.01380643,"domain_scores_codex":[0.9993125,0.00003098611,0.0001552229,0.0002726325,0.00006975516,0.000158955],"domain_scores_gemma":[0.9989514,0.0002530891,0.00004890709,0.0005311359,0.0001222417,0.00009319367],"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":[0.00008770586,0.0006529054,0.0001794388,0.0003774284,0.00033622,8.210013e-7,0.01383094,0.009816675,0.0004445658,0.00832794,0.002970865,0.9629745],"study_design_scores_gemma":[0.00269741,0.0002246404,0.001670392,0.0003974407,0.0005777846,0.000001744047,0.005068279,0.6309093,0.002334788,0.0008611495,0.3540578,0.001199289],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003057183,0.00009582618,0.9947436,0.0006640108,0.0003971272,0.0002391585,0.0001469217,0.00007361134,0.0005825625],"genre_scores_gemma":[0.9984527,0.000136494,0.0005384065,0.00002467311,0.0001569795,0.00006885589,0.00007853625,0.00001006728,0.0005333262],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9953955,"threshold_uncertainty_score":0.9998364,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400033057","doi":"10.1109/tkde.2024.3419215","title":"Ze-HFS: Zentropy-Based Uncertainty Measure for Heterogeneous Feature Selection and Knowledge Discovery","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Computer science; Measure (data warehouse); Feature selection; Selection (genetic algorithm); Feature (linguistics); Knowledge extraction; Data mining; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01879242851704101,"gpt":0.2692210126805711,"spread":0.2504285841635301,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001568315,0.0001943338,0.0001445946,0.0002110521,0.0002353045,0.0003425572,0.0002946206,0.0001071373,0.000001732272],"category_scores_gemma":[0.000004303283,0.0001827791,0.0000615668,0.0004113356,0.00002032895,0.0005846975,0.00001167126,0.0002211755,0.000006103894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006047479,"about_ca_system_score_gemma":0.00007672987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007699914,"about_ca_topic_score_gemma":0.00005128375,"domain_scores_codex":[0.9989806,0.00001604591,0.0001435326,0.000586026,0.00007060778,0.0002031849],"domain_scores_gemma":[0.9992468,0.0001433946,0.00001756575,0.0004466204,0.00005321255,0.00009242217],"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":[0.0000862649,0.0005739864,0.000007314223,0.001604992,0.0003954202,0.00000961273,0.0008018842,0.1041398,0.04746437,0.01483329,0.00623766,0.8238454],"study_design_scores_gemma":[0.0001852594,0.0001155016,0.000007127246,0.0001015356,0.0000462391,0.00003639336,0.000004735117,0.9303893,0.02142643,0.00008567284,0.04738554,0.0002162571],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009760287,0.002304933,0.994902,0.0001980797,0.00039826,0.0003231851,0.0001968506,0.0006625709,0.00003813776],"genre_scores_gemma":[0.9863064,0.0001362985,0.01286401,0.00001930343,0.0001220666,0.0001871325,0.00003091596,0.00002886764,0.0003050368],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9853303,"threshold_uncertainty_score":0.7453517,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2894983428","doi":"10.1109/tkde.2018.2874004","title":"Precise and Fast Cryptanalysis for Bloom Filter Based Privacy-Preserving Record Linkage","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":56,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"Australian Research Council; Engineering and Physical Sciences Research Council; Simons Foundation","keywords":"Bloom filter; Computer science; Cryptanalysis; Encoding (memory); Scalability; Data mining; Filter (signal processing); Information retrieval; Algorithm; Database; Cryptography; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1370625278578638,"gpt":0.3797145295626111,"spread":0.2426520017047473,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001525118,0.0001829118,0.0002667271,0.0004003592,0.0002609995,0.0003488799,0.0009780501,0.00007015829,0.0002581577],"category_scores_gemma":[0.0002989434,0.0001578733,0.00006376469,0.0004641517,0.00005962108,0.0008003472,0.00006468348,0.0001273126,0.00006195874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001583655,"about_ca_system_score_gemma":0.00002151901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002224448,"about_ca_topic_score_gemma":0.0002727275,"domain_scores_codex":[0.9982842,0.00005503653,0.0004259618,0.0007207556,0.0002662091,0.0002478651],"domain_scores_gemma":[0.9969954,0.001053056,0.00006252074,0.001607981,0.0001325132,0.0001484721],"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":[0.0001853527,0.0003797008,0.00007094775,0.0002937481,0.0002929227,0.000004459372,0.001264957,0.003542091,0.002119344,0.0001492414,0.0328073,0.95889],"study_design_scores_gemma":[0.0006101198,0.0001228409,0.0001670246,0.00007932181,0.0001378783,0.000001272751,0.0001222751,0.7403471,0.002760311,0.0002067025,0.2552008,0.0002443934],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008671869,0.0001383258,0.9888781,0.0002773677,0.0005128523,0.0002550057,0.0008922806,0.00007159388,0.0003026408],"genre_scores_gemma":[0.9360349,0.000165437,0.06076394,0.0001533003,0.0003241334,0.00008447131,0.0001119919,0.00004107708,0.002320793],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9586455,"threshold_uncertainty_score":0.6437886,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2128933128","doi":"10.1109/tkde.2008.38","title":"Simultaneous Pattern and Data Clustering for Pattern Cluster Analysis","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data mining; Cluster analysis; Categorical variable; Relation (database); Cluster (spacecraft); Data set; Set (abstract data type); Pattern recognition (psychology); Consensus clustering; Measure (data warehouse); Artificial intelligence; Fuzzy clustering; CURE data clustering algorithm; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.03944602358900941,"gpt":0.2853976676282162,"spread":0.2459516440392067,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001813423,0.0001793191,0.0002126531,0.0002071204,0.0002621051,0.0001344155,0.001130899,0.00005526418,0.000003524892],"category_scores_gemma":[0.00001035234,0.0001797189,0.00003147147,0.0003646181,0.00002770916,0.0007536913,0.0001060719,0.0001342254,0.000008439316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001337328,"about_ca_system_score_gemma":0.00001837376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000531368,"about_ca_topic_score_gemma":0.000173749,"domain_scores_codex":[0.9986657,0.00001147176,0.0002194205,0.0007784782,0.00009137484,0.0002335386],"domain_scores_gemma":[0.9975773,0.0003515846,0.00003332007,0.001879468,0.0000352214,0.0001231342],"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":[0.000003652913,0.000115368,0.00004601441,0.00008470062,0.0002774402,0.000009875062,0.0005666926,0.0234435,0.0001046683,0.000006353896,0.0006013871,0.9747403],"study_design_scores_gemma":[0.0002960615,0.00003270895,0.0001220898,0.00002281983,0.0001306145,0.00004300318,0.00001013623,0.9912726,0.000101866,0.000001467904,0.007755422,0.0002112155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002079815,0.0002102385,0.9953512,0.0001335435,0.0001888187,0.0001714565,0.001713836,0.0001401918,0.00001088752],"genre_scores_gemma":[0.9283933,0.0003045149,0.07050336,0.00008659467,0.00009904372,0.00004571191,0.0004347808,0.00002441043,0.0001083032],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9745291,"threshold_uncertainty_score":0.7328723,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3167049326","doi":"10.1109/tkde.2023.3328882","title":"DASVDD: Deep Autoencoding Support Vector Data Descriptor for Anomaly Detection","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Anomaly detection; Support vector machine; Artificial intelligence; Pattern recognition (psychology); Anomaly (physics); Data mining; Data modeling","retraction":null,"screen_n_in":null,"score":{"opus":0.05801809301462153,"gpt":0.298694577054953,"spread":0.2406764840403315,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000336086,0.0001718271,0.0001509202,0.0002965219,0.0003315262,0.0001498753,0.001183627,0.00008446008,0.000009373998],"category_scores_gemma":[0.00001397443,0.0001850844,0.00003905367,0.0007114841,0.00001802784,0.001070251,0.00005725256,0.0001631189,0.00005968888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004079521,"about_ca_system_score_gemma":0.00003843066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001338223,"about_ca_topic_score_gemma":0.00004569875,"domain_scores_codex":[0.9986665,0.00001161535,0.0002344904,0.000705694,0.00009711589,0.0002845343],"domain_scores_gemma":[0.9980186,0.0001386841,0.0000388742,0.001642612,0.00004730701,0.0001139881],"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":[0.00002689302,0.0002474704,0.0000109109,0.0002973043,0.0001495351,0.000007874267,0.000588613,0.005900703,0.06146315,0.002287498,0.006098426,0.9229216],"study_design_scores_gemma":[0.0001806605,0.00009270017,0.0001083353,0.00001765719,0.00002598815,0.00001735241,0.00001644587,0.9287847,0.02327662,0.000037578,0.04723144,0.0002104908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009128288,0.00006004719,0.9962047,0.00009836668,0.0006872516,0.0003208499,0.0003281974,0.001328597,0.00005915534],"genre_scores_gemma":[0.9505385,0.0001444363,0.04842865,0.00002567412,0.000147994,0.000221268,0.0001486347,0.00003493699,0.0003098846],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9496257,"threshold_uncertainty_score":0.7547522,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3163325638","doi":"10.1109/tkde.2021.3075052","title":"Learning Hierarchical Review Graph Representations for Recommendation","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"BC Research (Canada)","funders":"Youth Innovation Promotion Association; Youth Innovation Promotion Association of the Chinese Academy of Sciences; National Research Foundation Singapore; National Natural Science Foundation of China; Nanyang Technological University; National Research Foundation","keywords":"Computer science; Pooling; Graph; Recommender system; Artificial intelligence; Convolutional neural network; Recurrent neural network; Machine learning; Information retrieval; Theoretical computer science; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.04649403019805645,"gpt":0.3242526013051148,"spread":0.2777585711070584,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002962213,0.0001006747,0.0001503309,0.00009661326,0.0001584115,0.00008299175,0.0002633084,0.00003913018,0.00001172021],"category_scores_gemma":[0.00002486308,0.0001032834,0.00004824166,0.0002980326,0.000006442916,0.0004742716,0.00001374136,0.0001850286,0.000004344913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001442548,"about_ca_system_score_gemma":0.00003065887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004319665,"about_ca_topic_score_gemma":0.000009611988,"domain_scores_codex":[0.9991678,0.00004861224,0.000209676,0.0003858417,0.00005334167,0.0001347323],"domain_scores_gemma":[0.9990819,0.0002299335,0.00002884694,0.0005277234,0.00006624627,0.00006531111],"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":[0.000003466255,0.0001846628,0.000009909862,0.001242023,0.0001019502,0.000004998812,0.0003333116,0.0007638694,0.001129815,0.004844619,0.01182279,0.9795586],"study_design_scores_gemma":[0.0005529416,0.0001584852,0.00005628011,0.001364047,0.00007423177,0.0001227792,0.00003794824,0.5360892,0.0122725,0.0004730817,0.4483151,0.0004834521],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002414277,0.001856027,0.9957923,0.001103429,0.0004161988,0.0001884099,0.00003521095,0.0002313289,0.0003530069],"genre_scores_gemma":[0.4166996,0.04266735,0.5361134,0.0007374038,0.000368614,0.0008602386,0.0007808705,0.00009759684,0.001674979],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9790751,"threshold_uncertainty_score":0.4211774,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2127426313","doi":"10.1109/69.929898","title":"Constructing the dependency structure of a multiagent probabilistic network","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Regina","funders":"","keywords":"Dependency (UML); Probabilistic logic; Computer science; Cover (algebra); Graphical model; Representation (politics); Theoretical computer science; Domain (mathematical analysis); Dependency graph; Conditional probability; Artificial intelligence; Data mining; Mathematics; Graph","retraction":null,"screen_n_in":null,"score":{"opus":0.0310304745145064,"gpt":0.2611466064437121,"spread":0.2301161319292057,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001307895,0.0001177266,0.0001216713,0.00004474395,0.0001167016,0.0000524777,0.0006049273,0.00004752879,0.000008143611],"category_scores_gemma":[0.00001016003,0.00008940815,0.00002285789,0.0002703344,0.00003234433,0.0002352226,0.00001625177,0.0002183403,0.000002629609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001456524,"about_ca_system_score_gemma":0.00003652559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001400424,"about_ca_topic_score_gemma":0.00007123351,"domain_scores_codex":[0.9992467,0.00002284001,0.0001821736,0.0002773891,0.00008849594,0.0001823873],"domain_scores_gemma":[0.9990463,0.0001565802,0.00003337226,0.0006642294,0.00004301067,0.00005646831],"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":[0.00001384069,0.0001099509,0.0001240198,0.0001568405,0.0001016242,0.00001039945,0.001086376,0.4699442,0.002311534,0.01524836,0.000118291,0.5107746],"study_design_scores_gemma":[0.0001287372,0.0000273814,0.00004999018,0.00007752793,0.00001970278,0.00006973524,0.00002334272,0.9977737,0.001068552,0.0004507422,0.0001934179,0.0001171447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01197128,0.0003896591,0.9868647,0.00004464524,0.0004407915,0.00009753496,0.0000304468,0.00007776269,0.00008311037],"genre_scores_gemma":[0.9776151,0.00007011861,0.02222091,0.00001058777,0.00005377846,0.000003689825,0.000003000656,0.000007091047,0.00001575361],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9656438,"threshold_uncertainty_score":0.3645959,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2807633791","doi":"10.1109/tkde.2018.2857471","title":"Secure and Efficient Skyline Queries on Encrypted Data","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Cryptography and Data Security","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"National Institutes of Health; National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Patient-Centered Outcomes Research Institute","keywords":"Computer science; Encryption; Cloud computing; Skyline; Scalability; Database; Outsourcing; Computer network; Data mining; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.02885223219186742,"gpt":0.2747359068435998,"spread":0.2458836746517324,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002694349,0.0001944149,0.0001571875,0.0002034296,0.0002340495,0.000152354,0.001067265,0.00007043251,0.00001367119],"category_scores_gemma":[0.00001754358,0.0001811466,0.00001594622,0.0004954873,0.00008907569,0.0006743341,0.00009002592,0.0002262428,0.00002620367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009107695,"about_ca_system_score_gemma":0.00002923531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001616767,"about_ca_topic_score_gemma":0.0000831423,"domain_scores_codex":[0.9987118,0.00002260998,0.0001735018,0.0007312957,0.0001274973,0.0002333467],"domain_scores_gemma":[0.9975647,0.0001429492,0.00002404711,0.002077244,0.00005100508,0.0001400144],"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":[0.0003695,0.003172555,0.00007025102,0.0009447517,0.0006581213,0.00008471085,0.01237388,0.00703934,0.01000794,0.1217287,0.02039197,0.8231583],"study_design_scores_gemma":[0.0004913128,0.0002286566,0.0002789197,0.0001128487,0.00003219968,0.00002875751,0.00003432758,0.936373,0.003111998,0.00006824882,0.05889122,0.0003485423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01080296,0.0006507462,0.9861723,0.00009742921,0.0007115857,0.0001134361,0.001074229,0.0002199408,0.00015735],"genre_scores_gemma":[0.9782171,0.0003216967,0.02109076,0.00005316688,0.0001323453,0.000006455839,0.0001564057,0.0000145897,0.000007526477],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9674141,"threshold_uncertainty_score":0.7386945,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2110420974","doi":"10.1109/tkde.2010.186","title":"Exact Top-K Queries in Wireless Sensor Networks","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Energy Efficient Wireless Sensor Networks","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Network topology; Wireless sensor network; Context (archaeology); Tree (set theory); Topology (electrical circuits); Algorithm; Set (abstract data type); Logical topology; Theoretical computer science; Computer network; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01204658840230878,"gpt":0.2362237369969768,"spread":0.224177148594668,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002244892,0.0002133824,0.000201207,0.0002267397,0.0001039126,0.0001262972,0.0007380766,0.0001472948,0.000008736735],"category_scores_gemma":[0.000005816469,0.0002185001,0.00003149772,0.0004988603,0.00003875292,0.0005577576,0.00002304328,0.0006539801,0.00001204892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001990702,"about_ca_system_score_gemma":0.0000252742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002930859,"about_ca_topic_score_gemma":0.000304543,"domain_scores_codex":[0.9987251,0.00002543694,0.0002286491,0.000548284,0.0001083199,0.0003641957],"domain_scores_gemma":[0.9984711,0.0002300723,0.00002756387,0.001113967,0.00002967239,0.0001276229],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008637493,0.0001615257,0.00009349635,0.00003053315,0.00002018314,0.00002487526,0.0002779141,0.9281231,0.00398115,0.001952676,0.00008631392,0.06523965],"study_design_scores_gemma":[0.0002469513,0.00002292901,0.000290618,0.0000528288,0.000005909207,0.00002626765,0.000009486736,0.9929169,0.003714307,0.000002324551,0.002460867,0.0002506207],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08187029,0.0001362357,0.9156399,0.00005421766,0.001756459,0.0000858374,0.000011557,0.0002468591,0.0001986583],"genre_scores_gemma":[0.984612,0.0001559273,0.01493092,0.0000215005,0.0001322716,0.00001398074,0.000008697975,0.00002432717,0.0001003195],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9027417,"threshold_uncertainty_score":0.8910177,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2003787915","doi":"10.1109/tkde.2014.2310219","title":"Discovery of Temporal Associations in Multivariate Time Series","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Data mining; Multivariate statistics; Time series; Pruning; Scalability; Redundancy (engineering); Series (stratigraphy); Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.01599466251246835,"gpt":0.2367904487629129,"spread":0.2207957862504445,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002448899,0.00009257191,0.0001740802,0.0001487202,0.00005595934,0.00006246076,0.0003074666,0.00003683161,0.000003294489],"category_scores_gemma":[0.00001836831,0.00008945377,0.00002783468,0.0003874938,0.0000132578,0.00114206,0.00001433438,0.00009906918,0.000007929561],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001555801,"about_ca_system_score_gemma":0.0000172274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006817064,"about_ca_topic_score_gemma":0.00008915098,"domain_scores_codex":[0.9993511,0.00002182126,0.0002062144,0.0002257185,0.00006620343,0.0001289228],"domain_scores_gemma":[0.9993775,0.0001084608,0.00004245601,0.0004142422,0.00002795047,0.00002933346],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008725067,0.001997831,0.002567084,0.0006163179,0.0008239264,0.00001613078,0.00893539,0.4537686,0.07590658,0.03436192,0.0007387589,0.4201802],"study_design_scores_gemma":[0.0001914053,0.00004178146,0.00146481,0.00004551745,0.00001379664,0.000001853644,0.000010138,0.9946885,0.002686882,0.00003353064,0.0006995121,0.0001223255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007291467,0.00005240763,0.992117,0.00004254807,0.0001264222,0.00004013892,0.00007382133,0.00004650432,0.000209687],"genre_scores_gemma":[0.98439,0.00001361,0.01529212,0.000003412658,0.00002262273,0.000003415511,0.00001773167,0.000007205678,0.0002498859],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9770985,"threshold_uncertainty_score":0.3647819,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3128735821","doi":"10.1109/tkde.2021.3054671","title":"Transfer Learning for Dynamic Feature Extraction Using Variational Bayesian Inference","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":47,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Inference; Bayesian inference; Weighting; Feature (linguistics); Machine learning; Transfer of learning; Artificial intelligence; Data mining; Bayesian probability; Domain (mathematical analysis); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01656466914588841,"gpt":0.2718116489394927,"spread":0.2552469797936043,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001110491,0.0001822586,0.0001781051,0.0001336834,0.0001590484,0.00007550175,0.00009332766,0.0001355929,0.00002726651],"category_scores_gemma":[0.00001183451,0.0002100131,0.00005520202,0.0002159697,0.000007417319,0.0004536027,0.000001486957,0.00033606,0.000005967284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007444487,"about_ca_system_score_gemma":0.0000369756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004153344,"about_ca_topic_score_gemma":0.00005722341,"domain_scores_codex":[0.9992234,0.00001966714,0.0001811378,0.0002885907,0.00008513875,0.0002021063],"domain_scores_gemma":[0.9994441,0.0001595066,0.000009736036,0.0002481256,0.00005620463,0.00008237432],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001161166,0.00002685493,0.000002205917,0.0001697897,0.00008832613,0.000002518252,0.0001091046,0.8854181,0.09827728,0.00004953545,0.0000223197,0.01582234],"study_design_scores_gemma":[0.0004916388,0.00002136998,0.00004077241,0.00008041497,0.00006232372,0.00004832169,0.00005734967,0.98028,0.00806698,0.000005448804,0.01062578,0.0002195324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007102989,0.000703805,0.9903407,0.00002526418,0.001219671,0.0001456808,0.0001279238,0.0002626469,0.00007134533],"genre_scores_gemma":[0.9963732,0.0001363614,0.002973301,0.000007373388,0.0001068042,0.00003847076,0.00007939077,0.00004563926,0.0002394504],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9892702,"threshold_uncertainty_score":0.8564085,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2134465446","doi":"10.1109/tkde.2006.11","title":"Input variable selection: mutual information and linear mixing measures","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Independent component analysis; Mutual information; Computer science; Preprocessor; Dependency (UML); Data pre-processing; Data mining; Mixing (physics); Feature selection; Pattern recognition (psychology); Blind signal separation; Algorithm; Gaussian; Artificial intelligence; Channel (broadcasting)","retraction":null,"screen_n_in":null,"score":{"opus":0.01617825178139467,"gpt":0.2422223643631334,"spread":0.2260441125817387,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002616715,0.0001104938,0.00009291824,0.000210269,0.0001379911,0.0001759056,0.000214509,0.00006634773,0.000002584585],"category_scores_gemma":[0.000006413752,0.0001158285,0.00001149364,0.0003172442,0.00001210822,0.00204226,0.00001061873,0.0001689793,0.00001014531],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001977243,"about_ca_system_score_gemma":0.00003757452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004024157,"about_ca_topic_score_gemma":0.00002637354,"domain_scores_codex":[0.9993829,0.00001886475,0.0001803681,0.0001963886,0.00009578375,0.0001257362],"domain_scores_gemma":[0.999519,0.00006217325,0.00002636732,0.0002883826,0.00005832102,0.00004575689],"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":[0.00005990833,0.0006279327,0.0001786944,0.0005660611,0.0002147042,0.000005391658,0.005714644,0.3452201,0.02143297,0.1156807,0.009177054,0.5011218],"study_design_scores_gemma":[0.0002126363,0.00004617682,0.0000858358,0.00003273804,0.00001046254,0.00002927102,0.000007494524,0.9382623,0.01401273,0.0001188042,0.04701042,0.0001710944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001244669,0.0001428562,0.9973345,0.00005775,0.0001562398,0.00009129879,0.00001778386,0.0004155549,0.000539362],"genre_scores_gemma":[0.8105866,0.00006501328,0.1890471,0.00006088649,0.00008302859,0.00001984734,0.00002381713,0.00001060824,0.000103052],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.809342,"threshold_uncertainty_score":0.4723347,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4312529005","doi":"10.1109/tkde.2022.3221316","title":"DMGAN: Dynamic Multi-Hop Graph Attention Network for Traffic Forecasting","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":40,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"National Natural Science Foundation of China","keywords":"Computer science; Leverage (statistics); Data mining; Graph; Network topology; Intelligent transportation system; Theoretical computer science; Artificial intelligence; Computer network","retraction":null,"screen_n_in":null,"score":{"opus":0.02779923458341519,"gpt":0.2480279719790504,"spread":0.2202287373956352,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002341267,0.0001913997,0.0001578284,0.000237457,0.0003115744,0.00003640445,0.0002444165,0.00004807865,0.00001129292],"category_scores_gemma":[0.000002387346,0.0002328631,0.0000664336,0.0003059541,0.00001229712,0.0002331275,0.00001092212,0.0002682309,0.00000273539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007048021,"about_ca_system_score_gemma":0.000006767061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001416163,"about_ca_topic_score_gemma":0.00003764582,"domain_scores_codex":[0.9990851,0.00001277108,0.0002222611,0.0003056532,0.0000871708,0.0002870141],"domain_scores_gemma":[0.9994822,0.00006475565,0.00001936799,0.0003486339,0.000015373,0.00006971938],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001022307,0.00006501647,9.546151e-7,0.0001391979,0.00007811825,0.000001735963,0.00008341792,0.9081423,0.0004722016,0.00003041314,0.004875211,0.08610117],"study_design_scores_gemma":[0.0004999231,0.00006517416,0.00003479746,0.00003680358,0.00006540879,0.00001256652,0.00006192854,0.9787058,0.00007137581,0.000003156649,0.02021709,0.0002260244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007822919,0.000626237,0.9858525,0.00001596378,0.001521715,0.0004253456,0.0003978929,0.003279385,0.00005805023],"genre_scores_gemma":[0.9850779,0.0002478141,0.01389266,0.00001138963,0.00006476737,0.0003432655,0.0001988616,0.00006498906,0.00009833041],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.977255,"threshold_uncertainty_score":0.9495882,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4312251623","doi":"10.1109/tkde.2022.3231929","title":"Multi-View Fuzzy Classification With Subspace Clustering and Information Granules","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Fuzzy Logic and Control Systems","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Science Foundation for Distinguished Young Scholars of Hunan Province; National Natural Science Foundation of China","keywords":"Computer science; Interpretability; Cluster analysis; Subspace topology; Data mining; Fuzzy logic; Artificial intelligence; Machine learning; Fuzzy clustering","retraction":null,"screen_n_in":null,"score":{"opus":0.02701039006990769,"gpt":0.234104556318824,"spread":0.2070941662489163,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002060756,0.0001164066,0.0001188718,0.0001348777,0.0002689505,0.0001198767,0.0003335766,0.00002453636,0.000001275739],"category_scores_gemma":[0.000002191564,0.0001055629,0.00001290704,0.0002364711,0.00001357255,0.001441143,0.00002324167,0.0001605672,0.000005900204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003169065,"about_ca_system_score_gemma":0.0000223368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000187662,"about_ca_topic_score_gemma":0.0000348643,"domain_scores_codex":[0.9993314,0.00002894995,0.0001499758,0.0002395779,0.0001123809,0.0001377781],"domain_scores_gemma":[0.9993734,0.00005260518,0.00003642321,0.000448976,0.00002449389,0.00006412085],"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":[0.0001065256,0.0002782223,0.000113118,0.0008200252,0.0001856553,0.00001310244,0.005916084,0.2004857,0.002901278,0.01656665,0.0002813429,0.7723323],"study_design_scores_gemma":[0.0006168117,0.00008726033,0.000631243,0.00003379447,0.00001523429,0.00005835283,0.0001641984,0.9875607,0.00004209939,0.000009989419,0.01060729,0.0001729575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001522071,0.0007875559,0.9966636,0.0001354422,0.0002739479,0.0001764539,0.00004537081,0.0001466919,0.0002489191],"genre_scores_gemma":[0.9898716,0.0001864953,0.009768493,0.00002983456,0.00001885364,0.00006703848,0.000015504,0.000007043981,0.00003515501],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9883495,"threshold_uncertainty_score":0.4304729,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2796213239","doi":"10.1109/tkde.2018.2821671","title":"Characterizing and Predicting Early Reviewers for Effective Product Marketing on E-Commerce Websites","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Digital Marketing and Social Media","field":"Social Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"National Key Research and Development Program of China; Innovate UK; Natural Science Foundation of Beijing Municipality; Renmin University of China; National Natural Science Foundation of China","keywords":"Helpfulness; Popularity; Product (mathematics); Computer science; New product development; Information retrieval; Artificial intelligence; World Wide Web; Psychology; Marketing; Mathematics; Business; Social psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.02389185359157603,"gpt":0.3001767249798764,"spread":0.2762848713883004,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001788232,0.0001471075,0.0001884078,0.00009598926,0.0006355236,0.0001433864,0.000161898,0.00006180073,0.000006823417],"category_scores_gemma":[0.0008170356,0.0001502987,0.00003279868,0.0001870432,0.0001124002,0.0004266698,0.000007008889,0.0001713777,0.00001083229],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003838036,"about_ca_system_score_gemma":0.00002718995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003749277,"about_ca_topic_score_gemma":0.00009723568,"domain_scores_codex":[0.9989306,0.0001158687,0.0001597029,0.0003912893,0.000115217,0.0002872844],"domain_scores_gemma":[0.9980558,0.001474484,0.00004235973,0.0002244674,0.00007875067,0.0001240958],"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":[0.0001925439,0.0001288871,0.0008824397,0.0005160551,0.0001124901,0.000001242459,0.01571827,0.000008987198,0.001790157,0.000159189,0.0005790615,0.9799107],"study_design_scores_gemma":[0.004197708,0.002368133,0.07435237,0.01346957,0.0008463509,0.00001597648,0.009126152,0.03058782,0.01219676,0.0001231308,0.8490614,0.003654601],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9484434,0.001410692,0.02837423,0.000584228,0.003624384,0.001935438,0.0002868291,0.0005348343,0.01480594],"genre_scores_gemma":[0.9977687,0.0003906885,0.0005486156,0.00003483989,0.000816381,0.00006866836,0.000008362794,0.00002514576,0.0003386252],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9762561,"threshold_uncertainty_score":0.6129003,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2160172686","doi":"10.1109/tkde.2009.138","title":"Credibility: How Agents Can Handle Unfair Third-Party Testimonies in Computational Trust Models","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Access Control and Trust","field":"Social Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Credibility; Computer science; Computer security; Work (physics); Computational trust; Empirical evidence; Computational model; Risk analysis (engineering); Artificial intelligence; Reputation; Business; Political science; Law","retraction":null,"screen_n_in":null,"score":{"opus":0.05783747098160918,"gpt":0.3104771853336928,"spread":0.2526397143520836,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002606901,0.0001320807,0.0001690656,0.0001437295,0.0002836781,0.0001275585,0.0002628894,0.00007826867,0.00001537931],"category_scores_gemma":[0.00002116871,0.0001327873,0.00002878292,0.0002825026,0.00006043889,0.0007329466,0.000003832331,0.0001945632,0.000004671284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006746312,"about_ca_system_score_gemma":0.00009954358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003024363,"about_ca_topic_score_gemma":0.002143791,"domain_scores_codex":[0.9990965,0.00003431756,0.0001465006,0.0003112389,0.0001610127,0.0002504071],"domain_scores_gemma":[0.9994364,0.0001380822,0.00002193211,0.0002379025,0.00004530219,0.0001203725],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005617999,0.0006797077,0.0006690598,0.0000622607,0.00007353054,0.00001819764,0.01004381,0.8923733,0.0001012633,0.00441379,0.0009623975,0.09054657],"study_design_scores_gemma":[0.0006606218,0.0000468688,0.003816734,0.00005727154,0.00002802441,0.000001540918,0.0004021025,0.9911923,0.00006364615,0.001303369,0.002203717,0.00022378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09402299,0.0007891028,0.8970188,0.002735875,0.0006427778,0.0004474031,0.0004894934,0.0003202429,0.003533253],"genre_scores_gemma":[0.9985486,0.0001002298,0.0009795846,0.00004033207,0.00008120397,0.00001102341,0.00002796481,0.000008155201,0.0002028725],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9045256,"threshold_uncertainty_score":0.5414909,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2784105835","doi":"10.1109/tkde.2018.2793862","title":"A Two-Phase Algorithm for Differentially Private Frequent Subgraph Mining","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"International Development Research Centre","funders":"National Institutes of Health; National Institute of General Medical Sciences; National Natural Science Foundation of China; Deutsche Forschungsgemeinschaft; Patient-Centered Outcomes Research Institute","keywords":"Computer science; Differential privacy; Support vector machine; Pruning; Data mining; Graph; Algorithm; Theoretical computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.03871756589284604,"gpt":0.3077567980364951,"spread":0.2690392321436491,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0002492009,0.0002252525,0.0001986629,0.0002987168,0.0002171137,0.0001556014,0.00818061,0.0000884539,0.000007188075],"category_scores_gemma":[0.0001914781,0.0002257582,0.00004554562,0.0003925131,0.00007264027,0.0008154448,0.0009905339,0.0001873602,0.00001301686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003410969,"about_ca_system_score_gemma":0.00003212218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008176911,"about_ca_topic_score_gemma":0.00002483343,"domain_scores_codex":[0.9985452,0.00001556281,0.0002431565,0.0006957363,0.0001214101,0.0003789458],"domain_scores_gemma":[0.9945644,0.0001823002,0.00004222077,0.005043653,0.00006342562,0.0001039912],"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":[0.00001303029,0.0003007593,0.000002881402,0.00006889689,0.000125542,0.000007198671,0.0001689998,0.00005493711,0.007956475,0.000580879,0.004846689,0.9858737],"study_design_scores_gemma":[0.001111142,0.0002189561,0.00000949943,0.00008308337,0.0000289864,0.00001495402,0.000007035458,0.9548575,0.03768294,0.000889477,0.004825789,0.0002705946],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005779073,0.0002101764,0.9910123,0.0002726426,0.001195009,0.0002459557,0.0004753407,0.0007758553,0.00003365443],"genre_scores_gemma":[0.2262995,0.00008532456,0.7733049,0.00002132545,0.0001311449,0.00006498567,0.00004678761,0.0000273368,0.00001868841],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9856031,"threshold_uncertainty_score":0.9971856,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2142595897","doi":"10.1109/tkde.2006.146","title":"On the Signature Tree Construction and Analysis","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Winnipeg","funders":"","keywords":"Computer science; Signature (topology); Tree (set theory); Set (abstract data type); Digital signature; Data structure; Data mining; File format; Information retrieval; Theoretical computer science; Database; Programming language; Hash function; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01171584614459828,"gpt":0.2185866327377866,"spread":0.2068707865931883,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001313225,0.0001093779,0.00009733934,0.0002148363,0.0001390378,0.0001738493,0.000382182,0.00003353002,0.000007955077],"category_scores_gemma":[0.000002313999,0.00008180596,0.00002622983,0.0005554708,0.0000245627,0.0004900537,0.00001364415,0.0001410446,0.000008149302],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008256931,"about_ca_system_score_gemma":0.00000476322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001166587,"about_ca_topic_score_gemma":0.00003743631,"domain_scores_codex":[0.9993747,0.00001341609,0.00009734451,0.0003144766,0.00008247857,0.0001175697],"domain_scores_gemma":[0.9992066,0.0001251743,0.000017144,0.000606898,0.0000126723,0.00003149718],"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":[0.00001453335,0.0002857207,0.00005199857,0.00007804209,0.000778729,0.0000167888,0.0002423662,0.03876492,0.001069701,0.1177375,0.008692375,0.8322673],"study_design_scores_gemma":[0.0001892049,0.00003194532,0.0005248123,0.00001693556,0.0001512913,0.000004648862,0.00001240049,0.9888142,0.0009803746,0.000264489,0.008842519,0.000167116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001681657,0.0001793226,0.9968415,0.0002278202,0.0002453326,0.00006917769,0.00008185748,0.00009805433,0.0005753075],"genre_scores_gemma":[0.9823975,0.0001198772,0.01691149,0.00005875981,0.00007768084,0.00001196132,0.000063676,0.000009691909,0.0003493808],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9807158,"threshold_uncertainty_score":0.333595,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400071817","doi":"10.1109/tkde.2024.3419698","title":"Laplacian Convolutional Representation for Traffic Time Series Imputation","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":31,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Polytechnique Montréal","funders":"Centre interuniversitaire de recherche sur les reseaux d'entreprise, la logistique et le transport","keywords":"Computer science; Time series; Imputation (statistics); Series (stratigraphy); Representation (politics); Data mining; Algorithm; Machine learning; Missing data; Geology","retraction":null,"screen_n_in":null,"score":{"opus":0.01660452875484313,"gpt":0.2639267242254463,"spread":0.2473221954706032,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010216,0.0001299708,0.00009778951,0.0002264116,0.00006587651,0.00008145353,0.00009522618,0.00006114363,0.00001425673],"category_scores_gemma":[0.000002843653,0.000143713,0.00003527146,0.000180672,0.00001539765,0.0005885348,0.000002158341,0.0001100099,0.00003752439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004115258,"about_ca_system_score_gemma":0.00001170152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.853356e-7,"about_ca_topic_score_gemma":0.000005948875,"domain_scores_codex":[0.9994064,0.000005567379,0.0001531351,0.0002372265,0.00006230814,0.000135362],"domain_scores_gemma":[0.999662,0.00007471334,0.0000057009,0.0001906359,0.00001776699,0.00004922688],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002767543,0.00005347851,4.137479e-7,0.0007603953,0.0002460968,0.000004414044,0.0004338846,0.6384242,0.004506083,0.001298282,0.05709207,0.297153],"study_design_scores_gemma":[0.0001492873,0.00003651612,0.00001528995,0.00007276377,0.00004941214,0.00001049393,0.00001772067,0.9531379,0.002063946,0.00001468077,0.04429146,0.0001404849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001516643,0.0006643387,0.9909197,0.00005210528,0.0009393769,0.000254961,0.0004043941,0.004948285,0.0003001878],"genre_scores_gemma":[0.9940639,0.0003712072,0.004640441,0.000006489375,0.0001285726,0.0001118035,0.0002858853,0.00004189759,0.0003498342],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9925472,"threshold_uncertainty_score":0.5860445,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1992440927","doi":"10.1109/tkde.2014.2359672","title":"Incorporating Social Role Theory into Topic Models for Social Media Content Analysis","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Expert finding and Q&A systems","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"National Key Research and Development Program of China; Engineering and Physical Sciences Research Council; National Natural Science Foundation of China","keywords":"Social media; Computer science; Microblogging; Generative model; Focus (optics); Topic model; Regularization (linguistics); Data science; Process (computing); World Wide Web; Information retrieval; Generative grammar; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.06034266008053929,"gpt":0.2760029146332962,"spread":0.2156602545527569,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005160914,0.0001376504,0.0002437797,0.0002134712,0.0003523603,0.0001069488,0.0004725849,0.00008252395,0.000001274919],"category_scores_gemma":[0.0000136916,0.0001325366,0.00008825614,0.0003233371,0.00001976593,0.0004287004,0.00001359593,0.0001206259,0.000003296483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003186954,"about_ca_system_score_gemma":0.0000199974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001856599,"about_ca_topic_score_gemma":0.000114692,"domain_scores_codex":[0.9990963,0.00004776707,0.0002153969,0.0003579402,0.0001012422,0.0001812933],"domain_scores_gemma":[0.9991835,0.0003202034,0.00004521238,0.000337905,0.00005114764,0.00006199816],"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":[0.00004446869,0.0003330523,0.00003704409,0.000330411,0.001285972,0.000001786649,0.05787529,0.05675768,0.009690684,0.2385054,0.0004243369,0.6347139],"study_design_scores_gemma":[0.0002789734,0.00002307336,0.00004101272,0.00001462423,0.00008705148,9.76832e-7,0.0001766249,0.9962506,0.0009428223,0.001358243,0.0006535567,0.0001724427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003146202,0.0001657948,0.9957112,0.00006782438,0.0004993561,0.00008682329,0.00003930881,0.0001412139,0.0001422438],"genre_scores_gemma":[0.9894822,0.000004553241,0.01006922,0.00001423975,0.0003020756,0.0000407139,0.00002292678,0.00001178615,0.00005224697],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9863361,"threshold_uncertainty_score":0.5404687,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2109468254","doi":"10.1109/tkde.2012.86","title":"Achieving Data Privacy through Secrecy Views and Null-Based Virtual Updates","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Logic, Reasoning, and Knowledge","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Technische Universität Wien","keywords":"Computer science; Null (SQL); Secrecy; Tuple; SQL; Semantics (computer science); Relational database; Information retrieval; Theoretical computer science; Database; Data mining; Programming language; Computer security; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.06739210014020883,"gpt":0.3002273917608937,"spread":0.2328352916206849,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005086358,0.0003014461,0.0002812241,0.0001309043,0.0002706371,0.0002051246,0.001524925,0.0001039787,0.00001822417],"category_scores_gemma":[0.0000347599,0.0002713964,0.00003411586,0.0003273944,0.0000476953,0.003018526,0.0001393783,0.0003198604,0.00005466358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002762373,"about_ca_system_score_gemma":0.0000534135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001269246,"about_ca_topic_score_gemma":0.00001263107,"domain_scores_codex":[0.9983616,0.0000555957,0.0002674632,0.0007102315,0.0001354865,0.0004696154],"domain_scores_gemma":[0.9973345,0.0002989805,0.00004801573,0.002064712,0.00002341915,0.000230394],"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":[0.00009376629,0.003111231,0.001394221,0.001293225,0.0006397944,0.00003412487,0.02590073,0.007223397,0.01188877,0.0289523,0.01231116,0.9071573],"study_design_scores_gemma":[0.001034534,0.0001571321,0.0008436706,0.0002166894,0.000116574,0.00006887887,0.00007494383,0.7572511,0.004520066,0.00003571324,0.2348303,0.0008503931],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007637916,0.004485798,0.9857094,0.0001042103,0.001032406,0.0001692144,0.0001491262,0.0002864572,0.000425478],"genre_scores_gemma":[0.9710444,0.0005481895,0.02787631,0.00006906714,0.0002361834,0.00001495996,0.0001064294,0.00002979578,0.00007470547],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9634064,"threshold_uncertainty_score":0.9999738,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4396886508","doi":"10.1109/tkde.2024.3400824","title":"Natural Language Interfaces for Tabular Data Querying and Visualization: A Survey","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Visualization; Data visualization; Natural language; Information retrieval; Information visualization; Programming language; Database; World Wide Web; Natural language processing; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.04275557603702698,"gpt":0.3340007813895201,"spread":0.2912452053524931,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003462592,0.0001293568,0.0001276066,0.0001168375,0.0001036696,0.0001752863,0.0003941359,0.00003135126,0.000001904792],"category_scores_gemma":[0.00002288362,0.0001165779,0.00001015192,0.0002219632,0.00001726113,0.001736749,0.00005102776,0.0001067773,0.000003768537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001101872,"about_ca_system_score_gemma":0.00002580022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004332367,"about_ca_topic_score_gemma":0.0002764459,"domain_scores_codex":[0.9991218,0.00002020989,0.0001459665,0.0005090469,0.00006058941,0.0001423335],"domain_scores_gemma":[0.9988398,0.0002756728,0.00001300598,0.0007956169,0.00002471186,0.00005118045],"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":[0.00008160728,0.0002248326,0.00004619582,0.005229327,0.0006571464,0.00008066191,0.009515133,0.006462435,0.02182146,0.0294847,0.007813312,0.9185832],"study_design_scores_gemma":[0.0001221323,0.00002336474,0.00002369549,0.000212411,0.00001354468,0.00001927936,0.00005498781,0.9632909,0.002123882,0.000003011438,0.03395004,0.0001627484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001725963,0.01337346,0.9818361,0.00002466967,0.00103592,0.0001359949,0.001643079,0.0002185885,0.000006158863],"genre_scores_gemma":[0.9652716,0.0003743615,0.03342944,0.00001228742,0.0001031138,0.00002073099,0.0006046438,0.00002468009,0.0001591711],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9635456,"threshold_uncertainty_score":0.4753908,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2342411541","doi":"10.1109/tkde.2016.2527003","title":"Conflict-Aware Weighted Bipartite B-Matching and Its Application to E-Commerce","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Optimization and Search Problems","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bipartite graph; Computer science; Scalability; Matching (statistics); Scheduling (production processes); The Internet; Time complexity; Approximation algorithm; Blossom algorithm; Context (archaeology); Theoretical computer science; Data mining; Graph; Combinatorics; Algorithm; Mathematics; World Wide Web; Mathematical optimization; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.03065758621392588,"gpt":0.2842775778446898,"spread":0.2536199916307639,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000155416,0.0001116036,0.0001004757,0.0001607541,0.000118274,0.00007300693,0.0003511543,0.00004131432,0.000008947444],"category_scores_gemma":[0.000003999195,0.00008972786,0.000011567,0.0002513235,0.000008907464,0.0006697907,0.00002203906,0.00008518409,0.00007874738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001609487,"about_ca_system_score_gemma":0.00001496835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004447699,"about_ca_topic_score_gemma":0.00001015522,"domain_scores_codex":[0.9992251,0.00001800995,0.0001368488,0.0003658567,0.00008075119,0.0001734408],"domain_scores_gemma":[0.9991876,0.0001116477,0.00001541199,0.000464072,0.0000473919,0.0001738551],"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":[0.00002470317,0.000240006,0.00002185454,0.0002095474,0.00009532113,0.00000388224,0.003317163,0.02328917,0.07247821,0.01508403,0.0007280586,0.8845081],"study_design_scores_gemma":[0.0004203606,0.00004913561,0.00007621282,0.0001080194,0.000007879756,0.000008720339,0.000008687533,0.9459383,0.009311027,0.00003180513,0.04381177,0.0002281004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002541052,0.0001441601,0.9959306,0.0007453961,0.0001300178,0.0001919734,0.00005274224,0.0001875112,0.00007652678],"genre_scores_gemma":[0.9879228,0.0003597311,0.01115968,0.0001065494,0.00003176548,0.00004904829,0.000006958998,0.00001552655,0.0003478681],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9853818,"threshold_uncertainty_score":0.3658996,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2147876569","doi":"10.1109/tkde.2015.2453171","title":"RankRC: Large-Scale Nonlinear Rare Class Ranking","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Robustness (evolution); Kernel (algebra); Machine learning; Artificial intelligence; Focus (optics); Class (philosophy); Nonlinear system; Rare events; Algorithm; Computational complexity theory; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03825382451170466,"gpt":0.2748310372290403,"spread":0.2365772127173357,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000444063,0.0001707125,0.0001716955,0.0001872728,0.0001549248,0.0001609138,0.0006236871,0.00007345687,0.00001341924],"category_scores_gemma":[0.0000157876,0.0001742929,0.00003781856,0.0003758133,0.00001622063,0.0008655317,0.00002269912,0.0002992652,0.000114158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003378848,"about_ca_system_score_gemma":0.00006294948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004226001,"about_ca_topic_score_gemma":0.00002262959,"domain_scores_codex":[0.9988549,0.00003637177,0.0002022812,0.0004402709,0.0001787096,0.000287424],"domain_scores_gemma":[0.9988402,0.0001032166,0.000029809,0.000737384,0.00006705767,0.0002223567],"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":[0.0001451498,0.001211941,0.0001110533,0.0003692108,0.0003146657,0.0001165883,0.0265561,0.3652972,0.003536103,0.004912726,0.00704809,0.5903811],"study_design_scores_gemma":[0.0008738352,0.00003684247,0.00002467952,0.00004337064,0.00001229662,0.00002069666,0.0001335672,0.8721533,0.0006308228,0.00001290072,0.1258609,0.000196752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00131792,0.0004720717,0.9955508,0.0001210872,0.0009526185,0.00009991909,0.00004655867,0.0003447604,0.00109427],"genre_scores_gemma":[0.8816363,0.0001073398,0.1170084,0.0001474939,0.0002103594,0.00001942281,0.00004778829,0.00004183437,0.0007811129],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8803183,"threshold_uncertainty_score":0.7107459,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2119387217","doi":"10.1109/tkde.2008.77","title":"Bias and Controversy in Evaluation Systems","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Set (abstract data type); Object (grammar); Feature (linguistics); Information retrieval; Data set; Data science; Artificial intelligence; Data mining; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.09300923597913141,"gpt":0.2950924542262088,"spread":0.2020832182470774,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004260021,0.00009434416,0.0001323295,0.0001753055,0.00006557798,0.00005640066,0.0002076719,0.00004541811,0.00000108276],"category_scores_gemma":[0.000006061748,0.00008996967,0.00001099802,0.0001607436,0.000009806508,0.0005437281,0.000007372378,0.0001029451,0.000003116504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003087398,"about_ca_system_score_gemma":0.00002471251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008641124,"about_ca_topic_score_gemma":0.00003406583,"domain_scores_codex":[0.9993213,0.00003866727,0.0001601247,0.0002703742,0.00009416199,0.0001153045],"domain_scores_gemma":[0.9993792,0.0001036133,0.0000202812,0.0004197874,0.0000276234,0.00004954994],"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":[0.00005252395,0.001143976,0.001918804,0.001244449,0.0003806052,0.0001390549,0.01304843,0.05505646,0.006612669,0.01673604,0.009736879,0.8939301],"study_design_scores_gemma":[0.0004056788,0.00003859074,0.0004602867,0.00007990502,0.00000645289,0.00007472407,0.0000171541,0.9936774,0.0005807853,0.0000101972,0.004527522,0.0001213544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00989875,0.001533589,0.9874365,0.0000351758,0.0004843295,0.0002168658,0.00001372282,0.0001189889,0.0002620989],"genre_scores_gemma":[0.9974378,0.0003758326,0.002068,0.000006524734,0.0000257812,0.00003769187,0.000002992476,0.000006311753,0.00003911849],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.987539,"threshold_uncertainty_score":0.3668857,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2766474394","doi":"10.1109/tkde.2017.2767044","title":"Workload Management in Database Management Systems: A Taxonomy","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Workload; Computer science; Database; Process (computing); Data management; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.03969699418589224,"gpt":0.2605875175153202,"spread":0.2208905233294279,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003754388,0.0001954523,0.0001697188,0.0003129245,0.0003061657,0.0004430243,0.001820392,0.00003502719,0.00000245424],"category_scores_gemma":[0.000001592674,0.0001960621,0.00002845031,0.0001691109,0.0000217506,0.0001974902,0.0001898147,0.0001797493,0.00004516359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005141088,"about_ca_system_score_gemma":0.000005781861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003669415,"about_ca_topic_score_gemma":0.00001628721,"domain_scores_codex":[0.9986668,0.00002028905,0.0002273851,0.0006401619,0.0001420665,0.0003032595],"domain_scores_gemma":[0.9972236,0.00003800407,0.00005074181,0.002581569,0.00001109646,0.0000949855],"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":[0.00001361902,0.0004243064,0.00003143849,0.0008176469,0.000285439,0.0003188467,0.0001991932,0.1746724,0.00001403187,0.007100449,0.001391552,0.814731],"study_design_scores_gemma":[0.0006950701,0.00002015559,0.0004397096,0.0006313131,0.00003475213,0.000009009657,0.00006447052,0.9446869,0.00003596309,0.000007844645,0.05309583,0.0002789581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002162538,0.0006647317,0.9888437,0.00007471817,0.001044475,0.000451468,0.00001639596,0.000170118,0.006571825],"genre_scores_gemma":[0.9748536,0.0003635584,0.02310316,0.00001952525,0.00007039854,0.0001569504,0.000004314363,0.00001835871,0.00141016],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9726911,"threshold_uncertainty_score":0.799518,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2051664277","doi":"10.1109/tkde.2011.100","title":"Discovery of Delta Closed Patterns and Noninduced Patterns from Sequences","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Substring; Computer science; Set (abstract data type); Sequence (biology); Data mining; Suffix tree; Pattern recognition (psychology); Artificial intelligence; Data structure","retraction":null,"screen_n_in":null,"score":{"opus":0.04450856788129964,"gpt":0.2576284759502814,"spread":0.2131199080689817,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008220023,0.0001262134,0.0001401228,0.00008788722,0.00006611582,0.00007266929,0.0005652994,0.00004339957,0.000005742747],"category_scores_gemma":[0.000002830996,0.0001186525,0.00001856895,0.0001110542,0.00002194859,0.0009402006,0.00002814479,0.000113582,0.000003543874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007019673,"about_ca_system_score_gemma":0.00002052679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006231207,"about_ca_topic_score_gemma":0.0001251101,"domain_scores_codex":[0.9992197,0.00001079218,0.0001736825,0.0003918775,0.00007070188,0.0001332884],"domain_scores_gemma":[0.9990593,0.00008489806,0.00003512103,0.0007328745,0.00002484158,0.00006294543],"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":[0.00001602998,0.000660152,0.001263814,0.0002268527,0.0002735484,0.00001880547,0.006349866,0.000163643,0.01894037,0.00198163,0.0001201577,0.9699851],"study_design_scores_gemma":[0.0007972752,0.0001953653,0.02403381,0.0004218032,0.0001047444,0.00002441947,0.0002223018,0.8538889,0.1190294,0.0001648698,0.000452145,0.0006649054],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2129474,0.00009241721,0.7851858,0.00001410132,0.0001642431,0.00005760756,0.001459923,0.00005175067,0.00002679902],"genre_scores_gemma":[0.9726999,0.0001959716,0.02696668,0.00001068646,0.00002765177,0.00001511871,0.00005974892,0.000009466268,0.00001480359],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9693202,"threshold_uncertainty_score":0.483851,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1978421404","doi":"10.1109/tkde.2014.3","title":"Editorial [State of the Transactions]","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Service-Oriented Architecture and Web Services","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Dalhousie University; University of Ottawa","keywords":"Computer science; Library science; Reputation; Operations research; Political science; Mathematics; Law","retraction":null,"screen_n_in":null,"score":{"opus":0.008794747565106346,"gpt":0.217637647023636,"spread":0.2088428994585297,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009147876,0.0001325395,0.0001200096,0.0001004004,0.0001223574,0.00006410103,0.0009655181,0.00004502562,0.0000142499],"category_scores_gemma":[0.000001053627,0.00009747183,0.00004505699,0.0004022793,0.00002051131,0.0006219624,0.00001130502,0.0002283585,0.00002500468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009357726,"about_ca_system_score_gemma":0.00003278228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001081105,"about_ca_topic_score_gemma":0.00009351087,"domain_scores_codex":[0.9992002,0.00002157281,0.0001776396,0.0002813812,0.0001487169,0.0001705302],"domain_scores_gemma":[0.9988233,0.0001108875,0.00003103863,0.0008978463,0.00006520263,0.00007171479],"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":[0.00003060885,0.0006691722,0.00001630856,0.000566738,0.0003340707,0.000001503091,0.008781675,0.1219988,0.03404455,0.0005333546,0.00697505,0.8260482],"study_design_scores_gemma":[0.001020091,0.0001451042,0.0005431786,0.0002170591,0.0000759991,0.00002328088,0.00006858526,0.8095722,0.09032711,0.0003575977,0.0970917,0.00055808],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004385514,0.0001360053,0.9739922,0.0001513776,0.02092265,0.0001585382,0.00004308538,0.00009913593,0.0001114926],"genre_scores_gemma":[0.9941966,0.00006548741,0.004108173,0.00005635302,0.001426559,0.00002930092,0.000002682661,0.00001526862,0.00009957256],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9898111,"threshold_uncertainty_score":0.3974786,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2114175725","doi":"10.1109/tkde.2009.49","title":"Enhancing Learning Objects with an Ontology-Based Memory","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Reusability; Learning object; Ontology; Semantic Web; Process (computing); Knowledge base; Artificial intelligence; Natural language processing; World Wide Web; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01977965045427822,"gpt":0.2566786341254655,"spread":0.2368989836711873,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001763178,0.0001660951,0.0001741435,0.0001698333,0.0001647985,0.00009123346,0.0005132376,0.00006520085,0.000003835032],"category_scores_gemma":[0.000009193711,0.0001452097,0.00001975886,0.0002256144,0.00002011512,0.0007008697,0.000004546623,0.0002580184,0.00001047555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001944985,"about_ca_system_score_gemma":0.00006030308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000138548,"about_ca_topic_score_gemma":0.0002029433,"domain_scores_codex":[0.9990444,0.00002832367,0.0001329849,0.0004452377,0.00009201658,0.0002570081],"domain_scores_gemma":[0.9990389,0.0001248341,0.00002443813,0.0006826794,0.00003035665,0.00009880445],"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":[0.000140328,0.0008538159,0.00008614992,0.0002491021,0.000134938,0.0001917087,0.005420721,0.3096004,0.04109005,0.001347324,0.00008090003,0.6408046],"study_design_scores_gemma":[0.0007077674,0.000808735,0.0009464563,0.0001406249,0.00003407681,0.00006120843,0.0001430918,0.9427091,0.05349594,0.00002796282,0.0005338168,0.0003912387],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02479727,0.0002988419,0.9737415,0.00008705628,0.0002463981,0.00007608286,0.000002911105,0.0004520516,0.0002979235],"genre_scores_gemma":[0.9527622,0.00001894879,0.04703993,0.00007092945,0.00003733833,0.000005127981,0.000005317,0.000008827369,0.00005134684],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.927965,"threshold_uncertainty_score":0.5921478,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2152225808","doi":"10.1109/tkde.2010.33","title":"Asking Generalized Queries to Domain Experts to Improve Learning","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"China University of Geosciences; Shanghai Jiao Tong University; University of Pennsylvania","keywords":"Computer science; Oracle; Construct (python library); Classifier (UML); Ask price; Domain (mathematical analysis); Set (abstract data type); Machine learning; Class (philosophy); Labeled data; Active learning (machine learning); Artificial intelligence; Theoretical computer science; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01083209693741239,"gpt":0.265796040034446,"spread":0.2549639430970336,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002732096,0.0001839547,0.0001641339,0.0002256699,0.0002391404,0.0002076542,0.0006227248,0.00006061877,0.00001543046],"category_scores_gemma":[0.00002760398,0.0001796962,0.00003054804,0.000324134,0.000009896495,0.0003938798,0.00003720854,0.0004146756,0.00004767792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001413057,"about_ca_system_score_gemma":0.00002428297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004357141,"about_ca_topic_score_gemma":0.00005947459,"domain_scores_codex":[0.9988756,0.00002592394,0.0001618217,0.0005335399,0.000114085,0.0002889908],"domain_scores_gemma":[0.9988844,0.00009229813,0.00001803489,0.0007313287,0.00003187698,0.0002420316],"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":[0.00001824053,0.0001151089,0.00002011267,0.00005978722,0.00005204965,0.00001743925,0.00635638,0.07961161,0.2781409,0.002155364,0.0005999985,0.632853],"study_design_scores_gemma":[0.0004547292,0.0001891897,0.00008337916,0.00006748383,0.00001040173,0.00003408696,0.00006715989,0.7895482,0.02870722,0.00002746908,0.1802563,0.0005544176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04446828,0.00004838717,0.952889,0.0003232337,0.001622263,0.0001216346,0.00001280131,0.0003441256,0.0001703345],"genre_scores_gemma":[0.7668335,0.00001127286,0.2320894,0.0001019093,0.0002584073,0.00004708506,0.00000572267,0.00002917436,0.0006235254],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7223653,"threshold_uncertainty_score":0.7327798,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}