{"meta":{"query_hash":"3a9fca90f174","filters":{"venue":"IEEE Transactions on Knowledge and Data Engineering"},"cohort_total":120,"direct_labels_cover":0,"predictions_cover":120,"exported":120,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/3a9fca90f174","api":"https://metacan.xera.ac/api/v1/cohort?venue=IEEE+Transactions+on+Knowledge+and+Data+Engineering"},"results":[{"id":"W1616993132","doi":"10.1109/tkde.2015.2448541","title":"A Family of Rank Similarity Measures Based on Maximized Effectiveness Difference","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Chinese Academy of Sciences; Google","keywords":"Relevance (law); Measure (data warehouse); Metric (unit); Similarity (geometry); Rank (graph theory); Computer science; Similarity measure; Learning to rank; Maximization; Context (archaeology); Ranking (information retrieval); Data mining; Information retrieval; Mathematics; Artificial intelligence; Mathematical optimization","score_opus":0.07556383053037817,"score_gpt":0.29334646976984136,"score_spread":0.21778263923946317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1616993132","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019789197,0.0019969558,0.97191894,0.00029831612,0.00006867621,0.00028846643,0.00035961802,0.0004497322,0.004830109],"genre_scores_gemma":[0.451519,0.0014586308,0.54197556,0.00031025207,0.0004023007,0.0009219023,0.00074530585,0.000318267,0.0023487073],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98540527,0.0057678623,0.0011286531,0.00178551,0.0054798685,0.0004328835],"domain_scores_gemma":[0.97006196,0.017594697,0.0034312052,0.003874004,0.0044560814,0.0005820409],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011752617,0.0019224361,0.0024191525,0.0078001367,0.00087567413,0.0034242189,0.0019549115,0.0018855508,0.0019097178],"category_scores_gemma":[0.049412105,0.0004909444,0.0013582789,0.004740885,0.0023750113,0.006631453,0.0024443865,0.0023870345,0.0009947456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005666599,0.00036919917,0.008560459,0.0010898224,0.0005012152,0.00018728634,0.00055440544,0.15679978,0.012691754,0.25543082,0.008735395,0.55451316],"study_design_scores_gemma":[0.00010127154,0.0013040712,0.0068361065,0.0001801659,0.00021071486,0.0010897315,0.00024381561,0.7485064,0.013599987,0.21398744,0.013683699,0.00025662477],"about_ca_topic_score_codex":0.0007498118,"about_ca_topic_score_gemma":0.0007145903,"teacher_disagreement_score":0.011752617,"about_ca_system_score_codex":0.002282574,"about_ca_system_score_gemma":0.0014437174,"threshold_uncertainty_score":0.06215453},"labels":[],"label_agreement":null},{"id":"W1903488793","doi":"10.1109/tkde.2015.2453952","title":"A Cooperative Coevolution Framework for Parallel Learning to Rank","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Science Foundation of Shandong Province; Academy of Finland; National Natural Science Foundation of China; National Science Foundation","keywords":"Computer science; Benchmark (surveying); Rank (graph theory); Coevolution; Context (archaeology); Learning to rank; Artificial intelligence; Divide and conquer algorithms; Machine learning; Evolutionary algorithm; Function (biology); Theoretical computer science; Algorithm; Ranking (information retrieval); Mathematics","score_opus":0.04245486072800539,"score_gpt":0.3010015428149192,"score_spread":0.2585466820869138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1903488793","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059544155,0.00024560172,0.99056983,0.00015208541,0.000052071173,0.000053819163,0.000026654006,0.00037984873,0.0025657208],"genre_scores_gemma":[0.32916865,0.00044126023,0.6626591,0.00036187735,0.00017735263,0.0004101595,0.00020732706,0.00025314675,0.006321068],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983581,0.00053455704,0.000086291475,0.00029875067,0.00055333483,0.00016905303],"domain_scores_gemma":[0.9975171,0.00087698986,0.00017831553,0.0005509634,0.0007094184,0.00016716994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003209914,0.0011706856,0.0017371022,0.0013239237,0.00077384314,0.0016094644,0.0024535193,0.0014321329,0.004116795],"category_scores_gemma":[0.008297639,0.00045829936,0.0009069662,0.0014713759,0.0016478874,0.00205787,0.002475146,0.0020713846,0.0011071286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000084239786,0.00012623056,0.00085340516,0.00012182862,0.00009299398,0.00011792696,0.000105965315,0.7490486,0.004255805,0.07305575,0.0037113312,0.1684259],"study_design_scores_gemma":[0.000014511359,0.00004381675,0.000053159118,0.0000052982655,0.000008378866,0.00003170419,0.000008151243,0.98272026,0.0006088191,0.014905688,0.0015919207,0.000008337576],"about_ca_topic_score_codex":0.0031884126,"about_ca_topic_score_gemma":0.0039683776,"teacher_disagreement_score":0.004116795,"about_ca_system_score_codex":0.0008746385,"about_ca_system_score_gemma":0.0018712219,"threshold_uncertainty_score":0.01697588},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.011726118781379809,"score_gpt":0.22815498637143758,"score_spread":0.21642886759005778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969381345","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42896992,0.0009711957,0.5650257,0.0007798115,0.000036117483,0.000114712944,0.0001021652,0.0003266936,0.0036737442],"genre_scores_gemma":[0.9847787,0.000544317,0.013194512,0.0000666609,0.00002470868,0.000040661376,0.000055252658,0.000020490077,0.0012747494],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937135,0.00022203948,0.000022982444,0.00011726676,0.00017688322,0.000089419846],"domain_scores_gemma":[0.9960627,0.0026912147,0.0006094266,0.00018717148,0.00034820975,0.00010130883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012588587,0.000634666,0.00056575646,0.0011475213,0.00075468613,0.0010631456,0.00067340356,0.0010890331,0.00055541086],"category_scores_gemma":[0.0057770796,0.00039747692,0.00055653503,0.00051130034,0.00121301,0.0026928205,0.0010418246,0.0008345139,0.00012318802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005366512,0.000059284717,0.007736172,0.000072002986,0.000052140756,0.00038794626,0.00025195128,0.9449491,0.005242622,0.025936544,0.00066032744,0.014598158],"study_design_scores_gemma":[0.0000034362583,0.000015399757,0.0007024295,0.000005364297,0.0000067867745,0.00007022965,0.00005239856,0.9901978,0.0005323788,0.008213243,0.00019410289,0.00000645778],"about_ca_topic_score_codex":0.0051256376,"about_ca_topic_score_gemma":0.003729693,"teacher_disagreement_score":0.0051256376,"about_ca_system_score_codex":0.0012341229,"about_ca_system_score_gemma":0.00051394495,"threshold_uncertainty_score":0.010191619},"labels":[],"label_agreement":null},{"id":"W1969742982","doi":"10.1109/69.979978","title":"A comprehensive analytical performance model for disk devices under random workloads","year":2002,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Waterloo; University of Toronto","keywords":"Optical disc; Computer science; Disk array; Magnetic storage; Server; Computer data storage; Optical storage; Constant (computer programming); Hard disk drive performance characteristics; Computer hardware; Computer network; Operating system","score_opus":0.06566339483825503,"score_gpt":0.28485298537923814,"score_spread":0.2191895905409831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969742982","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051309954,0.0034062352,0.8788057,0.003153117,0.00032371917,0.00037331303,0.0021511877,0.0011444773,0.059332304],"genre_scores_gemma":[0.8690726,0.0050988644,0.082071535,0.0009798049,0.0005440908,0.0008136777,0.0012864616,0.0005699644,0.03956293],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998511,0.00027176426,0.000084175306,0.00024423574,0.0006378593,0.00025094012],"domain_scores_gemma":[0.99771786,0.00091178296,0.00022979293,0.0002920978,0.00076779607,0.00008073771],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011657187,0.0014993587,0.0015720723,0.0017176879,0.0007753168,0.0021664836,0.00269949,0.0023853148,0.0046378337],"category_scores_gemma":[0.0065403865,0.00065987365,0.0011174883,0.0015018164,0.0009931149,0.0038395915,0.0011947453,0.0013546956,0.0022654987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003166817,0.000064758075,0.00047727424,0.000100152174,0.000016640277,0.00016968454,0.000114220406,0.90385276,0.0027559747,0.08322444,0.0036599867,0.0055324296],"study_design_scores_gemma":[0.0000028705601,0.000012942942,0.000073198484,0.0000075472335,0.0000050163676,0.00004180763,0.000012799609,0.9911608,0.0002100205,0.0072019678,0.0012637123,0.000007381259],"about_ca_topic_score_codex":0.0054452447,"about_ca_topic_score_gemma":0.0027440432,"teacher_disagreement_score":0.0054452447,"about_ca_system_score_codex":0.0023394166,"about_ca_system_score_gemma":0.0017181645,"threshold_uncertainty_score":0.016973794},"labels":[],"label_agreement":null},{"id":"W1969972789","doi":"10.1109/tkde.2011.260","title":"The Minimum Consistent Subset Cover Problem: A Minimization View of Data Mining","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Complexity and Algorithms in Graphs","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Cluster analysis; Bipartite graph; Cardinality (data modeling); Clique; Set cover problem; Set (abstract data type); Theoretical computer science; Artificial intelligence; Graph; Mathematics; Data mining; Combinatorics","score_opus":0.08975363559799747,"score_gpt":0.27409211179744,"score_spread":0.1843384761994425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969972789","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012004011,0.0017443243,0.98172647,0.0017443451,0.00005357345,0.00018973088,0.00036560252,0.00013341407,0.002038577],"genre_scores_gemma":[0.21411562,0.0026130618,0.77759606,0.0006819157,0.0005299131,0.00071133184,0.0018414754,0.00017932191,0.0017313651],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99315107,0.0031666665,0.0003710716,0.0013769395,0.001664158,0.00027016958],"domain_scores_gemma":[0.98994714,0.0077707088,0.00054658466,0.0010366964,0.00051114603,0.000187757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050019235,0.0013713602,0.0030405615,0.002578443,0.001032122,0.0028304886,0.0032203575,0.002302014,0.0018687574],"category_scores_gemma":[0.014256622,0.00093323644,0.0020733105,0.00524364,0.0028660751,0.0059729926,0.0025606188,0.00270591,0.00038896798],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026203867,0.00033816588,0.0043979306,0.0016569719,0.0006726508,0.00043106792,0.00054398447,0.45074216,0.0039005573,0.33166638,0.013024544,0.19236358],"study_design_scores_gemma":[0.000048301084,0.00014504227,0.0006379319,0.00012968441,0.00010337302,0.00044821604,0.00015948719,0.593562,0.0022404264,0.39376384,0.008724886,0.0000367187],"about_ca_topic_score_codex":0.0013114923,"about_ca_topic_score_gemma":0.0011890959,"teacher_disagreement_score":0.0050019235,"about_ca_system_score_codex":0.0015749787,"about_ca_system_score_gemma":0.0015248008,"threshold_uncertainty_score":0.026452959},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Dalhousie University; University of Ottawa","keywords":"Computer science; Library science; Reputation; Operations research; Political science; Mathematics; Law","score_opus":0.008794747565106346,"score_gpt":0.21763764702363603,"score_spread":0.20884289945852968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978421404","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004977302,0.003020404,0.00027328706,0.011490655,0.97786385,0.000054122993,0.00018939341,0.0002710437,0.0067874766],"genre_scores_gemma":[0.00087138545,0.008478979,0.00054643705,0.016667759,0.9133981,0.000095466916,0.0005442301,0.00037174733,0.059025902],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99095845,0.00075192325,0.0012644089,0.0012051206,0.005142122,0.00067800866],"domain_scores_gemma":[0.9501776,0.0039223502,0.0031440388,0.0020293884,0.033258855,0.0074676857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005740683,0.00261817,0.0030887742,0.0046193446,0.002966447,0.014600789,0.0041071298,0.006659096,0.13638993],"category_scores_gemma":[0.036754742,0.001119309,0.0027199711,0.002645719,0.0022563676,0.0057735094,0.0023197178,0.009628485,0.15855129],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023608067,0.000007667663,0.000020223039,0.00020935974,0.000008189631,0.000053281066,0.0000067816,0.000018526085,0.00007147958,0.00018485503,0.9855816,0.013814444],"study_design_scores_gemma":[0.000017894006,0.0000183096,0.000095131145,0.00029405448,0.000009903792,0.00011955469,0.00001716033,0.000049203987,0.0000808949,0.000312422,0.9989723,0.000013125938],"about_ca_topic_score_codex":0.001088205,"about_ca_topic_score_gemma":0.0018062304,"teacher_disagreement_score":0.13638993,"about_ca_system_score_codex":0.0025680426,"about_ca_system_score_gemma":0.00581351,"threshold_uncertainty_score":0.45626974},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06034266008053929,"score_gpt":0.27600291463329624,"score_spread":0.21566025455275695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992440927","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008329822,0.00076469406,0.98863554,0.0005429049,0.000094351715,0.00010643179,0.00020897001,0.0002436859,0.0010735681],"genre_scores_gemma":[0.59972095,0.002107651,0.3872825,0.00050457194,0.0011481463,0.0011160398,0.0014449565,0.00037257033,0.0063026072],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99628603,0.0021744247,0.00016384391,0.000683702,0.0004947983,0.00019710381],"domain_scores_gemma":[0.98788935,0.009994959,0.0006030026,0.0006701527,0.00058738096,0.00025523122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006425377,0.0014477093,0.0013158376,0.004367538,0.00080149487,0.0025523943,0.0026288219,0.0021703783,0.002415296],"category_scores_gemma":[0.016896702,0.0009832849,0.0027688555,0.002945804,0.0017362143,0.006138133,0.0015930565,0.0026194816,0.0014337383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027811245,0.00036669208,0.0106047755,0.00068822934,0.00058067276,0.0005680627,0.0029455237,0.4143981,0.005604357,0.36080024,0.0077790827,0.19538614],"study_design_scores_gemma":[0.00001855014,0.000035381403,0.00058902515,0.000025643101,0.000039037757,0.000078640114,0.00010767296,0.9148447,0.00037214934,0.08084132,0.003024797,0.000023143999],"about_ca_topic_score_codex":0.005579534,"about_ca_topic_score_gemma":0.0069164853,"teacher_disagreement_score":0.006425377,"about_ca_system_score_codex":0.0021244485,"about_ca_system_score_gemma":0.001076591,"threshold_uncertainty_score":0.033981085},"labels":[],"label_agreement":null},{"id":"W1997668352","doi":"10.1109/tkde.2012.190","title":"Efficient Cluster Labeling for Support Vector Clustering","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Cluster analysis; Disjoint sets; Interconnection; Cluster (spacecraft); Process (computing); Algorithm; Point (geometry); Function (biology); Data mining; Pattern recognition (psychology); Artificial intelligence; Mathematics","score_opus":0.03179128225384418,"score_gpt":0.3012782757759483,"score_spread":0.2694869935221041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997668352","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029353092,0.00006056556,0.99608743,0.00006429996,0.000023023176,0.000041884217,0.00003764731,0.00047278914,0.00027709623],"genre_scores_gemma":[0.07008161,0.000102904356,0.92780983,0.00007054501,0.000060881368,0.00022508447,0.00057870545,0.00015884665,0.0009116412],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99715024,0.0008122285,0.00016651078,0.0004910038,0.0011793119,0.00020064761],"domain_scores_gemma":[0.9964534,0.0012893475,0.00029985636,0.0005711472,0.0012636313,0.00012258666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00191557,0.0012650839,0.0015826938,0.0022702182,0.0012219178,0.0019497873,0.0023749762,0.001817733,0.0025055],"category_scores_gemma":[0.008627493,0.0006456508,0.0008624028,0.0027280555,0.0010480289,0.0021725965,0.0017237008,0.0021725977,0.0020775513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003282766,0.00015491535,0.0012965833,0.00025129065,0.000090963804,0.00011685231,0.00027195338,0.30648518,0.013459126,0.043268397,0.009463143,0.62481326],"study_design_scores_gemma":[0.000015342628,0.0000354663,0.00011771765,0.000009074528,0.000005473014,0.00003265209,0.000027600117,0.98147947,0.0032551822,0.013159409,0.0018499985,0.000012704066],"about_ca_topic_score_codex":0.00331953,"about_ca_topic_score_gemma":0.0026776206,"teacher_disagreement_score":0.00331953,"about_ca_system_score_codex":0.0011974336,"about_ca_system_score_gemma":0.0020901344,"threshold_uncertainty_score":0.010130644},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.015994662512468352,"score_gpt":0.23679044876291291,"score_spread":0.22079578625044455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003787915","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2533352,0.00059835735,0.7434038,0.00019411097,0.000060834867,0.000074633455,0.00070153916,0.0005946676,0.0010368606],"genre_scores_gemma":[0.80029756,0.0005281142,0.1964441,0.00005196581,0.00013724685,0.00010737807,0.0016567443,0.000061081846,0.00071573845],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987362,0.00019409753,0.00013580309,0.0003304659,0.00049025513,0.00011314442],"domain_scores_gemma":[0.99540025,0.002312486,0.0011578398,0.0004523808,0.0005371135,0.00013990654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015223266,0.00068408693,0.0008588765,0.0034898394,0.0005214961,0.00097567344,0.00068836,0.00046055036,0.00057191774],"category_scores_gemma":[0.008611109,0.00031280634,0.00085740135,0.004889132,0.00037961028,0.0014049534,0.0009800222,0.0009087472,0.00023401978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058190885,0.00043421678,0.1487457,0.0004370781,0.00044516148,0.002083504,0.00089206663,0.1718499,0.029252794,0.023526194,0.0036005646,0.6181509],"study_design_scores_gemma":[0.0000139481,0.00009509289,0.024673894,0.000028695538,0.00007848774,0.00050073955,0.00017309503,0.9502528,0.0042619137,0.01667311,0.0032163695,0.00003190058],"about_ca_topic_score_codex":0.0020845137,"about_ca_topic_score_gemma":0.0031669165,"teacher_disagreement_score":0.0034898394,"about_ca_system_score_codex":0.00029127562,"about_ca_system_score_gemma":0.00064077636,"threshold_uncertainty_score":0.008050978},"labels":[],"label_agreement":null},{"id":"W2026060326","doi":"10.1109/tkde.2012.151","title":"NHOP: A Nested Associative Pattern for Analysis of Consensus Sequence Ensembles","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Associative property; Computer science; Sequence (biology); Tree (set theory); Theoretical computer science; Tree structure; Pattern recognition (psychology); Core (optical fiber); Artificial intelligence; Algorithm; Data mining; Computational biology; Mathematics; Combinatorics; Biology; Binary tree","score_opus":0.03855882831999959,"score_gpt":0.2947681018071184,"score_spread":0.2562092734871188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026060326","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009858163,0.00006526373,0.98590535,0.00005320426,0.000025854028,0.00008524181,0.00063384103,0.0028449716,0.0005280752],"genre_scores_gemma":[0.1339486,0.0001142752,0.86129594,0.00009914569,0.000048644095,0.0004966938,0.002173655,0.0005890465,0.0012340964],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987197,0.00033581682,0.00013511798,0.00032167134,0.0003984346,0.000089196365],"domain_scores_gemma":[0.99742043,0.0014040155,0.00019618083,0.0005155685,0.00033239447,0.00013133517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019843746,0.0008609257,0.0009477355,0.0024219584,0.0006090222,0.0011841429,0.0014821953,0.00095550285,0.0051417765],"category_scores_gemma":[0.0074333563,0.00041374305,0.00082271243,0.002444376,0.00079630263,0.0024790296,0.0017118711,0.0011200636,0.0018357822],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076533295,0.00033058712,0.014351362,0.00062021305,0.00029964568,0.0005911019,0.00044714808,0.09487472,0.028178077,0.046369795,0.009769653,0.8034023],"study_design_scores_gemma":[0.00005405517,0.00015001227,0.0020549272,0.000032088752,0.000034274988,0.00032689908,0.000101805555,0.92101914,0.007806563,0.061830312,0.0065516606,0.000038322523],"about_ca_topic_score_codex":0.0015065904,"about_ca_topic_score_gemma":0.0016755491,"teacher_disagreement_score":0.0051417765,"about_ca_system_score_codex":0.0003586024,"about_ca_system_score_gemma":0.00097198173,"threshold_uncertainty_score":0.017200947},"labels":[],"label_agreement":null},{"id":"W2030978449","doi":"10.1109/tkde.2014.2357012","title":"ISC: An Iterative Social Based Classifier for Adult Account Detection on Twitter","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Classifier (UML); Social graph; Graph; Machine learning; Social media; Artificial intelligence; Data mining; Information retrieval; World Wide Web; Theoretical computer science","score_opus":0.03642803597983174,"score_gpt":0.27845537529562386,"score_spread":0.24202733931579212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030978449","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18513812,0.0010019944,0.7943362,0.001518854,0.000547157,0.001100154,0.0022363863,0.0061537325,0.007967441],"genre_scores_gemma":[0.759652,0.0003448175,0.22597383,0.0004906087,0.00046626315,0.00066266005,0.0039317347,0.00017459907,0.008303411],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820626,0.00037344208,0.00013094507,0.00035107209,0.0006970798,0.0002412239],"domain_scores_gemma":[0.9951735,0.0018206935,0.00054092985,0.00039979236,0.0017810412,0.00028397693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016809554,0.0013564166,0.001492256,0.0047987523,0.0013934086,0.0011536201,0.0022886514,0.0020757585,0.0020421331],"category_scores_gemma":[0.0061234864,0.00026479218,0.0008769083,0.0021748242,0.0007034845,0.0020773388,0.0011836569,0.0016250352,0.0019690983],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000728519,0.001145274,0.063977115,0.00030777222,0.00029769857,0.00065479666,0.00051379256,0.067837834,0.016104992,0.009023634,0.046348833,0.79305977],"study_design_scores_gemma":[0.000015998821,0.0001085708,0.003265796,0.000016541664,0.000029538296,0.00014239183,0.00010598499,0.9857319,0.0035151606,0.0038264312,0.0032206222,0.000021061585],"about_ca_topic_score_codex":0.0077009136,"about_ca_topic_score_gemma":0.0106765535,"teacher_disagreement_score":0.0077009136,"about_ca_system_score_codex":0.0010773727,"about_ca_system_score_gemma":0.0014961896,"threshold_uncertainty_score":0.015312195},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04450856788129964,"score_gpt":0.2576284759502814,"score_spread":0.21311990806898173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051664277","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23123968,0.0005761514,0.76559037,0.00020427308,0.000032766296,0.00014973669,0.0004342442,0.0006380317,0.0011347748],"genre_scores_gemma":[0.40128404,0.00047708323,0.59484017,0.000092348964,0.000032975582,0.00013806514,0.0020479753,0.000075935284,0.0010114678],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988662,0.00022906721,0.00019490358,0.00023540012,0.00040317234,0.0000712792],"domain_scores_gemma":[0.9947078,0.0028835998,0.00075115234,0.0008035665,0.0006859981,0.00016785412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001274288,0.00043992052,0.00088992016,0.002038661,0.00045738916,0.0010884223,0.00093211053,0.00075881823,0.00088248064],"category_scores_gemma":[0.0074793524,0.0003381285,0.00083010434,0.0021004544,0.00062067545,0.0019377106,0.00093354814,0.000871457,0.00045426245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007537596,0.0004616674,0.031964853,0.0008488065,0.00016552597,0.0014859536,0.0007645803,0.022858111,0.07069928,0.020140475,0.0013749485,0.8484821],"study_design_scores_gemma":[0.00013065626,0.0008147806,0.01873796,0.00018564917,0.00014241955,0.0046563125,0.0009085353,0.76355404,0.0814157,0.1200418,0.009317835,0.00009429782],"about_ca_topic_score_codex":0.00025020968,"about_ca_topic_score_gemma":0.00039054244,"teacher_disagreement_score":0.002038661,"about_ca_system_score_codex":0.00020057552,"about_ca_system_score_gemma":0.0006847173,"threshold_uncertainty_score":0.0067391396},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Data mining; Correlation; Artificial intelligence; Pattern recognition (psychology); Mathematics","score_opus":0.02346222270620061,"score_gpt":0.2662764905445469,"score_spread":0.24281426783834628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059054797","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49048126,0.0013715563,0.49700245,0.0008132793,0.000090699185,0.0003657822,0.0046725892,0.0017933425,0.0034091105],"genre_scores_gemma":[0.8360413,0.00026566949,0.15682217,0.000102705824,0.00007412263,0.00024279828,0.0053465157,0.0000940187,0.001010698],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964766,0.0005696064,0.00045597155,0.0011583127,0.0010018784,0.0003376984],"domain_scores_gemma":[0.982091,0.010556085,0.0028434207,0.0017972182,0.002235043,0.00047719578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023948299,0.0011390054,0.0018991188,0.009241989,0.0013638994,0.0018286541,0.0021091388,0.0016808754,0.0017265002],"category_scores_gemma":[0.018306773,0.00049783854,0.0014217015,0.008087779,0.0008862258,0.0020967268,0.001925344,0.0011097948,0.0014161485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001078712,0.00088352035,0.5279152,0.0011240148,0.00104656,0.0029023634,0.001047757,0.04372813,0.016613191,0.009384167,0.010222231,0.38405418],"study_design_scores_gemma":[0.00017459618,0.0004211813,0.14154842,0.00019712528,0.00055501953,0.0048037088,0.002699974,0.7630833,0.022074979,0.052992467,0.0113082025,0.00014112247],"about_ca_topic_score_codex":0.0029249,"about_ca_topic_score_gemma":0.0051689153,"teacher_disagreement_score":0.009241989,"about_ca_system_score_codex":0.000629233,"about_ca_system_score_gemma":0.0013604894,"threshold_uncertainty_score":0.012665212},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.1546157879818343,"score_gpt":0.36613754980686486,"score_spread":0.21152176182503055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076039115","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8988647,0.000856367,0.07929979,0.0006158837,0.00012778924,0.0013426145,0.002410328,0.0046237865,0.011858734],"genre_scores_gemma":[0.67460537,0.0005144653,0.30424497,0.00022025654,0.00003265066,0.001032556,0.014230281,0.0006784412,0.0044409814],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.98950785,0.005993048,0.0008969897,0.001039462,0.002334165,0.00022856523],"domain_scores_gemma":[0.941774,0.04761125,0.0015121897,0.003718784,0.004642796,0.0007411059],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011352773,0.0010837074,0.00089521427,0.0025746713,0.0008788874,0.0023253309,0.001997393,0.001963608,0.0028791174],"category_scores_gemma":[0.06540478,0.0004931436,0.00058970996,0.002676472,0.0011830695,0.004852819,0.0035030225,0.0012406069,0.00075598276],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0043143257,0.0038382378,0.018344767,0.0031201944,0.00043628964,0.0016273275,0.006198972,0.16609229,0.018576037,0.01264454,0.022782387,0.74202466],"study_design_scores_gemma":[0.0014745524,0.0036329068,0.026520375,0.00040295455,0.00031869914,0.0013029085,0.006953436,0.81965816,0.07659437,0.013284235,0.049661987,0.00019542685],"about_ca_topic_score_codex":0.005153508,"about_ca_topic_score_gemma":0.0051202616,"teacher_disagreement_score":0.011352773,"about_ca_system_score_codex":0.0018253069,"about_ca_system_score_gemma":0.0016431169,"threshold_uncertainty_score":0.060039937},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06209211290478007,"score_gpt":0.32537221592102517,"score_spread":0.2632801030162451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085909071","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03720265,0.00021952555,0.96070784,0.00044405178,0.000031451145,0.000039033184,0.0003020616,0.0002121632,0.0008411471],"genre_scores_gemma":[0.7230715,0.00037899526,0.27377307,0.00021277173,0.00007737637,0.00014697043,0.0010204465,0.000054531072,0.0012643397],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98947936,0.0044988636,0.0010980853,0.0016762782,0.0026818814,0.000565639],"domain_scores_gemma":[0.9749035,0.013010773,0.0016747902,0.008708278,0.0013502272,0.00035235344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009581977,0.0005089937,0.001399883,0.0010058144,0.0008776012,0.003297595,0.0019856829,0.0010701122,0.00080585893],"category_scores_gemma":[0.027293779,0.00052361394,0.001191462,0.0018265698,0.0022935509,0.007855451,0.0031626052,0.0024783893,0.00029958147],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016555329,0.00029946966,0.00553314,0.00030634954,0.00023265163,0.00066603476,0.00083825097,0.39155534,0.01087179,0.36131546,0.0025630842,0.2241629],"study_design_scores_gemma":[0.000046905025,0.00017211193,0.00038608033,0.00002965347,0.000032681408,0.00037372755,0.00009586967,0.7315882,0.010893828,0.25346237,0.0028844462,0.00003408494],"about_ca_topic_score_codex":0.00052292837,"about_ca_topic_score_gemma":0.00039373,"teacher_disagreement_score":0.009581977,"about_ca_system_score_codex":0.0010678764,"about_ca_system_score_gemma":0.0014321663,"threshold_uncertainty_score":0.050674975},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.10547437860269274,"score_gpt":0.291973674795889,"score_spread":0.18649929619319625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091214390","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013035471,0.001106972,0.98241454,0.0010676681,0.00045880897,0.00015767507,0.0001773003,0.00036871768,0.0012128272],"genre_scores_gemma":[0.55841845,0.0015903148,0.42939377,0.0030858074,0.0012005745,0.0010286741,0.0008122456,0.0003820747,0.0040882025],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9725424,0.018254638,0.001158369,0.003457364,0.0040245894,0.00056273356],"domain_scores_gemma":[0.8127549,0.15487109,0.007563912,0.01717614,0.0069139316,0.00071991625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.053362943,0.000985488,0.0017478298,0.0020738225,0.001121138,0.0023063987,0.002341002,0.001940022,0.0017038268],"category_scores_gemma":[0.25691313,0.0008615612,0.0010249272,0.0029247538,0.0028590818,0.0045542284,0.0028942516,0.0029228507,0.00065552664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010836585,0.00026046328,0.06111751,0.0017686132,0.00161141,0.001844329,0.002093448,0.18717782,0.005235617,0.39581662,0.018713892,0.3232767],"study_design_scores_gemma":[0.00019585021,0.00028813415,0.010555222,0.00036411654,0.00027230126,0.000863247,0.00037666893,0.5855778,0.006137665,0.37881863,0.01642889,0.00012155873],"about_ca_topic_score_codex":0.002482749,"about_ca_topic_score_gemma":0.0019733207,"teacher_disagreement_score":0.053362943,"about_ca_system_score_codex":0.001225923,"about_ca_system_score_gemma":0.0014747762,"threshold_uncertainty_score":0.28221363},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09066818198011457,"score_gpt":0.36427771998820674,"score_spread":0.2736095380080922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096451472","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09970058,0.032697007,0.83139646,0.00467087,0.002160357,0.0005362559,0.0019522896,0.0028867405,0.02399947],"genre_scores_gemma":[0.6527705,0.0064378283,0.331517,0.0014232853,0.002100779,0.0007827391,0.0023466947,0.00076981785,0.0018513656],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.87714064,0.06951564,0.011905516,0.0065174033,0.033190105,0.001730851],"domain_scores_gemma":[0.66528267,0.26697147,0.019551327,0.017460847,0.027945861,0.002787818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.058746677,0.0023837073,0.0032813372,0.021581749,0.001275367,0.009896017,0.0024169039,0.005252562,0.0014912232],"category_scores_gemma":[0.333273,0.0005635749,0.0017450101,0.01611619,0.0042639077,0.012326924,0.0036551668,0.003964902,0.0012792636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001333094,0.00037073976,0.118572816,0.002068989,0.0021246865,0.00046140145,0.0011748122,0.14930066,0.0028019703,0.10442013,0.016648427,0.60072225],"study_design_scores_gemma":[0.00021666633,0.002354494,0.05139852,0.0017030608,0.00087371015,0.0022687207,0.0011310446,0.5649844,0.011071892,0.31914356,0.044242255,0.0006117574],"about_ca_topic_score_codex":0.0019891178,"about_ca_topic_score_gemma":0.0012045415,"teacher_disagreement_score":0.058746677,"about_ca_system_score_codex":0.0022444692,"about_ca_system_score_gemma":0.0023811902,"threshold_uncertainty_score":0.31068587},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.06739210014020883,"score_gpt":0.3002273917608937,"score_spread":0.23283529162068486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109468254","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0313521,0.00021180348,0.96119785,0.0011091783,0.00005680165,0.000091983275,0.00021143758,0.00076976995,0.0049991366],"genre_scores_gemma":[0.7206561,0.00066486845,0.27115008,0.0008319452,0.00026005507,0.0002869899,0.0005196398,0.00040636412,0.00522398],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9881644,0.004122072,0.00125864,0.0014397785,0.0039908946,0.0010241896],"domain_scores_gemma":[0.9814098,0.0068253223,0.0014938244,0.007600015,0.00213544,0.0005356278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009718719,0.00083607,0.0010113115,0.0014062611,0.0017496953,0.007988882,0.0025749332,0.0014013074,0.00158052],"category_scores_gemma":[0.018868024,0.0009864589,0.0022047153,0.0017672098,0.0075632622,0.01994334,0.0089445505,0.0037897862,0.0005160403],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017340161,0.000055964338,0.00085219496,0.0000658881,0.000036993024,0.0001915758,0.0009607816,0.008203553,0.0032237873,0.96825904,0.0011598718,0.016816849],"study_design_scores_gemma":[0.00006318793,0.00009548402,0.00016438354,0.00004316586,0.00008854787,0.000314434,0.00032229177,0.07279181,0.015763117,0.90107757,0.009224696,0.00005132245],"about_ca_topic_score_codex":0.0017548867,"about_ca_topic_score_gemma":0.0014913866,"teacher_disagreement_score":0.009718719,"about_ca_system_score_codex":0.0014588826,"about_ca_system_score_gemma":0.0029788695,"threshold_uncertainty_score":0.0513981},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.012046588402308779,"score_gpt":0.23622373699697677,"score_spread":0.224177148594668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110420974","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08190465,0.003137994,0.9088887,0.0010572335,0.00017284228,0.00018994202,0.00075734395,0.0020938942,0.0017974201],"genre_scores_gemma":[0.6944894,0.0010961539,0.30102277,0.00048033643,0.00019109505,0.00016361743,0.0009979985,0.00021292409,0.0013457289],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946792,0.0013629046,0.00058776827,0.0012607174,0.0016092376,0.00050021586],"domain_scores_gemma":[0.9838324,0.0104877725,0.0013017685,0.0030235923,0.0010121648,0.00034231154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005270128,0.0013610187,0.0033805445,0.0015795586,0.0022145608,0.0034880536,0.0034979114,0.00248267,0.0016782648],"category_scores_gemma":[0.01909655,0.0008448166,0.00094919535,0.0040669516,0.002307876,0.010376022,0.0030168232,0.0016510905,0.00074741803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020793343,0.000280587,0.008136188,0.0011308218,0.00035014722,0.00067080517,0.000925385,0.6422607,0.014087181,0.041961852,0.012189631,0.27592736],"study_design_scores_gemma":[0.00006566426,0.00016616187,0.00067178154,0.0000287253,0.000050711464,0.0005683939,0.0003710093,0.91039836,0.00579366,0.07954909,0.0022872495,0.000049166003],"about_ca_topic_score_codex":0.0028584443,"about_ca_topic_score_gemma":0.0031232224,"teacher_disagreement_score":0.005270128,"about_ca_system_score_codex":0.0012285911,"about_ca_system_score_gemma":0.0018205998,"threshold_uncertainty_score":0.02787143},"labels":[],"label_agreement":null},{"id":"W2111680152","doi":"10.1109/tkde.2005.111","title":"Integration and efficient lookup of compressed XML accessibility maps","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Access Control and Trust","field":"Social Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Simon Fraser University; Chinese University of Hong Kong; University of Hong Kong","keywords":"Computer science; XML; XML database; Efficient XML Interchange; Streaming XML; Document Structure Description; XML framework; XML Signature; Representation (politics); Database; Information retrieval; World Wide Web","score_opus":0.029268377672019983,"score_gpt":0.3110997126736295,"score_spread":0.2818313350016095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111680152","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13945495,0.00062221836,0.8244726,0.0005167012,0.0002732454,0.0004327803,0.002380589,0.01976819,0.01207879],"genre_scores_gemma":[0.5467447,0.00027098553,0.4412195,0.00010595737,0.00012207277,0.00028693222,0.005022541,0.00066732697,0.00555991],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99840146,0.00028166533,0.00015579474,0.00021537124,0.00077166694,0.00017400026],"domain_scores_gemma":[0.9947096,0.0017422491,0.0003629492,0.0018120628,0.0011918638,0.00018132124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008265116,0.000687836,0.0014610577,0.003339969,0.0009296852,0.0022527324,0.0017477609,0.0009431613,0.0073408284],"category_scores_gemma":[0.010950929,0.0004951004,0.0005994007,0.00450871,0.0005429726,0.0043871743,0.0032986575,0.00082871964,0.0017161685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001497969,0.00051248376,0.009458026,0.00063774467,0.00013488076,0.0017999836,0.0014178972,0.03253014,0.04110342,0.06394489,0.030354137,0.81660837],"study_design_scores_gemma":[0.00028680268,0.0004667937,0.004949595,0.000100777586,0.00016846678,0.0027057473,0.0014032293,0.77641016,0.10014123,0.06349789,0.049682733,0.00018652837],"about_ca_topic_score_codex":0.0035571149,"about_ca_topic_score_gemma":0.0033100133,"teacher_disagreement_score":0.0073408284,"about_ca_system_score_codex":0.00068485475,"about_ca_system_score_gemma":0.0012146345,"threshold_uncertainty_score":0.024557471},"labels":[],"label_agreement":null},{"id":"W2112154958","doi":"10.1109/tkde.2009.59","title":"Discovering Transitional Patterns and Their Significant Milestones in Transaction Databases","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Database; Database transaction; Transaction processing; Transaction log; Distributed database; Information retrieval; Data science","score_opus":0.02862650924382022,"score_gpt":0.26474186092001395,"score_spread":0.23611535167619374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112154958","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3945386,0.0027671251,0.5931224,0.00074288715,0.00008689811,0.00035803553,0.003344891,0.0012746699,0.0037644848],"genre_scores_gemma":[0.7138617,0.0012225878,0.2796689,0.000117712814,0.000060203874,0.00032545876,0.0034733335,0.000083824125,0.0011863986],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997512,0.00037898935,0.00047199198,0.0006024358,0.000817434,0.0002172556],"domain_scores_gemma":[0.99128586,0.004013802,0.001771474,0.0010864998,0.0014099285,0.00043242262],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018746858,0.00056500983,0.0007834533,0.00529917,0.001014439,0.0024784787,0.0013758943,0.00082541595,0.0010396527],"category_scores_gemma":[0.015359477,0.0005913836,0.000874859,0.007846926,0.00080783566,0.005282489,0.0017629787,0.001009484,0.00063046213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012922519,0.00046818866,0.19340944,0.0013652819,0.00048968423,0.004846871,0.0047280327,0.048180122,0.021519227,0.07274156,0.0069821905,0.6439772],"study_design_scores_gemma":[0.000108858556,0.0006383157,0.06763569,0.0004866188,0.00041219871,0.005485123,0.005025877,0.516828,0.026438626,0.34075987,0.035940457,0.00024038547],"about_ca_topic_score_codex":0.0015817959,"about_ca_topic_score_gemma":0.0014582139,"teacher_disagreement_score":0.00529917,"about_ca_system_score_codex":0.00049398956,"about_ca_system_score_gemma":0.00079696684,"threshold_uncertainty_score":0.009914398},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.01977965045427822,"score_gpt":0.2566786341254655,"score_spread":0.23689898367118728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114175725","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.086482316,0.000659201,0.8813296,0.0018248626,0.00019127378,0.00025078646,0.00019245158,0.0037250188,0.025344498],"genre_scores_gemma":[0.3993351,0.0007762984,0.5864334,0.00040330982,0.00007622405,0.00023372375,0.00048029522,0.0002413111,0.012020346],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99941695,0.000093522794,0.000087154054,0.00010699826,0.00021496965,0.00008044052],"domain_scores_gemma":[0.9985123,0.0003040167,0.00015977558,0.0006459436,0.00024416667,0.00013380722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010978987,0.0003121765,0.00038605975,0.0009362364,0.0007836079,0.0029783922,0.001763621,0.00081443804,0.00201338],"category_scores_gemma":[0.0034090378,0.00034039898,0.0006977285,0.0009684542,0.0011125766,0.008829594,0.0038422574,0.0010946231,0.0008101422],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021861044,0.0007561985,0.004561213,0.000505617,0.0001273068,0.00058804016,0.0037421961,0.018882334,0.035722695,0.28063926,0.008167138,0.6460894],"study_design_scores_gemma":[0.00017587513,0.0005053799,0.0035978458,0.00033392775,0.00060411636,0.0015807702,0.002884198,0.24540368,0.089201435,0.31558427,0.33993107,0.00019751686],"about_ca_topic_score_codex":0.0032230818,"about_ca_topic_score_gemma":0.0039014586,"teacher_disagreement_score":0.0032230818,"about_ca_system_score_codex":0.00063602027,"about_ca_system_score_gemma":0.0013716624,"threshold_uncertainty_score":0.006735444},"labels":[],"label_agreement":null},{"id":"W2117287993","doi":"10.1109/tkde.2008.94","title":"Detecting Word Substitutions in Text","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Sentence; Word (group theory); Natural language processing; Set (abstract data type); Artificial intelligence; Linguistics","score_opus":0.06066739218277305,"score_gpt":0.31280192462405365,"score_spread":0.2521345324412806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117287993","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8045488,0.0013735666,0.18147838,0.00050542085,0.00026194917,0.00057580206,0.0040241266,0.0035949182,0.003637082],"genre_scores_gemma":[0.8728727,0.00023779282,0.120437205,0.0001615928,0.00012943191,0.00021104298,0.004484815,0.00023739808,0.0012279385],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9917779,0.0024456177,0.0013731553,0.0020735557,0.0020115282,0.00031827635],"domain_scores_gemma":[0.9582957,0.026111552,0.0058731246,0.0030434767,0.0062314053,0.0004447633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035333398,0.001029851,0.0012986566,0.0054058847,0.0008132182,0.0018795022,0.0010088249,0.0015525003,0.0015783003],"category_scores_gemma":[0.028511766,0.0004951372,0.0005808178,0.0031845851,0.00079287565,0.003813155,0.0013297892,0.0007721099,0.0017127768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021413036,0.0004266149,0.19303304,0.0025802818,0.00043397248,0.0029099807,0.008387045,0.009248809,0.1998322,0.010105966,0.011702198,0.55919856],"study_design_scores_gemma":[0.00016852934,0.0012833421,0.20109336,0.00031637697,0.00067991525,0.009292183,0.0071100593,0.43311858,0.27059394,0.03158684,0.044347737,0.00040914043],"about_ca_topic_score_codex":0.001037647,"about_ca_topic_score_gemma":0.0011532826,"teacher_disagreement_score":0.0054058847,"about_ca_system_score_codex":0.0004995855,"about_ca_system_score_gemma":0.00064667215,"threshold_uncertainty_score":0.018686295},"labels":[],"label_agreement":null},{"id":"W2118532575","doi":"10.1109/tkde.2005.201","title":"Localization site prediction for membrane proteins by integrating rule and SVM classification","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Support vector machine; Computer science; Subsequence; Artificial intelligence; Machine learning; Precision and recall; Data mining; Curse of dimensionality; Kernel (algebra); Feature vector","score_opus":0.01169135818690139,"score_gpt":0.2569569636183845,"score_spread":0.2452656054314831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118532575","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18756717,0.0011847796,0.8064459,0.000454799,0.00012241147,0.00008251945,0.0002469532,0.0022643325,0.0016311134],"genre_scores_gemma":[0.77563053,0.00037868175,0.22136045,0.00016671677,0.00009581959,0.00005785694,0.0008859079,0.000054237444,0.0013698578],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989674,0.00022988683,0.00010811325,0.00025849335,0.00033799026,0.00009808027],"domain_scores_gemma":[0.99713033,0.0014717604,0.0002888182,0.00023191267,0.00077388907,0.00010326159],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016239639,0.00093607453,0.0014999585,0.0013258536,0.0002820131,0.0011809472,0.0013294872,0.0014214199,0.000605475],"category_scores_gemma":[0.003659318,0.0002543246,0.0008624931,0.001127783,0.00038499173,0.0012447804,0.00061712274,0.00103408,0.00065544236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040346966,0.0005903578,0.01792239,0.00020408907,0.00019417715,0.00051035115,0.00008721737,0.4198726,0.02143754,0.0021671709,0.0025336817,0.5340769],"study_design_scores_gemma":[0.00000493387,0.0000380263,0.00054838666,0.0000037650523,0.000010831079,0.00003647737,0.000008111398,0.9961624,0.0021163148,0.0009259988,0.00013940796,0.000005352509],"about_ca_topic_score_codex":0.0033608577,"about_ca_topic_score_gemma":0.002269079,"teacher_disagreement_score":0.0033608577,"about_ca_system_score_codex":0.00048487104,"about_ca_system_score_gemma":0.0006333931,"threshold_uncertainty_score":0.008588433},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09300923597913141,"score_gpt":0.29509245422620883,"score_spread":0.20208321824707742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119387217","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042784154,0.006982482,0.92583054,0.0074865147,0.00040360278,0.00075684296,0.00019561996,0.00070797186,0.014852342],"genre_scores_gemma":[0.7814409,0.0013854863,0.2112347,0.0013680455,0.0009421436,0.0008920407,0.00019560636,0.00016395727,0.0023769904],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.7619199,0.15733872,0.014019558,0.025215736,0.03882136,0.002684615],"domain_scores_gemma":[0.5184613,0.39864513,0.02932931,0.021441717,0.028945366,0.0031771793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15172961,0.002222696,0.0042573474,0.009435309,0.0041188058,0.012835024,0.004737952,0.006168974,0.003401253],"category_scores_gemma":[0.4305668,0.0019789895,0.0016452381,0.0056943162,0.012182105,0.019695887,0.009494485,0.005486071,0.00079461717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006813184,0.0002081588,0.027175909,0.0013597389,0.0007981609,0.00044647173,0.004807076,0.063206136,0.0017196808,0.61519873,0.0053223516,0.27907634],"study_design_scores_gemma":[0.00021716856,0.000265448,0.004760244,0.00043005613,0.00026876802,0.00055298023,0.0005120935,0.19735186,0.0021015825,0.7798671,0.013474381,0.00019827446],"about_ca_topic_score_codex":0.002632966,"about_ca_topic_score_gemma":0.0013403568,"teacher_disagreement_score":0.15172961,"about_ca_system_score_codex":0.0083580585,"about_ca_system_score_gemma":0.0043047764,"threshold_uncertainty_score":0.8024325},"labels":[],"label_agreement":null},{"id":"W2122115541","doi":"10.1109/tkde.2003.1232279","title":"Reasoning about uniqueness constraints in object relational databases","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Relational database; Uniqueness; Generalization; Functional dependency; Theoretical computer science; Relational model; Object (grammar); Simple (philosophy); Relational calculus; Representation (politics); Core (optical fiber); Database; Artificial intelligence; Mathematics","score_opus":0.03363073257960945,"score_gpt":0.27978618866793326,"score_spread":0.24615545608832382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122115541","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027876124,0.0010536715,0.96525663,0.0020293514,0.00004653363,0.000111603265,0.00032247652,0.00035944366,0.0029442592],"genre_scores_gemma":[0.41891316,0.0020622108,0.5730703,0.0006975381,0.00029411147,0.00029285235,0.001155058,0.00020547419,0.0033093302],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98575807,0.006545165,0.0014793696,0.0020085606,0.003469297,0.000739519],"domain_scores_gemma":[0.9743896,0.020441175,0.001500312,0.002121264,0.001177469,0.00037012793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013913274,0.0010020527,0.0015658097,0.0019442166,0.0031167236,0.0072989725,0.0034211266,0.002779393,0.0035368928],"category_scores_gemma":[0.03767237,0.0015144532,0.0027446772,0.0043119704,0.0042837695,0.025530655,0.006035931,0.003876223,0.00051071314],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013683704,0.00007420541,0.002009736,0.00036986123,0.00012005643,0.0008083706,0.00080035714,0.052067425,0.0017422898,0.8795572,0.0038540221,0.05845949],"study_design_scores_gemma":[0.000030989617,0.000025071493,0.00023591435,0.00005298188,0.00008361493,0.00030549738,0.00041694724,0.104734726,0.0034730001,0.8851229,0.0054798583,0.000038434613],"about_ca_topic_score_codex":0.0034074038,"about_ca_topic_score_gemma":0.004556721,"teacher_disagreement_score":0.013913274,"about_ca_system_score_codex":0.0019964448,"about_ca_system_score_gemma":0.002306853,"threshold_uncertainty_score":0.07358128},"labels":[],"label_agreement":null},{"id":"W2124070832","doi":"10.1109/tkde.2002.1033784","title":"The presumed-either two-phase commit protocol","year":2002,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; IBM (Canada)","funders":"","keywords":"Commit; Abort; Computer science; Two-phase commit protocol; Exploit; Compensating transaction; Protocol (science); Computer security; Distributed transaction; Transaction processing; Operating system; Database; Medicine; Database transaction","score_opus":0.03674964714283385,"score_gpt":0.3081144308505624,"score_spread":0.27136478370772854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124070832","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012436058,0.0015293052,0.939121,0.0013368815,0.00093785085,0.0018685067,0.0012764608,0.007369283,0.034124658],"genre_scores_gemma":[0.3754615,0.0030704662,0.5600005,0.001352438,0.0006170243,0.0021111278,0.0035967687,0.0012943152,0.05249595],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963198,0.00084527,0.0003745969,0.00039258727,0.0016827909,0.0003849899],"domain_scores_gemma":[0.99484104,0.0007125456,0.0004310632,0.0024576834,0.0011556717,0.00040193347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024775113,0.0006738841,0.000663506,0.00067208,0.0012722391,0.0024693392,0.0037197645,0.0014277243,0.01063869],"category_scores_gemma":[0.0067065093,0.00061436655,0.0004717103,0.0012752351,0.0013606345,0.005270073,0.0056202575,0.0029312368,0.0036808867],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015470675,0.0003362254,0.0011132053,0.0013066517,0.00009904759,0.00063185487,0.0006915358,0.021680899,0.031879786,0.5170864,0.07851,0.34511733],"study_design_scores_gemma":[0.000585648,0.0008333188,0.0005722531,0.00022435338,0.00014569549,0.0016138408,0.00039956046,0.16676047,0.05199786,0.1364798,0.64010274,0.0002845808],"about_ca_topic_score_codex":0.0014962914,"about_ca_topic_score_gemma":0.0014639156,"teacher_disagreement_score":0.01063869,"about_ca_system_score_codex":0.00068713597,"about_ca_system_score_gemma":0.0036460578,"threshold_uncertainty_score":0.035589933},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0310304745145064,"score_gpt":0.2611466064437121,"score_spread":0.23011613192920571,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127426313","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021081863,0.000056910467,0.97591364,0.0002108158,0.0000070300553,0.00005011915,0.00041745513,0.00027517046,0.0019871236],"genre_scores_gemma":[0.4746268,0.0002591506,0.5205736,0.00010193481,0.00003226506,0.00029926453,0.0022152963,0.000105021936,0.0017866512],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985903,0.0004361602,0.000080026824,0.0003978226,0.00041646668,0.00007922116],"domain_scores_gemma":[0.9967669,0.002010412,0.00028276636,0.00045592652,0.00039572825,0.00008829095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012297812,0.0004910256,0.00044688367,0.0018520383,0.0008444364,0.00086786237,0.0008681125,0.00079451606,0.0028680312],"category_scores_gemma":[0.0068130796,0.0007002478,0.0011253892,0.0009912523,0.0010185523,0.0028311727,0.0017319369,0.0010439925,0.00044767675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021192015,0.00008237459,0.008263402,0.0003219383,0.00020342093,0.0012775443,0.00094393996,0.4794039,0.009241381,0.36811104,0.0050700754,0.126869],"study_design_scores_gemma":[0.0000138812575,0.000025061054,0.0016055403,0.00003313114,0.00005573219,0.00017808178,0.00005266473,0.7768009,0.0035554864,0.21260454,0.0050509875,0.000023977846],"about_ca_topic_score_codex":0.0036345755,"about_ca_topic_score_gemma":0.0038028357,"teacher_disagreement_score":0.0036345755,"about_ca_system_score_codex":0.00114968,"about_ca_system_score_gemma":0.0011161626,"threshold_uncertainty_score":0.0095945},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.039446023589009414,"score_gpt":0.28539766762821617,"score_spread":0.24595164403920675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128933128","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00091333885,0.00038809274,0.99670863,0.0001382165,0.000070086746,0.00012153916,0.0001258526,0.0009001699,0.00063402276],"genre_scores_gemma":[0.023654105,0.00045078545,0.97347623,0.00014050177,0.000098762604,0.00052400754,0.0006247838,0.00022548679,0.0008053708],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9891651,0.0039779367,0.0007816641,0.002444285,0.0032920998,0.00033885316],"domain_scores_gemma":[0.9919435,0.0033569282,0.0006361281,0.002329498,0.0015751322,0.0001588444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053750025,0.00257738,0.0023552151,0.0059525953,0.0022379393,0.002918095,0.0032491214,0.002132346,0.0059254407],"category_scores_gemma":[0.018429881,0.0009902064,0.0029088268,0.012492417,0.0021075779,0.0047043185,0.004339161,0.00391329,0.0030100802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003539117,0.00023920728,0.0027660537,0.0015645023,0.0007248315,0.0004305415,0.0010851305,0.06390357,0.009194709,0.14778422,0.01842519,0.7535281],"study_design_scores_gemma":[0.00006922565,0.00015176077,0.0015437745,0.0001648066,0.00018557115,0.00075490883,0.00030241956,0.68095964,0.012876722,0.234316,0.06850021,0.00017497638],"about_ca_topic_score_codex":0.0029423118,"about_ca_topic_score_gemma":0.003081787,"teacher_disagreement_score":0.0059525953,"about_ca_system_score_codex":0.001336112,"about_ca_system_score_gemma":0.0025906183,"threshold_uncertainty_score":0.028426051},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03923416376241975,"score_gpt":0.2902071390881266,"score_spread":0.2509729753257069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129500661","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062254626,0.00037787625,0.93497145,0.00025137703,0.00004252632,0.0001841339,0.0004301528,0.0006967588,0.0007910997],"genre_scores_gemma":[0.33653647,0.0005125635,0.65809417,0.00010140152,0.000094959585,0.00041475554,0.0028697595,0.00013304417,0.0012428489],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99439764,0.0017170828,0.00039058377,0.001161525,0.0019965617,0.0003366333],"domain_scores_gemma":[0.99090004,0.0037489207,0.0009833293,0.0012555055,0.0027737212,0.00033842959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038430674,0.0014589146,0.002320229,0.0058765067,0.0020845176,0.0034048478,0.0027619621,0.002166633,0.00091697136],"category_scores_gemma":[0.018570248,0.0010569788,0.001927939,0.0059831226,0.001610611,0.0034013514,0.00403104,0.001920173,0.00085037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007366231,0.0005352815,0.02626669,0.00088613713,0.000890365,0.0015013831,0.0028139418,0.51516795,0.009665623,0.06391372,0.011021431,0.36660084],"study_design_scores_gemma":[0.00003637567,0.000078055295,0.0026737624,0.000046894023,0.000041927673,0.0002743098,0.00062768225,0.919227,0.0024768417,0.0724598,0.002007036,0.00005036467],"about_ca_topic_score_codex":0.0033761282,"about_ca_topic_score_gemma":0.0031436025,"teacher_disagreement_score":0.0058765067,"about_ca_system_score_codex":0.0009341603,"about_ca_system_score_gemma":0.0016228295,"threshold_uncertainty_score":0.02032435},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.02779020595604768,"score_gpt":0.2810140212831417,"score_spread":0.253223815327094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129546202","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004177923,0.00016792033,0.9939487,0.00014103999,0.000031562126,0.0001640004,0.00013614744,0.0005482856,0.0006844412],"genre_scores_gemma":[0.06240765,0.0003027297,0.93394667,0.00016234317,0.000045913082,0.00055062526,0.0007043881,0.00008416014,0.0017954471],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803203,0.00042183872,0.00012758425,0.0004775755,0.0008587477,0.00008221613],"domain_scores_gemma":[0.99803144,0.00076307275,0.00012661787,0.00018156884,0.00084948016,0.000047796864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024012534,0.0012081497,0.0015636203,0.002691224,0.001174269,0.001540669,0.0031651182,0.0014817126,0.0018518734],"category_scores_gemma":[0.0059894016,0.000546024,0.0016378001,0.0038363833,0.00065004634,0.0037742942,0.0012812141,0.0016015565,0.0013824913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025778115,0.00046383947,0.0022565767,0.0004817782,0.00022717258,0.00036037917,0.0006281056,0.3258717,0.012870876,0.05980281,0.011179038,0.5855999],"study_design_scores_gemma":[0.00001140514,0.000028721808,0.0001354591,0.000011420226,0.000015415562,0.000096718,0.000026594382,0.9864913,0.0013247916,0.009396266,0.0024488636,0.000013027726],"about_ca_topic_score_codex":0.006205599,"about_ca_topic_score_gemma":0.0064928136,"teacher_disagreement_score":0.006205599,"about_ca_system_score_codex":0.0014675299,"about_ca_system_score_gemma":0.002304716,"threshold_uncertainty_score":0.012699187},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Advantage Forensics (Canada)","funders":"Australian Research Council; University of Warwick","keywords":"Computer science; Identity (music); Computer security","score_opus":0.03861372655258806,"score_gpt":0.271454297643489,"score_spread":0.23284057109090095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131967083","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36305046,0.00040525946,0.6169004,0.0010888376,0.00017112226,0.0004915092,0.0005381503,0.010514615,0.006839645],"genre_scores_gemma":[0.88497525,0.00011753098,0.11217321,0.00022987979,0.000043333996,0.00008073035,0.00031298868,0.00005685861,0.0020102914],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968004,0.00049013953,0.00027101886,0.0007344895,0.0013134601,0.0003904373],"domain_scores_gemma":[0.9913669,0.0020317163,0.0017037443,0.0026616831,0.0018690721,0.0003668573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022675162,0.0007431807,0.0011040132,0.0033621087,0.0008835218,0.0022200868,0.0018795934,0.0011590503,0.0013699712],"category_scores_gemma":[0.011154575,0.000438796,0.00075506227,0.0014096972,0.0007824133,0.0026926026,0.004092277,0.0012463061,0.0008278784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007500381,0.00085693033,0.07616997,0.00023983348,0.00037682056,0.00076716783,0.0007445374,0.061649583,0.05203388,0.011896596,0.0075803665,0.78693414],"study_design_scores_gemma":[0.000043922635,0.00054906466,0.022230081,0.000054656142,0.00017205413,0.0014937257,0.0003895353,0.8707913,0.07682346,0.016969532,0.010331887,0.0001507479],"about_ca_topic_score_codex":0.00198873,"about_ca_topic_score_gemma":0.0015642846,"teacher_disagreement_score":0.0033621087,"about_ca_system_score_codex":0.0010226035,"about_ca_system_score_gemma":0.0011629786,"threshold_uncertainty_score":0.0119918585},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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)","score_opus":0.01617825178139467,"score_gpt":0.24222236436313338,"score_spread":0.2260441125817387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134465446","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023576105,0.0003218394,0.97407156,0.0002452199,0.000017747176,0.000054486994,0.000078695455,0.0003110074,0.0013233512],"genre_scores_gemma":[0.6299979,0.00035093713,0.36749455,0.0001663455,0.00014187569,0.0003014824,0.00037597993,0.00021322428,0.0009577162],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959371,0.0019320399,0.00025132298,0.00063990953,0.001067388,0.00017223928],"domain_scores_gemma":[0.9836767,0.013064697,0.0013232181,0.0008547797,0.00088163535,0.00019898915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064534596,0.0011110007,0.0010243434,0.0020833474,0.0006129742,0.0021913855,0.0012345474,0.0017049165,0.0012293227],"category_scores_gemma":[0.028146137,0.00040722766,0.0008457256,0.0014183457,0.0019987642,0.0030802388,0.0018737583,0.0014028249,0.0002843376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007859314,0.00031143535,0.0143523365,0.00048784752,0.0005093671,0.00026865618,0.000306101,0.51523584,0.022456517,0.13401385,0.002423245,0.30884895],"study_design_scores_gemma":[0.00002270102,0.00012967933,0.0023350096,0.00003126285,0.000051231655,0.00009347305,0.000029799407,0.9376958,0.010958456,0.04787211,0.0007351019,0.000045376873],"about_ca_topic_score_codex":0.0007006774,"about_ca_topic_score_gemma":0.00050522195,"teacher_disagreement_score":0.0064534596,"about_ca_system_score_codex":0.00091405044,"about_ca_system_score_gemma":0.00093825994,"threshold_uncertainty_score":0.03412956},"labels":[],"label_agreement":null},{"id":"W2137420824","doi":"10.1109/tkde.2002.1047768","title":"Efficient queries over Web views","year":2002,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Relational database; Information retrieval; Redundancy (engineering); Materialized view; Data redundancy; Set (abstract data type); SQL; Data mining; World Wide Web; Theoretical computer science; Database; View; Database design; Programming language","score_opus":0.036669561203935296,"score_gpt":0.2640088886651401,"score_spread":0.2273393274612048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137420824","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053177577,0.00081894774,0.9218262,0.0008228606,0.00009543469,0.0003086972,0.002525731,0.010092668,0.0103319455],"genre_scores_gemma":[0.4096172,0.0015342046,0.5648744,0.00046838727,0.00027877087,0.00035151266,0.010027363,0.0025390768,0.010309016],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9933571,0.0016109966,0.00080143294,0.0007193549,0.0029600537,0.00055097335],"domain_scores_gemma":[0.99237025,0.0035477437,0.0004196839,0.0022209547,0.0012728353,0.00016848327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029094063,0.00092352333,0.0016581868,0.0018768348,0.0010171167,0.0061451322,0.0023471129,0.001650615,0.0042400346],"category_scores_gemma":[0.015400399,0.00092611474,0.0015460978,0.0032296341,0.001215734,0.010139185,0.004440961,0.0017223613,0.0018054998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008259831,0.00040291267,0.0043621687,0.0009234331,0.00031997488,0.0014682114,0.003119778,0.09747008,0.048458718,0.42588264,0.05188553,0.36488056],"study_design_scores_gemma":[0.00024209924,0.00017465482,0.0010684228,0.00014400925,0.00019267057,0.0008272591,0.0016111338,0.51012915,0.0410604,0.36655942,0.07785262,0.00013808087],"about_ca_topic_score_codex":0.004563574,"about_ca_topic_score_gemma":0.00543475,"teacher_disagreement_score":0.0061451322,"about_ca_system_score_codex":0.0011680229,"about_ca_system_score_gemma":0.0013692641,"threshold_uncertainty_score":0.015386581},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.050218342144370126,"score_gpt":0.32520649560718534,"score_spread":0.27498815346281524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137525015","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028345145,0.0007836768,0.96742254,0.0003319578,0.00007133339,0.00009625843,0.0004018303,0.0010558988,0.0014913555],"genre_scores_gemma":[0.358053,0.0009426634,0.6382083,0.000089084984,0.0000666227,0.00018491909,0.00095642946,0.000050575236,0.0014483954],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927336,0.00017493406,0.00008597284,0.0001482859,0.00027790037,0.000039490355],"domain_scores_gemma":[0.99828374,0.0009505914,0.00015031126,0.00021804974,0.00035881804,0.000038540846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011853278,0.0004194577,0.0008214544,0.002315829,0.0003820669,0.0008857774,0.0007849008,0.0006189582,0.0018031836],"category_scores_gemma":[0.006341463,0.00020978467,0.00070059457,0.0029161396,0.00037805393,0.0012690646,0.00047142303,0.00065739616,0.00041504248],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026012966,0.00015221695,0.00584677,0.0003771207,0.0001326603,0.0004251004,0.00028780222,0.088235326,0.013738076,0.025884243,0.0044500143,0.86021054],"study_design_scores_gemma":[0.000016017178,0.000047586356,0.0017448582,0.000027125114,0.000030418865,0.00014768957,0.000056256504,0.97135824,0.004761319,0.018399676,0.003388354,0.000022382543],"about_ca_topic_score_codex":0.0039660716,"about_ca_topic_score_gemma":0.0027759138,"teacher_disagreement_score":0.0039660716,"about_ca_system_score_codex":0.0005259755,"about_ca_system_score_gemma":0.00063959055,"threshold_uncertainty_score":0.007885933},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.020283882135440662,"score_gpt":0.2679597706680517,"score_spread":0.24767588853261105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137763598","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033131705,0.0003755327,0.993883,0.000062756495,0.000034330118,0.000090919486,0.0003639852,0.0011645204,0.0007118771],"genre_scores_gemma":[0.03637255,0.0005158997,0.9601054,0.00004729038,0.00007315654,0.0002402213,0.0016766472,0.00021146996,0.0007574298],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835736,0.00043355348,0.00012424887,0.00026482795,0.0007371228,0.00008283414],"domain_scores_gemma":[0.9980203,0.0006195031,0.00016766375,0.0005740468,0.0005630313,0.00005553494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001256536,0.000784139,0.0013990686,0.0044058217,0.0010985264,0.0016053497,0.0017828386,0.0010073637,0.0023364516],"category_scores_gemma":[0.007110163,0.0004591109,0.0010245938,0.009499787,0.00066112063,0.0027966232,0.0016434251,0.001270631,0.0026181182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020136283,0.00012079171,0.00089925394,0.00042227894,0.000103364946,0.000107588065,0.0002800754,0.0887168,0.02255181,0.059162132,0.01699824,0.8104363],"study_design_scores_gemma":[0.000045926172,0.00008310653,0.0005826834,0.000024824387,0.000049003404,0.00023363775,0.00007138492,0.9032925,0.008853515,0.07417627,0.012537624,0.000049595845],"about_ca_topic_score_codex":0.004000303,"about_ca_topic_score_gemma":0.0041786847,"teacher_disagreement_score":0.0044058217,"about_ca_system_score_codex":0.0011038744,"about_ca_system_score_gemma":0.0015698292,"threshold_uncertainty_score":0.008009255},"labels":[],"label_agreement":null},{"id":"W2140849876","doi":"10.1109/tkde.2010.223","title":"Effective and Efficient Shape-Based Pattern Detection over Streaming Time Series","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Euclidean distance; Series (stratigraphy); Time series; Measure (data warehouse); Distance measures; Scaling; Data mining; Pattern recognition (psychology); Artificial intelligence; Algorithm; Machine learning; Mathematics","score_opus":0.006535432479670956,"score_gpt":0.21111493770867348,"score_spread":0.20457950522900253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140849876","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040892437,0.00021084548,0.95733416,0.00009084798,0.000033970467,0.000043291802,0.00013959128,0.0008096996,0.00044513989],"genre_scores_gemma":[0.32636234,0.00029234737,0.67143726,0.00005116429,0.00006579155,0.00008268495,0.00068397616,0.00009697838,0.000927519],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991019,0.00012430701,0.00009624646,0.00021373646,0.00042118947,0.00004271856],"domain_scores_gemma":[0.99734855,0.0010455052,0.00040642693,0.00042759327,0.00065807765,0.000113941605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006900135,0.00057477114,0.00097173214,0.0020037557,0.00030058253,0.0008086644,0.001090857,0.00053912593,0.0005879794],"category_scores_gemma":[0.005460515,0.00027064193,0.00050718436,0.002290087,0.00044446214,0.0016322698,0.0010168959,0.00061490486,0.00044494538],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025177808,0.000120089404,0.0056172595,0.00018691013,0.00006191697,0.00022566659,0.00018226633,0.0583432,0.058544993,0.004930942,0.0023395082,0.8691956],"study_design_scores_gemma":[0.000012960872,0.00007215115,0.0028925254,0.0000071568124,0.000013071933,0.0003082716,0.000054590935,0.9784253,0.012535569,0.00429623,0.0013610171,0.000021060292],"about_ca_topic_score_codex":0.0012554468,"about_ca_topic_score_gemma":0.0012726311,"teacher_disagreement_score":0.0020037557,"about_ca_system_score_codex":0.00031212353,"about_ca_system_score_gemma":0.0005178709,"threshold_uncertainty_score":0.0036491752},"labels":[],"label_agreement":null},{"id":"W2141277572","doi":"10.1109/tkde.2013.53","title":"Extended Subtree: A New Similarity Function for Tree Structured Data","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Similarity (geometry); Edit distance; Cluster analysis; Data mining; Tree (set theory); Function (biology); Theoretical computer science; Artificial intelligence; Mathematics","score_opus":0.058334273774491116,"score_gpt":0.3147285319055442,"score_spread":0.25639425813105304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141277572","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018552322,0.00072548515,0.9778242,0.00013983005,0.000095705014,0.000098585326,0.00046011346,0.0012525616,0.0008512388],"genre_scores_gemma":[0.17310433,0.0006824738,0.821148,0.00019667827,0.00015021858,0.00029239597,0.0022966065,0.0004138959,0.0017154814],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965545,0.0006672787,0.00044956984,0.0004965391,0.0017033953,0.0001287311],"domain_scores_gemma":[0.9962134,0.001222057,0.00046824792,0.0008346188,0.0010454516,0.00021628893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020865132,0.0006251882,0.0011114791,0.0041650156,0.00064342126,0.0016451104,0.0016604419,0.0012452323,0.0014690218],"category_scores_gemma":[0.009092638,0.00028146862,0.0011802017,0.0056081,0.00065390277,0.0056574373,0.0026038205,0.0011617058,0.001104382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035406242,0.00020077499,0.005824598,0.0005695277,0.00021830612,0.00031622913,0.0008288116,0.040022794,0.033286124,0.05511758,0.009282807,0.85397846],"study_design_scores_gemma":[0.00009091879,0.0009738301,0.0061877873,0.00017894206,0.00014824962,0.0027839465,0.0005954216,0.7546619,0.032485835,0.13474983,0.066936545,0.00020683679],"about_ca_topic_score_codex":0.0010391814,"about_ca_topic_score_gemma":0.0014896074,"teacher_disagreement_score":0.0041650156,"about_ca_system_score_codex":0.0007460965,"about_ca_system_score_gemma":0.0010801341,"threshold_uncertainty_score":0.011034727},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.017260913842518027,"score_gpt":0.24542276892658657,"score_spread":0.22816185508406855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142103633","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27222303,0.001294818,0.71563655,0.00068417593,0.00006437194,0.00043840907,0.005819207,0.0019859548,0.001853438],"genre_scores_gemma":[0.41132307,0.00078748417,0.5706759,0.00019535249,0.000081608756,0.00040109822,0.015236661,0.00014945013,0.0011494062],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9971616,0.00046726078,0.00041012443,0.0005759661,0.0011708846,0.00021424454],"domain_scores_gemma":[0.9869489,0.008455784,0.0014018129,0.0013166936,0.0015332801,0.00034353998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014858709,0.00082628714,0.0016507729,0.004723179,0.0010166237,0.0019181719,0.0010986144,0.00096252654,0.0009231555],"category_scores_gemma":[0.015011779,0.0005743806,0.001394089,0.004411127,0.00089753006,0.0034320334,0.0011923896,0.0011497282,0.00044516154],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001060183,0.00074955804,0.053015396,0.0016234518,0.00044575753,0.0043911524,0.0016661453,0.14089273,0.03525902,0.05267023,0.008462062,0.6997643],"study_design_scores_gemma":[0.00009789277,0.0003136003,0.009357158,0.00015384665,0.00011783261,0.002682037,0.00069113466,0.7034766,0.019036468,0.25361317,0.010365211,0.00009503088],"about_ca_topic_score_codex":0.0015371002,"about_ca_topic_score_gemma":0.0026196726,"teacher_disagreement_score":0.004723179,"about_ca_system_score_codex":0.0005395763,"about_ca_system_score_gemma":0.0019184019,"threshold_uncertainty_score":0.007858098},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.036150843997362125,"score_gpt":0.3036804357149973,"score_spread":0.2675295917176352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142407957","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029543152,0.0050776666,0.9463759,0.003036985,0.0005575659,0.0009008871,0.007989472,0.0026561108,0.0038621905],"genre_scores_gemma":[0.20764992,0.00177557,0.77022076,0.00085681415,0.0012234941,0.0015860393,0.013496944,0.00012215662,0.0030682816],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99557686,0.0016490916,0.0007966117,0.001066242,0.00078206963,0.00012914646],"domain_scores_gemma":[0.98871243,0.009198558,0.0008685,0.00041626894,0.00067013566,0.00013406368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037036338,0.0014498367,0.0010760013,0.008528781,0.0012503392,0.0017027095,0.0012663895,0.002082722,0.0032395334],"category_scores_gemma":[0.014033899,0.00041736054,0.0015403581,0.006561076,0.0008854509,0.0032748578,0.001145486,0.001897935,0.0021485945],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005914831,0.0007850201,0.010086382,0.0016916329,0.00049745396,0.0008792362,0.0009176021,0.021205531,0.015361419,0.01547331,0.015266018,0.91724485],"study_design_scores_gemma":[0.00025400944,0.00084955094,0.01765995,0.0005058808,0.000660889,0.0021348891,0.000790077,0.809005,0.015308147,0.094279625,0.05831947,0.0002324901],"about_ca_topic_score_codex":0.0024617983,"about_ca_topic_score_gemma":0.003383113,"teacher_disagreement_score":0.008528781,"about_ca_system_score_codex":0.0010037238,"about_ca_system_score_gemma":0.0016850717,"threshold_uncertainty_score":0.01958692},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.011715846144598278,"score_gpt":0.2185866327377866,"score_spread":0.20687078659318833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142595897","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048663286,0.0006757962,0.9913248,0.000252945,0.000058167305,0.00007677974,0.00020242875,0.0005707425,0.0019720325],"genre_scores_gemma":[0.06422652,0.0014360504,0.9289873,0.00017234124,0.00022762174,0.00014897306,0.0014422814,0.0002948702,0.003063974],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968713,0.000726717,0.0002824432,0.00049574167,0.0014232784,0.00020044995],"domain_scores_gemma":[0.99250436,0.0028172287,0.0006533103,0.0018445406,0.0019068186,0.0002737359],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020521258,0.0008683396,0.0011568443,0.004942249,0.001540506,0.0029334913,0.0019882454,0.0011780564,0.0041445745],"category_scores_gemma":[0.012572039,0.0006516917,0.0012295751,0.009070652,0.001689327,0.008252941,0.0023037384,0.002337043,0.002916873],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019305159,0.00014609033,0.0022698226,0.00036900153,0.00006202583,0.0003378647,0.00044421115,0.035829578,0.011947421,0.26466912,0.014652949,0.6690788],"study_design_scores_gemma":[0.000052931337,0.00020082701,0.001118241,0.00013223317,0.000071316485,0.0013426539,0.00019970439,0.4917144,0.016757179,0.43731374,0.050989665,0.00010717844],"about_ca_topic_score_codex":0.0028864916,"about_ca_topic_score_gemma":0.0018614932,"teacher_disagreement_score":0.004942249,"about_ca_system_score_codex":0.001233792,"about_ca_system_score_gemma":0.0024451506,"threshold_uncertainty_score":0.013864994},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.026532542095579034,"score_gpt":0.26306770202565416,"score_spread":0.23653515993007512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142804492","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00457055,0.00013033266,0.978224,0.00010445403,0.00004499501,0.0003118023,0.0006708455,0.0154181495,0.0005249332],"genre_scores_gemma":[0.035959456,0.000090457106,0.95797133,0.000091908325,0.00004448365,0.00047978453,0.002799107,0.0006694241,0.0018940021],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99767166,0.00029461834,0.0003437117,0.0005074628,0.0010347725,0.00014765735],"domain_scores_gemma":[0.9948461,0.0020689985,0.00072464533,0.001211239,0.0010263651,0.00012276275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018307683,0.001515722,0.0010348231,0.004903258,0.0011865913,0.0021340856,0.0022091276,0.0012321738,0.0040700296],"category_scores_gemma":[0.009325748,0.0007872199,0.0012189158,0.0032290695,0.00065382896,0.0036969043,0.0021079327,0.001653233,0.004285804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038782402,0.00021388875,0.0035831567,0.00041808852,0.00007312309,0.00015640586,0.00027117788,0.010861091,0.020971708,0.0065154703,0.016551971,0.93999624],"study_design_scores_gemma":[0.00019427633,0.00024382844,0.0034245958,0.00011574017,0.00007666229,0.0007593101,0.00023430913,0.8646445,0.052788384,0.03601812,0.041386195,0.000114106944],"about_ca_topic_score_codex":0.002370723,"about_ca_topic_score_gemma":0.0035750347,"teacher_disagreement_score":0.004903258,"about_ca_system_score_codex":0.0012493143,"about_ca_system_score_gemma":0.0024653347,"threshold_uncertainty_score":0.013615668},"labels":[],"label_agreement":null},{"id":"W2147312192","doi":"10.1109/tkde.2006.73","title":"Approximate processing of massive continuous quantile queries over high-speed data streams","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"China Academy of Space Technology; University of New South Wales","keywords":"Computer science; Data stream mining; STREAMS; Quantile; Data mining; Parallel computing; Computer network; Statistics; Mathematics","score_opus":0.020542173346513697,"score_gpt":0.2531488894735193,"score_spread":0.23260671612700562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147312192","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08510664,0.00094511587,0.9092313,0.00033953087,0.00007208404,0.000095753836,0.00046643597,0.0029047334,0.000838409],"genre_scores_gemma":[0.71967405,0.0005522156,0.27661002,0.00014349981,0.00015547492,0.000119813885,0.0014230593,0.00017252886,0.0011493663],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99797446,0.00032642216,0.00019877242,0.00043597017,0.0008762752,0.00018802963],"domain_scores_gemma":[0.9964187,0.0013386576,0.00045603333,0.00092909776,0.0006894848,0.00016805305],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016846556,0.0009746532,0.0016027984,0.0009700097,0.0008390953,0.0016813211,0.0016790639,0.0007162113,0.0010226064],"category_scores_gemma":[0.0072101117,0.00044053802,0.00061550416,0.0029087258,0.000727087,0.0025999385,0.0015322932,0.0009986655,0.00046071477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023556752,0.00032840206,0.013750646,0.00049116486,0.0003088349,0.0008163706,0.0010284433,0.46941787,0.07152443,0.01625702,0.009933361,0.41378778],"study_design_scores_gemma":[0.00002765065,0.000119935656,0.0015817381,0.0000066765924,0.000025055173,0.00016000307,0.00017768345,0.976901,0.010405037,0.008754604,0.0018258517,0.000014702316],"about_ca_topic_score_codex":0.003641268,"about_ca_topic_score_gemma":0.0032051238,"teacher_disagreement_score":0.003641268,"about_ca_system_score_codex":0.00085206755,"about_ca_system_score_gemma":0.0008900011,"threshold_uncertainty_score":0.008909404},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.03825382451170466,"score_gpt":0.27483103722904034,"score_spread":0.23657721271733567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147876569","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016466463,0.00032197856,0.9778265,0.00031904515,0.00008279479,0.00014986524,0.0002312261,0.003042616,0.0015595279],"genre_scores_gemma":[0.3727706,0.0003319029,0.6167295,0.0004934108,0.00020449475,0.0003560472,0.0017615401,0.0006580561,0.006694471],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99667513,0.0011803788,0.00016136859,0.0005457434,0.0011583567,0.00027904872],"domain_scores_gemma":[0.993258,0.002465226,0.00064899714,0.0019307734,0.001405256,0.00029176826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045770067,0.0011736517,0.0020659203,0.0016903075,0.0010528067,0.0023503744,0.0030208358,0.0021857936,0.003967816],"category_scores_gemma":[0.014905957,0.000438874,0.00089996157,0.0013873106,0.0012734235,0.0030739696,0.0027506538,0.0024791944,0.0028511565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048385587,0.0004735461,0.002579386,0.00032901333,0.00014666597,0.0002509505,0.00017575012,0.22113615,0.009610462,0.037545115,0.03168866,0.6955804],"study_design_scores_gemma":[0.00002588075,0.00010273119,0.0003540216,0.000010543497,0.000011706781,0.0001400602,0.000029661958,0.97951114,0.0036355418,0.0137792295,0.0023750216,0.000024368845],"about_ca_topic_score_codex":0.0033337208,"about_ca_topic_score_gemma":0.0041384995,"teacher_disagreement_score":0.0045770067,"about_ca_system_score_codex":0.0010933189,"about_ca_system_score_gemma":0.0019069132,"threshold_uncertainty_score":0.024205863},"labels":[],"label_agreement":null},{"id":"W2149473201","doi":"10.1109/tkde.2009.17","title":"Learning Heuristics for the Superblock Instruction Scheduling Problem","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Heuristics; Compiler; Parallel computing; Scheduling (production processes); Instruction scheduling; Benchmark (surveying); Register allocation; Schedule; Dynamic priority scheduling; Two-level scheduling; Programming language; Mathematical optimization; Operating system; Mathematics","score_opus":0.02210105566365551,"score_gpt":0.2659790234019478,"score_spread":0.2438779677382923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149473201","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10939526,0.000841932,0.8835655,0.0005994842,0.00008573091,0.00040358643,0.00055531866,0.001793395,0.0027598427],"genre_scores_gemma":[0.5268424,0.00036061762,0.46824583,0.00038320827,0.00011515725,0.0005908209,0.0016764576,0.00018449592,0.0016009904],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893326,0.00046719433,0.00007310664,0.00027578877,0.00013686414,0.000113764385],"domain_scores_gemma":[0.9916312,0.006891599,0.0004060897,0.0003327827,0.0006006807,0.00013767499],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002509818,0.0011995849,0.0013277277,0.001341084,0.0006994405,0.00091506646,0.0016355414,0.0015430372,0.002047101],"category_scores_gemma":[0.007930142,0.00080393115,0.000985911,0.0011654595,0.0011228187,0.0015283681,0.000707346,0.00223913,0.0004179179],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019019491,0.00018755217,0.0010792409,0.00013387908,0.000035266807,0.000053167307,0.00008582434,0.89984846,0.0006708391,0.005325403,0.0029422883,0.08944784],"study_design_scores_gemma":[0.000037419144,0.000037302383,0.000100655656,0.000009119487,0.000007128987,0.0000073205333,0.000010949804,0.9926835,0.00035061402,0.0065054963,0.00024612297,0.0000044532403],"about_ca_topic_score_codex":0.006552748,"about_ca_topic_score_gemma":0.00919117,"teacher_disagreement_score":0.006552748,"about_ca_system_score_codex":0.0019586326,"about_ca_system_score_gemma":0.0029320174,"threshold_uncertainty_score":0.014210999},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.05517782314487753,"score_gpt":0.3067297556925058,"score_spread":0.2515519325476283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151953639","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004194064,0.0012566178,0.990008,0.00021948286,0.00011942866,0.00022719498,0.0004799875,0.0027604613,0.0007347819],"genre_scores_gemma":[0.024912206,0.0008922489,0.9714082,0.00008709006,0.00011184272,0.00055577,0.0013231467,0.00013815185,0.00057141786],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99528545,0.0011284762,0.0007426538,0.00076596654,0.0017806708,0.00029686195],"domain_scores_gemma":[0.98015,0.013016299,0.0013235909,0.0015650648,0.003760589,0.00018442806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063311206,0.0027101818,0.003150566,0.0074423607,0.002156128,0.0025594938,0.003521581,0.002636136,0.0043886886],"category_scores_gemma":[0.028531963,0.0017480087,0.0024248923,0.010387564,0.00077285303,0.006881258,0.0015517059,0.0026306754,0.005217967],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048198685,0.00026383516,0.0032428857,0.0008821056,0.00037620874,0.00036204892,0.00030725548,0.0569064,0.0044092834,0.017650485,0.01712701,0.8979905],"study_design_scores_gemma":[0.00033407198,0.00037995778,0.0016548272,0.00027508003,0.0002647925,0.001877789,0.00022775008,0.83985066,0.014175682,0.11238606,0.028409906,0.00016345677],"about_ca_topic_score_codex":0.0024232964,"about_ca_topic_score_gemma":0.0021189374,"teacher_disagreement_score":0.0074423607,"about_ca_system_score_codex":0.0010136531,"about_ca_system_score_gemma":0.002183775,"threshold_uncertainty_score":0.03348255},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.010832096937412392,"score_gpt":0.265796040034446,"score_spread":0.25496394309703363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152225808","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043291826,0.0003066156,0.95137584,0.00079283613,0.00004704852,0.00022764994,0.00012009942,0.0023718432,0.0014661882],"genre_scores_gemma":[0.5127568,0.00020674168,0.48243806,0.00080163067,0.00020175597,0.00044976885,0.0008665992,0.0003196863,0.0019589309],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98838764,0.00538301,0.00085900316,0.002462897,0.0023529134,0.0005544581],"domain_scores_gemma":[0.9429019,0.04266129,0.0022576808,0.0073725735,0.0039247484,0.00088168617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00988446,0.0022444671,0.003020145,0.0016130182,0.0010900731,0.002825211,0.004128054,0.0036949306,0.003855173],"category_scores_gemma":[0.04832206,0.00081465655,0.0011626132,0.0017579326,0.0018985512,0.0093127005,0.0043023797,0.0041496847,0.0012971578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013739346,0.0014264222,0.011622085,0.0005643048,0.00025022923,0.00036421407,0.0019987444,0.23474956,0.017689174,0.031095792,0.017088123,0.68177736],"study_design_scores_gemma":[0.00010741219,0.00017356582,0.00051022053,0.000017625225,0.00003922844,0.00011918847,0.00025551044,0.96070707,0.0050593745,0.030153416,0.0028311692,0.000026261509],"about_ca_topic_score_codex":0.0019177173,"about_ca_topic_score_gemma":0.0030617644,"teacher_disagreement_score":0.00988446,"about_ca_system_score_codex":0.0014547055,"about_ca_system_score_gemma":0.0018491343,"threshold_uncertainty_score":0.052274644},"labels":[],"label_agreement":null},{"id":"W2155826795","doi":"10.1109/tkde.2010.205","title":"Static and Dynamic Delegation in the Role Graph Model","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Access Control and Trust","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Shandong University","keywords":"Delegation; Computer science; Static analysis; Role-based access control; Graph; Distributed computing; Session (web analytics); Access control; Context (archaeology); Computer security; Theoretical computer science; Programming language; World Wide Web","score_opus":0.01446956893650409,"score_gpt":0.2885935015401711,"score_spread":0.274123932603667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155826795","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0144929215,0.0002477473,0.9688777,0.0007457108,0.00007780725,0.0000913843,0.00016703384,0.00031197787,0.014987704],"genre_scores_gemma":[0.53939015,0.0009732642,0.44295475,0.00047182667,0.00023683735,0.00047447023,0.00043172255,0.000289502,0.014777491],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955095,0.0020517947,0.00025244305,0.00067234033,0.0010216205,0.0004923048],"domain_scores_gemma":[0.99667513,0.0013828742,0.00031946597,0.0010191011,0.00035722437,0.00024610583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032865377,0.00078502344,0.0005557116,0.0010541702,0.0010551377,0.002654738,0.0018207774,0.0017059532,0.0030205431],"category_scores_gemma":[0.0052928748,0.00056640746,0.001375549,0.0009957848,0.0029673018,0.0076655913,0.0019514628,0.0022774965,0.00094380847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004233883,0.000037155303,0.0002656235,0.00004436081,0.00001325569,0.00019532445,0.00034298052,0.034691814,0.0013421143,0.9509773,0.001069709,0.0109778885],"study_design_scores_gemma":[0.00003530972,0.00005792304,0.0002601209,0.00004556893,0.00004517577,0.00036882982,0.0001984043,0.273978,0.0019869865,0.6960159,0.026952868,0.00005493916],"about_ca_topic_score_codex":0.0069937347,"about_ca_topic_score_gemma":0.0073888614,"teacher_disagreement_score":0.0069937347,"about_ca_system_score_codex":0.0018319661,"about_ca_system_score_gemma":0.0021368272,"threshold_uncertainty_score":0.017381072},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.02750885075641095,"score_gpt":0.28599389310441553,"score_spread":0.25848504234800457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157751754","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06898145,0.00065860385,0.9269359,0.00072231115,0.00004199526,0.00035892354,0.00012841374,0.0006175368,0.0015548114],"genre_scores_gemma":[0.71073914,0.00019960446,0.28717357,0.00038004768,0.00005016589,0.00042779103,0.00026869707,0.00008477883,0.00067623664],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99499243,0.0031121322,0.00031022704,0.0004144892,0.00094447174,0.00022629736],"domain_scores_gemma":[0.9725062,0.02344914,0.0009926545,0.000857797,0.0018129922,0.00038135186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007781953,0.0010928644,0.0011884624,0.001620086,0.0005341926,0.0011893972,0.002172521,0.0017309726,0.0017974423],"category_scores_gemma":[0.03599237,0.00048821978,0.000577639,0.0010254899,0.0010738028,0.0029698857,0.0012277652,0.0014457317,0.00028420426],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052873313,0.0003975281,0.0058492008,0.00020896381,0.00013317047,0.000288524,0.00024833652,0.6964708,0.0023821362,0.05256984,0.0026314238,0.23829134],"study_design_scores_gemma":[0.000054841305,0.00010845197,0.00023033719,0.000016902244,0.000020679816,0.00004571373,0.000019777335,0.9624189,0.0011050066,0.035616316,0.00035231755,0.000010681697],"about_ca_topic_score_codex":0.0014855497,"about_ca_topic_score_gemma":0.0013073002,"teacher_disagreement_score":0.007781953,"about_ca_system_score_codex":0.0013032102,"about_ca_system_score_gemma":0.0012309238,"threshold_uncertainty_score":0.041155398},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.057837470981609185,"score_gpt":0.3104771853336928,"score_spread":0.2526397143520836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160172686","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012745538,0.00030219392,0.976987,0.0021402116,0.00008319476,0.000102515034,0.00007966561,0.00020873196,0.007350964],"genre_scores_gemma":[0.7321249,0.00073980354,0.25849196,0.00048471254,0.0002686614,0.00036561093,0.00021446637,0.00012175489,0.007188144],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.990311,0.0059301923,0.00059417746,0.00096373353,0.0016741956,0.0005266239],"domain_scores_gemma":[0.95346856,0.034676705,0.0031462295,0.0044192267,0.0032696214,0.0010197372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012227935,0.0011083981,0.001833408,0.001710739,0.0019505426,0.005861089,0.0035711962,0.0048805675,0.004600425],"category_scores_gemma":[0.0731471,0.0010128673,0.001607025,0.0015979199,0.003474248,0.011074954,0.0057019778,0.0045637325,0.0008605886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016737437,0.000064731474,0.0012549621,0.00017820802,0.00012724978,0.00056079676,0.0011493998,0.3392533,0.0006730929,0.62307554,0.0028057604,0.030689681],"study_design_scores_gemma":[0.000036958136,0.00003314451,0.0001036149,0.000036746038,0.000036773665,0.00013230536,0.000080428,0.7189458,0.00035016448,0.27762496,0.0025916959,0.000027399186],"about_ca_topic_score_codex":0.0045569614,"about_ca_topic_score_gemma":0.0027119233,"teacher_disagreement_score":0.012227935,"about_ca_system_score_codex":0.0021258076,"about_ca_system_score_gemma":0.0019723498,"threshold_uncertainty_score":0.0646683},"labels":[],"label_agreement":null},{"id":"W2168616308","doi":"10.1109/tkde.2008.34","title":"Automatic Website Summarization by Image Content: A Case Study with Logo and Trademark Images","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Killam Trusts","keywords":"Automatic summarization; Computer science; Trademark; Logo (programming language); Information retrieval; Logos Bible Software; World Wide Web; Web page; Image (mathematics); Trademark infringement; Artificial intelligence; Process (computing); Abstraction","score_opus":0.034974161712979936,"score_gpt":0.2577001686089124,"score_spread":0.2227260068959325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168616308","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9178832,0.00086388004,0.072495826,0.0006287985,0.0000516162,0.00096895685,0.0013730357,0.001724949,0.004009716],"genre_scores_gemma":[0.78158116,0.0005796135,0.20961846,0.00014849138,0.00008503195,0.00021979347,0.0025924738,0.00034028027,0.0048346682],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884087,0.00043964983,0.00009980626,0.00019379123,0.00035888152,0.00006706653],"domain_scores_gemma":[0.99032354,0.0066233138,0.00067346223,0.0007935975,0.0012893231,0.00029672508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001443547,0.0005666213,0.00061723683,0.0031313612,0.00096292427,0.0012464182,0.0011394802,0.0013740087,0.0016725446],"category_scores_gemma":[0.006546338,0.00027296826,0.0005608222,0.002936864,0.0005240938,0.0011439191,0.0005874162,0.0005156256,0.00072032056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014955672,0.0037892773,0.050639544,0.0036644826,0.0002681775,0.024198089,0.011537181,0.028927844,0.09994285,0.0019945032,0.016220924,0.7573217],"study_design_scores_gemma":[0.0005415774,0.0036351539,0.17012504,0.00039534405,0.0006951624,0.025813017,0.019908773,0.46194276,0.22783232,0.005177205,0.083548166,0.00038559065],"about_ca_topic_score_codex":0.004044503,"about_ca_topic_score_gemma":0.010511752,"teacher_disagreement_score":0.004044503,"about_ca_system_score_codex":0.000567614,"about_ca_system_score_gemma":0.0003488674,"threshold_uncertainty_score":0.008041918},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.01997980423624899,"score_gpt":0.24933739576293726,"score_spread":0.22935759152668828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170595610","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021295575,0.00047336187,0.9866919,0.00023380676,0.00021568454,0.0001487855,0.00049039343,0.0014237476,0.008192882],"genre_scores_gemma":[0.047665883,0.0004711386,0.94142044,0.00031002393,0.00012369142,0.00044096264,0.0020828845,0.00029047634,0.007194489],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799395,0.00033453113,0.00021236936,0.0004442981,0.0008521936,0.00016269233],"domain_scores_gemma":[0.9974064,0.00090848,0.00012625795,0.00058060524,0.00090683973,0.00007136902],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017672697,0.00082996837,0.0013905447,0.0020712977,0.0010910596,0.0028503921,0.002671128,0.0019931945,0.014297221],"category_scores_gemma":[0.008092287,0.0005263722,0.0015752444,0.0030631633,0.00071762997,0.0021933175,0.0021397064,0.002620577,0.005243058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002864814,0.00010627415,0.0016073869,0.0004224239,0.00010461915,0.00018891561,0.00024176574,0.13099444,0.004943051,0.089435294,0.0501657,0.7215037],"study_design_scores_gemma":[0.0000851648,0.000075794545,0.00051931,0.000086425796,0.000036911035,0.00034985397,0.000096259675,0.847951,0.0062259585,0.061916426,0.08261566,0.000041101946],"about_ca_topic_score_codex":0.003637834,"about_ca_topic_score_gemma":0.0030746898,"teacher_disagreement_score":0.014297221,"about_ca_system_score_codex":0.0013445767,"about_ca_system_score_gemma":0.0020098218,"threshold_uncertainty_score":0.047828972},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.030657586213925878,"score_gpt":0.28427757784468977,"score_spread":0.2536199916307639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2342411541","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04071235,0.0022255636,0.9452356,0.0018972249,0.00015878731,0.00028924397,0.0007425092,0.0008764867,0.007862237],"genre_scores_gemma":[0.39251798,0.0018456426,0.59865534,0.0008003626,0.0002163891,0.00036708277,0.0016082904,0.0003192657,0.0036696882],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997006,0.0014099869,0.0001538893,0.00072624773,0.0004950973,0.00020874564],"domain_scores_gemma":[0.99531436,0.0028997993,0.00044773656,0.0006876975,0.00040238173,0.00024800183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002932391,0.0011561281,0.0020132966,0.0018903662,0.0017632374,0.0020081038,0.0031167383,0.0026143617,0.005286394],"category_scores_gemma":[0.012452737,0.0009676278,0.0016443526,0.0071870782,0.0013317905,0.004582715,0.0024905861,0.0024713508,0.00095652393],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039012535,0.0006668593,0.003358434,0.00077133114,0.0003151171,0.00034292764,0.0003187773,0.6191391,0.0036940554,0.14965078,0.022072973,0.1992795],"study_design_scores_gemma":[0.000045935896,0.000051236206,0.0003640938,0.000023484728,0.00003324751,0.0001638708,0.00006614447,0.8667449,0.0006214534,0.12731068,0.0045548226,0.000020241356],"about_ca_topic_score_codex":0.0055528153,"about_ca_topic_score_gemma":0.0045634834,"teacher_disagreement_score":0.0055528153,"about_ca_system_score_codex":0.0016824516,"about_ca_system_score_gemma":0.0018313733,"threshold_uncertainty_score":0.017684758},"labels":[],"label_agreement":null},{"id":"W2342671210","doi":"10.1109/tkde.2016.2525993","title":"Clearing Contamination in Large Networks","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Clearing; Graph; Mathematical optimization; Theoretical computer science; Algorithm; Mathematics","score_opus":0.014555985345564236,"score_gpt":0.2634419975948157,"score_spread":0.24888601224925144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2342671210","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09230511,0.0011107444,0.8957752,0.0022855108,0.0000881667,0.00019765577,0.0003977359,0.0010526848,0.006787061],"genre_scores_gemma":[0.85491437,0.0007526126,0.13553654,0.00063554494,0.00011458676,0.00024527864,0.000693289,0.00042159398,0.006686242],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99537355,0.0018213149,0.00018939699,0.0012108154,0.0008440662,0.0005609908],"domain_scores_gemma":[0.97120404,0.021860885,0.002139087,0.002643683,0.0011948758,0.00095737714],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004181106,0.0013960871,0.0021848017,0.0013729425,0.0026124164,0.0040270314,0.003338049,0.0040515913,0.0061689247],"category_scores_gemma":[0.034941938,0.0012501195,0.0011409714,0.0028245097,0.0035730544,0.010472386,0.0044054845,0.00311674,0.0010205305],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035441105,0.00012693225,0.002438787,0.00026404945,0.00011552893,0.00048142724,0.0005246082,0.85631907,0.0024940867,0.09528894,0.006422576,0.035169527],"study_design_scores_gemma":[0.00005134908,0.00004820479,0.0002907971,0.000025516549,0.000027958402,0.00018639512,0.00018626772,0.8373644,0.0018587544,0.15651688,0.0034246892,0.000018761792],"about_ca_topic_score_codex":0.006195356,"about_ca_topic_score_gemma":0.004455193,"teacher_disagreement_score":0.006195356,"about_ca_system_score_codex":0.0027140947,"about_ca_system_score_gemma":0.0017684771,"threshold_uncertainty_score":0.022112072},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.010554535711334448,"score_gpt":0.26786463651132125,"score_spread":0.2573101007999868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2543722153","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022675786,0.00041375952,0.97468084,0.00039301813,0.000019338075,0.00007766149,0.00008599837,0.00018000237,0.0014736922],"genre_scores_gemma":[0.7317803,0.0010916617,0.26218742,0.00027829836,0.00016221059,0.0004902862,0.00038079798,0.00019485294,0.0034342473],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968727,0.0017313947,0.000121041034,0.00066490716,0.000396071,0.00021385387],"domain_scores_gemma":[0.98121476,0.015884487,0.0011955898,0.000877679,0.0004948883,0.00033268298],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063352794,0.001711823,0.0024443993,0.0021549556,0.00083884026,0.0023620338,0.003056147,0.0021126322,0.0018285259],"category_scores_gemma":[0.026481505,0.0013698798,0.0014082654,0.0023329717,0.0031906473,0.005333093,0.0024978314,0.0020427743,0.00040356404],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013774808,0.00007660185,0.0015861527,0.00024243002,0.000102693826,0.00010224772,0.00024727377,0.84755605,0.0016561478,0.11634334,0.0013123191,0.030636942],"study_design_scores_gemma":[0.000013057906,0.000016139498,0.00013977001,0.000010936666,0.00000855644,0.00001846903,0.000013931056,0.9514596,0.0003509022,0.047659867,0.0003001423,0.000008548936],"about_ca_topic_score_codex":0.0031637915,"about_ca_topic_score_gemma":0.002950142,"teacher_disagreement_score":0.0063352794,"about_ca_system_score_codex":0.0027500468,"about_ca_system_score_gemma":0.0011260218,"threshold_uncertainty_score":0.033504546},"labels":[],"label_agreement":null},{"id":"W2610350176","doi":"10.1109/tkde.2017.2699965","title":"Finding Related Forum Posts through Content Similarity over Intention-Based Segmentation","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"European Research Council; Université Paris-Saclay; European Cooperation in Science and Technology","keywords":"Segmentation; Similarity (geometry); Computer science; Set (abstract data type); Point (geometry); Information retrieval; Contrast (vision); Content (measure theory); Artificial intelligence; Image (mathematics); Mathematics","score_opus":0.0766944298027059,"score_gpt":0.3090613877724966,"score_spread":0.23236695796979068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610350176","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3693159,0.0015287882,0.61994696,0.0005222565,0.0001218608,0.00079467247,0.00074172625,0.0020115895,0.005016286],"genre_scores_gemma":[0.74880683,0.0002998133,0.24610525,0.00010437786,0.00033748045,0.00035093,0.0014949508,0.00018952136,0.0023109156],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99762243,0.0006037924,0.00018634587,0.00072712934,0.000625586,0.00023467847],"domain_scores_gemma":[0.9888686,0.006355958,0.0018824242,0.0007892225,0.0015362119,0.0005674574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026743985,0.0011493608,0.0016756409,0.009365087,0.0014417128,0.0022693174,0.0014064172,0.0017829593,0.0019285604],"category_scores_gemma":[0.013481594,0.00041452984,0.0011529729,0.0052694385,0.0011777933,0.0043122163,0.0018415966,0.000996811,0.00089026283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021615038,0.0017923511,0.08143952,0.0012444154,0.00048921286,0.00083407335,0.0033566628,0.062615514,0.040160272,0.020548021,0.00765284,0.7777056],"study_design_scores_gemma":[0.00010475706,0.0011297709,0.034191303,0.000113000955,0.00027763937,0.0008167717,0.0014511484,0.8939607,0.017415049,0.04501634,0.0053866133,0.00013685953],"about_ca_topic_score_codex":0.0028437306,"about_ca_topic_score_gemma":0.004066708,"teacher_disagreement_score":0.009365087,"about_ca_system_score_codex":0.00095613673,"about_ca_system_score_gemma":0.0012449038,"threshold_uncertainty_score":0.014143765},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0619002510906548,"score_gpt":0.3532966062404341,"score_spread":0.2913963551497793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766449686","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08498084,0.0023033444,0.8639768,0.001313059,0.0001314434,0.0005863325,0.035581026,0.0030469224,0.008080285],"genre_scores_gemma":[0.49398276,0.001389818,0.46030876,0.0005222034,0.000089763176,0.00049416383,0.039201368,0.00027108873,0.003740049],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913603,0.00021789798,0.0000458919,0.00034520307,0.00020645358,0.00004863704],"domain_scores_gemma":[0.9973231,0.0010789253,0.00027498446,0.00077689847,0.0004033832,0.00014268263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004316978,0.0007776735,0.00069054373,0.00277406,0.00096582534,0.0008583753,0.0013269762,0.0011643675,0.0033656736],"category_scores_gemma":[0.0049356264,0.0004933047,0.0010334074,0.0055230046,0.0005845435,0.0019083685,0.00093488104,0.000923437,0.0010050065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046242145,0.00061112357,0.059981853,0.002167301,0.0008290329,0.0015534401,0.0018211895,0.34489444,0.017367443,0.12292733,0.0932772,0.3541072],"study_design_scores_gemma":[0.00005973523,0.00014905087,0.018542081,0.00019645691,0.0003389926,0.0014503609,0.00058466685,0.83734465,0.0033858872,0.080342926,0.05749501,0.00011016304],"about_ca_topic_score_codex":0.04347202,"about_ca_topic_score_gemma":0.08334941,"teacher_disagreement_score":0.04347202,"about_ca_system_score_codex":0.0011174759,"about_ca_system_score_gemma":0.0012317108,"threshold_uncertainty_score":0.086438},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Workload; Computer science; Database; Process (computing); Data management; Operating system","score_opus":0.03969699418589224,"score_gpt":0.26058751751532017,"score_spread":0.22089052332942793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766474394","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061777856,0.21509403,0.6730722,0.008962342,0.0012423457,0.002990784,0.0012862465,0.0024692435,0.03310495],"genre_scores_gemma":[0.15920866,0.10554006,0.7208831,0.0020165602,0.0015651401,0.0018347022,0.0026659754,0.0002914667,0.0059943614],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9892837,0.0017074274,0.0023166002,0.0012004015,0.0047661415,0.0007257919],"domain_scores_gemma":[0.9873591,0.0047140685,0.0020777804,0.0012541714,0.0038182752,0.0007766061],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056875357,0.0015424753,0.0016507565,0.010594459,0.0028369818,0.008733058,0.0040428764,0.0036515323,0.0012194761],"category_scores_gemma":[0.011127364,0.001330882,0.0016042335,0.014920927,0.0024923137,0.0129262395,0.0028683941,0.003275684,0.00083594414],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021249606,0.00081983,0.025333075,0.006762943,0.00022056828,0.0007196634,0.005658437,0.017012928,0.009630371,0.19409211,0.02164022,0.71789736],"study_design_scores_gemma":[0.000107277316,0.0010239027,0.025259582,0.00702953,0.00027840296,0.00685819,0.006641834,0.1394917,0.006541251,0.27403763,0.53219956,0.0005311456],"about_ca_topic_score_codex":0.0035250764,"about_ca_topic_score_gemma":0.0025043266,"teacher_disagreement_score":0.010594459,"about_ca_system_score_codex":0.0030706103,"about_ca_system_score_gemma":0.0040902835,"threshold_uncertainty_score":0.030078948},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.038717565892846036,"score_gpt":0.30775679803649514,"score_spread":0.2690392321436491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2784105835","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013088077,0.000100136334,0.9848108,0.00032509957,0.00002741295,0.00021005586,0.00024621145,0.0007317441,0.00046050677],"genre_scores_gemma":[0.24720737,0.00012076213,0.74908745,0.0002619501,0.00006693995,0.00060558633,0.0013366226,0.00011474591,0.0011986129],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957729,0.0012401904,0.00036625462,0.00084571686,0.0014796183,0.00029533272],"domain_scores_gemma":[0.99253243,0.0037334077,0.0005848359,0.0021949068,0.00073103607,0.00022335554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032697795,0.0008524488,0.0012474052,0.0018514505,0.0010733636,0.0013204124,0.002848475,0.0016999511,0.0020636949],"category_scores_gemma":[0.01620085,0.0005010224,0.0013328482,0.002488927,0.0010771787,0.0030176148,0.0034805737,0.0017968742,0.0008521017],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014454485,0.0006717845,0.007160991,0.00034121287,0.00022038555,0.00056239,0.0005608528,0.17140505,0.020632224,0.08366254,0.009716583,0.7036205],"study_design_scores_gemma":[0.00018536509,0.00015729631,0.0004748497,0.000017109176,0.00003319716,0.0004988054,0.00007734701,0.8968024,0.0066210167,0.09195329,0.003154266,0.000024981367],"about_ca_topic_score_codex":0.001127965,"about_ca_topic_score_gemma":0.0018102359,"teacher_disagreement_score":0.0032697795,"about_ca_system_score_codex":0.0011810777,"about_ca_system_score_gemma":0.0026470642,"threshold_uncertainty_score":0.01729244},"labels":[],"label_agreement":null},{"id":"W2792179143","doi":"10.1109/tkde.2018.2810873","title":"Supervised Search Result Diversification via Subtopic Attention","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Chinese Academy of Sciences; National Natural Science Foundation of China; Natural Science Foundation of Beijing Municipality; Microsoft Research","keywords":"Computer science; Pooling; Diversification (marketing strategy); Machine learning; Artificial intelligence; Ranking (information retrieval); Relevance (law); Information retrieval; Data mining","score_opus":0.04992458604131879,"score_gpt":0.2878324295515918,"score_spread":0.237907843510273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792179143","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20749523,0.0027272236,0.7775038,0.0004092733,0.000083254214,0.00024146876,0.00025798345,0.0037171966,0.007564608],"genre_scores_gemma":[0.89178425,0.00038829132,0.102030724,0.0002364096,0.000120751494,0.00011521233,0.0005596431,0.00016255572,0.0046020877],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992861,0.00014914684,0.000042208445,0.00020052165,0.00024072031,0.00008129244],"domain_scores_gemma":[0.9986625,0.00055509584,0.00017472329,0.00025709148,0.0002524851,0.000098015174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009022265,0.00079493155,0.001268835,0.0016313896,0.00037944384,0.00064372766,0.0013279667,0.0008360541,0.0017118442],"category_scores_gemma":[0.003440482,0.00030800607,0.00071020593,0.0012350848,0.00049524434,0.0017351619,0.0013133204,0.0007753071,0.0005762895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006484286,0.0006242339,0.0062299506,0.00031814893,0.00021948163,0.0002729718,0.00034805815,0.121696725,0.04617574,0.01039646,0.010365116,0.80270463],"study_design_scores_gemma":[0.00006876501,0.00023817588,0.0022973584,0.00001763729,0.00008831927,0.00023911081,0.000048751743,0.9710379,0.010230668,0.013351204,0.0023560128,0.000026113103],"about_ca_topic_score_codex":0.002052244,"about_ca_topic_score_gemma":0.0038588464,"teacher_disagreement_score":0.002052244,"about_ca_system_score_codex":0.00062991795,"about_ca_system_score_gemma":0.0008613532,"threshold_uncertainty_score":0.005726695},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.023891853591576025,"score_gpt":0.3001767249798764,"score_spread":0.2762848713883004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796213239","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9902463,0.0018383986,0.0045484966,0.00039772136,0.00007115436,0.00015409084,0.0004177641,0.000108450266,0.0022176486],"genre_scores_gemma":[0.99326974,0.00047140094,0.0038174994,0.00005254969,0.00010153958,0.00005683462,0.0004062215,0.000027767268,0.0017965252],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9939889,0.0021061522,0.0006701814,0.0010711205,0.0017622114,0.00040140518],"domain_scores_gemma":[0.8452938,0.072741136,0.045435354,0.003284122,0.025761569,0.0074839685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074564535,0.0007409006,0.0006353726,0.0041970373,0.0010116296,0.002865233,0.00079646235,0.00133673,0.0018448612],"category_scores_gemma":[0.07583565,0.0004895712,0.00046225314,0.0017946664,0.0004923421,0.0027879225,0.00075299,0.00091705867,0.0013757567],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037300936,0.00026947868,0.9565096,0.00022427748,0.000108244785,0.000330662,0.00082020863,0.0015037627,0.00223484,0.00037621215,0.0027192228,0.034530584],"study_design_scores_gemma":[0.00004114044,0.000642703,0.9422721,0.000095761454,0.00020101629,0.0010690917,0.0013218427,0.044246156,0.004290935,0.0008799171,0.004833684,0.00010562439],"about_ca_topic_score_codex":0.003253844,"about_ca_topic_score_gemma":0.0082807485,"teacher_disagreement_score":0.0074564535,"about_ca_system_score_codex":0.0007658376,"about_ca_system_score_gemma":0.0011529849,"threshold_uncertainty_score":0.039433956},"labels":[],"label_agreement":null},{"id":"W2796436043","doi":"10.1109/tkde.2020.2981311","title":"HyperMinHash: MinHash in LogLog space","year":2020,"lang":"en","type":"preprint","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Cancer Institute; National Human Genome Research Institute; National Institutes of Health","keywords":"Jaccard index; Cardinality (data modeling); Combinatorics; Mathematics; Discrete mathematics; Computer science; Data mining; Statistics","score_opus":0.04477670225587619,"score_gpt":0.28229477497768213,"score_spread":0.23751807272180595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796436043","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019285489,0.0014724972,0.93421113,0.0011292387,0.0005660467,0.00029600784,0.0024075634,0.028196756,0.012435346],"genre_scores_gemma":[0.28337914,0.0011753531,0.6874025,0.0015025787,0.0005160156,0.00074766576,0.004372739,0.0049658995,0.015938066],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978259,0.00035163818,0.00016326841,0.00034985715,0.001120261,0.00018891538],"domain_scores_gemma":[0.99468935,0.0017450373,0.00020127295,0.0025754413,0.00059313496,0.00019587048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014167804,0.0010273125,0.00087629893,0.0010996897,0.0006775057,0.003138729,0.00236129,0.0012223388,0.024936015],"category_scores_gemma":[0.013539694,0.0005730311,0.0006214766,0.0021235128,0.001346093,0.0061688395,0.0033567748,0.002199578,0.008965727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015036041,0.00023244231,0.0015609636,0.000853671,0.000079644415,0.0002959715,0.0005946997,0.048700795,0.021992682,0.16589835,0.07646733,0.68181986],"study_design_scores_gemma":[0.0002831931,0.00034303576,0.0006169669,0.00021155397,0.00004354723,0.0006967098,0.00029313055,0.5961723,0.0496827,0.23958573,0.11195824,0.00011288464],"about_ca_topic_score_codex":0.0013040669,"about_ca_topic_score_gemma":0.0019479017,"teacher_disagreement_score":0.024936015,"about_ca_system_score_codex":0.0012019565,"about_ca_system_score_gemma":0.0019458095,"threshold_uncertainty_score":0.08341932},"labels":[],"label_agreement":null},{"id":"W2797819729","doi":"10.1109/tkde.2018.2828095","title":"Fast Cosine Similarity Search in Binary Space with Angular Multi-Index Hashing","year":2018,"lang":"en","type":"preprint","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hamming distance; Nearest neighbor search; Binary code; Hash function; Hash table; Cosine similarity; Dynamic perfect hashing; Hamming space; Binary number; Computer science; Locality-sensitive hashing; Similarity (geometry); Linear search; Algorithm; Binary search algorithm; Hamming code; Search algorithm; Mathematics; Theoretical computer science; Double hashing; Data mining; Pattern recognition (psychology); Block code; Artificial intelligence; Decoding methods","score_opus":0.04571143733524703,"score_gpt":0.31959227247375244,"score_spread":0.2738808351385054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797819729","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052640036,0.001354405,0.9364515,0.00035683528,0.00017814535,0.00027117124,0.00125041,0.003931237,0.0035661946],"genre_scores_gemma":[0.23926365,0.0005100853,0.75272626,0.00021929125,0.00012661188,0.00035360083,0.0036633515,0.00023956082,0.0028976123],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824655,0.00025197736,0.00020910906,0.00048819938,0.00064844266,0.0001557701],"domain_scores_gemma":[0.9980483,0.00066952856,0.00022150077,0.00061905454,0.0003528316,0.00008873294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011082629,0.0007947744,0.0016100652,0.0017135319,0.00070461346,0.0020641612,0.0021167768,0.0011311404,0.005474028],"category_scores_gemma":[0.007152548,0.00047472573,0.0007870132,0.0042182333,0.000650296,0.0042298078,0.0024873954,0.0010155675,0.0038147822],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012540176,0.0004043803,0.005907569,0.0010473364,0.00015312813,0.00035332725,0.0005506022,0.09674953,0.040572684,0.04065436,0.022428887,0.78992414],"study_design_scores_gemma":[0.00022079486,0.00035175539,0.0016859028,0.00005515456,0.000034973687,0.0006154565,0.000317254,0.9285795,0.01872558,0.039837305,0.00950141,0.000074940624],"about_ca_topic_score_codex":0.0034334084,"about_ca_topic_score_gemma":0.004381925,"teacher_disagreement_score":0.005474028,"about_ca_system_score_codex":0.00075538404,"about_ca_system_score_gemma":0.0021543435,"threshold_uncertainty_score":0.018312454},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.02885223219186742,"score_gpt":0.2747359068435998,"score_spread":0.24588367465173236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807633791","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15149789,0.00029678323,0.84226245,0.00069112016,0.000032007625,0.00029603177,0.00063138775,0.001097796,0.003194551],"genre_scores_gemma":[0.83801925,0.00025048302,0.15802492,0.00014422093,0.00005103223,0.0002377427,0.0007288422,0.00014045667,0.002402951],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99509287,0.0013148164,0.00051182864,0.00059853046,0.0017483186,0.0007336594],"domain_scores_gemma":[0.99314356,0.0023869264,0.0009051582,0.0024539628,0.0009103302,0.00020015417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030287115,0.0006326549,0.001178503,0.00064045034,0.0010711699,0.0023985158,0.0013030643,0.0009972113,0.0018948412],"category_scores_gemma":[0.0072984686,0.00035511583,0.00081333093,0.0012575147,0.0012546333,0.005943774,0.0032840224,0.0011924254,0.0007991684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036762808,0.0005608113,0.0056375824,0.0005793499,0.00031024875,0.0012722018,0.0028565663,0.3116879,0.18238978,0.25950667,0.013616292,0.21790637],"study_design_scores_gemma":[0.00021702414,0.00040228036,0.00097249186,0.000030734427,0.00004472583,0.00051830645,0.00080550084,0.82289934,0.06958849,0.09675914,0.0077071134,0.00005481993],"about_ca_topic_score_codex":0.0012704143,"about_ca_topic_score_gemma":0.0013378544,"teacher_disagreement_score":0.0030287115,"about_ca_system_score_codex":0.0011341599,"about_ca_system_score_gemma":0.0016477352,"threshold_uncertainty_score":0.016017497},"labels":[],"label_agreement":null},{"id":"W2820145021","doi":"10.1109/tkde.2018.2854797","title":"Introducing Cuts Into a Top-Down Process for Checking Tree Inclusion","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"","keywords":"Tree (set theory); Matching (statistics); Bounded function; Computer science; Set (abstract data type); Combinatorics; Order (exchange); Space (punctuation); Theoretical computer science; Algorithm; Discrete mathematics; Mathematics; Programming language; Statistics","score_opus":0.021276819399349816,"score_gpt":0.2953921537667026,"score_spread":0.27411533436735275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2820145021","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0095673585,0.00018610424,0.98394763,0.00023045462,0.00008179942,0.00041700125,0.0004556422,0.004006475,0.0011074172],"genre_scores_gemma":[0.06183376,0.00011943536,0.9330922,0.00023715598,0.00006546035,0.00037277828,0.0017796998,0.0007977198,0.0017017795],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9871793,0.0024551095,0.0013450196,0.0031959892,0.004573306,0.0012514121],"domain_scores_gemma":[0.96380687,0.023796085,0.0021403602,0.005012632,0.004285565,0.000958397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065602115,0.0022606624,0.0025318444,0.004333053,0.0020827884,0.005155134,0.004565752,0.0026459566,0.007747043],"category_scores_gemma":[0.034004014,0.0020616367,0.0043079266,0.00348284,0.004044601,0.009410451,0.0075546918,0.0053543444,0.0022334568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025176415,0.00085822225,0.0106067415,0.0019608226,0.0005257136,0.0022886952,0.0018671451,0.15390594,0.056102354,0.15684466,0.013463741,0.5990584],"study_design_scores_gemma":[0.00022747277,0.00051991164,0.0016631873,0.00033528247,0.00026805594,0.0005056067,0.0004169965,0.6764312,0.038050193,0.26166385,0.01974139,0.0001768519],"about_ca_topic_score_codex":0.009084604,"about_ca_topic_score_gemma":0.00903638,"teacher_disagreement_score":0.009084604,"about_ca_system_score_codex":0.0018145656,"about_ca_system_score_gemma":0.003687441,"threshold_uncertainty_score":0.034694076},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.1370625278578638,"score_gpt":0.37971452956261115,"score_spread":0.24265200170474735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894983428","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053670228,0.0011564286,0.93291837,0.0013077316,0.00016936584,0.00040641078,0.00043109464,0.005563008,0.004377346],"genre_scores_gemma":[0.60878927,0.00066187157,0.38399288,0.0007536131,0.00011605849,0.0003894629,0.0005912464,0.00026634012,0.0044392203],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.98273164,0.0041718516,0.0014913304,0.0015650995,0.008570208,0.0014699552],"domain_scores_gemma":[0.97553205,0.009919424,0.0029100336,0.008930675,0.002313276,0.00039457832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058503766,0.0011087719,0.0015724772,0.002319164,0.0019806148,0.0036092966,0.0020599675,0.0024197786,0.002685955],"category_scores_gemma":[0.020873755,0.00075357145,0.0014360716,0.0032750256,0.00231772,0.009522171,0.0042148833,0.0031712595,0.0018672941],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030544922,0.0007620446,0.0080675045,0.00074311305,0.0005532136,0.0010433979,0.0015084903,0.090854764,0.121162124,0.1693958,0.016214095,0.58664095],"study_design_scores_gemma":[0.00028435787,0.00062128337,0.0013921655,0.00021581218,0.0001726644,0.002172864,0.00038320458,0.6150941,0.20786297,0.14529003,0.026274124,0.00023637229],"about_ca_topic_score_codex":0.0012071242,"about_ca_topic_score_gemma":0.0008897713,"teacher_disagreement_score":0.0058503766,"about_ca_system_score_codex":0.003027432,"about_ca_system_score_gemma":0.0039812033,"threshold_uncertainty_score":0.030940115},"labels":[],"label_agreement":null},{"id":"W2900691829","doi":"10.1109/tkde.2019.2893175","title":"Similarity Join and Similarity Self-Join Size Estimation in a Streaming Environment","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Similarity (geometry); Join (topology); Nearest neighbor search; Sublinear function; Range (aeronautics); Unary operation; Range query (database)","score_opus":0.0592414764365441,"score_gpt":0.3250866367617011,"score_spread":0.265845160325157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900691829","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047567494,0.0004829929,0.9491134,0.00028032536,0.000044498636,0.0001116269,0.00023746361,0.0013058401,0.0008562581],"genre_scores_gemma":[0.43471354,0.00028601004,0.56121,0.00013822303,0.0001887246,0.0002016174,0.0009646149,0.00021675571,0.002080584],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942122,0.0010398199,0.0004404968,0.001688699,0.0022493945,0.00036928325],"domain_scores_gemma":[0.9821284,0.009946557,0.002174752,0.003043858,0.002110787,0.0005956065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041529136,0.0009851683,0.0020901682,0.0017388882,0.0010789077,0.0022823177,0.0033865694,0.0020527402,0.0019662366],"category_scores_gemma":[0.019717285,0.0007387457,0.0009365455,0.0026294535,0.0012427068,0.0055075292,0.0024820983,0.0013732433,0.00075404235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014065789,0.00056704896,0.017652959,0.0005180104,0.00023324588,0.00046192223,0.0008489854,0.5072699,0.03632749,0.03151319,0.0075609875,0.39563966],"study_design_scores_gemma":[0.00002279194,0.00010995819,0.0012937561,0.000008085674,0.000016264374,0.00024692932,0.00009774821,0.9790693,0.00925255,0.008690711,0.0011734748,0.000018417684],"about_ca_topic_score_codex":0.0028873314,"about_ca_topic_score_gemma":0.0023160283,"teacher_disagreement_score":0.0041529136,"about_ca_system_score_codex":0.0011724517,"about_ca_system_score_gemma":0.0015433817,"threshold_uncertainty_score":0.02196294},"labels":[],"label_agreement":null},{"id":"W2902521181","doi":"10.1109/tkde.2019.2923914","title":"Skyline Diagram: Efficient Space Partitioning for Skyline Queries","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Science Foundation","keywords":"Skyline; Computer science; Voronoi diagram; Set (abstract data type); Scalability; Data mining; Space (punctuation); Theoretical computer science; Database; Mathematics","score_opus":0.0196882249210968,"score_gpt":0.2580137143152098,"score_spread":0.23832548939411302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902521181","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010578696,0.0008273261,0.9790178,0.00020135472,0.00007868308,0.0002844175,0.0020054658,0.005122343,0.0018839473],"genre_scores_gemma":[0.13231614,0.00067619217,0.85554034,0.00011746941,0.00006353264,0.0004406252,0.008220297,0.00068936124,0.0019361272],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99809355,0.0004061127,0.00016880156,0.0004040748,0.0007634034,0.00016401036],"domain_scores_gemma":[0.99759704,0.0007369468,0.00024837372,0.00066723727,0.00054926774,0.00020101145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089049904,0.0012522646,0.0018242829,0.0031193157,0.0013818851,0.0025430722,0.0023250242,0.0013678767,0.0051011033],"category_scores_gemma":[0.005695955,0.0005970815,0.0011902744,0.006293241,0.00060636573,0.005603361,0.0035802976,0.0012762789,0.0025469614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00088466564,0.00034813082,0.005861663,0.001050288,0.00018003145,0.00037519613,0.0009959302,0.14627668,0.018915761,0.05945334,0.07061195,0.69504637],"study_design_scores_gemma":[0.00015577915,0.00015250583,0.000685443,0.00005461139,0.000028569726,0.0004319633,0.00037804784,0.9128619,0.009599573,0.035939872,0.03965133,0.000060422266],"about_ca_topic_score_codex":0.0050651236,"about_ca_topic_score_gemma":0.0085495915,"teacher_disagreement_score":0.0051011033,"about_ca_system_score_codex":0.0010721668,"about_ca_system_score_gemma":0.0020247668,"threshold_uncertainty_score":0.017064929},"labels":[],"label_agreement":null},{"id":"W2972941956","doi":"10.1109/tkde.2019.2940019","title":"Bayesian Networks for Data Integration in the Absence of Foreign Keys","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Centres of Excellence","keywords":"Computer science; Relational database; Probabilistic logic; Inference; Data integration; Bayesian network; Data mining; Cardinality (data modeling); Relation (database); Population; Theoretical computer science; Data science; Information retrieval; Machine learning; Artificial intelligence","score_opus":0.12352446206391332,"score_gpt":0.36871568932336674,"score_spread":0.24519122725945341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972941956","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026202076,0.00024813268,0.9954757,0.00051569997,0.00001590534,0.000043292748,0.00016813018,0.00027580038,0.0006369895],"genre_scores_gemma":[0.19688036,0.00081200845,0.7967286,0.00083366776,0.0002430873,0.000513001,0.0016581438,0.00025981927,0.0020713212],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9794922,0.009880295,0.0012482129,0.005177793,0.0036096335,0.00059183873],"domain_scores_gemma":[0.94509614,0.04319925,0.0033975726,0.005053985,0.0026549296,0.0005981139],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024196872,0.0015272836,0.0026133384,0.00453459,0.0016934904,0.0053636315,0.00417495,0.0026783426,0.0028336355],"category_scores_gemma":[0.08909432,0.002722905,0.0034119114,0.005167773,0.0035126065,0.01280874,0.0065338956,0.006499369,0.0008003059],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001702395,0.00009354457,0.0042316415,0.000265082,0.00048904127,0.00037103152,0.00066686206,0.6137443,0.0007190916,0.29602185,0.0026053747,0.08062199],"study_design_scores_gemma":[0.000014607658,0.000011503953,0.00036021095,0.000033380395,0.000045735058,0.000047610847,0.00003249727,0.74110144,0.0002849596,0.25612217,0.0019264548,0.000019446023],"about_ca_topic_score_codex":0.024927998,"about_ca_topic_score_gemma":0.02193068,"teacher_disagreement_score":0.024927998,"about_ca_system_score_codex":0.005082397,"about_ca_system_score_gemma":0.0037701176,"threshold_uncertainty_score":0.12796688},"labels":[],"label_agreement":null},{"id":"W2990448760","doi":"10.1109/tkde.2019.2956520","title":"Self-Healing Event Logs","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Business Process Modeling and Analysis","field":"Business, Management and Accounting","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China; Deutsche Forschungsgemeinschaft","keywords":"Computer science; Event (particle physics); Process mining; Complex event processing; Process (computing); Data mining; Business process; Rendering (computer graphics); Business process discovery; Event tree analysis; Business process management; Data science; Artificial intelligence; Business process modeling; Work in process; Reliability engineering","score_opus":0.018099234945841133,"score_gpt":0.23949345707916098,"score_spread":0.22139422213331983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990448760","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05069474,0.00036482935,0.907733,0.0005098246,0.000212134,0.00077484985,0.0008832293,0.03608927,0.0027381242],"genre_scores_gemma":[0.5545669,0.0003845463,0.43314502,0.00046250186,0.00012175811,0.0005920916,0.0040352773,0.001697715,0.004994271],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99170625,0.0015421417,0.0009910839,0.0012498694,0.00414969,0.0003610312],"domain_scores_gemma":[0.94907033,0.013163547,0.004573587,0.02636086,0.0059711775,0.00086045737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0067363027,0.001576898,0.0011184515,0.002648932,0.0010187168,0.0029914149,0.0048778034,0.0017859915,0.002038917],"category_scores_gemma":[0.03794733,0.0009524857,0.0008476134,0.0015047844,0.0013073493,0.0057212343,0.0034777895,0.0024990637,0.0013592035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018938932,0.001649024,0.019136589,0.0009140827,0.00026664985,0.0020542673,0.0031908865,0.118293524,0.05490447,0.028613469,0.02090545,0.7481777],"study_design_scores_gemma":[0.00013871751,0.00036928768,0.0031120507,0.0001906362,0.00013002729,0.0011293169,0.00074287603,0.85233414,0.06847468,0.03489905,0.038351823,0.00012736696],"about_ca_topic_score_codex":0.0016898087,"about_ca_topic_score_gemma":0.001381047,"teacher_disagreement_score":0.0067363027,"about_ca_system_score_codex":0.00069828756,"about_ca_system_score_gemma":0.0018848116,"threshold_uncertainty_score":0.035625458},"labels":[],"label_agreement":null},{"id":"W2994742394","doi":"10.1109/tkde.2019.2960347","title":"Group-Based Skyline for Pareto Optimal Groups","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Air Force Office of Scientific Research; National Science Foundation","keywords":"Skyline; Computer science; Pareto principle; Dimension (graph theory); Heuristic; Group (periodic table); Point (geometry); Pareto optimal; Computation; Set (abstract data type); Theoretical computer science; Data mining; Combinatorics; Artificial intelligence; Mathematics; Algorithm; Mathematical optimization","score_opus":0.02137811809518209,"score_gpt":0.2535165900882512,"score_spread":0.23213847199306914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994742394","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016906489,0.00015604931,0.97915226,0.00011394274,0.000018274144,0.00014276418,0.00043377362,0.00097493257,0.0021014395],"genre_scores_gemma":[0.16489592,0.00022043342,0.8291133,0.0000895119,0.00004071092,0.0003256565,0.0025914668,0.00032659233,0.0023964613],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99857235,0.00032820983,0.00010056595,0.00034980045,0.0004855688,0.00016346364],"domain_scores_gemma":[0.99747133,0.0008940536,0.0003484841,0.00040415404,0.00072835165,0.00015363535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012920665,0.0013098345,0.0015032807,0.0032387653,0.0013255033,0.0024796075,0.0016773256,0.0012294059,0.007863597],"category_scores_gemma":[0.0060030664,0.0005334052,0.001736283,0.0029930368,0.00096998893,0.0035263044,0.0023280848,0.0014562135,0.0019475151],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004975038,0.00024276986,0.0054350006,0.00055548904,0.00016050792,0.00027366128,0.0009968724,0.5458623,0.008062344,0.14220314,0.013978197,0.28173223],"study_design_scores_gemma":[0.00003658367,0.00007488485,0.00038817993,0.000034669112,0.000016318238,0.00007071979,0.00013675074,0.9310396,0.0025497298,0.05995379,0.0056797676,0.000019006744],"about_ca_topic_score_codex":0.0058084745,"about_ca_topic_score_gemma":0.005533569,"teacher_disagreement_score":0.007863597,"about_ca_system_score_codex":0.0016622753,"about_ca_system_score_gemma":0.0015605638,"threshold_uncertainty_score":0.02630639},"labels":[],"label_agreement":null},{"id":"W3002803388","doi":"10.1109/tkde.2020.2969419","title":"Paywall Policy Learning in Digital News Media","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University; York University; Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Reinforcement learning; Newspaper; Function (biology); Thompson sampling; Artificial intelligence; Baseline (sea); Reading (process); Machine learning","score_opus":0.035056090995382753,"score_gpt":0.2633731265782509,"score_spread":0.22831703558286814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3002803388","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24372548,0.0030869546,0.7367513,0.0038700001,0.00033635698,0.0003962305,0.0005968513,0.0024928786,0.008743807],"genre_scores_gemma":[0.9426272,0.00044537717,0.05212753,0.0004347363,0.00012628705,0.00016417599,0.00039393277,0.00008102042,0.003599766],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99809915,0.00082299445,0.00011205309,0.00044528753,0.0002795831,0.00024089756],"domain_scores_gemma":[0.98308957,0.014566448,0.00073728047,0.00045630374,0.00070600986,0.000444438],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051021874,0.0008689206,0.0021809537,0.00118472,0.0006922322,0.0019321283,0.002060657,0.0024831328,0.0038113734],"category_scores_gemma":[0.017558573,0.00086375716,0.00054113223,0.0010831594,0.0011807408,0.0035755052,0.0010506816,0.0028326982,0.0006404464],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055125385,0.00050961337,0.0049596527,0.0002010388,0.00008268086,0.00013791812,0.00020064002,0.8541242,0.00057105074,0.015164038,0.0038052392,0.119692676],"study_design_scores_gemma":[0.000031626045,0.00003608021,0.00025108218,0.00001134496,0.00000990029,0.000008709041,0.000023424187,0.9930784,0.00023143,0.005900236,0.00041065217,0.000007098235],"about_ca_topic_score_codex":0.0099685425,"about_ca_topic_score_gemma":0.008444021,"teacher_disagreement_score":0.0099685425,"about_ca_system_score_codex":0.002330425,"about_ca_system_score_gemma":0.0020352558,"threshold_uncertainty_score":0.026983261},"labels":[],"label_agreement":null},{"id":"W3009808474","doi":"10.1109/tkde.2020.2978469","title":"A Framework for Anomaly Detection in Time-Driven and Event-Driven Processes using Kernel Traces","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Anomaly detection; Abstraction; Model checking; Kernel (algebra); Exploit; Probabilistic logic; Process (computing); Theoretical computer science; Distributed computing; Data mining; Programming language; Artificial intelligence","score_opus":0.033683838327205805,"score_gpt":0.2828885598886682,"score_spread":0.24920472156146237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009808474","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025571769,0.00005318941,0.9925007,0.000053247775,0.000010909247,0.000056853256,0.0001305308,0.004453667,0.0001837694],"genre_scores_gemma":[0.23457544,0.00018241564,0.761763,0.00009307819,0.000040749426,0.0002869229,0.0010991684,0.00074029434,0.0012189071],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99679726,0.0006282019,0.00028556984,0.00082116685,0.0011850495,0.00028276985],"domain_scores_gemma":[0.9931503,0.0028203651,0.0010065796,0.0016490627,0.0011021019,0.00027161508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003878433,0.0015948958,0.0011619244,0.003295458,0.0007252828,0.0029851017,0.0038049277,0.0019369628,0.0017041828],"category_scores_gemma":[0.013731538,0.0010972301,0.002810125,0.0015643523,0.0016261131,0.003942788,0.003108859,0.0029768732,0.0008439075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002800805,0.00042896558,0.010536146,0.000408475,0.0003444885,0.00073163846,0.0006500281,0.69807816,0.008412607,0.12747629,0.0029126904,0.14974052],"study_design_scores_gemma":[0.000009074261,0.000032811102,0.00023754983,0.000021277965,0.000020314363,0.000059375056,0.000023176666,0.9672413,0.0022034268,0.028386975,0.0017478724,0.000016721824],"about_ca_topic_score_codex":0.013087688,"about_ca_topic_score_gemma":0.012002729,"teacher_disagreement_score":0.013087688,"about_ca_system_score_codex":0.0017373196,"about_ca_system_score_gemma":0.0031349966,"threshold_uncertainty_score":0.02602303},"labels":[],"label_agreement":null},{"id":"W3030885106","doi":"10.1109/tkde.2020.2997938","title":"SCHAIN-IRAM: An Efficient and Effective Semi-Supervised Clustering Algorithm for Attributed Heterogeneous Information Networks","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Cluster analysis; Computer science; Set (abstract data type); Algorithm; Theoretical computer science; Artificial intelligence; Data mining; Information retrieval; Programming language","score_opus":0.019994299086997888,"score_gpt":0.25005122190912826,"score_spread":0.23005692282213036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3030885106","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028873992,0.000191822,0.99424803,0.00016704881,0.000039547278,0.0001394021,0.00013282434,0.0016549478,0.0005388787],"genre_scores_gemma":[0.053496603,0.00017861502,0.94133043,0.00027526222,0.00008088389,0.00039808004,0.0011703426,0.00040664073,0.0026631323],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99623185,0.0014122565,0.00023895141,0.0011224968,0.0007659217,0.00022859668],"domain_scores_gemma":[0.99631554,0.0014914923,0.0003533252,0.0007091831,0.00096258405,0.00016782041],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054349457,0.0025506602,0.0031141972,0.0051279794,0.0026683041,0.00246855,0.0071666557,0.00399046,0.002673245],"category_scores_gemma":[0.011299804,0.001576167,0.002924793,0.004204264,0.0018265009,0.004132398,0.0034507825,0.0037558957,0.0027528796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029386763,0.00023848061,0.0015556675,0.00031628067,0.00043778986,0.0001709206,0.0004581018,0.4910497,0.0036166867,0.021437451,0.016528767,0.46389627],"study_design_scores_gemma":[0.000017555914,0.000019364878,0.00009559173,0.000010962097,0.000015057725,0.00002759008,0.000033309236,0.9873504,0.0009337806,0.010185765,0.0012972788,0.000013406586],"about_ca_topic_score_codex":0.01407791,"about_ca_topic_score_gemma":0.02209714,"teacher_disagreement_score":0.01407791,"about_ca_system_score_codex":0.0027670588,"about_ca_system_score_gemma":0.0039293035,"threshold_uncertainty_score":0.028743088},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.01656466914588841,"score_gpt":0.27181164893949267,"score_spread":0.2552469797936043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128735821","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015121608,0.00007069647,0.99800295,0.000047719393,0.000006530469,0.000016278125,0.000023105144,0.000114813,0.00020574349],"genre_scores_gemma":[0.50200546,0.00062931987,0.49133942,0.0002465135,0.000119615936,0.0006138463,0.0006957216,0.00030899188,0.0040410846],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992092,0.00027343247,0.00004800809,0.00019045784,0.00019775266,0.00008120042],"domain_scores_gemma":[0.9975757,0.0019029987,0.00013329292,0.00010940645,0.00023247607,0.000046142537],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002615644,0.0011666785,0.0013636968,0.0012885475,0.0005192772,0.0011149372,0.002161351,0.0014714776,0.002701658],"category_scores_gemma":[0.0073932065,0.0010135209,0.0016637769,0.0012640601,0.0011884437,0.0018850619,0.0021789426,0.0026932608,0.0005656411],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044951496,0.000047352984,0.00046428485,0.00007921138,0.000064695836,0.000057007037,0.00007015337,0.8954777,0.0014931489,0.020915506,0.0008803271,0.080405615],"study_design_scores_gemma":[0.0000019739743,0.000004290163,0.000027825838,0.0000022196489,0.0000020668972,0.000003697505,0.0000015991069,0.9947082,0.0001448475,0.0049826102,0.000117879164,0.0000027737067],"about_ca_topic_score_codex":0.008378936,"about_ca_topic_score_gemma":0.0064061335,"teacher_disagreement_score":0.008378936,"about_ca_system_score_codex":0.0013638851,"about_ca_system_score_gemma":0.0015514216,"threshold_uncertainty_score":0.016660333},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04649403019805645,"score_gpt":0.3242526013051148,"score_spread":0.27775857110705837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163325638","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060515415,0.004587523,0.9245968,0.0006269384,0.00015791689,0.00019055481,0.0022516563,0.0030224917,0.0040506567],"genre_scores_gemma":[0.69006294,0.0029049516,0.28775504,0.0004989982,0.00025157144,0.0002916246,0.0075453017,0.00023846238,0.010451135],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946076,0.00015521872,0.000032799675,0.00020269703,0.000112669186,0.00003590137],"domain_scores_gemma":[0.9985708,0.0005998067,0.00021723122,0.00026468156,0.00030024748,0.000047177233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000664695,0.0008747086,0.0008660458,0.0018063388,0.00029842698,0.00071071443,0.0010856807,0.00095353177,0.001994242],"category_scores_gemma":[0.004877248,0.00041301915,0.00091692543,0.0021117015,0.0002813181,0.0020398109,0.0005098816,0.001190876,0.0011935567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036868555,0.00027700575,0.0071812524,0.00063617877,0.00047685846,0.00019282944,0.00024813565,0.25217885,0.011223186,0.019235961,0.02237755,0.68560344],"study_design_scores_gemma":[0.000011961567,0.000065611304,0.0013814415,0.000021246498,0.000068544265,0.000063221974,0.00001955116,0.9811101,0.001214986,0.012651857,0.0033723696,0.00001916445],"about_ca_topic_score_codex":0.013653561,"about_ca_topic_score_gemma":0.033067614,"teacher_disagreement_score":0.013653561,"about_ca_system_score_codex":0.0008441636,"about_ca_system_score_gemma":0.0006838197,"threshold_uncertainty_score":0.027148128},"labels":[],"label_agreement":null},{"id":"W3163458230","doi":"10.1109/tkde.2021.3078099","title":"A Generalized Framework for Preserving Both Privacy and Utility in Data Outsourcing","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Division of Computer and Network Systems; National Institute of General Medical Sciences; National Institutes of Health","keywords":"Outsourcing; Computer science; Information privacy; Computer security; Data modeling; Data mining; Database; Business","score_opus":0.07632184727430395,"score_gpt":0.3213946121611277,"score_spread":0.24507276488682372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163458230","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009826118,0.0005917876,0.9864738,0.0006962172,0.00004208123,0.00017286456,0.00022046568,0.0003146463,0.0016620577],"genre_scores_gemma":[0.53130126,0.0016442195,0.4615169,0.0005416724,0.00025883625,0.00046435648,0.00064530165,0.00016550368,0.0034620038],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98789656,0.0043722447,0.0010176932,0.0017306124,0.0039826636,0.0010002637],"domain_scores_gemma":[0.9851746,0.0025097867,0.00085938437,0.009750902,0.0012655917,0.0004397168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008592685,0.0010475398,0.0016376956,0.0013637772,0.0015736393,0.0041990727,0.0032989932,0.001578099,0.0021700365],"category_scores_gemma":[0.013959445,0.0007782102,0.0025190506,0.0037335625,0.0038483979,0.011862457,0.008638157,0.0046732244,0.0007496146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004786267,0.00023791794,0.003103189,0.00046193984,0.00023408624,0.000930008,0.0015253723,0.10725204,0.014307904,0.6749903,0.006693504,0.18978515],"study_design_scores_gemma":[0.00012822845,0.00034667444,0.0013043452,0.00013754124,0.00017866863,0.0019624678,0.0006105099,0.47689912,0.018251337,0.47268325,0.027360491,0.00013738865],"about_ca_topic_score_codex":0.0023184393,"about_ca_topic_score_gemma":0.0016875805,"teacher_disagreement_score":0.008592685,"about_ca_system_score_codex":0.001928743,"about_ca_system_score_gemma":0.0037065945,"threshold_uncertainty_score":0.045443},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.058018093014621526,"score_gpt":0.298694577054953,"score_spread":0.24067648404033148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167049326","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017286262,0.0004280815,0.9790071,0.00015808622,0.00010921768,0.000045153545,0.00045769513,0.0019909497,0.0005173338],"genre_scores_gemma":[0.5257683,0.0006880765,0.46304035,0.00030185864,0.00010276895,0.00019312707,0.004976867,0.00027984774,0.0046486906],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992619,0.00010584466,0.000056429002,0.00016860427,0.00032798824,0.00007926204],"domain_scores_gemma":[0.9990994,0.0002514796,0.00011766563,0.00018917957,0.00028151218,0.00006071829],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008499808,0.0008297375,0.0011373975,0.0013701238,0.00026051956,0.000999077,0.0015585226,0.00071474223,0.001310738],"category_scores_gemma":[0.002765095,0.00030049487,0.0008239795,0.0012515027,0.000541766,0.0013947138,0.0013812154,0.0016699368,0.00069775473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026246297,0.0001732153,0.005045607,0.0001504516,0.00013621237,0.00013495401,0.00006691235,0.17838292,0.013812472,0.009024957,0.013913703,0.77889615],"study_design_scores_gemma":[0.000007795094,0.000031388503,0.00042361228,0.0000063844273,0.0000058941546,0.00005654841,0.0000138405485,0.98922694,0.0050237793,0.003598226,0.0015936141,0.00001195051],"about_ca_topic_score_codex":0.003871246,"about_ca_topic_score_gemma":0.003907304,"teacher_disagreement_score":0.003871246,"about_ca_system_score_codex":0.0007342415,"about_ca_system_score_gemma":0.0011324806,"threshold_uncertainty_score":0.0076974034},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.019042807564391837,"score_gpt":0.25704086656540814,"score_spread":0.2379980590010163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173856251","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024473228,0.0004601093,0.9706002,0.00018068409,0.00006336943,0.00007065657,0.00020097589,0.0027250228,0.0012258762],"genre_scores_gemma":[0.5919028,0.0005893334,0.40001303,0.0005063817,0.00011763826,0.00017446584,0.00172288,0.00040128228,0.004572208],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994746,0.00008988207,0.000023752595,0.00022481313,0.00010939195,0.00007764897],"domain_scores_gemma":[0.99945754,0.00012456372,0.00008199184,0.00018872005,0.00009560729,0.000051598992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080349576,0.0019622403,0.0014201589,0.0011987117,0.0004647678,0.000834914,0.0024502187,0.0012015977,0.0023808992],"category_scores_gemma":[0.0021095593,0.000510866,0.0015948708,0.0014841555,0.0008658304,0.0035017477,0.0020055377,0.001548621,0.0007173188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002470582,0.00025042618,0.0016875364,0.0002704109,0.0002936201,0.00022890896,0.00017050293,0.36891568,0.025855552,0.021681773,0.010687491,0.56971097],"study_design_scores_gemma":[0.000011239422,0.00007947481,0.0002977316,0.000007383136,0.000033343036,0.000045091143,0.000019343752,0.97841334,0.005332912,0.014737939,0.0010105078,0.000011787253],"about_ca_topic_score_codex":0.006221428,"about_ca_topic_score_gemma":0.010956993,"teacher_disagreement_score":0.006221428,"about_ca_system_score_codex":0.0010785973,"about_ca_system_score_gemma":0.0009897688,"threshold_uncertainty_score":0.012370408},"labels":[],"label_agreement":null},{"id":"W3185277158","doi":"10.1109/tkde.2021.3100353","title":"On the Benefits of Two Dimensional Metric Learning","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Western University; Université Laval; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Boosting (machine learning); Computer science; Metric (unit); Dimension (graph theory); Benchmark (surveying); Generalization; Intrinsic dimension; Algorithm; Rank (graph theory); Data structure; Artificial intelligence; Feature learning; External Data Representation; Learning to rank; Machine learning; Curse of dimensionality; Mathematics; Ranking (information retrieval)","score_opus":0.029957211545899712,"score_gpt":0.25831982516662566,"score_spread":0.22836261362072596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185277158","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01645768,0.002732859,0.97447145,0.0019622813,0.000104411985,0.00005935207,0.000086446074,0.00035996843,0.0037656003],"genre_scores_gemma":[0.46306038,0.002833615,0.527212,0.001729937,0.00073558296,0.000279028,0.00043516228,0.00030006503,0.0034140896],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9911107,0.0049067806,0.0003232078,0.0010159855,0.0023716998,0.0002715398],"domain_scores_gemma":[0.95351386,0.033478543,0.002211625,0.0064626904,0.0034189406,0.00091429864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010482288,0.0017451182,0.0017655384,0.0018117264,0.0010515723,0.0030470106,0.0019981272,0.0025048675,0.0021841521],"category_scores_gemma":[0.052454256,0.00074782164,0.00094132184,0.0024636528,0.004129481,0.007815516,0.0057390584,0.0048199864,0.0011618093],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036223803,0.00025410496,0.004140109,0.00047001106,0.00015157985,0.0002575727,0.00041582953,0.2809484,0.005147925,0.42781904,0.0060746567,0.27395853],"study_design_scores_gemma":[0.000025636142,0.00018939257,0.00063937006,0.000047528152,0.000013857466,0.00019788956,0.000049047994,0.7693379,0.0021323639,0.22302051,0.0043064626,0.000040066257],"about_ca_topic_score_codex":0.0011667007,"about_ca_topic_score_gemma":0.00096721447,"teacher_disagreement_score":0.010482288,"about_ca_system_score_codex":0.0016014101,"about_ca_system_score_gemma":0.0012231027,"threshold_uncertainty_score":0.055436254},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.05141376820259933,"score_gpt":0.27064618378567723,"score_spread":0.2192324155830779,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185513611","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055313404,0.00015878509,0.99244434,0.00017812857,0.00003301086,0.00003272153,0.00011286694,0.0007050357,0.0008036736],"genre_scores_gemma":[0.38894203,0.0006893813,0.5988596,0.0004419587,0.00013434408,0.00023075301,0.0009906252,0.00089167705,0.008819647],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99834406,0.0005924914,0.00007154192,0.00045814892,0.0004103802,0.00012343172],"domain_scores_gemma":[0.9956416,0.0020422905,0.00028784407,0.0012143904,0.00062845147,0.00018539382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024348046,0.0011326715,0.0011702992,0.0011844153,0.0006724589,0.0016363575,0.0035684044,0.0019169434,0.0024868953],"category_scores_gemma":[0.008733813,0.00077472883,0.0012298996,0.0012885001,0.001603412,0.0036678065,0.0027195702,0.0030519047,0.0013712902],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009675703,0.00007987524,0.00083645975,0.00013060114,0.00007806214,0.0000989495,0.00022910308,0.76429313,0.002997769,0.13559486,0.0029974794,0.09256693],"study_design_scores_gemma":[0.0000040869672,0.000009832629,0.000034225934,0.0000054454745,0.0000045471925,0.000015648031,0.000008982327,0.97494954,0.000699477,0.023595238,0.00066629826,0.0000067560172],"about_ca_topic_score_codex":0.0076794964,"about_ca_topic_score_gemma":0.011984061,"teacher_disagreement_score":0.0076794964,"about_ca_system_score_codex":0.0020411897,"about_ca_system_score_gemma":0.0021038945,"threshold_uncertainty_score":0.0152695775},"labels":[],"label_agreement":null},{"id":"W3190788066","doi":"10.1109/tkde.2021.3052927","title":"Discovering Structural Errors From Business Process Event Logs","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Business Process Modeling and Analysis","field":"Business, Management and Accounting","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Natural Science Foundation of China; Deutsche Forschungsgemeinschaft","keywords":"Process mining; Computer science; Event (particle physics); Process (computing); Business process; Data mining; Business process discovery; Business process management; Synchronization (alternating current); Complex event processing; Business process modeling; Data science; Work in process; Engineering; Programming language","score_opus":0.021232336016666055,"score_gpt":0.25215761205603626,"score_spread":0.23092527603937021,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3190788066","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29737887,0.0006873184,0.676915,0.00059846183,0.0000970608,0.00073866,0.0039694374,0.018438086,0.0011771248],"genre_scores_gemma":[0.7294123,0.000416214,0.2609591,0.000121950674,0.000049988634,0.00036451,0.0074491976,0.00046213157,0.00076454313],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99159193,0.0013891712,0.0010147317,0.0013026219,0.004271526,0.00043003127],"domain_scores_gemma":[0.9489673,0.030330103,0.007313756,0.0066353763,0.0060703433,0.00068314164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006061491,0.0019646643,0.0012460159,0.005705009,0.0007996358,0.0021378805,0.0021036551,0.0012620222,0.00058110326],"category_scores_gemma":[0.040815752,0.00079986703,0.0010306155,0.003195902,0.00074047636,0.0029297362,0.0019470527,0.0018016291,0.0003876653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015334665,0.0019080424,0.18342522,0.0017470359,0.00052594184,0.0046994723,0.0023128027,0.20470755,0.034302734,0.0103879385,0.0069055962,0.5475441],"study_design_scores_gemma":[0.00006148946,0.00018704598,0.011487021,0.00011512156,0.00012821666,0.0006726336,0.00041010824,0.9406817,0.030961461,0.011355652,0.0038878699,0.00005168686],"about_ca_topic_score_codex":0.004622713,"about_ca_topic_score_gemma":0.0060753594,"teacher_disagreement_score":0.006061491,"about_ca_system_score_codex":0.00076629204,"about_ca_system_score_gemma":0.0028912826,"threshold_uncertainty_score":0.03205663},"labels":[],"label_agreement":null},{"id":"W3212438094","doi":"10.1109/tkde.2021.3126642","title":"Constrained Generative Adversarial Learning for Dimensionality Reduction","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dimensionality reduction; Computer science; Artificial intelligence; Feature vector; Diffusion map; Big data; Pattern recognition (psychology); Data mining; Pairwise comparison; Projection (relational algebra); Curse of dimensionality; Reduction (mathematics); Transformation (genetics); Benchmark (surveying); Feature (linguistics); Machine learning; Nonlinear dimensionality reduction; Algorithm; Mathematics","score_opus":0.029209038685555043,"score_gpt":0.2658531333269815,"score_spread":0.23664409464142647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212438094","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050309617,0.00031036488,0.9935226,0.00015414208,0.000026742178,0.00002096769,0.00003586815,0.00013971601,0.00075859996],"genre_scores_gemma":[0.70999765,0.0011349608,0.28144825,0.0004930534,0.00016710939,0.0003572089,0.0005489563,0.00015518349,0.005697683],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990232,0.0004039119,0.000041795633,0.00020010065,0.00024954826,0.000081515645],"domain_scores_gemma":[0.9980872,0.0013819467,0.00015000705,0.00017436071,0.00015290527,0.00005356823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015715954,0.0011811766,0.0011474857,0.0006958462,0.00035595678,0.0007899827,0.0011011118,0.000859188,0.0013287859],"category_scores_gemma":[0.0040230094,0.0004587511,0.00091959443,0.00076418277,0.0013064109,0.0011320221,0.0019331834,0.002338876,0.00039748166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005102253,0.000029607063,0.0004923732,0.000054748736,0.00006488225,0.0000665043,0.00005483851,0.93090177,0.0021538057,0.019771978,0.0014477097,0.044910718],"study_design_scores_gemma":[0.0000017118392,0.000009493902,0.000049142214,0.0000033589076,0.0000036529511,0.0000139389185,0.0000033080657,0.99338114,0.0004105105,0.0058528376,0.00026682013,0.0000041437356],"about_ca_topic_score_codex":0.0020580324,"about_ca_topic_score_gemma":0.0017625509,"teacher_disagreement_score":0.0020580324,"about_ca_system_score_codex":0.00079106475,"about_ca_system_score_gemma":0.00065919355,"threshold_uncertainty_score":0.00831151},"labels":[],"label_agreement":null},{"id":"W4210647131","doi":"10.1109/tkde.2022.3144294","title":"Low-Rank Linear Embedding for Robust Clustering","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China; Natural Science Foundation of Shenzhen City","keywords":"Cluster analysis; Dimensionality reduction; Computer science; Embedding; Robustness (evolution); Correlation clustering; Curse of dimensionality; Artificial intelligence; Pattern recognition (psychology); Algorithm","score_opus":0.03821421735241483,"score_gpt":0.27930823292496615,"score_spread":0.24109401557255133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210647131","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020261768,0.00019989439,0.9963644,0.00008082219,0.000025688976,0.000019514813,0.00006981968,0.0007166779,0.0004969661],"genre_scores_gemma":[0.16756074,0.0006259572,0.8239546,0.00021253744,0.00016546623,0.0002577586,0.0014763739,0.0005253333,0.00522128],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977748,0.0006568384,0.00010864818,0.000608703,0.00071478053,0.00013629666],"domain_scores_gemma":[0.9982862,0.0004424596,0.00020501263,0.0004487639,0.0005592691,0.000058200523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014522881,0.0018113547,0.0014170342,0.0014998235,0.00077363476,0.0013803783,0.0016466116,0.0014621873,0.0028020116],"category_scores_gemma":[0.0052942205,0.000559608,0.0009996712,0.0019839345,0.0010814576,0.001967546,0.0016158812,0.0022989037,0.0037798209],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016800818,0.000109708635,0.00048244966,0.00028801986,0.00012435137,0.00009480421,0.00020660846,0.48103037,0.018244844,0.03572703,0.013383576,0.45014024],"study_design_scores_gemma":[0.000004214278,0.000038767157,0.00014067307,0.000008775356,0.000007311457,0.000039319264,0.000023588103,0.98068917,0.0036695735,0.013125892,0.0022310184,0.000021683181],"about_ca_topic_score_codex":0.0034358762,"about_ca_topic_score_gemma":0.0041258545,"teacher_disagreement_score":0.0034358762,"about_ca_system_score_codex":0.00089631736,"about_ca_system_score_gemma":0.001269295,"threshold_uncertainty_score":0.009373665},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.027010390069907686,"score_gpt":0.234104556318824,"score_spread":0.2070941662489163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312251623","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010558547,0.00020218406,0.9885923,0.00006475436,0.000018034842,0.000025097757,0.00003998347,0.00012944335,0.00036976888],"genre_scores_gemma":[0.55697536,0.000407903,0.44072974,0.0000963186,0.0000931057,0.00015769628,0.00046929557,0.00004398849,0.0010266128],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990085,0.00023850506,0.000086156695,0.00027774245,0.0003059097,0.000083237835],"domain_scores_gemma":[0.9991667,0.0002855779,0.00012050583,0.0001483592,0.00023679259,0.00004199311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012044349,0.00074950606,0.0013920353,0.0017002157,0.00059974845,0.0014887679,0.0012950476,0.0011919831,0.0007846424],"category_scores_gemma":[0.0027651095,0.000338411,0.0015395749,0.0017795473,0.00074856065,0.0020010837,0.0011453666,0.0010666553,0.0002824113],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025148748,0.00012365756,0.0028368696,0.00021974447,0.0002462719,0.00020690582,0.0003896862,0.5547646,0.008169776,0.043172818,0.0027529413,0.38686523],"study_design_scores_gemma":[0.0000038542676,0.000017558235,0.00021987989,0.0000063935904,0.000010874203,0.000018920633,0.000020467352,0.9899893,0.0007776363,0.0086322045,0.00029397296,0.000008786736],"about_ca_topic_score_codex":0.0043065995,"about_ca_topic_score_gemma":0.002771792,"teacher_disagreement_score":0.0043065995,"about_ca_system_score_codex":0.0007508375,"about_ca_system_score_gemma":0.0007208123,"threshold_uncertainty_score":0.008563101},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.027799234583415194,"score_gpt":0.2480279719790504,"score_spread":0.22022873739563523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312529005","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06527487,0.002495989,0.91629344,0.0011712804,0.00030651133,0.00012444271,0.0017609792,0.007293635,0.005278778],"genre_scores_gemma":[0.7899227,0.0013777375,0.19077165,0.0010615358,0.00026713306,0.00016769565,0.005844566,0.0003597395,0.010227165],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997737,0.000054283075,0.000007734317,0.00008419563,0.00003828861,0.00004179808],"domain_scores_gemma":[0.9996069,0.00021137086,0.000037428166,0.000051442094,0.00007120014,0.000021575193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005095306,0.0013018778,0.00067993195,0.0012528164,0.0003544203,0.00043018622,0.0014692701,0.0008675341,0.0016042633],"category_scores_gemma":[0.0015450241,0.0004083303,0.00069346465,0.0010226195,0.00035221878,0.0013111593,0.00086864457,0.0012216206,0.0005116928],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019849047,0.00014674636,0.0026271564,0.00014025945,0.00016994395,0.00015656835,0.0001045033,0.59592485,0.005948281,0.008246978,0.016910411,0.36942586],"study_design_scores_gemma":[0.0000040948867,0.000014543741,0.00032579448,0.0000054176153,0.000013196967,0.000021078056,0.000008765658,0.9937196,0.00093376543,0.00397662,0.0009714305,0.000005660344],"about_ca_topic_score_codex":0.022497594,"about_ca_topic_score_gemma":0.031778835,"teacher_disagreement_score":0.022497594,"about_ca_system_score_codex":0.0014259971,"about_ca_system_score_gemma":0.0007570209,"threshold_uncertainty_score":0.044733286},"labels":[],"label_agreement":null},{"id":"W4319459101","doi":"10.1109/tkde.2023.3243169","title":"Towards Lightweight and Automated Representation Learning System for Networks","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Computer science; Scalability; Embedding; Singular value decomposition; Parallel computing; Theoretical computer science; Algorithm; Artificial intelligence","score_opus":0.027618364107412027,"score_gpt":0.28861185003460915,"score_spread":0.2609934859271971,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319459101","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019690932,0.00008675904,0.97763944,0.00017995192,0.000039460512,0.000069245114,0.00030101638,0.018830065,0.0008848287],"genre_scores_gemma":[0.04810153,0.00022684968,0.94297206,0.00021459535,0.00007146629,0.0002786969,0.0023737971,0.0010814036,0.0046796114],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849224,0.00032263948,0.00009869741,0.000458026,0.00051294477,0.00011545434],"domain_scores_gemma":[0.9982811,0.00046514292,0.00012007107,0.00060631114,0.00044837123,0.000078995225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016904571,0.0013772367,0.0011338589,0.0020056292,0.00078730466,0.0027668986,0.0038923707,0.0016752229,0.008285711],"category_scores_gemma":[0.0061617168,0.0009941832,0.0016659208,0.0015003105,0.0007173886,0.006424857,0.0036271492,0.002982113,0.006054026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029637295,0.00028204205,0.0010827425,0.0003268472,0.00015907506,0.00019833341,0.00023931383,0.13470563,0.010977682,0.07694307,0.040256932,0.73453194],"study_design_scores_gemma":[0.000021698706,0.000028764432,0.000093773604,0.0000185093,0.000016097913,0.000049277893,0.000025553478,0.94778425,0.004553928,0.037811123,0.009578933,0.00001808184],"about_ca_topic_score_codex":0.004421759,"about_ca_topic_score_gemma":0.00669183,"teacher_disagreement_score":0.008285711,"about_ca_system_score_codex":0.0015495961,"about_ca_system_score_gemma":0.0016540468,"threshold_uncertainty_score":0.027718425},"labels":[],"label_agreement":null},{"id":"W4319863485","doi":"10.1109/tkde.2023.3240431","title":"Cost-Sensitive Learning for Medical Insurance Fraud Detection With Temporal Information","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data mining","score_opus":0.027099778289374654,"score_gpt":0.27910290259692533,"score_spread":0.2520031243075507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319863485","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18291458,0.0009840464,0.8119113,0.0019940676,0.000078859906,0.00014893195,0.00029924608,0.00037204826,0.0012969725],"genre_scores_gemma":[0.9455377,0.00034031022,0.052449845,0.00022383721,0.000107861706,0.00009738269,0.00041376648,0.000028089307,0.00080119213],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998066,0.00080891955,0.00014022569,0.00038373307,0.00042028356,0.00018086085],"domain_scores_gemma":[0.9912158,0.0060097366,0.0009176146,0.00074010325,0.0008720298,0.00024466703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055580735,0.0007626888,0.0011547843,0.0013240535,0.000637392,0.00136159,0.0015427609,0.0012014495,0.000782417],"category_scores_gemma":[0.020421904,0.00040553822,0.0006089334,0.001527221,0.0008964442,0.0026551345,0.0016250599,0.0021005184,0.00019311206],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034785483,0.0005271868,0.017221404,0.00009834752,0.00011589497,0.00020237455,0.00015328116,0.7792138,0.0013837628,0.017371869,0.002317855,0.1810463],"study_design_scores_gemma":[0.0000029475518,0.00001984607,0.0006149999,0.0000040474147,0.000004761744,0.000017278004,0.00001129882,0.99303174,0.0002286844,0.0059330706,0.00012746437,0.0000039043284],"about_ca_topic_score_codex":0.004467676,"about_ca_topic_score_gemma":0.0032012383,"teacher_disagreement_score":0.0055580735,"about_ca_system_score_codex":0.0018755356,"about_ca_system_score_gemma":0.0016481471,"threshold_uncertainty_score":0.029394269},"labels":[],"label_agreement":null},{"id":"W4322730971","doi":"10.1109/tkde.2023.3238993","title":"Semi-Supervised Entity Alignment With Global Alignment and Local Information Aggregation","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Fundamental Research Funds for the Central Universities; State Key Laboratory of Software Development Environment","keywords":"Computer science; Merge (version control); Knowledge graph; Forcing (mathematics); Data mining; Theoretical computer science; Artificial intelligence; Information retrieval; Mathematics","score_opus":0.014223436611622209,"score_gpt":0.23993458954117783,"score_spread":0.22571115292955563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322730971","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026615959,0.0006138492,0.9674965,0.00024088687,0.000087688124,0.0001325499,0.0006579743,0.0027137198,0.0014408189],"genre_scores_gemma":[0.5289298,0.00038148844,0.45853585,0.00036649406,0.00024529078,0.00041082356,0.0066850395,0.00048798695,0.0039573037],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958081,0.0012282141,0.0003037806,0.0018444835,0.0005726723,0.00024275345],"domain_scores_gemma":[0.99370754,0.0021115083,0.001001664,0.0019492914,0.00102855,0.00020131088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029654459,0.0018671508,0.0023060015,0.0029338677,0.0011815643,0.0018252193,0.002970346,0.0018756657,0.0018539503],"category_scores_gemma":[0.008530761,0.00069396244,0.0016192888,0.0050569843,0.0012667418,0.0061315936,0.0032004488,0.0024249419,0.001538813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064694986,0.00054953754,0.008742353,0.00048512334,0.000628972,0.0004013423,0.0007840631,0.35534367,0.009298575,0.023173839,0.018596098,0.5813495],"study_design_scores_gemma":[0.000022086997,0.000078173885,0.0010055387,0.000020507472,0.00005560057,0.000077164965,0.000081902086,0.97406703,0.0029056463,0.019282172,0.0023803327,0.000023683373],"about_ca_topic_score_codex":0.0034842605,"about_ca_topic_score_gemma":0.0074482774,"teacher_disagreement_score":0.0034842605,"about_ca_system_score_codex":0.0008660305,"about_ca_system_score_gemma":0.0014575946,"threshold_uncertainty_score":0.015682995},"labels":[],"label_agreement":null},{"id":"W4364321947","doi":"10.1109/tkde.2023.3265840","title":"Summarizing Provenance of Aggregate Query Results in Relational Databases","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Automatic summarization; Provenance; Relevance (law); Information retrieval; Aggregate (composite); Tuple; Database; Relational database; Data mining","score_opus":0.1898363623171656,"score_gpt":0.37494008237530535,"score_spread":0.18510372005813974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4364321947","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051204573,0.0016087482,0.93796,0.0005314231,0.00007713012,0.0003227595,0.0016050673,0.0052827913,0.0014074504],"genre_scores_gemma":[0.335195,0.0012592068,0.6561652,0.00016890463,0.00012083152,0.000273256,0.0049036723,0.00066946005,0.0012444921],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9866882,0.004338421,0.0018271373,0.0012320546,0.00558721,0.0003269399],"domain_scores_gemma":[0.96810776,0.015442361,0.0024906632,0.0074735326,0.006072892,0.00041294046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010363549,0.00084060093,0.0013602673,0.0045019,0.0013831154,0.0052599614,0.001530291,0.00096626073,0.0010364841],"category_scores_gemma":[0.045275476,0.0007035053,0.0011280113,0.005777353,0.000870644,0.0064974576,0.0024520014,0.00097599137,0.00060832],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016275494,0.00038222945,0.014767742,0.0014435133,0.00046972363,0.00076457666,0.0055350666,0.20421083,0.02926923,0.082024775,0.015654596,0.6438502],"study_design_scores_gemma":[0.00016717047,0.00047854165,0.0035130845,0.00023144337,0.00036513037,0.00049434474,0.0012896083,0.78290886,0.052081272,0.12902817,0.029283524,0.0001588557],"about_ca_topic_score_codex":0.0055442513,"about_ca_topic_score_gemma":0.0057141804,"teacher_disagreement_score":0.010363549,"about_ca_system_score_codex":0.0013204367,"about_ca_system_score_gemma":0.0018769322,"threshold_uncertainty_score":0.05480832},"labels":[],"label_agreement":null},{"id":"W4366200499","doi":"10.1109/tkde.2023.3267854","title":"Hiding From Centrality Measures: A Stackelberg Game Perspective","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Army Research Office; National Science Foundation of Sri Lanka; Multidisciplinary University Research Initiative; Hong Kong Polytechnic University; National Natural Science Foundation of China; Narodowe Centrum Nauki; York University; New York University Abu Dhabi; National Science Foundation","keywords":"Centrality; Betweenness centrality; Computer science; Ranking (information retrieval); Stackelberg competition; Node (physics); Closeness; Social network (sociolinguistics); Theoretical computer science; Katz centrality; Mathematical optimization; Artificial intelligence; Mathematics; Mathematical economics; Social media; Statistics","score_opus":0.04118757028655001,"score_gpt":0.3047716404612869,"score_spread":0.2635840701747369,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366200499","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0497693,0.0004233318,0.93391484,0.0019126552,0.000067387155,0.00014199434,0.00015502544,0.000106184874,0.013509346],"genre_scores_gemma":[0.83419836,0.0010624651,0.15541282,0.00036889763,0.00021164524,0.00031986946,0.00013627793,0.00007778029,0.008211888],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99685115,0.0016612497,0.00008677557,0.0003963534,0.0006339063,0.00037058987],"domain_scores_gemma":[0.9901968,0.008037902,0.00064501475,0.00045991672,0.0003347799,0.00032564512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038529602,0.0015775649,0.0013286467,0.0011189459,0.0012680099,0.0030788789,0.0022418546,0.0024215851,0.0037926536],"category_scores_gemma":[0.014158255,0.0006714141,0.001222914,0.0010921531,0.002950128,0.0073077055,0.002155128,0.0036581117,0.00038816803],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001346673,0.00011403022,0.0009170598,0.00015819861,0.00010789618,0.00029891494,0.00041242174,0.2874624,0.0033504225,0.6836737,0.0016711871,0.021699077],"study_design_scores_gemma":[0.00002406292,0.00009065814,0.00017789063,0.000022816563,0.000035710767,0.00008885956,0.00010378832,0.5010173,0.00082516606,0.4959572,0.0016289242,0.000027722308],"about_ca_topic_score_codex":0.0022713612,"about_ca_topic_score_gemma":0.002652372,"teacher_disagreement_score":0.0038529602,"about_ca_system_score_codex":0.0023750043,"about_ca_system_score_gemma":0.0017143005,"threshold_uncertainty_score":0.020376682},"labels":[],"label_agreement":null},{"id":"W4382568066","doi":"10.1109/tkde.2023.3290792","title":"Individual and Structural Graph Information Bottlenecks for Out-of-Distribution Generalization","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"National Natural Science Foundation of China","keywords":"Spurious relationship; Computer science; Graph; Leverage (statistics); Artificial intelligence; Bottleneck; Theoretical computer science; Algorithm; Machine learning","score_opus":0.028363888784600035,"score_gpt":0.2753856377479403,"score_spread":0.24702174896334025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382568066","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049526837,0.0015169765,0.9371938,0.0029776269,0.00019349316,0.00014450318,0.00047445923,0.0028418663,0.0051305173],"genre_scores_gemma":[0.82125485,0.0015833593,0.16284806,0.0022771105,0.0005442051,0.00037914433,0.001935279,0.001266836,0.007911167],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996067,0.001177673,0.00018025193,0.0014210496,0.00069211994,0.00046197991],"domain_scores_gemma":[0.96808887,0.02261622,0.001841594,0.004548926,0.0017283518,0.0011760814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0076900744,0.0019461864,0.003387941,0.0028426289,0.0018940241,0.002981461,0.0048578186,0.003227426,0.005885115],"category_scores_gemma":[0.046070457,0.0012434669,0.0019016323,0.0025447505,0.0027674288,0.009271656,0.004671907,0.0058759353,0.0014151407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00084915507,0.0006700482,0.0071906894,0.00062723004,0.00027416906,0.00056482264,0.0006341696,0.4915234,0.004340774,0.18048722,0.033144653,0.27969363],"study_design_scores_gemma":[0.000025296393,0.00004357145,0.00067982747,0.0000237417,0.000022812645,0.00009210979,0.000051586925,0.87663674,0.0011528914,0.11960356,0.0016491995,0.000018731198],"about_ca_topic_score_codex":0.0092493845,"about_ca_topic_score_gemma":0.009629281,"teacher_disagreement_score":0.0092493845,"about_ca_system_score_codex":0.00425962,"about_ca_system_score_gemma":0.0029176304,"threshold_uncertainty_score":0.0406695},"labels":[],"label_agreement":null},{"id":"W4385732413","doi":"10.1109/tkde.2023.3303916","title":"XMQAs: Constructing Complex-Modified Question-Answering Dataset for Robust Question Understanding","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"Science and Technology Commission of Shanghai Municipality; National Natural Science Foundation of China","keywords":"Computer science; Question answering; Robustness (evolution); Construct (python library); Semantics (computer science); Simple (philosophy); Artificial intelligence; Machine learning; Information retrieval; Natural language processing; Programming language","score_opus":0.15051792830781893,"score_gpt":0.3267831472600723,"score_spread":0.17626521895225336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385732413","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16839415,0.004817163,0.4124681,0.0034608075,0.0009519354,0.0064812223,0.32271573,0.07076926,0.009941677],"genre_scores_gemma":[0.11417629,0.0005218745,0.36520702,0.0011096037,0.00014133955,0.0036617727,0.51190436,0.000412882,0.0028648076],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9949043,0.0016728308,0.0007685109,0.0015072154,0.00091435417,0.00023282667],"domain_scores_gemma":[0.99225616,0.0028725038,0.00053309667,0.002080187,0.0018074667,0.00045058195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047216644,0.002148067,0.0010971627,0.005414131,0.001327712,0.0019452437,0.0041683675,0.0028754768,0.0042943773],"category_scores_gemma":[0.018872237,0.0004930668,0.0023639898,0.0034242298,0.0008997871,0.0044537806,0.004437661,0.003073293,0.0031984139],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013895408,0.002624623,0.03651801,0.006241007,0.0007466947,0.00105363,0.00402556,0.028665284,0.043389656,0.021445785,0.36846942,0.48543084],"study_design_scores_gemma":[0.0007635216,0.0011457554,0.04400479,0.0005688471,0.00040894642,0.001312518,0.0037341802,0.4841541,0.046732467,0.040407125,0.37637588,0.000391793],"about_ca_topic_score_codex":0.012933268,"about_ca_topic_score_gemma":0.016172487,"teacher_disagreement_score":0.012933268,"about_ca_system_score_codex":0.0016560357,"about_ca_system_score_gemma":0.0024184047,"threshold_uncertainty_score":0.025715947},"labels":[],"label_agreement":null},{"id":"W4385863304","doi":"10.1109/tkde.2023.3305809","title":"Hierarchical Aggregations for High-Dimensional Multiplex Graph Embedding","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Multiplex; Graph; Embedding; Graph theory; Theoretical computer science; Artificial intelligence; Mathematics; Combinatorics; Bioinformatics","score_opus":0.031247219794920875,"score_gpt":0.2927645023608479,"score_spread":0.261517282565927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385863304","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032760225,0.00026000445,0.96543014,0.00015696768,0.000021150885,0.000033482047,0.00017643269,0.00046161204,0.00069995434],"genre_scores_gemma":[0.6961902,0.00038830697,0.29832995,0.0002062096,0.00010333647,0.00016999082,0.0012545597,0.00023765334,0.003119887],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991603,0.0002683256,0.00004655317,0.00025722233,0.00018330089,0.00008433469],"domain_scores_gemma":[0.9977254,0.0010340174,0.00036875988,0.00046015487,0.00027812345,0.00013358693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010459238,0.0009895652,0.00085340906,0.0017815671,0.00060533016,0.00085916376,0.0010939274,0.00092619593,0.0016024016],"category_scores_gemma":[0.0052643167,0.00047289746,0.0008367458,0.0017139594,0.0008547173,0.0030097323,0.0015934849,0.0014635413,0.0004958301],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017305424,0.00018783964,0.005203872,0.000252536,0.00017335915,0.00032255368,0.00061915745,0.64419204,0.009240935,0.0852108,0.0065415027,0.24788238],"study_design_scores_gemma":[0.0000041692106,0.000016080156,0.00030196007,0.000006993683,0.000008218785,0.000027741788,0.000029118708,0.97139794,0.00063407334,0.026954042,0.00061273936,0.0000068470677],"about_ca_topic_score_codex":0.0028570544,"about_ca_topic_score_gemma":0.005724048,"teacher_disagreement_score":0.0028570544,"about_ca_system_score_codex":0.0007706643,"about_ca_system_score_gemma":0.00048132593,"threshold_uncertainty_score":0.0056807995},"labels":[],"label_agreement":null},{"id":"W4385863765","doi":"10.1109/tkde.2023.3303617","title":"HSMH: A Hierarchical Sequence Multi-Hop Reasoning Model With Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"State Key Laboratory of Integrated Services Networks; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Interpretability; Reinforcement learning; Reasoning system; Information retrieval; Natural language processing","score_opus":0.046428252697422394,"score_gpt":0.289260324197042,"score_spread":0.2428320714996196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385863765","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015594091,0.00045102776,0.97553056,0.00059543725,0.00012877394,0.00014849407,0.0003047008,0.0015665033,0.005680337],"genre_scores_gemma":[0.77273506,0.0004248859,0.21499689,0.00041856422,0.00008942587,0.00045271288,0.00054185506,0.00011154731,0.010228936],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938524,0.00014779113,0.00004161411,0.0001891498,0.00014832868,0.00008790403],"domain_scores_gemma":[0.9991698,0.00041545427,0.000098582204,0.00007604182,0.00015974787,0.00008037455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009918143,0.0008206618,0.0011286873,0.0005437964,0.0005778959,0.0011139346,0.0028341652,0.001416651,0.007110352],"category_scores_gemma":[0.0025491128,0.00047300002,0.0009861017,0.00052544934,0.00079418987,0.0017381981,0.0015657307,0.0018444835,0.0010251538],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001554429,0.00011513296,0.0005849433,0.00012067188,0.000070216585,0.00017884221,0.000112860114,0.9088576,0.0014828811,0.022410572,0.0026537124,0.06325712],"study_design_scores_gemma":[0.000018224184,0.000021219865,0.000033792512,0.0000036658325,0.000007405334,0.000010216973,0.0000042058737,0.99471706,0.00019842052,0.004424465,0.0005567201,0.000004627555],"about_ca_topic_score_codex":0.014975942,"about_ca_topic_score_gemma":0.011207695,"teacher_disagreement_score":0.014975942,"about_ca_system_score_codex":0.0012276067,"about_ca_system_score_gemma":0.0020542156,"threshold_uncertainty_score":0.029777527},"labels":[],"label_agreement":null},{"id":"W4387682100","doi":"10.1109/tkde.2023.3324932","title":"A Robust Database Watermarking Scheme That Preserves Statistical Characteristics","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Computer science; Digital watermarking; Scheme (mathematics); Robustness (evolution); Data mining; Database; Artificial intelligence; Image (mathematics); Mathematics","score_opus":0.0642338633944093,"score_gpt":0.2844346963423049,"score_spread":0.2202008329478956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387682100","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009488331,0.00080392405,0.98427063,0.00025903448,0.00007844295,0.00007766345,0.00008938642,0.00036675629,0.004565764],"genre_scores_gemma":[0.5211079,0.003319649,0.46418917,0.00038691796,0.00043778913,0.00021873681,0.00041057725,0.0001378269,0.009791462],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99789184,0.00032586078,0.00016805067,0.00048917846,0.0009945574,0.00013038304],"domain_scores_gemma":[0.99733174,0.00056495215,0.00045913117,0.001152247,0.00044066276,0.000051358504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015308071,0.0006388309,0.00070086744,0.0016095588,0.0004403455,0.0018292884,0.001529744,0.0013478943,0.002818593],"category_scores_gemma":[0.0053218664,0.00033822714,0.0008438898,0.0021369958,0.0011392995,0.0046529253,0.0013675811,0.00095437525,0.0016307777],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024794374,0.00017623155,0.00084323384,0.0004472058,0.00009638393,0.00037094255,0.00016708182,0.04774233,0.16888697,0.34680215,0.0031832159,0.43103635],"study_design_scores_gemma":[0.00006948543,0.0005810204,0.0011012,0.00009600078,0.00013527338,0.0018933412,0.00010413634,0.7344517,0.14238341,0.07558299,0.043452304,0.0001491552],"about_ca_topic_score_codex":0.0003947624,"about_ca_topic_score_gemma":0.00025834955,"teacher_disagreement_score":0.002818593,"about_ca_system_score_codex":0.0007252165,"about_ca_system_score_gemma":0.00083399133,"threshold_uncertainty_score":0.009429097},"labels":[],"label_agreement":null},{"id":"W4389040608","doi":"10.1109/tkde.2023.3336630","title":"Preventing Inferences Through Data Dependencies on Sensitive Data","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency; National Science Foundation","keywords":"Computer science; Data modeling; Data mining; Database","score_opus":0.11338065600082713,"score_gpt":0.32908617227716463,"score_spread":0.2157055162763375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389040608","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09426185,0.00038581286,0.8958421,0.0032432731,0.00007375828,0.0002589447,0.0005244706,0.0026534554,0.0027563614],"genre_scores_gemma":[0.8251469,0.0003402408,0.16934603,0.0013611981,0.00009966658,0.00022782813,0.0007342854,0.00037205528,0.002371736],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9735607,0.00911653,0.0021046833,0.0050695543,0.007995512,0.0021529768],"domain_scores_gemma":[0.89233893,0.05541859,0.006123779,0.04241411,0.0029400475,0.0007645352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014322638,0.0010885188,0.001400039,0.0012618101,0.00188853,0.003900549,0.0042963475,0.0024064402,0.002036712],"category_scores_gemma":[0.06585482,0.0015193217,0.0024570287,0.0014499768,0.005052792,0.016232809,0.010398319,0.0069292514,0.00066973176],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021597962,0.00054976565,0.02395299,0.0009586762,0.0006145562,0.0011385833,0.0034861634,0.22120011,0.05249926,0.4292357,0.012454755,0.25174975],"study_design_scores_gemma":[0.00012882394,0.00020008988,0.0016915229,0.00016183864,0.00022837352,0.0010278556,0.00046557217,0.44694406,0.11729168,0.41837656,0.013360565,0.00012305874],"about_ca_topic_score_codex":0.0018838797,"about_ca_topic_score_gemma":0.0018865248,"teacher_disagreement_score":0.014322638,"about_ca_system_score_codex":0.0020075764,"about_ca_system_score_gemma":0.0047314735,"threshold_uncertainty_score":0.07574624},"labels":[],"label_agreement":null},{"id":"W4390120254","doi":"10.1109/tkde.2023.3344662","title":"ODIN: Object Density Aware Index for C$k$k NN Queries Over Moving Objects on Road Networks","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; York University","funders":"National Natural Science Foundation of China","keywords":"Notation; Object (grammar); Computer science; Index (typography); Identification (biology); Theoretical computer science; Algorithm; Data mining; Artificial intelligence; Information retrieval; Mathematics; Programming language; Arithmetic","score_opus":0.026107012340016018,"score_gpt":0.2666511080454351,"score_spread":0.2405440957054191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390120254","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13098884,0.001614597,0.844403,0.00094147003,0.00018115866,0.0004934578,0.003958097,0.0086673945,0.008751938],"genre_scores_gemma":[0.4626136,0.0005905506,0.5240151,0.0003158374,0.00011194787,0.00029530955,0.006722515,0.0006218024,0.0047132866],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989661,0.00008911667,0.00008151098,0.00026901384,0.00043021757,0.00016405153],"domain_scores_gemma":[0.9985656,0.000513502,0.00016905172,0.00042249452,0.00020870643,0.000120757766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077591575,0.0010472859,0.0016542492,0.0012930558,0.0010639034,0.0024001547,0.0025380647,0.001328736,0.003106227],"category_scores_gemma":[0.0045341337,0.0004739575,0.000703334,0.0026351467,0.00060385553,0.004053822,0.0029331981,0.0010165975,0.0013227648],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008502309,0.00043465305,0.0094751865,0.0009174157,0.00013896101,0.00043699052,0.0009415956,0.45473778,0.02612313,0.03142813,0.03064584,0.44387007],"study_design_scores_gemma":[0.00002269009,0.000071042676,0.00081465096,0.000016361864,0.000015069692,0.00016549249,0.00021404497,0.977758,0.0048604384,0.010727463,0.0053161574,0.000018640807],"about_ca_topic_score_codex":0.009407345,"about_ca_topic_score_gemma":0.01423769,"teacher_disagreement_score":0.009407345,"about_ca_system_score_codex":0.001476537,"about_ca_system_score_gemma":0.0016275126,"threshold_uncertainty_score":0.01870519},"labels":[],"label_agreement":null},{"id":"W4390480779","doi":"10.1109/tkde.2023.3346377","title":"A Distributed Solution for Efficient K Shortest Paths Computation Over Dynamic Road Networks","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; University of Toronto; York University","funders":"National Natural Science Foundation of China","keywords":"Shortest path problem; Graph; Computer science; Centrality; Computation; Notation; Algorithm; Scalability; Theoretical computer science; Combinatorics; Mathematics; Database","score_opus":0.016598783254482878,"score_gpt":0.26794138589068084,"score_spread":0.25134260263619795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390480779","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019574532,0.00034731894,0.9718436,0.00047949443,0.00012753728,0.00012334017,0.0005568735,0.0019895392,0.0049577532],"genre_scores_gemma":[0.26525342,0.0003136322,0.7251087,0.00015381542,0.0000999858,0.00033827533,0.0014809469,0.00032613537,0.006925157],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931955,0.000098488716,0.000043308657,0.00028228943,0.00012859004,0.00012782733],"domain_scores_gemma":[0.9990876,0.0004700671,0.00006940847,0.00013602561,0.00016217917,0.00007465291],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000701281,0.0012085111,0.0016856189,0.0008395324,0.0012216187,0.0017567197,0.0024647252,0.0018659816,0.0073963036],"category_scores_gemma":[0.0029848705,0.0006063701,0.0011325388,0.0017791647,0.0006822031,0.0021392626,0.0021946589,0.0013047582,0.0018834028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035915466,0.00013032142,0.00077188347,0.0002883171,0.00007318992,0.00020042156,0.00022704976,0.8399811,0.003162248,0.022561716,0.013612715,0.11863185],"study_design_scores_gemma":[0.00004413597,0.000019819296,0.00006018093,0.000006482146,0.00000781958,0.000025280771,0.00006132507,0.98816586,0.00032367627,0.0099186115,0.0013603867,0.0000063856496],"about_ca_topic_score_codex":0.011704025,"about_ca_topic_score_gemma":0.015968036,"teacher_disagreement_score":0.011704025,"about_ca_system_score_codex":0.0012408491,"about_ca_system_score_gemma":0.0025800513,"threshold_uncertainty_score":0.02474314},"labels":[],"label_agreement":null},{"id":"W4393144966","doi":"10.1109/tkde.2024.3381192","title":"DIBA: A Re-Configurable Stream Processor","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":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Alexander von Humboldt-Stiftung","keywords":"Computer science; Stream processing; Computer architecture; Parallel computing","score_opus":0.02496765267250139,"score_gpt":0.2756281570028197,"score_spread":0.2506605043303183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393144966","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0546198,0.0007812241,0.8946455,0.00059400895,0.000500386,0.0006729995,0.0009150777,0.0383758,0.008895188],"genre_scores_gemma":[0.5303336,0.0008430482,0.44389772,0.0015470675,0.00027769976,0.0008073162,0.003828695,0.00256521,0.015899654],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99900275,0.000111400026,0.00009632451,0.00025087033,0.00037886287,0.00015984123],"domain_scores_gemma":[0.99882644,0.00019567036,0.00008007094,0.0003664438,0.00037208138,0.00015934157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008902764,0.0007819143,0.00055972906,0.00096543116,0.00040275755,0.0020230282,0.0026043272,0.00065370154,0.004569407],"category_scores_gemma":[0.0022691719,0.00047339674,0.0004247305,0.000823638,0.0006282332,0.0023701095,0.0016683548,0.001952532,0.0021513198],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041185813,0.0010185589,0.01125085,0.0009179252,0.00024758137,0.00091439404,0.0008514746,0.039384943,0.31752175,0.03289125,0.08441967,0.5064631],"study_design_scores_gemma":[0.00078251114,0.0010606729,0.0032967562,0.00008171822,0.00018633647,0.0012403438,0.00022342277,0.5659038,0.21427387,0.011224431,0.20151116,0.00021496607],"about_ca_topic_score_codex":0.0017986121,"about_ca_topic_score_gemma":0.0012555944,"teacher_disagreement_score":0.004569407,"about_ca_system_score_codex":0.0009378372,"about_ca_system_score_gemma":0.0012960723,"threshold_uncertainty_score":0.015286207},"labels":[],"label_agreement":null},{"id":"W4394862804","doi":"10.1109/tkde.2024.3388526","title":"Feature Selection With Discernibility and Independence Criteria","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Computer science; Feature selection; Selection (genetic algorithm); Independence (probability theory); Artificial intelligence; Feature (linguistics); Data mining; Pattern recognition (psychology); Mathematics; Statistics","score_opus":0.01885862692112788,"score_gpt":0.2740728741851766,"score_spread":0.25521424726404873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394862804","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011485111,0.00040158897,0.9853092,0.00016436145,0.000044355063,0.00027197832,0.000246213,0.0006377157,0.0014395622],"genre_scores_gemma":[0.3506616,0.00069490244,0.63976806,0.00029970697,0.00037369918,0.0012608668,0.0025722736,0.00025929857,0.004109529],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9950917,0.0012096573,0.00050211226,0.00077110494,0.002079631,0.0003458195],"domain_scores_gemma":[0.9940672,0.003403342,0.00045587137,0.0005112236,0.0013704557,0.00019183522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052129747,0.002041048,0.0027535458,0.0048643188,0.00079440785,0.0024998183,0.0020421748,0.0015156204,0.0025874746],"category_scores_gemma":[0.015965495,0.00059684593,0.0025009268,0.003954451,0.0011130531,0.0017658822,0.0020569104,0.0017128624,0.001121756],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00089050893,0.0002420198,0.004036619,0.0004606986,0.00036574807,0.0004690473,0.00016485363,0.23819059,0.01132775,0.025997873,0.008701055,0.7091532],"study_design_scores_gemma":[0.00013115721,0.0002559493,0.0019506857,0.000048831458,0.000105542465,0.00024609594,0.000039667226,0.96332884,0.0067104986,0.022265563,0.0048629516,0.000054221044],"about_ca_topic_score_codex":0.0023014983,"about_ca_topic_score_gemma":0.0013103948,"teacher_disagreement_score":0.0052129747,"about_ca_system_score_codex":0.0010088105,"about_ca_system_score_gemma":0.0019520806,"threshold_uncertainty_score":0.027569175},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.042755576037026975,"score_gpt":0.33400078138952005,"score_spread":0.2912452053524931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396886508","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009992749,0.26234147,0.6530475,0.0048023555,0.0005292224,0.00094129494,0.005453424,0.028720539,0.03417145],"genre_scores_gemma":[0.047398943,0.21793886,0.7016841,0.0040038824,0.00084849406,0.0018032391,0.010954658,0.0057541346,0.009613626],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9929212,0.0021452259,0.0010852385,0.00068439584,0.0029200637,0.00024383624],"domain_scores_gemma":[0.96929306,0.024292333,0.00082355214,0.0020270203,0.0031368434,0.00042726236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009524159,0.0016481135,0.0018571854,0.008704691,0.0007255728,0.007277838,0.003302865,0.0016380419,0.011427456],"category_scores_gemma":[0.02837188,0.0010964198,0.0016517406,0.0100739775,0.0013943851,0.014924523,0.0030291984,0.0025549752,0.004918026],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022465758,0.00018640191,0.002273111,0.0108728735,0.00013525161,0.00021088793,0.0030878682,0.0015310304,0.006245496,0.062071644,0.07334028,0.83982056],"study_design_scores_gemma":[0.00005092949,0.0001457877,0.0023054185,0.0044633523,0.00010732266,0.0013518287,0.0012813378,0.012866205,0.0066021276,0.044759378,0.925866,0.00020033156],"about_ca_topic_score_codex":0.0022291765,"about_ca_topic_score_gemma":0.0017109596,"teacher_disagreement_score":0.011427456,"about_ca_system_score_codex":0.0013983692,"about_ca_system_score_gemma":0.001582293,"threshold_uncertainty_score":0.050369143},"labels":[],"label_agreement":null},{"id":"W4400033029","doi":"10.1109/tkde.2024.3419449","title":"Hessian Aware Low-Rank Perturbation for Order-Robust Continual Learning","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Geophysical Methods and Applications","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; McGill University; Vector Institute; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Hessian matrix; Perturbation (astronomy); Artificial intelligence; Mathematical optimization; Machine learning; Mathematics; Applied mathematics","score_opus":0.025899535669202722,"score_gpt":0.28029992811947274,"score_spread":0.25440039245027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400033029","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010634783,0.00038409155,0.9865455,0.00018768999,0.00004657502,0.000051774285,0.00007578691,0.0012003221,0.0008735953],"genre_scores_gemma":[0.5507675,0.00049013156,0.4401124,0.00047519,0.00021653975,0.00028707736,0.0008556178,0.0005223069,0.006273283],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988526,0.0002796941,0.00006924209,0.00028975087,0.0003879596,0.000120696204],"domain_scores_gemma":[0.9973374,0.0012002393,0.00026989036,0.0005170381,0.00052572147,0.00014973446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022210642,0.0018565977,0.0016674211,0.00094516866,0.0006653883,0.001260616,0.0022796297,0.0017781969,0.0024546655],"category_scores_gemma":[0.008421745,0.0006901497,0.00085121556,0.00088742736,0.001720172,0.0022173221,0.0018256173,0.0030406439,0.0013035198],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025583713,0.00021258608,0.0010036911,0.00019218065,0.000097007076,0.0001260057,0.00011571151,0.7649853,0.0065822382,0.010297414,0.0049072215,0.21122488],"study_design_scores_gemma":[0.000006846312,0.000034324334,0.00007088535,0.0000048161455,0.0000038052008,0.000017957867,0.000005787356,0.9951931,0.0008233324,0.0035227835,0.00030980443,0.000006617384],"about_ca_topic_score_codex":0.0050241333,"about_ca_topic_score_gemma":0.005953205,"teacher_disagreement_score":0.0050241333,"about_ca_system_score_codex":0.0012196283,"about_ca_system_score_gemma":0.0017816527,"threshold_uncertainty_score":0.011746228},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.018792428517041014,"score_gpt":0.2692210126805711,"score_spread":0.2504285841635301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400033057","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011268288,0.00044390355,0.98730755,0.00013127121,0.000026479769,0.000043210734,0.00009944229,0.00014753365,0.0005323414],"genre_scores_gemma":[0.6771804,0.00097148056,0.31854996,0.00026508077,0.00020571265,0.0003628865,0.0009066692,0.000096972,0.0014609228],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99598557,0.001059379,0.00035129438,0.0006738567,0.0017219204,0.00020786366],"domain_scores_gemma":[0.9965953,0.0020196512,0.00036813781,0.0003360453,0.0005740916,0.000106771804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035883598,0.000963534,0.001507117,0.0029199729,0.00081040466,0.0016564857,0.0014498291,0.000876471,0.0009418677],"category_scores_gemma":[0.00921812,0.00029597967,0.0017419421,0.0022195703,0.001315421,0.0025257405,0.0018499936,0.0011297603,0.00014129799],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035856685,0.00012927278,0.0076623564,0.0004939198,0.000626958,0.00035157517,0.00034536846,0.48653817,0.010412239,0.092109814,0.0036736033,0.39729813],"study_design_scores_gemma":[0.000022656057,0.000109815126,0.002209519,0.000033615877,0.0000690113,0.00013265107,0.000055161774,0.94507635,0.003997188,0.04639456,0.0018458097,0.000053733598],"about_ca_topic_score_codex":0.0031915104,"about_ca_topic_score_gemma":0.0018673055,"teacher_disagreement_score":0.0035883598,"about_ca_system_score_codex":0.0014360559,"about_ca_system_score_gemma":0.0013445606,"threshold_uncertainty_score":0.018977284},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.01660452875484313,"score_gpt":0.26392672422544633,"score_spread":0.2473221954706032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400071817","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024301272,0.00018504215,0.9734128,0.00031354552,0.000030273632,0.00001837627,0.00030137567,0.0006611149,0.0007762439],"genre_scores_gemma":[0.7967255,0.0007830239,0.19311805,0.0002478321,0.00012752548,0.00014320078,0.0022322512,0.00019702996,0.0064255884],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995671,0.00011074785,0.000026326705,0.00012275246,0.00010216036,0.00007089045],"domain_scores_gemma":[0.998825,0.00049845816,0.00015526472,0.00021401883,0.00025448762,0.000052731237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001336544,0.0006583259,0.00073469605,0.00094630045,0.00037903173,0.0006605837,0.001497766,0.0010292021,0.0013775175],"category_scores_gemma":[0.0046964707,0.00038060028,0.000984519,0.001755424,0.00063664495,0.0016354371,0.0008282259,0.0016883888,0.0004927144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000970746,0.000073839685,0.002134558,0.00006560802,0.000058422524,0.000108133136,0.00006612719,0.873587,0.0028431232,0.030920258,0.003331183,0.086714596],"study_design_scores_gemma":[9.019355e-7,0.000002836671,0.000083610845,0.0000014326827,0.000002724077,0.0000054369084,0.0000018657233,0.99688196,0.00020924483,0.0026575972,0.00014968879,0.0000026798473],"about_ca_topic_score_codex":0.014129578,"about_ca_topic_score_gemma":0.011364071,"teacher_disagreement_score":0.014129578,"about_ca_system_score_codex":0.0011712116,"about_ca_system_score_gemma":0.001710134,"threshold_uncertainty_score":0.02809465},"labels":[],"label_agreement":null},{"id":"W4400904993","doi":"10.1109/tkde.2024.3432767","title":"One Subgraph for All: Efficient Reasoning on Opening Subgraphs for Inductive Knowledge Graph Completion","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"China Postdoctoral Science Foundation; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Knowledge graph; Subgraph isomorphism problem; Induced subgraph isomorphism problem; Graph; Inductive reasoning; Theoretical computer science; Artificial intelligence; Line graph; Voltage graph","score_opus":0.0577649098250396,"score_gpt":0.3025058440658079,"score_spread":0.2447409342407683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400904993","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063341297,0.00017515289,0.98979807,0.00023301024,0.000022956005,0.00011847188,0.00038769766,0.0021968298,0.00073364034],"genre_scores_gemma":[0.2248367,0.00042146433,0.7649707,0.00039907513,0.00008850302,0.0003676591,0.005340536,0.00052992336,0.0030453017],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977525,0.00049442484,0.0001274713,0.00083931274,0.0005980736,0.00018818404],"domain_scores_gemma":[0.99649185,0.0015061564,0.0003373474,0.0010265873,0.00044724654,0.00019073785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00181579,0.0016434792,0.0016567049,0.0028023233,0.0010599878,0.0014922156,0.0036911692,0.0018266,0.0051176245],"category_scores_gemma":[0.008066889,0.0006908782,0.00281506,0.0027689016,0.0017494414,0.0048456597,0.0037682177,0.0033958345,0.0017796913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022833956,0.00037257446,0.002275139,0.000533672,0.00016111432,0.0006160329,0.0007208472,0.29782093,0.006834484,0.055174537,0.023432676,0.61182976],"study_design_scores_gemma":[0.000024062816,0.000043555137,0.0002306419,0.000029023997,0.00003597059,0.00011611115,0.00012108658,0.9235815,0.0030825308,0.068637,0.004076935,0.000021664291],"about_ca_topic_score_codex":0.008483996,"about_ca_topic_score_gemma":0.012732636,"teacher_disagreement_score":0.008483996,"about_ca_system_score_codex":0.0014201818,"about_ca_system_score_gemma":0.002337858,"threshold_uncertainty_score":0.017120183},"labels":[],"label_agreement":null},{"id":"W4401943123","doi":"10.1109/tkde.2024.3443928","title":"PLBR: A Semi-Supervised Document Key Information Extraction via Pseudo-Labeling Bias Rectification","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Rectification; Key (lock); Artificial intelligence; Information extraction; Information retrieval; Pattern recognition (psychology)","score_opus":0.02764258680815602,"score_gpt":0.2946802442361714,"score_spread":0.2670376574280154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401943123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0092713265,0.0010557283,0.9770454,0.00024683756,0.00013640976,0.00016059728,0.0006958573,0.010104133,0.00128381],"genre_scores_gemma":[0.09746048,0.0006994254,0.8852008,0.00048962666,0.00017867242,0.0003822497,0.0061391713,0.00094316463,0.008506403],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970421,0.0005295197,0.00018823845,0.001129413,0.00090891594,0.00020180292],"domain_scores_gemma":[0.9973399,0.0006121995,0.0003127884,0.0007418186,0.000901045,0.00009217606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019155317,0.0020012285,0.0018156413,0.00247869,0.0008591077,0.0015685337,0.0029815217,0.0018327633,0.003500603],"category_scores_gemma":[0.0048242016,0.00077115727,0.0014196269,0.0024658074,0.0009163525,0.0035297074,0.002440058,0.0025709074,0.006194839],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040561473,0.00014222757,0.00069358794,0.000433892,0.00008440006,0.00013075404,0.00017984118,0.014233131,0.051666252,0.0030291788,0.018128006,0.91087306],"study_design_scores_gemma":[0.00012465996,0.00029228802,0.0015381118,0.00006642726,0.00010209304,0.000609313,0.00019214656,0.8560234,0.10066471,0.012367134,0.027896026,0.00012369575],"about_ca_topic_score_codex":0.0024447876,"about_ca_topic_score_gemma":0.0042050006,"teacher_disagreement_score":0.003500603,"about_ca_system_score_codex":0.00062594085,"about_ca_system_score_gemma":0.0016957113,"threshold_uncertainty_score":0.011710703},"labels":[],"label_agreement":null},{"id":"W4403600950","doi":"10.1109/tkde.2024.3484009","title":"Order-2 Probabilistic Information Fusion on Random Permutation Set","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Random permutation; Probabilistic logic; Permutation (music); Set (abstract data type); Fusion; Theoretical computer science; Artificial intelligence; Data mining; Mathematics; Combinatorics","score_opus":0.023837821536252177,"score_gpt":0.26031453317933057,"score_spread":0.23647671164307837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403600950","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012990463,0.00043483413,0.98210746,0.0002942288,0.000058615897,0.00004395121,0.000099535515,0.00014050312,0.003830376],"genre_scores_gemma":[0.7955025,0.00127278,0.19869493,0.00034213232,0.00022284556,0.00017931213,0.00041142813,0.000069422415,0.0033047074],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962804,0.0009013419,0.00028418214,0.00086106395,0.0013994821,0.00027348797],"domain_scores_gemma":[0.9974185,0.0012503326,0.00034424124,0.00043196205,0.00046064024,0.00009428671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030089954,0.0008799805,0.0011657842,0.002494883,0.0007402841,0.0024774463,0.00129477,0.0010711302,0.0017120489],"category_scores_gemma":[0.0067023747,0.0004243527,0.0017139292,0.0024131415,0.0017871336,0.006070429,0.0021133842,0.001319509,0.00044797556],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002468608,0.000078575635,0.0020182529,0.00026191803,0.00021993076,0.0007144578,0.00055204856,0.1899181,0.0070360024,0.64552206,0.0025074962,0.15092434],"study_design_scores_gemma":[0.000019474714,0.00008812234,0.0008873751,0.000043501954,0.000079856065,0.00031694936,0.00006960734,0.61884916,0.004203242,0.37140262,0.0039624376,0.000077653334],"about_ca_topic_score_codex":0.0015170332,"about_ca_topic_score_gemma":0.00080390665,"teacher_disagreement_score":0.0030089954,"about_ca_system_score_codex":0.0015081428,"about_ca_system_score_gemma":0.0008896951,"threshold_uncertainty_score":0.015913248},"labels":[],"label_agreement":null},{"id":"W4404238465","doi":"10.1109/tkde.2024.3496586","title":"Finding Antagonistic Communities in Signed Uncertain Graphs","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Constraint Satisfaction and Optimization","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"McMaster University","keywords":"Computer science; Signed graph; Theoretical computer science; Graph","score_opus":0.03610903175891978,"score_gpt":0.28217160425459886,"score_spread":0.2460625724956791,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404238465","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09651108,0.00060886884,0.8987963,0.00047360564,0.000034953246,0.00011697764,0.0005537969,0.00045702868,0.0024473707],"genre_scores_gemma":[0.7307159,0.0006445055,0.26343217,0.00031741237,0.00012807972,0.00016142568,0.0019935055,0.00013115881,0.0024758724],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984646,0.0004417927,0.000082593455,0.00044503296,0.00044714325,0.0001188033],"domain_scores_gemma":[0.9950818,0.002613518,0.0010851921,0.00043874545,0.00050481234,0.000275893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013463226,0.0011661851,0.0010400425,0.0027186743,0.0013055322,0.0014076983,0.0016644234,0.0014781788,0.0012728017],"category_scores_gemma":[0.009047104,0.000643951,0.0010701219,0.002106952,0.0011799431,0.003413264,0.0017300089,0.0011860298,0.00034744517],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042935106,0.00017463313,0.013545353,0.00045503385,0.00023071078,0.001325648,0.0007183108,0.69234973,0.008503641,0.06972886,0.0067222845,0.20581654],"study_design_scores_gemma":[0.000016704282,0.000026607308,0.0009457002,0.000018373237,0.000023040304,0.00021599873,0.00012532537,0.91217744,0.0012214729,0.08340582,0.0018073068,0.000016197728],"about_ca_topic_score_codex":0.0039797593,"about_ca_topic_score_gemma":0.004774017,"teacher_disagreement_score":0.0039797593,"about_ca_system_score_codex":0.0009741019,"about_ca_system_score_gemma":0.0007660902,"threshold_uncertainty_score":0.007913232},"labels":[],"label_agreement":null},{"id":"W4405838316","doi":"10.1109/tkde.2024.3523857","title":"A Survey of Change Point Detection in Dynamic Graphs","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Point (geometry); Mathematics","score_opus":0.027271724777452266,"score_gpt":0.268731027236579,"score_spread":0.24145930245912672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405838316","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038047418,0.17413843,0.7419581,0.0027788195,0.0007515581,0.0005495675,0.015368603,0.008653744,0.017753696],"genre_scores_gemma":[0.3545699,0.15024251,0.44268933,0.001795114,0.0014825816,0.0007887015,0.041222196,0.0016851373,0.0055245147],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952329,0.00090650853,0.00051184406,0.0015780362,0.0015523093,0.00021841448],"domain_scores_gemma":[0.9852329,0.008989572,0.0012182284,0.0018064873,0.0024837735,0.0002690243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027530116,0.001873193,0.0018644016,0.012855703,0.0008731023,0.0027582138,0.0028418787,0.0016971277,0.0019378636],"category_scores_gemma":[0.020439077,0.00082429516,0.00193447,0.01673757,0.0009952111,0.0050307857,0.0013452587,0.0011725533,0.0014605514],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018907356,0.00014831993,0.023523133,0.005323164,0.00032870835,0.000266534,0.00042353076,0.035089925,0.0028452044,0.016678462,0.03888765,0.8762963],"study_design_scores_gemma":[0.000056149456,0.0004001225,0.044237897,0.0028741807,0.00066998386,0.0028660349,0.0016123152,0.41464612,0.014584442,0.1296467,0.38797805,0.00042799322],"about_ca_topic_score_codex":0.009647383,"about_ca_topic_score_gemma":0.0085439915,"teacher_disagreement_score":0.012855703,"about_ca_system_score_codex":0.0012773095,"about_ca_system_score_gemma":0.0015070947,"threshold_uncertainty_score":0.019182444},"labels":[],"label_agreement":null},{"id":"W4406890913","doi":"10.1109/tkde.2025.3527380","title":"Computing Shapley Values for Dynamic Data","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Data mining","score_opus":0.031760860730233605,"score_gpt":0.31844716841906573,"score_spread":0.28668630768883213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406890913","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042587996,0.00026023007,0.9512601,0.0005085382,0.00007096573,0.00015754245,0.00025246403,0.00033749267,0.00456468],"genre_scores_gemma":[0.56651235,0.00040931228,0.42568332,0.0003333021,0.00012634903,0.00036468057,0.001015503,0.00023691662,0.005318293],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962792,0.0013733428,0.0002330244,0.0009796894,0.00079797953,0.00033681237],"domain_scores_gemma":[0.9886777,0.0076191747,0.00067202083,0.0015498642,0.0009243737,0.000556885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005810303,0.0016506762,0.0022837352,0.0022746443,0.0015617098,0.004341244,0.0029183824,0.002131727,0.006887015],"category_scores_gemma":[0.025541136,0.0008974206,0.0015241976,0.0031024108,0.0023772663,0.009851926,0.0044760886,0.003601003,0.0008336588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023614835,0.00019628686,0.0016293062,0.00024737327,0.0001753221,0.0001493951,0.00034572821,0.52546054,0.0015833497,0.35478565,0.003804387,0.11138655],"study_design_scores_gemma":[0.000022326982,0.00003641158,0.00010706276,0.000017820072,0.0000124805565,0.000028686136,0.00004821745,0.60698974,0.00067426154,0.39122462,0.0008224511,0.000015823733],"about_ca_topic_score_codex":0.0016395568,"about_ca_topic_score_gemma":0.0024424815,"teacher_disagreement_score":0.006887015,"about_ca_system_score_codex":0.0035868357,"about_ca_system_score_gemma":0.0024340139,"threshold_uncertainty_score":0.030728221},"labels":[],"label_agreement":null},{"id":"W4408358653","doi":"10.1109/tkde.2025.3550877","title":"Correlating Time Series With Interpretable Convolutional Kernels","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"U.S. Department of Energy","keywords":"Computer science; Series (stratigraphy); Kernel (algebra); Artificial intelligence; Convolutional neural network; Time series; Pattern recognition (psychology); Machine learning; Mathematics","score_opus":0.00925635699884033,"score_gpt":0.22123404702606728,"score_spread":0.21197769002722694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408358653","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16784003,0.0004858738,0.82909787,0.0004167723,0.00005741743,0.000026977406,0.00037835777,0.00067130564,0.0010254333],"genre_scores_gemma":[0.9209592,0.0005409113,0.07584905,0.00009013253,0.00006840371,0.000030160858,0.00084946794,0.000099453944,0.0015132389],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99954766,0.00010855439,0.000034141904,0.00014834868,0.000093629285,0.0000675993],"domain_scores_gemma":[0.9981735,0.0008490778,0.0003707801,0.0002827514,0.00026432378,0.000059579095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011244944,0.0008149395,0.00048205594,0.0010365868,0.00023517931,0.00093418127,0.00061961124,0.0006941073,0.00068716315],"category_scores_gemma":[0.0066799866,0.00035552977,0.00067033194,0.0012708851,0.00066435017,0.0019942247,0.00090339646,0.0012678602,0.00029218846],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026648896,0.0001358338,0.018474359,0.0001745733,0.00016775267,0.00034264327,0.00027011216,0.74873555,0.025826659,0.031119939,0.0027108956,0.17177513],"study_design_scores_gemma":[0.0000017717492,0.000008599452,0.0012115078,0.0000046983837,0.000006920147,0.000019581565,0.0000107832375,0.9918296,0.0013021651,0.0052926536,0.00030516743,0.0000065356135],"about_ca_topic_score_codex":0.0053395014,"about_ca_topic_score_gemma":0.005429824,"teacher_disagreement_score":0.0053395014,"about_ca_system_score_codex":0.00075072737,"about_ca_system_score_gemma":0.0007206001,"threshold_uncertainty_score":0.010616839},"labels":[],"label_agreement":null},{"id":"W4413785340","doi":"10.1109/tkde.2025.3603594","title":"Multi-View Clustering via High-Order Bipartite Graph Learning and Tensor Low-Rank Representation","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Computer science; Cluster analysis; Bipartite graph; Representation (politics); Graph; Tensor (intrinsic definition); Rank (graph theory); Artificial intelligence; Theoretical computer science; Pattern recognition (psychology); Combinatorics; Mathematics","score_opus":0.021527688451080735,"score_gpt":0.28638668068049006,"score_spread":0.26485899222940934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413785340","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034536584,0.00012972933,0.9950917,0.00007192051,0.000018420089,0.000022777163,0.000078741636,0.0006837856,0.0004492727],"genre_scores_gemma":[0.21201931,0.0005873595,0.78107107,0.00029149922,0.00012213363,0.00020664674,0.0020254038,0.0005611177,0.0031153786],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978241,0.0006333624,0.000092747534,0.0006699836,0.0005905963,0.00018927896],"domain_scores_gemma":[0.99796367,0.00045263834,0.00032272033,0.0005249875,0.0005925911,0.00014343113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015032872,0.0021687534,0.0019235811,0.0029140483,0.0010241688,0.0017756603,0.002492557,0.0016272848,0.0018821732],"category_scores_gemma":[0.0047267247,0.0007998496,0.0018654703,0.003384142,0.0012049938,0.0027025987,0.0020184857,0.0022563557,0.0017388196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026625994,0.00019975126,0.0021048007,0.00043648205,0.00034981788,0.00024079555,0.00040857823,0.4458855,0.03397177,0.04488394,0.01464568,0.4566067],"study_design_scores_gemma":[0.000007557191,0.000028490393,0.000258704,0.000008365502,0.000020231902,0.00007234042,0.000038277805,0.98247874,0.0030975072,0.012744142,0.0012169826,0.000028681248],"about_ca_topic_score_codex":0.00889748,"about_ca_topic_score_gemma":0.01159869,"teacher_disagreement_score":0.00889748,"about_ca_system_score_codex":0.0011106414,"about_ca_system_score_gemma":0.0018312521,"threshold_uncertainty_score":0.017691374},"labels":[],"label_agreement":null},{"id":"W4414116777","doi":"10.1109/tkde.2025.3609302","title":"Flexible Keyword-Aware Top-$k$k Route Search","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Science Foundation of Shandong Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Process (computing); Sequence (biology); Route planning; Semantics (computer science); Point of interest","score_opus":0.028948581485631814,"score_gpt":0.29190815446982205,"score_spread":0.26295957298419026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414116777","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0825481,0.0013655962,0.887858,0.00058160623,0.00009547752,0.0003675386,0.0036061353,0.01733654,0.0062411586],"genre_scores_gemma":[0.47933358,0.00035787938,0.50814044,0.0002888191,0.000053233554,0.00018040679,0.0062864446,0.0012664322,0.0040927944],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998259,0.00035399888,0.00019330853,0.0005046014,0.0004718151,0.00021734118],"domain_scores_gemma":[0.9975932,0.0009357628,0.00019700588,0.0007205647,0.00041320975,0.00014011157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00091934775,0.0014972272,0.002297961,0.0016587906,0.0010514861,0.00211139,0.002989142,0.0016532133,0.005234547],"category_scores_gemma":[0.005349002,0.0007628963,0.0015707166,0.0028411774,0.0006554436,0.004431242,0.003248558,0.0011435356,0.0030520845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017830962,0.00064096064,0.008869327,0.0014403767,0.00041227654,0.0012335366,0.0014376506,0.33428714,0.051759124,0.027504994,0.048078734,0.5225528],"study_design_scores_gemma":[0.00008142105,0.0001942849,0.00074937125,0.000023037439,0.00007671417,0.000661186,0.00056121463,0.9505915,0.011404437,0.0277558,0.007831033,0.00006987583],"about_ca_topic_score_codex":0.007964812,"about_ca_topic_score_gemma":0.019373769,"teacher_disagreement_score":0.007964812,"about_ca_system_score_codex":0.0008993243,"about_ca_system_score_gemma":0.0016501381,"threshold_uncertainty_score":0.017511308},"labels":[],"label_agreement":null},{"id":"W4414270260","doi":"10.1109/tkde.2025.3611170","title":"A Multi-Objective Explanation Framework for Graph Neural Networks","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Natural Science Foundation of Shandong Province; National Natural Science Foundation of China","keywords":"Focus (optics); Graph; Artificial neural network; Attribution; Graph theory; Data modeling; Pareto principle","score_opus":0.03820802667668711,"score_gpt":0.31086400128210495,"score_spread":0.27265597460541785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414270260","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007868742,0.00040101024,0.98903054,0.0004489014,0.000024147435,0.00006141052,0.0001502107,0.0002362567,0.0017787875],"genre_scores_gemma":[0.4958695,0.00081376295,0.49747214,0.0002730755,0.00010674838,0.0004918156,0.0006836096,0.00013355477,0.0041557653],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990845,0.00046633772,0.00004745498,0.00018084835,0.00015901879,0.00006187721],"domain_scores_gemma":[0.9982692,0.001144347,0.00019500678,0.00009907545,0.00023235253,0.000060001188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017322007,0.001178686,0.0005762813,0.0014575357,0.00046886946,0.0010794973,0.001529326,0.0010912197,0.0032461607],"category_scores_gemma":[0.004623385,0.000331735,0.0011632922,0.0010504844,0.0007487276,0.0016414031,0.0014044564,0.0014745593,0.0002351959],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039083297,0.000056627905,0.0016907881,0.00018530464,0.00012504713,0.00015171421,0.00022014853,0.79930246,0.0008648199,0.113975465,0.001655881,0.08173268],"study_design_scores_gemma":[0.0000082566885,0.000022229262,0.0002258181,0.00002303889,0.000020597741,0.00001858554,0.000018723485,0.9436304,0.00020347725,0.054850426,0.00097031955,0.000008118338],"about_ca_topic_score_codex":0.0066979346,"about_ca_topic_score_gemma":0.008810559,"teacher_disagreement_score":0.0066979346,"about_ca_system_score_codex":0.0015472575,"about_ca_system_score_gemma":0.0011978168,"threshold_uncertainty_score":0.013317883},"labels":[],"label_agreement":null},{"id":"W4414908411","doi":"10.1109/tkde.2025.3618763","title":"Breaking Information Granularity Heterogeneity: A Mutual Information-Inspired Causal Discovery Framework for Multi-Rate Time Series","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Granularity; Sampling (signal processing); Key (lock); Time series; Mutual information; Series (stratigraphy); Encoder; Information theory","score_opus":0.02118411617827084,"score_gpt":0.2668840398867101,"score_spread":0.24569992370843927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414908411","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003998499,0.00044667418,0.99329835,0.00077587325,0.00004739454,0.000069458416,0.00017603833,0.0002055739,0.0009821282],"genre_scores_gemma":[0.45717442,0.0013490624,0.53495884,0.00073111436,0.00064712024,0.0007369069,0.0009837066,0.00021522159,0.0032035888],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98827565,0.0066804443,0.000659858,0.0022102126,0.0017355869,0.00043828934],"domain_scores_gemma":[0.95191747,0.038619358,0.004318065,0.0028950109,0.001509424,0.00074064685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02085849,0.0015125177,0.0029622668,0.0053509097,0.0014833807,0.004216587,0.005863009,0.0032307396,0.0031267505],"category_scores_gemma":[0.049599383,0.001351182,0.004002418,0.0050525763,0.0026486132,0.007011211,0.0051721088,0.005123002,0.00041005484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022336756,0.00017442755,0.0050574965,0.00044581838,0.0007430838,0.00052540115,0.00067565026,0.3971559,0.0010442793,0.48144493,0.0034870014,0.10902261],"study_design_scores_gemma":[0.000024311948,0.000034577188,0.00045272132,0.000032531058,0.00007180868,0.00006208984,0.00003233027,0.80671185,0.00026122207,0.19041067,0.0018699169,0.00003592251],"about_ca_topic_score_codex":0.0044969385,"about_ca_topic_score_gemma":0.003577619,"teacher_disagreement_score":0.02085849,"about_ca_system_score_codex":0.0027541574,"about_ca_system_score_gemma":0.0027433948,"threshold_uncertainty_score":0.11031157},"labels":[],"label_agreement":null},{"id":"W4415221793","doi":"10.1109/tkde.2025.3621851","title":"A Causal Perspective of Stock Prediction Models","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Spurious relationship; Generalizability theory; Causal model; Stock market; Predictive modelling; Mean squared prediction error; Perspective (graphical); Predictive power; Stock (firearms)","score_opus":0.12024319050058595,"score_gpt":0.3983024348601164,"score_spread":0.27805924435953044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415221793","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008220462,0.0006866829,0.9837336,0.0027834885,0.00008442008,0.000028579418,0.0002260097,0.00017807777,0.0040588006],"genre_scores_gemma":[0.74210256,0.0037624384,0.24346136,0.0014355598,0.0011792692,0.00029836706,0.0007826639,0.00016420247,0.006813637],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968701,0.0015085619,0.00015141854,0.0006260426,0.00064949674,0.00019446437],"domain_scores_gemma":[0.9804049,0.014922815,0.0016573246,0.0017228732,0.0010054568,0.00028658332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053916564,0.0011554989,0.0009900451,0.0024407164,0.0009191734,0.0026005718,0.0030423934,0.0025435197,0.005527333],"category_scores_gemma":[0.03523074,0.0008614718,0.0018412232,0.0022940964,0.0028031,0.00589752,0.002853831,0.004598545,0.0004880532],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031525637,0.00005292042,0.0018398792,0.000108111984,0.0000739911,0.00016553371,0.00017211551,0.28410468,0.0003328753,0.6867379,0.0012105908,0.025169905],"study_design_scores_gemma":[0.000010697734,0.000017688673,0.00023701186,0.0000263139,0.000019237805,0.0000336609,0.00002251754,0.5512747,0.00017590052,0.44665432,0.001513981,0.000013985434],"about_ca_topic_score_codex":0.006380967,"about_ca_topic_score_gemma":0.00364219,"teacher_disagreement_score":0.006380967,"about_ca_system_score_codex":0.0018527657,"about_ca_system_score_gemma":0.001824006,"threshold_uncertainty_score":0.028514147},"labels":[],"label_agreement":null},{"id":"W4416873169","doi":"10.1109/tkde.2025.3638821","title":"A Log-Likelihood Chain Framework for Defending Against LDP Data Poisoning Attacks","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Internet Traffic Analysis and Secure E-voting","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; Fundamental Research Funds for the Central Universities; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Differential privacy; Categorical variable; Anomaly detection; Intrusion detection system; Skew; Data modeling; Privacy protection; Denial-of-service attack","score_opus":0.03431367048434421,"score_gpt":0.30368963994464293,"score_spread":0.26937596946029874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416873169","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068331785,0.00043985894,0.99053496,0.00026557376,0.000027503718,0.0000602179,0.00011202777,0.0007717078,0.00095482497],"genre_scores_gemma":[0.66406333,0.0010838342,0.32419246,0.0005349479,0.000429921,0.0004297407,0.0014304157,0.00036513235,0.007470163],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99578166,0.0017055223,0.00019995759,0.0008141427,0.001166433,0.00033239755],"domain_scores_gemma":[0.98939276,0.006648409,0.0011495685,0.0013558383,0.0010760376,0.00037734813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063932864,0.0014344184,0.0021971455,0.0028436992,0.0009679252,0.0030131196,0.0031021247,0.0023024378,0.0032862988],"category_scores_gemma":[0.018449273,0.0008013571,0.0012332464,0.002097584,0.0023178493,0.005224243,0.004248424,0.0033076624,0.0018190457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006902051,0.00026919923,0.009126791,0.0002792774,0.00024281585,0.0005950811,0.00036030257,0.6719401,0.0058332854,0.07944053,0.0057993964,0.22542301],"study_design_scores_gemma":[0.00001604311,0.000042279135,0.00019903152,0.000010074279,0.000012105737,0.00007442635,0.000013683455,0.97821915,0.0008470714,0.0196108,0.00093876466,0.000016462764],"about_ca_topic_score_codex":0.0027374679,"about_ca_topic_score_gemma":0.0022429824,"teacher_disagreement_score":0.0063932864,"about_ca_system_score_codex":0.001397162,"about_ca_system_score_gemma":0.0019656557,"threshold_uncertainty_score":0.03381133},"labels":[],"label_agreement":null},{"id":"W7084580536","doi":"10.1109/tkde.2025.3617583","title":"Adaptive Hyper-Box Granulation With Justifiable Granularity for Feature Selection","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Plant Parasitism and Resistance","field":"Agricultural and Biological Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Science Foundation of Chongqing; National Natural Science Foundation of China","keywords":"Cluster analysis; Granularity; Feature selection; CURE data clustering algorithm; Feature (linguistics); Correlation clustering; Constrained clustering; Partition (number theory); Canopy clustering algorithm","score_opus":0.018823306022998865,"score_gpt":0.23718832009148672,"score_spread":0.21836501406848785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7084580536","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03004086,0.00031162464,0.96845925,0.00010707859,0.000030360668,0.00007988778,0.00009182295,0.00050242257,0.00037671434],"genre_scores_gemma":[0.48001608,0.00029030754,0.5173602,0.00018807802,0.00008650446,0.00042220086,0.000653526,0.00012118068,0.0008619174],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854016,0.00035007735,0.00013415646,0.00029505263,0.0005427707,0.00013771429],"domain_scores_gemma":[0.99772674,0.0012571778,0.00022071258,0.0003238117,0.00040454965,0.00006703519],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017677785,0.0007056237,0.0014726192,0.001556628,0.0006180707,0.0011377237,0.00119428,0.00096856867,0.0012213856],"category_scores_gemma":[0.006847593,0.00030000106,0.0011555711,0.0018402279,0.0008453417,0.0015484815,0.0011989778,0.0009850257,0.00032574375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071787194,0.00020763399,0.006082587,0.00029056377,0.0001784817,0.0003073241,0.0004395402,0.35943207,0.02920691,0.017813684,0.0048026494,0.5805206],"study_design_scores_gemma":[0.000048531623,0.000077494835,0.0013090101,0.000019435238,0.000027406695,0.00009197177,0.00004616228,0.9823782,0.00504831,0.009363959,0.0015668017,0.000022725477],"about_ca_topic_score_codex":0.0023948208,"about_ca_topic_score_gemma":0.0018263776,"teacher_disagreement_score":0.0023948208,"about_ca_system_score_codex":0.0006754346,"about_ca_system_score_gemma":0.0009222395,"threshold_uncertainty_score":0.009349048},"labels":[],"label_agreement":null},{"id":"W7104533847","doi":"10.1109/tkde.2025.3631025","title":"Region Embedding With Adaptive Correlation Discovery for Predicting Urban Socioeconomic Indicators","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China; Ministry of Natural Resources","keywords":"Embedding; Feature learning; ENCODE; Representation (politics); Feature (linguistics); Graph","score_opus":0.01794958544766521,"score_gpt":0.2882866304678555,"score_spread":0.2703370450201903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7104533847","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059688203,0.00083882886,0.93594426,0.00017534698,0.000041646093,0.000058506346,0.00080937124,0.0014872844,0.00095664244],"genre_scores_gemma":[0.730403,0.0007881343,0.26334265,0.00010942562,0.00008672078,0.00012762225,0.0029989858,0.00021118869,0.0019322085],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993166,0.00019714607,0.000026460919,0.00027344615,0.00011500043,0.0000714577],"domain_scores_gemma":[0.99902487,0.00040312484,0.00016913592,0.00016720068,0.0001915536,0.00004419789],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006016957,0.0012040203,0.0008540925,0.0021024144,0.0002444518,0.0005629537,0.0013080711,0.0007221207,0.000876276],"category_scores_gemma":[0.002733651,0.0003770514,0.0009598113,0.002683658,0.00043073608,0.0017686455,0.0011780474,0.0010508703,0.0005754108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042749828,0.00029309283,0.017983671,0.00031595226,0.00033085427,0.00034101214,0.0002646175,0.50832015,0.012748861,0.014580354,0.01073093,0.43366298],"study_design_scores_gemma":[0.000007671755,0.000033097305,0.0018621666,0.000010675584,0.00003456449,0.000071858536,0.000041970914,0.9881126,0.0023120467,0.00622658,0.0012688723,0.0000178488],"about_ca_topic_score_codex":0.005331004,"about_ca_topic_score_gemma":0.007156203,"teacher_disagreement_score":0.005331004,"about_ca_system_score_codex":0.00048175533,"about_ca_system_score_gemma":0.0005624437,"threshold_uncertainty_score":0.010599971},"labels":[],"label_agreement":null}]}