{"meta":{"query_hash":"c4fafddebffc","filters":{"venue":"The VLDB Journal"},"cohort_total":59,"direct_labels_cover":0,"predictions_cover":59,"exported":59,"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/c4fafddebffc","api":"https://metacan.xera.ac/api/v1/cohort?venue=The+VLDB+Journal"},"results":[{"id":"W1974932383","doi":"10.1007/s00778-011-0228-8","title":"Elastic SI-Cache: consistent and scalable caching in multi-tier architectures","year":2011,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Cache; Scalability; Cloud computing; Smart Cache; Distributed computing; Cache invalidation; Cache coloring; Cache algorithms; Benchmark (surveying); Software deployment; Operating system; CPU cache","score_opus":0.03874119627521677,"score_gpt":0.23404084669650793,"score_spread":0.19529965042129116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974932383","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9066166,0.000717523,0.09010724,0.0009442485,0.00029245476,0.00008419785,1.3866816e-7,0.00003763028,0.0011999409],"genre_scores_gemma":[0.9897119,0.000010325611,0.009570578,0.00029560147,0.00006729673,0.0000014894583,2.5204711e-8,0.0000064404485,0.0003363525],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893796,0.00019615999,0.00021430467,0.00017511625,0.00018792153,0.00028852635],"domain_scores_gemma":[0.99942434,0.00011383024,0.00009549522,0.00025427982,0.000020797845,0.00009123496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009628779,0.000110610075,0.00012362,0.00012977881,0.000300729,0.00016100415,0.0006155982,0.000028335146,0.000008530581],"category_scores_gemma":[0.00004243954,0.00006561685,0.00004831019,0.0001577373,0.00007816981,0.000015807991,0.00032235216,0.00047741248,0.000009189101],"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":[0.00014528497,0.0011468031,0.06847589,0.00012773304,0.00046933105,0.0011865817,0.11856188,0.24388824,0.0012996853,0.012780956,0.0015950531,0.55032253],"study_design_scores_gemma":[0.0017098176,0.00020852762,0.18373258,0.00024562873,0.000038076676,0.0017804962,0.0006172302,0.8024429,0.0002444639,0.0066711227,0.0019111586,0.00039801118],"about_ca_topic_score_codex":0.00008012759,"about_ca_topic_score_gemma":0.000021687323,"teacher_disagreement_score":0.55855465,"about_ca_system_score_codex":0.00002437623,"about_ca_system_score_gemma":0.000020733054,"threshold_uncertainty_score":0.26757774},"labels":[],"label_agreement":null},{"id":"W1977320861","doi":"10.1007/s00778-004-0136-2","title":"Preserving mapping consistency under schema changes","year":2004,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":false,"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; Schema (genetic algorithms); Rewriting; Conceptual schema; Theoretical computer science; Semantics (computer science); Information retrieval; Programming language","score_opus":0.05595234486683632,"score_gpt":0.2594263878383082,"score_spread":0.20347404297147187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977320861","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23783568,0.003947163,0.6516857,0.097449444,0.0012548208,0.00011551781,2.6370898e-7,0.00017736775,0.0075340043],"genre_scores_gemma":[0.96999574,0.00017794369,0.027602514,0.0016106241,0.00036425423,0.0000023025616,6.65987e-8,0.0000058736887,0.00024065735],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991664,0.000054639877,0.00014426695,0.00012391646,0.00023382419,0.0002769505],"domain_scores_gemma":[0.99932116,0.00009007427,0.00010392402,0.00035962113,0.0000649216,0.000060274928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005438649,0.00008815133,0.0001106276,0.000071089606,0.00043104903,0.00029298864,0.0011367056,0.000034499186,0.000023156104],"category_scores_gemma":[0.00007999302,0.000052187774,0.000053906966,0.00019381408,0.00007037903,0.00026134436,0.00028123497,0.0002372122,0.00003928179],"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":[0.000025202295,0.0002511962,0.0034556363,0.000090730326,0.00043774676,0.00064796605,0.023876568,0.0038473904,0.031515863,0.8259058,0.010083808,0.09986209],"study_design_scores_gemma":[0.0023833984,0.00026818947,0.043494165,0.00062404264,0.00004706354,0.0075599086,0.006995878,0.004566762,0.022682944,0.89388573,0.016716212,0.0007757014],"about_ca_topic_score_codex":0.000025273013,"about_ca_topic_score_gemma":0.00003296142,"teacher_disagreement_score":0.7321601,"about_ca_system_score_codex":0.00004012847,"about_ca_system_score_gemma":0.00010299655,"threshold_uncertainty_score":0.33153242},"labels":[],"label_agreement":null},{"id":"W1988668397","doi":"10.1007/s00778-007-0058-x","title":"Temporal XML: modeling, indexing, and query processing","year":2007,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":false,"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; XPath; Information retrieval; Search engine indexing; Query language; XML database; XML validation; Streaming XML; XML; Temporal database; Document Structure Description; Data mining; World Wide Web","score_opus":0.01980670494016319,"score_gpt":0.2688788118537077,"score_spread":0.24907210691354453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988668397","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07542167,0.0013310154,0.9220118,0.00042349868,0.00021938828,0.000043334345,6.1447827e-7,0.000044596873,0.00050409575],"genre_scores_gemma":[0.92287284,0.000041614225,0.07626171,0.00026424805,0.00039435085,8.8339266e-7,3.8140303e-7,0.000008682094,0.00015528193],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906826,0.000036774323,0.0002575701,0.0001381554,0.00023676749,0.00026245083],"domain_scores_gemma":[0.99942863,0.000028624683,0.00014665737,0.00021321801,0.00007636434,0.0001065162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001406971,0.00009594926,0.000105519845,0.00007213592,0.00051399396,0.00017731881,0.00030446623,0.000030248975,0.0000030232504],"category_scores_gemma":[0.00003067149,0.00005758015,0.000028534689,0.00015106756,0.00005630378,0.00091442507,0.00015957598,0.00029564032,0.0000036779206],"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":[0.00010872465,0.000113200964,0.011650891,0.00012101511,0.00007526488,0.00054858637,0.014198875,0.0062880367,0.002992651,0.2641085,0.0022593339,0.6975349],"study_design_scores_gemma":[0.0013936192,0.00023264937,0.0021998233,0.00066177815,0.000024468605,0.010143333,0.0024299156,0.78780526,0.0015765253,0.035997063,0.15662453,0.0009110165],"about_ca_topic_score_codex":0.000040841445,"about_ca_topic_score_gemma":0.000030585747,"teacher_disagreement_score":0.8474512,"about_ca_system_score_codex":0.000021378788,"about_ca_system_score_gemma":0.00007761713,"threshold_uncertainty_score":0.3953278},"labels":[],"label_agreement":null},{"id":"W1995541812","doi":"10.1007/s00778-009-0161-2","title":"Creating probabilistic databases from duplicated data","year":2009,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":61,"is_retracted":false,"has_abstract":false,"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; Probabilistic logic; Data mining; Scalability; Data deduplication; Task (project management); Cluster analysis; Database; String (physics); Probabilistic database; Information retrieval; Machine learning; Artificial intelligence; Database theory; Relational database","score_opus":0.47988074415434634,"score_gpt":0.47707972753851563,"score_spread":0.0028010166158307093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995541812","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5293232,0.0024235547,0.29970905,0.11263835,0.0023009914,0.0012078404,0.0038811231,0.000291307,0.048224542],"genre_scores_gemma":[0.9837586,0.00013517753,0.008627635,0.0044257157,0.0009578771,0.0000020623975,0.00033766124,0.00001003771,0.0017452181],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972023,0.000427707,0.00063121796,0.00036957616,0.0011368819,0.00023231217],"domain_scores_gemma":[0.99543417,0.0015396734,0.00036138826,0.0024319235,0.000117250085,0.00011561006],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0078893,0.00010474284,0.00018366906,0.00008003911,0.00054754975,0.0008991892,0.003927862,0.000017288223,0.0011956808],"category_scores_gemma":[0.0072119026,0.000053632048,0.000042746473,0.00040196124,0.000089754525,0.0009507232,0.0007711769,0.0002714593,0.0005578696],"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":[0.0000921679,0.00023965357,0.0005343524,0.0000019410327,0.00006524661,0.000058830145,0.0007895941,0.00035886202,0.00069943623,0.0189341,0.53608024,0.44214556],"study_design_scores_gemma":[0.000629178,0.00009594285,0.03953699,0.00007246639,0.000114039925,0.0001060638,0.002344685,0.013276628,0.00012037296,0.34037748,0.6030555,0.0002706689],"about_ca_topic_score_codex":0.00014816517,"about_ca_topic_score_gemma":0.000065203116,"teacher_disagreement_score":0.45443538,"about_ca_system_score_codex":0.000020064817,"about_ca_system_score_gemma":0.000058346992,"threshold_uncertainty_score":0.99971735},"labels":[],"label_agreement":null},{"id":"W1999968379","doi":"10.1007/s00778-010-0180-z","title":"Streaming multiple aggregations using phantoms","year":2010,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"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; Granularity; Data stream mining; Aggregate (composite); Petabyte; Computation; Volume (thermodynamics); Distributed computing; Set (abstract data type); Data mining; The Internet; Service (business); Computer network; Real-time computing; Big data; Algorithm","score_opus":0.020176654432361135,"score_gpt":0.26893277961267065,"score_spread":0.2487561251803095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999968379","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2632176,0.00013096796,0.73518413,0.00029559952,0.0009515302,0.000041362877,0.0000031292109,0.0000323308,0.00014335684],"genre_scores_gemma":[0.83924305,0.000012550146,0.16017978,0.000068017136,0.00039012142,0.0000013395935,6.211229e-7,0.000006334915,0.0000981942],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993233,0.00004260556,0.00016903068,0.00009942555,0.0001774041,0.00018819976],"domain_scores_gemma":[0.99925536,0.000100250494,0.00015372687,0.00035797592,0.00007335832,0.000059353224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036791063,0.00007411346,0.00007623628,0.000050886913,0.0006849633,0.00014353181,0.00042293163,0.000021430487,0.000019214413],"category_scores_gemma":[0.00010589855,0.00004465009,0.00004460479,0.00016575638,0.000056646237,0.0008101279,0.00012274965,0.0003413681,0.000015785568],"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":[0.000011123506,0.00008880693,0.0031385217,0.000012511933,0.00007201596,0.00011884869,0.0043369955,0.0026981991,0.47218725,0.18490253,0.0005723925,0.3318608],"study_design_scores_gemma":[0.001695947,0.000098059696,0.005532039,0.00026234062,0.000040250452,0.012672206,0.0012851187,0.63343805,0.055766392,0.012849696,0.27553192,0.0008279908],"about_ca_topic_score_codex":0.00004329199,"about_ca_topic_score_gemma":0.00005674579,"teacher_disagreement_score":0.6307398,"about_ca_system_score_codex":0.000013225998,"about_ca_system_score_gemma":0.000062612286,"threshold_uncertainty_score":0.5268253},"labels":[],"label_agreement":null},{"id":"W2002220286","doi":"10.1007/s00778-013-0312-3","title":"Eliminating unscalable communication in transaction processing","year":2013,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"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; Online transaction processing; Transaction processing; Transaction processing system; Scalability; Distributed transaction; Distributed computing; Database transaction; Concurrency; Thread (computing); Compensating transaction; Operating system; Database","score_opus":0.010700441848596995,"score_gpt":0.2297111019525497,"score_spread":0.2190106601039527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002220286","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14563167,0.0011672525,0.8424468,0.0072963373,0.00017936928,0.00016275984,3.2031886e-7,0.000046554724,0.0030689319],"genre_scores_gemma":[0.99500453,0.000038480735,0.004682118,0.00010325789,0.000036415273,0.000009604098,3.0997714e-7,0.0000033051476,0.00012195885],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992449,0.00012470914,0.00023131455,0.00007462643,0.00016263926,0.00016177188],"domain_scores_gemma":[0.9994748,0.000037386464,0.00013302047,0.00022245532,0.00009709059,0.000035198427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072939316,0.000055489578,0.00007506197,0.00004472532,0.00030532505,0.00047764616,0.00065197307,0.000026650026,0.000017716126],"category_scores_gemma":[0.000014055167,0.000036278638,0.000025418634,0.0002898088,0.000020538775,0.0010130983,0.000024600386,0.00029061586,0.00003144205],"study_design_candidate":"design_other","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":[0.000003351953,0.00007337379,0.0006597193,0.000021585467,0.0000068516956,0.0000037061027,0.0051323245,0.00297067,0.0031297088,0.0024346688,0.0013016126,0.9842624],"study_design_scores_gemma":[0.000756018,0.000048552443,0.032357346,0.00049145403,0.0000052256833,0.0005238406,0.0013209387,0.947131,0.0010038438,0.011491528,0.0046446687,0.00022560621],"about_ca_topic_score_codex":0.000093487324,"about_ca_topic_score_gemma":0.000012715549,"teacher_disagreement_score":0.9840368,"about_ca_system_score_codex":0.00004499301,"about_ca_system_score_gemma":0.00003537703,"threshold_uncertainty_score":0.4605953},"labels":[],"label_agreement":null},{"id":"W2006326991","doi":"10.1007/s007780100059","title":"Efficient retrieval of similar shapes","year":2002,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Alberta","funders":"","keywords":"Search engine indexing; Normalization (sociology); Computer science; Pattern recognition (psychology); Artificial intelligence; Similarity (geometry); Invariant (physics); Image retrieval; Computer vision; Mathematics; Algorithm; Image (mathematics)","score_opus":0.029799517877208973,"score_gpt":0.2431261256838491,"score_spread":0.21332660780664012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006326991","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03985538,0.0017081413,0.9432848,0.009464792,0.00027726786,0.00012395102,0.0000016312085,0.00013676505,0.005147256],"genre_scores_gemma":[0.9923286,0.00019300141,0.006628607,0.0002188408,0.00009857462,5.218289e-7,4.245384e-8,0.0000047108656,0.000527109],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990247,0.00008568938,0.00024930312,0.00009838912,0.00038355574,0.00015837113],"domain_scores_gemma":[0.99928,0.0000746016,0.00018608243,0.00025295513,0.00014964296,0.000056743967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065312244,0.0000717366,0.0001014374,0.00007173125,0.00018551145,0.00009579099,0.0009597921,0.00003121584,0.00017129611],"category_scores_gemma":[0.00008080333,0.000041748564,0.00008996567,0.00039685282,0.00008381856,0.00008217354,0.00009540265,0.00021816819,0.00004550251],"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":[0.00011359916,0.0012735407,0.00051671936,0.00006985281,0.00020550513,0.00012342849,0.010139883,0.0011734684,0.28725275,0.13735259,0.031481925,0.53029674],"study_design_scores_gemma":[0.00057984877,0.00033589636,0.0038127322,0.00008213458,0.000028932142,0.0008990161,0.00012347779,0.6736659,0.28802142,0.012615672,0.019509358,0.00032564864],"about_ca_topic_score_codex":5.7663243e-7,"about_ca_topic_score_gemma":3.3803214e-8,"teacher_disagreement_score":0.9524732,"about_ca_system_score_codex":0.000023479366,"about_ca_system_score_gemma":0.000018884559,"threshold_uncertainty_score":0.18755722},"labels":[],"label_agreement":null},{"id":"W2012848182","doi":"10.1007/s00778-009-0176-8","title":"Supporting ranking queries on uncertain and incomplete data","year":2010,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Ranking (information retrieval); Computer science; Data mining; Uncertain data; Set (abstract data type); Rank (graph theory); Probabilistic logic; Ranking SVM; Information retrieval; Semantics (computer science); Learning to rank; Artificial intelligence; Mathematics","score_opus":0.04986115690612704,"score_gpt":0.32384594359330166,"score_spread":0.27398478668717463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012848182","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32698643,0.00031820973,0.61455727,0.044242136,0.005006408,0.00034856566,0.000039664104,0.0002467631,0.008254587],"genre_scores_gemma":[0.9263455,0.000099272016,0.069992706,0.0018326705,0.0011326694,0.000001639854,0.000015163494,0.000014097324,0.000566239],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991431,0.00005266081,0.00017022941,0.00017847166,0.00023273089,0.00022280276],"domain_scores_gemma":[0.99893653,0.000100333804,0.00013772542,0.00074901123,0.00002062609,0.000055778903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018826207,0.00007932663,0.00008101635,0.00005978276,0.00047493412,0.0008610262,0.0021023354,0.000015104263,0.000030660347],"category_scores_gemma":[0.00010024191,0.000047787216,0.000015840642,0.000118644886,0.00006614261,0.0010247392,0.001170204,0.0004000725,0.000016558735],"study_design_candidate":"design_other","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":[0.0000114307395,0.000026304357,0.0012748558,0.000008910653,0.000044409015,0.000110170826,0.00094702025,0.000023833865,0.0010454505,0.073504776,0.01585557,0.9071473],"study_design_scores_gemma":[0.0012639725,0.00019400431,0.009477008,0.00010124661,0.00004219463,0.0012734199,0.00047461863,0.31676924,0.0004760506,0.06690371,0.6024582,0.0005663432],"about_ca_topic_score_codex":0.000017672866,"about_ca_topic_score_gemma":0.000019061941,"teacher_disagreement_score":0.9065809,"about_ca_system_score_codex":0.0000044440226,"about_ca_system_score_gemma":0.000023905584,"threshold_uncertainty_score":0.8302895},"labels":[],"label_agreement":null},{"id":"W2014871820","doi":"10.1007/s00778-011-0238-6","title":"Answering pattern match queries in large graph databases via graph embedding","year":2011,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":false,"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; Reachability; Graph database; Graph; Factor-critical graph; Theoretical computer science; Web search query; Data mining; Information retrieval; Line graph; Search engine; Voltage graph","score_opus":0.03072226293727882,"score_gpt":0.25766782772861585,"score_spread":0.22694556479133704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014871820","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28127044,0.0004303626,0.71723217,0.00014898788,0.00058656465,0.00005330385,0.0000045296338,0.000052415235,0.00022123315],"genre_scores_gemma":[0.98839575,0.00021026454,0.010952051,0.00029782354,0.000108180844,0.0000046365994,8.603423e-7,0.00001241388,0.000018026098],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985435,0.0002206235,0.00030735,0.00021209521,0.00023946022,0.00047696923],"domain_scores_gemma":[0.9991695,0.000072328505,0.00014242306,0.00047293046,0.000039456034,0.000103306185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014369392,0.00016421141,0.00016922649,0.0002682276,0.00042509093,0.00015938941,0.0012010998,0.00002903884,0.000104076214],"category_scores_gemma":[0.000012803408,0.00011116882,0.000113000366,0.00053754164,0.00008510495,0.0010070733,0.00029186194,0.00046656444,0.000023358582],"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":[0.00018887228,0.0013283946,0.20464101,0.0001246022,0.00041278717,0.003212361,0.110624574,0.0006128268,0.010794843,0.28420898,0.0015292353,0.3823215],"study_design_scores_gemma":[0.0031248145,0.00042836668,0.14694874,0.00091110106,0.00005420244,0.006062472,0.005205266,0.02442066,0.024662767,0.7824022,0.003936718,0.0018426861],"about_ca_topic_score_codex":0.000054186003,"about_ca_topic_score_gemma":0.000044582626,"teacher_disagreement_score":0.7071253,"about_ca_system_score_codex":0.000012049156,"about_ca_system_score_gemma":0.000018831253,"threshold_uncertainty_score":0.45333326},"labels":[],"label_agreement":null},{"id":"W2021255304","doi":"10.1007/s00778-013-0316-z","title":"Sampling from repairs of conditional functional dependency violations","year":2013,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":46,"is_retracted":false,"has_abstract":false,"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; Dependency (UML); Functional dependency; Data mining; Sampling (signal processing); Class (philosophy); Space (punctuation); Variety (cybernetics); Semantics (computer science); Artificial intelligence; Relational database; Programming language","score_opus":0.30258014556785606,"score_gpt":0.4077661213846789,"score_spread":0.10518597581682282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021255304","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5255728,0.00014875627,0.45826215,0.008137734,0.0011281417,0.00018448102,0.00020223566,0.000023685832,0.0063400534],"genre_scores_gemma":[0.9938018,0.000017909788,0.0042364188,0.00052212935,0.00035565748,0.000005609836,0.000034731307,0.0000040329514,0.0010217244],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976121,0.00023751272,0.0006314425,0.00014891579,0.0012398835,0.00013014345],"domain_scores_gemma":[0.9973035,0.001510576,0.00038332923,0.00035796437,0.0003674103,0.00007721853],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002777442,0.00006720267,0.00012663219,0.00013036036,0.0004084485,0.00027681302,0.0006001603,0.000028753566,0.019987103],"category_scores_gemma":[0.0011682183,0.00003846421,0.00012279763,0.00023071459,0.00010497769,0.0006429749,0.00014097407,0.00020341852,0.0010577996],"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":[0.00010342408,0.00038714407,0.027957793,0.000005219534,0.00046604552,0.00000876316,0.0019606177,0.010501975,0.005718399,0.19865547,0.65474266,0.09949247],"study_design_scores_gemma":[0.00019170891,0.000018501014,0.24179137,0.000009104972,0.000017470886,0.00002413864,0.0014654264,0.001197145,0.00005459741,0.7391202,0.016055167,0.0000551596],"about_ca_topic_score_codex":0.00013953717,"about_ca_topic_score_gemma":0.000030045974,"teacher_disagreement_score":0.6386875,"about_ca_system_score_codex":0.000021683234,"about_ca_system_score_gemma":0.00006853491,"threshold_uncertainty_score":0.99972},"labels":[],"label_agreement":null},{"id":"W2024336226","doi":"10.1007/s00778-006-0015-0","title":"Histograms based on the minimum description length principle","year":2006,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Saint Mary's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Histogram; Computer science; Data mining; Set (abstract data type); Representation (politics); Overhead (engineering); Online analytical processing; Data set; Algorithm; Pattern recognition (psychology); Artificial intelligence; Image (mathematics); Data warehouse","score_opus":0.023451583210226296,"score_gpt":0.22292722325460765,"score_spread":0.19947564004438134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024336226","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03660053,0.00012438398,0.91961765,0.025189443,0.0015530981,0.00023273939,0.0000026558178,0.00011808909,0.016561415],"genre_scores_gemma":[0.98314613,0.000015839181,0.010037646,0.0020711937,0.00075162196,0.000008051918,0.00000420153,0.000011377466,0.0039539444],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896365,0.00012528732,0.00016912355,0.00013257762,0.00038233175,0.00022699857],"domain_scores_gemma":[0.99921286,0.00007748162,0.00012161638,0.0005186553,0.00003463183,0.000034731664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001063981,0.000094649775,0.000065537024,0.00006663921,0.00050259434,0.0006620637,0.0013975977,0.00001756113,0.000046893903],"category_scores_gemma":[0.000020078425,0.000046132744,0.000071976,0.00023337282,0.000049878618,0.00038374026,0.00013133345,0.00023863246,0.0000995493],"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":[0.000053361076,0.0006412743,0.0012961057,0.000012645572,0.00006431521,0.00012821527,0.0004837118,0.005667223,0.0012823993,0.37594196,0.34471676,0.26971203],"study_design_scores_gemma":[0.0005922371,0.0001784756,0.0080949385,0.000038033395,0.000022120983,0.000054836175,0.00004914692,0.52347285,0.00034715375,0.018314531,0.44861725,0.00021845744],"about_ca_topic_score_codex":0.000019859619,"about_ca_topic_score_gemma":0.000006544608,"teacher_disagreement_score":0.9465456,"about_ca_system_score_codex":0.000051020583,"about_ca_system_score_gemma":0.000027462775,"threshold_uncertainty_score":0.6384296},"labels":[],"label_agreement":null},{"id":"W2026485377","doi":"10.1007/s007780200061","title":"Locating and accessing data repositories with WebSemantics","year":2002,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Metadata; Computer science; World Wide Web; Data element; Interoperability; Data discovery; Data sharing; Metadata repository; Data mapping; Linked data; Semantics (computer science); Data publishing; Information retrieval; Data science; Semantic Web; Publishing; Database","score_opus":0.059896002714666226,"score_gpt":0.26536957458185456,"score_spread":0.20547357186718834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026485377","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019064382,0.0021255324,0.9760068,0.0018533828,0.00032896633,0.00003890696,0.0000024803087,0.000035723297,0.0005438156],"genre_scores_gemma":[0.7713348,0.0002021106,0.22738448,0.00014253079,0.0006319269,8.536715e-7,0.0000010233063,0.0000097360025,0.00029250048],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992916,0.000050411512,0.00015976501,0.00015134965,0.00019515136,0.00015170283],"domain_scores_gemma":[0.99896395,0.0000666205,0.00016470798,0.00069974194,0.000052435917,0.00005254174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037306032,0.00007438666,0.0000884909,0.000023900267,0.0006901779,0.00046325702,0.00067020516,0.0000124036305,0.0000035838227],"category_scores_gemma":[0.000048418475,0.00003873181,0.0000072044677,0.00014254723,0.00008430439,0.0017126441,0.00047370646,0.00017995037,0.0000028139214],"study_design_candidate":"design_other","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":[0.000050559927,0.00016319589,0.030286191,0.00025905273,0.0002965659,0.0013871029,0.024957635,0.0011002375,0.004917883,0.19149737,0.020870276,0.7242139],"study_design_scores_gemma":[0.0019698448,0.000507936,0.007333971,0.0016159753,0.00013615018,0.05863261,0.005154338,0.5959258,0.0044083367,0.00427085,0.31862527,0.0014189024],"about_ca_topic_score_codex":0.00000955006,"about_ca_topic_score_gemma":0.000007925438,"teacher_disagreement_score":0.75227046,"about_ca_system_score_codex":0.000007994224,"about_ca_system_score_gemma":0.000018300821,"threshold_uncertainty_score":0.53083605},"labels":[],"label_agreement":null},{"id":"W2026808466","doi":"10.1007/s00778-010-0196-4","title":"Ranking queries on uncertain data","year":2010,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Ranking (information retrieval); Uncertain data; Rank (graph theory); Computer science; Set (abstract data type); Probabilistic logic; Data mining; Ranking SVM; Information retrieval; Mathematics; Combinatorics; Artificial intelligence","score_opus":0.05671574245012417,"score_gpt":0.29787606197723465,"score_spread":0.24116031952711048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026808466","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045520578,0.0002550732,0.86423314,0.054775015,0.010523404,0.0002549137,0.000027259182,0.00026483278,0.024145769],"genre_scores_gemma":[0.82687265,0.0003528732,0.15672626,0.006223842,0.0050596963,0.000004970337,0.00003658857,0.00003576325,0.004687391],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999206,0.000049330098,0.00012004464,0.00015634815,0.00028180526,0.00018648797],"domain_scores_gemma":[0.998611,0.000071710216,0.000079550744,0.0011690425,0.00002219071,0.000046541412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013032828,0.0000724418,0.00006386697,0.00005533796,0.00037783533,0.00079836923,0.004017516,0.000016080743,0.000066790475],"category_scores_gemma":[0.00006720414,0.000041046933,0.000022652152,0.00015420228,0.000049360046,0.0010523899,0.00086597144,0.00043990294,0.00010278594],"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":[0.000009602906,0.000040151423,0.00014850708,0.0000029547646,0.000038252332,0.00007906924,0.0004358894,0.00004675603,0.00044844535,0.15740053,0.062124096,0.77922577],"study_design_scores_gemma":[0.00052582246,0.000082365244,0.0016149159,0.000034515615,0.000017009594,0.0003225796,0.00010546843,0.07833266,0.00037742392,0.032842983,0.8854977,0.00024653666],"about_ca_topic_score_codex":0.000010591588,"about_ca_topic_score_gemma":0.000014229257,"teacher_disagreement_score":0.8233736,"about_ca_system_score_codex":0.0000056196095,"about_ca_system_score_gemma":0.000029937342,"threshold_uncertainty_score":0.76986927},"labels":[],"label_agreement":null},{"id":"W2027705590","doi":"10.1007/s00778-012-0298-2","title":"Recommending XML physical designs for XML databases","year":2012,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); University of Waterloo","funders":"","keywords":"Computer science; XML database; Database; Materialized view; Efficient XML Interchange; XML Schema Editor; XML validation; XML; Relational database; Streaming XML; Information retrieval; Database design; XML Schema (W3C); XML framework; View; XML Encryption; World Wide Web","score_opus":0.13732934415176967,"score_gpt":0.35816510893963266,"score_spread":0.220835764787863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027705590","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010362115,0.0004051381,0.98656833,0.0011359679,0.0011132149,0.0001274291,0.000028636796,0.00004602312,0.0002131422],"genre_scores_gemma":[0.5960639,0.000085233674,0.39787403,0.0007233644,0.004888044,0.000038289607,0.000009419319,0.000028570375,0.0002891488],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989419,0.00011584025,0.0001924268,0.00012480834,0.00018893146,0.0004361147],"domain_scores_gemma":[0.99882984,0.00038852275,0.00015957601,0.00042272918,0.000050393555,0.00014895256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009736187,0.00011925924,0.00015277712,0.000046319452,0.00061386207,0.000087231914,0.00049222057,0.00001331519,0.00001403587],"category_scores_gemma":[0.00010910205,0.00007016728,0.00009220924,0.00013440727,0.000042181986,0.0017223229,0.0002027439,0.0002020409,0.000033614895],"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":[0.000043323013,0.00021326712,0.0006343068,0.00003238343,0.000087129076,0.000009657908,0.0048385435,0.00010566634,0.009755337,0.8332103,0.03425666,0.116813414],"study_design_scores_gemma":[0.00053405087,0.00012218405,0.0004860908,0.00009786469,0.000028376002,0.00094323675,0.0004863644,0.006132059,0.007590898,0.0044091516,0.9788489,0.00032084557],"about_ca_topic_score_codex":0.00000604868,"about_ca_topic_score_gemma":0.0000016656227,"teacher_disagreement_score":0.94459224,"about_ca_system_score_codex":0.000036747944,"about_ca_system_score_gemma":0.000037034908,"threshold_uncertainty_score":0.47213927},"labels":[],"label_agreement":null},{"id":"W2029487844","doi":"10.1007/s00778-010-0184-8","title":"Efficient evaluation of generalized tree-pattern queries on XML streams","year":2010,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada)","funders":"","keywords":"XPath; Computer science; XML; Scalability; Query language; Fragment (logic); Spatial query; Theoretical computer science; Query optimization; Tree (set theory); Focus (optics); Node (physics); Time complexity; Data mining; XML database; Information retrieval; Algorithm; Web query classification; Web search query; Database; Search engine; Mathematics","score_opus":0.02671680487953133,"score_gpt":0.2935799402125482,"score_spread":0.26686313533301687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029487844","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7358871,0.0000956433,0.26177317,0.0006016794,0.0010647309,0.00010844121,0.0000071610984,0.000018365377,0.00044373304],"genre_scores_gemma":[0.99092495,0.00001090181,0.00860931,0.000091626076,0.00028739375,0.0000069866314,0.0000015478807,0.00000668414,0.000060582774],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848884,0.00021335928,0.0002814029,0.0001364813,0.0007103971,0.00016953611],"domain_scores_gemma":[0.99883115,0.00007041719,0.00026757963,0.00052648777,0.00024277599,0.00006157554],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017546442,0.0001036256,0.00013914052,0.00007028648,0.00022327575,0.000057088266,0.00042898365,0.000029475448,0.00006988321],"category_scores_gemma":[0.000083841616,0.000058760168,0.00006969023,0.00013727797,0.00008119456,0.00014144715,0.0000875013,0.0002658508,0.00001748916],"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":[0.000042811273,0.00015398937,0.00043414833,0.000011912809,0.000055035,0.000010265549,0.0028551305,0.022522664,0.045904458,0.11246283,0.0008893724,0.8146574],"study_design_scores_gemma":[0.003791369,0.0005882238,0.01434719,0.00023858908,0.00010272039,0.00091733225,0.0006385213,0.85795826,0.08624307,0.010749669,0.02380548,0.0006195608],"about_ca_topic_score_codex":0.00004180247,"about_ca_topic_score_gemma":0.00008499122,"teacher_disagreement_score":0.8354356,"about_ca_system_score_codex":0.000024571193,"about_ca_system_score_gemma":0.000108986365,"threshold_uncertainty_score":0.239617},"labels":[],"label_agreement":null},{"id":"W2035006988","doi":"10.1007/s00778-006-0017-y","title":"Query processing of multi-way stream window joins","year":2006,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Joins; Computer science; Join (topology); Data stream mining; Window (computing); Sliding window protocol; Data stream; Database; Data mining; Aggregate (composite); Distributed computing; Real-time computing; Programming language","score_opus":0.019450964385993072,"score_gpt":0.24129503545532632,"score_spread":0.22184407106933324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035006988","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043797106,0.0006571636,0.9499882,0.001625226,0.00041075042,0.00010005817,0.0000038506187,0.0000614379,0.003356243],"genre_scores_gemma":[0.9468489,0.000040304953,0.050905555,0.00013749175,0.00045075297,0.0000014449513,0.000001937194,0.000008942293,0.0016046332],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991414,0.00004753935,0.00022865225,0.00011188637,0.00027099292,0.00019954174],"domain_scores_gemma":[0.9994143,0.000021895938,0.0001986636,0.00027032735,0.00006002028,0.000034755572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005045711,0.000083057515,0.00010189473,0.000087865235,0.00021750036,0.00032094642,0.0010035979,0.00001752062,0.000012431272],"category_scores_gemma":[0.000010678296,0.000050558505,0.000055621604,0.00024500082,0.000051404404,0.000777001,0.00019804611,0.00016625707,0.000015126358],"study_design_candidate":"design_other","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":[0.000007836883,0.00035072578,0.0027351363,0.00003375369,0.000043066535,0.000075947544,0.00059469056,0.0011084483,0.0032589098,0.0089728935,0.00882972,0.9739889],"study_design_scores_gemma":[0.006336587,0.0005258674,0.21433781,0.00076549675,0.00017833369,0.0012477294,0.000984577,0.61946046,0.032255635,0.043949816,0.07847398,0.0014837228],"about_ca_topic_score_codex":0.00003725395,"about_ca_topic_score_gemma":0.000011343609,"teacher_disagreement_score":0.97250515,"about_ca_system_score_codex":0.0000152957,"about_ca_system_score_gemma":0.00004164412,"threshold_uncertainty_score":0.30948937},"labels":[],"label_agreement":null},{"id":"W2040374677","doi":"10.1007/s00778-002-0081-x","title":"TIMBER: A native XML database","year":2002,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":408,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"","keywords":"Computer science; XPath; XML database; Streaming XML; XML validation; Efficient XML Interchange; XML Schema Editor; XML Encryption; Database; Query optimization; XML Schema (W3C); Information retrieval; XML; XML Signature; Document Structure Description; Rewriting; Relational database; Programming language; World Wide Web","score_opus":0.02968092915324465,"score_gpt":0.24349118944614273,"score_spread":0.21381026029289807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040374677","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018126323,0.0013584528,0.9909439,0.0022006417,0.0005367672,0.000067735375,0.0000169109,0.00005201986,0.0030109566],"genre_scores_gemma":[0.27547184,0.0016717206,0.69787955,0.0038458013,0.0022904691,0.000029147572,0.000008005244,0.00005364561,0.018749816],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990461,0.00011645849,0.00019233089,0.00014387254,0.00026715657,0.000234078],"domain_scores_gemma":[0.9991105,0.00007756587,0.00013564844,0.0005016373,0.00007460163,0.00010002641],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045020843,0.00009932323,0.0001068203,0.000053784614,0.00043713968,0.00011012644,0.0006410889,0.000016457056,0.00019986424],"category_scores_gemma":[0.00007004832,0.000056619472,0.000052635656,0.00023068886,0.000066405926,0.0009867345,0.00023874306,0.0002978495,0.00028464705],"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":[0.000020843894,0.00031247584,0.00042963694,0.000026956555,0.00016933068,0.0008215351,0.011479419,0.0007874581,0.002135739,0.6944815,0.20219107,0.08714402],"study_design_scores_gemma":[0.00083363237,0.00011515629,0.00024047946,0.000116183284,0.000013142516,0.00642273,0.00036434864,0.08017634,0.0010750981,0.0024763928,0.9078112,0.00035528056],"about_ca_topic_score_codex":0.000009409436,"about_ca_topic_score_gemma":0.000007987997,"teacher_disagreement_score":0.70562017,"about_ca_system_score_codex":0.00002780593,"about_ca_system_score_gemma":0.000021134905,"threshold_uncertainty_score":0.36586568},"labels":[],"label_agreement":null},{"id":"W2046474027","doi":"10.1007/s00778-013-0318-x","title":"Consistency anomalies in multi-tier architectures: automatic detection and prevention","year":2013,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Consistency (knowledge bases); Computer science; Anomaly detection; Isolation (microbiology); Database transaction; Set (abstract data type); Data mining; Database; Distributed computing; Artificial intelligence; Programming language","score_opus":0.017376135837386203,"score_gpt":0.24773613173478778,"score_spread":0.23035999589740158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046474027","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6651632,0.00058849575,0.3331377,0.00051884016,0.00023583605,0.00017638839,4.8633024e-7,0.000029611261,0.00014943014],"genre_scores_gemma":[0.9939563,0.000017163227,0.0057529896,0.00006243857,0.00003940168,0.000015784632,1.1568848e-7,0.0000034129866,0.00015239314],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916726,0.00016564695,0.00025215303,0.0001111797,0.00013767478,0.0001661094],"domain_scores_gemma":[0.9995567,0.00004507844,0.00012746034,0.00017333862,0.000045870565,0.000051541272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004275525,0.0000798184,0.0001099955,0.00007852236,0.0001939051,0.00031085682,0.0002683119,0.00003240485,0.000014450945],"category_scores_gemma":[0.000037037265,0.000049039892,0.000037824124,0.00016288686,0.000047161866,0.00024686515,0.000051375468,0.0001996122,0.000019141746],"study_design_candidate":"design_other","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":[0.0000046412465,0.00008049011,0.0036621017,0.000041637588,0.000035271845,0.000016969585,0.0039310316,0.00044315378,0.004000664,0.0007856808,0.00020820873,0.9867901],"study_design_scores_gemma":[0.001198721,0.00015851634,0.46072257,0.00026063254,0.0000099594445,0.0019195547,0.0004971633,0.5142197,0.0004574899,0.019544994,0.0007758898,0.00023479265],"about_ca_topic_score_codex":0.000060922208,"about_ca_topic_score_gemma":0.000070230606,"teacher_disagreement_score":0.98655534,"about_ca_system_score_codex":0.000024594961,"about_ca_system_score_gemma":0.000028871405,"threshold_uncertainty_score":0.29975995},"labels":[],"label_agreement":null},{"id":"W2061240327","doi":"10.1007/s007780050006","title":"Distance-based outliers: algorithms and applications","year":2000,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":1196,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Outlier; Computer science; Anomaly detection; Simple (philosophy); Algorithm; Data mining; Curse of dimensionality; Identification (biology); Time complexity; Credit card fraud; Task (project management); Artificial intelligence; Machine learning; Pattern recognition (psychology); Credit card","score_opus":0.009606939193727806,"score_gpt":0.23790982533144633,"score_spread":0.22830288613771854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061240327","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001174469,0.00022313686,0.9922234,0.00367721,0.000019654583,0.0001290657,0.0000014409571,0.000111159,0.0024404968],"genre_scores_gemma":[0.86437434,0.0005941439,0.12985371,0.0018090813,0.0005290942,0.00021776551,0.0000010701245,0.000016389968,0.0026043751],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99948424,0.00002705092,0.00013174632,0.00011951901,0.000115438525,0.000121991805],"domain_scores_gemma":[0.99949783,0.000031863918,0.000055977704,0.00030579208,0.00003405972,0.00007448502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020413689,0.00006188159,0.000056440116,0.000032952645,0.0005590137,0.00021158886,0.00047479337,0.000023021017,0.000081258455],"category_scores_gemma":[0.0000017348323,0.000040986884,0.000038097256,0.00023271285,0.00007168726,0.0001381454,0.000023811483,0.00016746328,0.0000419698],"study_design_candidate":"design_other","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":[0.0000024162757,0.00003081308,0.000056799574,0.0000012789249,0.0000058951064,0.0000010932301,0.00009286433,0.00009874982,0.000082797924,0.021260304,0.0012086303,0.97715837],"study_design_scores_gemma":[0.00026448895,0.00006770319,0.001558429,0.00001074585,0.000011685461,0.00029202734,0.000037266156,0.042887863,0.001168249,0.04698056,0.90655196,0.00016902688],"about_ca_topic_score_codex":0.0000046236514,"about_ca_topic_score_gemma":9.050422e-7,"teacher_disagreement_score":0.9769893,"about_ca_system_score_codex":0.00001992156,"about_ca_system_score_gemma":0.000029957953,"threshold_uncertainty_score":0.42995375},"labels":[],"label_agreement":null},{"id":"W2064580935","doi":"10.1007/s00778-004-0123-7","title":"Querying XML streams","year":2004,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":126,"is_retracted":false,"has_abstract":false,"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; XQuery; XML; Streaming XML; Tuple; XML database; Path (computing); Query plan; Programming language; Database; Efficient XML Interchange; XML Encryption; Concurrency; Information retrieval; Operating system; Search engine; Web search query; Sargable","score_opus":0.010352431843665732,"score_gpt":0.22936693184287188,"score_spread":0.21901449999920614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064580935","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028786296,0.00046143477,0.9665375,0.0023594615,0.00059748016,0.000041916956,0.0000017641913,0.000052217296,0.0011619821],"genre_scores_gemma":[0.8522169,0.00015539542,0.14565866,0.0007159693,0.0008431707,0.000003987384,8.2435673e-7,0.00001309432,0.00039199562],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99927515,0.000040632753,0.00016710897,0.00010195068,0.00020786667,0.00020727636],"domain_scores_gemma":[0.99939865,0.000030255156,0.00010479752,0.00034734578,0.000043436292,0.000075501644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037151965,0.00007689577,0.00008500771,0.000036374546,0.00041387725,0.00012018699,0.00048549625,0.000016588572,0.000011601659],"category_scores_gemma":[0.000028206721,0.0000431918,0.000050457737,0.00014876078,0.00003972677,0.00067646266,0.00013107804,0.00022017953,0.000066231754],"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":[0.0000072031517,0.000037268455,0.0001549671,0.0000068036475,0.00003104713,0.00017172251,0.0023316192,0.0050919363,0.0025240479,0.88051635,0.0009616829,0.10816533],"study_design_scores_gemma":[0.003772527,0.000511151,0.0034103007,0.00075677055,0.000036162444,0.019976186,0.002460464,0.00449881,0.026561677,0.27781436,0.65895134,0.0012502241],"about_ca_topic_score_codex":0.00004021532,"about_ca_topic_score_gemma":0.000013559236,"teacher_disagreement_score":0.8234306,"about_ca_system_score_codex":0.000044720222,"about_ca_system_score_gemma":0.0000858348,"threshold_uncertainty_score":0.3183251},"labels":[],"label_agreement":null},{"id":"W2065714066","doi":"10.1007/s00778-005-0177-1","title":"Optimization and evaluation of shortest path queries","year":2006,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Constrained Shortest Path First; Shortest path problem; K shortest path routing; Computer science; Yen's algorithm; Dijkstra's algorithm; Shortest Path Faster Algorithm; Euclidean shortest path; Scalability; Pruning; Path (computing); Query optimization; Algorithm; Theoretical computer science; Data mining; Database; Graph; Computer network","score_opus":0.01871367238197218,"score_gpt":0.2452819636881325,"score_spread":0.2265682913061603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065714066","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04335089,0.0003897087,0.9529162,0.0010201208,0.00018725745,0.00007922156,0.0000012626489,0.000014247076,0.0020411161],"genre_scores_gemma":[0.9603171,0.00009348289,0.039289616,0.000039156836,0.00014611652,0.0000015688851,0.0000035300404,0.0000027274632,0.000106727064],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99941707,0.00006526477,0.000113772956,0.000056098972,0.00028572293,0.000062059305],"domain_scores_gemma":[0.9996618,0.000016746117,0.00008869624,0.00012629488,0.000094370225,0.000012082408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011033706,0.000035269462,0.000041436946,0.0000392315,0.00010547161,0.00016587792,0.00023665639,0.000008088287,0.000015755151],"category_scores_gemma":[0.000013669818,0.00002221151,0.000012207989,0.00011040521,0.000028536746,0.00051939755,0.00007360286,0.000042469335,0.0000010648195],"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":[0.0000085976435,0.00013970167,0.0052931337,0.000010588425,0.00005529022,0.000008601028,0.00089802826,0.41341978,0.00057140365,0.09619103,0.011696041,0.4717078],"study_design_scores_gemma":[0.00020593076,0.000027920454,0.009616632,0.000010802889,0.00002275747,0.000029136827,0.000036981983,0.9788633,0.00015549276,0.010512485,0.00047604894,0.00004250859],"about_ca_topic_score_codex":0.000011312054,"about_ca_topic_score_gemma":0.0000024396625,"teacher_disagreement_score":0.9169662,"about_ca_system_score_codex":0.000008616592,"about_ca_system_score_gemma":0.000020121983,"threshold_uncertainty_score":0.15995647},"labels":[],"label_agreement":null},{"id":"W2068157134","doi":"10.1007/s00778-002-0076-7","title":"Tree pattern query minimization","year":2002,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Minification; Computer science; Tree (set theory); XML; Reduction (mathematics); Pattern matching; Algorithm; Query optimization; Data mining; Theoretical computer science; Mathematics; Artificial intelligence","score_opus":0.02434631267444179,"score_gpt":0.2217052823758772,"score_spread":0.1973589697014354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068157134","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029190723,0.0005303772,0.9909993,0.0029101858,0.00055423105,0.00003898393,0.0000020316304,0.00003957451,0.0020062604],"genre_scores_gemma":[0.91992503,0.00078032137,0.070376456,0.002354438,0.001862101,0.000009728052,0.000002694906,0.000027049282,0.004662156],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992989,0.00008147853,0.00017474814,0.000095303265,0.00019127126,0.00015835487],"domain_scores_gemma":[0.9994293,0.000043680262,0.00011737858,0.00030930544,0.000044042834,0.00005629663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020277967,0.00006970706,0.000076359596,0.00004148651,0.00026708245,0.0001006634,0.00038329445,0.000017655819,0.00013744015],"category_scores_gemma":[0.000025335981,0.000040843715,0.000041750023,0.00013613935,0.000027725351,0.0006134053,0.000083973064,0.00014313396,0.00011742267],"study_design_candidate":"design_other","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":[0.000003168756,0.0000520615,0.00086764124,0.000007978183,0.000027199061,0.0000903717,0.002903177,0.00045087727,0.00044298562,0.020474156,0.057291254,0.91738915],"study_design_scores_gemma":[0.0012336214,0.00021848665,0.005261986,0.00017829987,0.000021194392,0.0047913506,0.0006142441,0.26470447,0.0016531027,0.0044791084,0.7162389,0.0006052436],"about_ca_topic_score_codex":0.0000069406387,"about_ca_topic_score_gemma":0.000010138372,"teacher_disagreement_score":0.9206228,"about_ca_system_score_codex":0.000014197004,"about_ca_system_score_gemma":0.000009769304,"threshold_uncertainty_score":0.20542091},"labels":[],"label_agreement":null},{"id":"W2077020471","doi":"10.1007/s00778-005-0179-z","title":"Special issue: Best papers of VLDB 2004","year":2005,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Waterloo","funders":"","keywords":"Very large database; Computer science; Data science; Data mining","score_opus":0.014589702295020011,"score_gpt":0.2587781872719452,"score_spread":0.24418848497692516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077020471","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0573638,0.0029430047,0.31021187,0.17527705,0.0071178745,0.0006856674,0.00011442477,0.0002626918,0.4460236],"genre_scores_gemma":[0.177718,0.0017547258,0.66843706,0.0043235137,0.114177465,0.000025357254,0.000009955754,0.00006956575,0.03348438],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.999222,0.000029347553,0.00021488777,0.00011044435,0.00024621177,0.0001771418],"domain_scores_gemma":[0.9993014,0.00004365264,0.00013406249,0.00038639095,0.00005554119,0.00007899155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037992458,0.00007173858,0.00009362105,0.00004415265,0.00024092749,0.00013726774,0.0011593692,0.000023436603,0.0004003565],"category_scores_gemma":[0.000019829386,0.000046618152,0.00005713786,0.00022302689,0.00006789793,0.0002652276,0.000120803124,0.00020236424,0.00029927574],"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":[0.0000020321797,0.000070878115,0.000028195685,0.0000011399104,0.000015074799,0.0000030721378,0.0007742054,0.00019643297,0.0004742358,0.0051049404,0.13746569,0.8558641],"study_design_scores_gemma":[0.00019913571,0.000050555365,0.00048795654,0.000017155262,0.000010134446,0.00022618877,0.00012204866,0.003871036,0.0007705681,0.00078023435,0.9933832,0.00008176363],"about_ca_topic_score_codex":0.000009797195,"about_ca_topic_score_gemma":0.000005982624,"teacher_disagreement_score":0.8559176,"about_ca_system_score_codex":0.000024168332,"about_ca_system_score_gemma":0.00006805162,"threshold_uncertainty_score":0.43836233},"labels":[],"label_agreement":null},{"id":"W2085472312","doi":"10.1007/s00778-013-0344-8","title":"Correlated network data publication via differential privacy","year":2013,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":214,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; McGill University","funders":"","keywords":"Differential privacy; Computer science; Adjacency matrix; Data publishing; Data mining; Privacy software; Information privacy; Enhanced Data Rates for GSM Evolution; Node (physics); Theoretical computer science; Data science; Publishing; Computer security; Artificial intelligence; Graph","score_opus":0.044471574677033665,"score_gpt":0.2691169814537689,"score_spread":0.22464540677673522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085472312","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0129890395,0.0002253221,0.85858494,0.12567432,0.0014401469,0.00021221771,0.0000047714257,0.0004724331,0.00039682438],"genre_scores_gemma":[0.7925283,0.00026119142,0.20499285,0.0008977062,0.00096384913,0.00001895036,0.000079702215,0.000028334756,0.00022913289],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817884,0.00018082937,0.00037767107,0.00035422473,0.00042530659,0.00048313258],"domain_scores_gemma":[0.98512274,0.00018083985,0.00034654944,0.014048921,0.00019314974,0.00010781481],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0008883012,0.00014942489,0.0001434096,0.00009007953,0.0005079797,0.0012654739,0.0764215,0.00010628009,0.00036549845],"category_scores_gemma":[0.0065674842,0.00009440979,0.00003946378,0.0006235365,0.000112058726,0.002623766,0.10795375,0.0008532937,0.00054562226],"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":[0.0000021536946,0.00002769973,0.00041742434,0.0000012956186,0.00003546102,0.0000029079608,0.000032201147,0.000013176259,0.00027891598,0.0009082855,0.9080707,0.09020981],"study_design_scores_gemma":[0.00024827887,0.000030870266,0.008871217,0.000022509255,0.000013263039,0.00037108042,0.000005950905,0.6399468,0.000097042765,0.33764273,0.012592643,0.00015761046],"about_ca_topic_score_codex":0.000036347465,"about_ca_topic_score_gemma":0.000001719874,"teacher_disagreement_score":0.895478,"about_ca_system_score_codex":0.00005442047,"about_ca_system_score_gemma":0.000069997914,"threshold_uncertainty_score":0.9997713},"labels":[],"label_agreement":null},{"id":"W2086395677","doi":"10.1007/s00778-011-0217-y","title":"Interaction-aware scheduling of report-generation workloads","year":2011,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":false,"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; Online aggregation; Query optimization; View; Sargable; Scheduling (production processes); Web query classification; Leverage (statistics); Query language; IBM; Database; Workload; Query plan; Query expansion; Web search query; Data mining; Database design; Information retrieval; Search engine; Artificial intelligence; Operating system","score_opus":0.08655948616922705,"score_gpt":0.28821611297236155,"score_spread":0.2016566268031345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086395677","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05534787,0.00018303275,0.9424018,0.00017713959,0.001135537,0.000036070796,7.9902037e-7,0.000018772978,0.00069892604],"genre_scores_gemma":[0.88940245,0.000039580325,0.10995672,0.000044511064,0.00040036926,0.0000020824184,0.0000011132256,0.000004583418,0.00014856363],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992579,0.00006304327,0.00031762753,0.00009558431,0.00016118777,0.00010463498],"domain_scores_gemma":[0.9990976,0.000024409546,0.0003592132,0.0003434748,0.00013430191,0.000041001953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005338311,0.000060606344,0.0000898587,0.00005032426,0.00019249503,0.00003580347,0.0002577514,0.000018705361,0.000042431348],"category_scores_gemma":[0.000054293516,0.0000372514,0.00004927814,0.00013311536,0.000029753946,0.00075821823,0.00008102551,0.00016976986,0.000009978753],"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":[0.00016028153,0.0004375371,0.010380329,0.000087887965,0.00047188945,0.0015840596,0.039318893,0.011692355,0.106704526,0.4568323,0.007768614,0.36456135],"study_design_scores_gemma":[0.0023562065,0.0009883769,0.011694971,0.0018549989,0.00013879141,0.07219977,0.008891207,0.23599309,0.49228364,0.027110847,0.14464213,0.0018459779],"about_ca_topic_score_codex":0.000025756484,"about_ca_topic_score_gemma":0.000009989133,"teacher_disagreement_score":0.8340546,"about_ca_system_score_codex":0.000017043272,"about_ca_system_score_gemma":0.000051548548,"threshold_uncertainty_score":0.1519068},"labels":[],"label_agreement":null},{"id":"W2089760975","doi":"10.1007/s00778-004-0122-8","title":"Views as first-class citizens in object-oriented databases","year":2004,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Class hierarchy; Hierarchy; Computer science; Class (philosophy); Schema (genetic algorithms); Object (grammar); Set (abstract data type); Schema evolution; Theoretical computer science; Human–computer interaction; Object-oriented programming; Programming language; Artificial intelligence; Database; Information retrieval; Database schema","score_opus":0.02986945958720896,"score_gpt":0.28454405881404765,"score_spread":0.2546745992268387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089760975","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.066182524,0.0014410826,0.9231675,0.0048633763,0.0012356683,0.00022368177,0.000026634078,0.00008393186,0.002775551],"genre_scores_gemma":[0.81990856,0.0019287026,0.17156939,0.003593183,0.0014891154,0.000053032305,0.000025332336,0.00005996596,0.0013726924],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985479,0.00010903558,0.00039073636,0.00022979245,0.0003481337,0.0003743981],"domain_scores_gemma":[0.99886024,0.0001001947,0.00018844423,0.00066361314,0.00006569498,0.00012182579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006974355,0.0001554193,0.00020392438,0.000121493846,0.00041055307,0.000086042084,0.00062350585,0.000023987577,0.000041711843],"category_scores_gemma":[0.0001575105,0.000096601725,0.00007297123,0.00047967848,0.00008230042,0.0008954771,0.000288581,0.0003862337,0.00015542726],"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":[0.00006342395,0.0002064871,0.00092825096,0.000035133708,0.00005014677,0.0010782656,0.0062504807,0.005388121,0.0016168666,0.9664844,0.0062194425,0.011678979],"study_design_scores_gemma":[0.0020099368,0.00018787432,0.0021375138,0.0005303612,0.000010633446,0.004213646,0.0008074621,0.0009057648,0.0035549784,0.012090263,0.9731195,0.00043205335],"about_ca_topic_score_codex":0.00021130039,"about_ca_topic_score_gemma":0.00059815875,"teacher_disagreement_score":0.96690005,"about_ca_system_score_codex":0.00010797692,"about_ca_system_score_gemma":0.00017296651,"threshold_uncertainty_score":0.3939304},"labels":[],"label_agreement":null},{"id":"W2092324613","doi":"10.1007/s007780200062","title":"Query processing techniques for arrays","year":2002,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":false,"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; Variety (cybernetics); Class (philosophy); Rewriting; Query plan; Function (biology); Query optimization; Data structure; Space (punctuation); Theoretical computer science; Programming language; Database; Information retrieval; Sargable; Artificial intelligence; Search engine; Web search query","score_opus":0.03430227086175861,"score_gpt":0.26878400891824294,"score_spread":0.23448173805648434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092324613","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00031115825,0.000998411,0.9949465,0.002150928,0.00019842465,0.00011193116,0.000002454474,0.000099405894,0.0011807787],"genre_scores_gemma":[0.10709498,0.00022210508,0.8891156,0.0008504358,0.0012754212,0.000044212848,6.659638e-7,0.000019757419,0.0013768374],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993262,0.000034171153,0.00018110285,0.00010888567,0.00014756223,0.00020204083],"domain_scores_gemma":[0.9994278,0.000047970083,0.00014106744,0.00024598802,0.00008670949,0.0000504558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043905305,0.00007879466,0.000095526695,0.00004428423,0.00050783216,0.00014696586,0.0004237339,0.000021522903,0.000012975658],"category_scores_gemma":[0.000040514733,0.000045240085,0.000053640815,0.00012479896,0.000041061154,0.00076736347,0.00006419055,0.00015266068,0.000009507266],"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":[0.0000075939224,0.000042261556,0.000034344972,0.000038979957,0.000015334033,0.000018972592,0.002007434,0.00004591509,0.004299584,0.07602889,0.0239795,0.8934812],"study_design_scores_gemma":[0.00024688436,0.00013458665,0.000033392927,0.00019343097,0.000008236284,0.0015901543,0.00020641705,0.02863702,0.012729494,0.015136235,0.940834,0.00025014576],"about_ca_topic_score_codex":0.0000018307165,"about_ca_topic_score_gemma":0.000001352278,"teacher_disagreement_score":0.9168545,"about_ca_system_score_codex":0.000021275104,"about_ca_system_score_gemma":0.000021956323,"threshold_uncertainty_score":0.39058858},"labels":[],"label_agreement":null},{"id":"W2099525917","doi":"10.1007/s00778-009-0157-y","title":"A framework for testing DBMS features","year":2009,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"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; Database; Generator (circuit theory); Set (abstract data type); Feature (linguistics); Test case; Test suite; Test (biology); Data mining; Programming language; Power (physics); Machine learning","score_opus":0.0426218733597992,"score_gpt":0.3124691026543456,"score_spread":0.26984722929454635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099525917","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012599695,0.0006733028,0.9924917,0.0045790984,0.00043085872,0.00008990974,0.0000027547783,0.000053639902,0.00041873608],"genre_scores_gemma":[0.072311826,0.000014146837,0.9252758,0.0012564443,0.000938075,0.0000037162347,3.3717382e-7,0.000005050097,0.00019459268],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993231,0.000035767713,0.0001506342,0.00010854444,0.00015332668,0.00022859541],"domain_scores_gemma":[0.9991007,0.00031935607,0.00013079502,0.0002994184,0.0000863788,0.00006338401],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045610027,0.00008008518,0.00009817517,0.00003157966,0.00050826784,0.00015439383,0.00047822826,0.000028660788,0.0000026354408],"category_scores_gemma":[0.00043944994,0.00004461407,0.00005465537,0.00018404608,0.000021640619,0.00036706802,0.000047602312,0.00027066408,0.000005696309],"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":[0.000009900504,0.000014371423,0.000034060984,0.0000034617985,0.000008713695,0.000014267883,0.00058207114,0.00024534258,0.00088409474,0.8091173,0.004034548,0.18505186],"study_design_scores_gemma":[0.0004272451,0.0004232914,0.005038683,0.00030487828,0.000012144981,0.0027196417,0.0002005978,0.004521076,0.0015373855,0.87115425,0.11336443,0.00029636573],"about_ca_topic_score_codex":0.000002140059,"about_ca_topic_score_gemma":7.3065127e-7,"teacher_disagreement_score":0.18475549,"about_ca_system_score_codex":0.000015130795,"about_ca_system_score_gemma":0.00004210469,"threshold_uncertainty_score":0.39092368},"labels":[],"label_agreement":null},{"id":"W2100257623","doi":"10.1007/s00778-010-0214-6","title":"Anonymity meets game theory: secure data integration with malicious participants","year":2010,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Anonymity; Scalability; Private information retrieval; Adversary; Data sharing; k-anonymity; Computer security; Data integration; Information privacy; Data anonymization; Partition (number theory); Table (database); Set (abstract data type); Data mining; Database","score_opus":0.057340703357166435,"score_gpt":0.3061374292867121,"score_spread":0.2487967259295457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100257623","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3392521,0.00016327036,0.5779714,0.08022847,0.0010642112,0.00021251485,0.00003795017,0.00047366126,0.00059639785],"genre_scores_gemma":[0.8949387,0.000050165516,0.10443643,0.0003430575,0.00017784972,0.0000045156394,0.000007132955,0.000012848591,0.00002931863],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981881,0.00025039568,0.00025056794,0.00036985427,0.00046564033,0.00047544317],"domain_scores_gemma":[0.9878203,0.000254127,0.00025562706,0.011444334,0.00011259937,0.000113009264],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0031673969,0.00017123896,0.00016179298,0.00008955316,0.0003358151,0.00058227463,0.04357652,0.000105031206,0.000051169915],"category_scores_gemma":[0.009567123,0.00009076298,0.000028187616,0.0003824155,0.00026783635,0.0014201143,0.033132583,0.0013959799,0.00004592259],"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":[0.0002530233,0.0003714166,0.0038838682,0.00001784806,0.00034664932,0.0005076274,0.002201933,0.000050549657,0.025751876,0.1261475,0.44494575,0.39552194],"study_design_scores_gemma":[0.00073392334,0.00020920688,0.0045533986,0.00008834348,0.00006165989,0.0024045827,0.00019878753,0.1460995,0.011399511,0.8222395,0.011610282,0.00040131013],"about_ca_topic_score_codex":0.000016734728,"about_ca_topic_score_gemma":0.00017774996,"teacher_disagreement_score":0.696092,"about_ca_system_score_codex":0.000027667278,"about_ca_system_score_gemma":0.00014396745,"threshold_uncertainty_score":0.9987757},"labels":[],"label_agreement":null},{"id":"W2110557355","doi":"10.1007/s007780100049","title":"Approximate query processing using wavelets","year":2001,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":477,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Computer science; Wavelet; Query optimization; Data mining; Tuple; Histogram; Algorithm; Artificial intelligence; Mathematics; Image (mathematics)","score_opus":0.0412518917975479,"score_gpt":0.2701677799750619,"score_spread":0.22891588817751402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110557355","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034526892,0.00030382822,0.9598022,0.0019527627,0.00040468297,0.000060603674,3.2629828e-7,0.000066857334,0.0028818445],"genre_scores_gemma":[0.72746295,0.00042513822,0.26561847,0.0020181194,0.001999093,0.0000036690133,0.0000019907761,0.000035616744,0.0024349603],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907273,0.000052464693,0.00017163588,0.00013422812,0.0002787817,0.00029016254],"domain_scores_gemma":[0.99946654,0.000014413066,0.00013212684,0.0002799736,0.000044994482,0.000061929786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074933516,0.00009056483,0.000084410414,0.00008444262,0.0005128147,0.00094994577,0.0011417409,0.000016997223,0.00002060897],"category_scores_gemma":[0.000012146505,0.00005534851,0.00004212929,0.00034043545,0.000034903576,0.0013174693,0.0002929477,0.00020876944,0.000026417265],"study_design_candidate":"design_other","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":[0.0000072674948,0.00006096278,0.00038157747,0.000014147826,0.000030650535,0.00030720618,0.00074300147,0.00045046257,0.0008754768,0.0050790035,0.0022840106,0.98976624],"study_design_scores_gemma":[0.00037533976,0.000029686194,0.00076121127,0.00008624982,0.000019849089,0.0025263412,0.00013601681,0.95633924,0.0002813176,0.014129849,0.025082799,0.00023211472],"about_ca_topic_score_codex":0.0000050491212,"about_ca_topic_score_gemma":5.986842e-7,"teacher_disagreement_score":0.98953414,"about_ca_system_score_codex":0.000028074313,"about_ca_system_score_gemma":0.000042921947,"threshold_uncertainty_score":0.91603494},"labels":[],"label_agreement":null},{"id":"W2121041488","doi":"10.1007/s00778-013-0337-7","title":"gStore: a graph-based SPARQL query engine","year":2013,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":202,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"SPARQL; Computer science; Named graph; RDF; Scalability; RDF query language; Information retrieval; Web search query; Query optimization; Graph; Query expansion; RDF Schema; Web query classification; Theoretical computer science; Semantic Web; Database; Search engine","score_opus":0.012074452013339535,"score_gpt":0.20327558979719282,"score_spread":0.19120113778385328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121041488","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29662147,0.0013558172,0.66664135,0.031576674,0.0016671023,0.00016116223,3.7026055e-7,0.00020424085,0.001771801],"genre_scores_gemma":[0.9776561,0.00004202197,0.020308843,0.0014948633,0.00027680642,0.0000065514682,1.4579382e-7,0.000006301845,0.00020833816],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990817,0.000090342844,0.0001767664,0.00011696424,0.00024797925,0.00028626574],"domain_scores_gemma":[0.99917847,0.0001495052,0.000095236595,0.00040464042,0.00008096073,0.00009121116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044478697,0.00010158506,0.00011956894,0.00009663794,0.00023036805,0.0003216651,0.0011323368,0.00003561852,0.00011379333],"category_scores_gemma":[0.00006526765,0.000055358316,0.00009742842,0.00022637204,0.0000720253,0.00032284838,0.000082629645,0.000269901,0.00021564797],"study_design_candidate":"design_other","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":[0.000047530164,0.00046642363,0.020771224,0.000047582784,0.0003119765,0.0004793532,0.004189568,0.0051435693,0.011035266,0.0737973,0.36866796,0.51504225],"study_design_scores_gemma":[0.0039381813,0.00090821524,0.3408511,0.00027378768,0.000096518495,0.0043704766,0.0007513975,0.2411776,0.020774415,0.3230245,0.06226984,0.0015639623],"about_ca_topic_score_codex":0.00006270313,"about_ca_topic_score_gemma":0.00000641991,"teacher_disagreement_score":0.6810347,"about_ca_system_score_codex":0.000019904344,"about_ca_system_score_gemma":0.00007974492,"threshold_uncertainty_score":0.31018242},"labels":[],"label_agreement":null},{"id":"W2123080243","doi":"10.1007/s00778-009-0159-9","title":"Schema mapping and query translation in heterogeneous P2P XML databases","year":2009,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia Hospital","funders":"","keywords":"Computer science; XQuery; Information retrieval; Scalability; Schema (genetic algorithms); Document Structure Description; Metadata; XML; Query language; XML Schema Editor; Database; World Wide Web","score_opus":0.04612929082107779,"score_gpt":0.2739027125305562,"score_spread":0.2277734217094784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123080243","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.175739,0.0026176202,0.81953245,0.0017322903,0.00013965725,0.00007527315,0.000004721637,0.00002800559,0.00013099132],"genre_scores_gemma":[0.90880084,0.00034498956,0.09022402,0.00041305283,0.00018577008,0.0000017258504,0.0000025558122,0.0000049424484,0.000022101602],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992227,0.00008047922,0.00022498563,0.00013728566,0.00015260765,0.00018192854],"domain_scores_gemma":[0.9995177,0.00006739565,0.00008926132,0.00024892035,0.000021261334,0.00005546201],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000459147,0.000086354055,0.00011205319,0.0000864539,0.00018981278,0.00007687136,0.00020142038,0.000016090858,0.0000045590964],"category_scores_gemma":[0.000025519796,0.00005731219,0.000026750053,0.00016639371,0.000029414894,0.0008220204,0.00004209443,0.0001784654,0.0000036081476],"study_design_candidate":"design_other","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":[0.00005708184,0.00011067752,0.0015047397,0.000039116632,0.000035469086,0.000504077,0.0060501047,0.0024472342,0.03278927,0.0934072,0.00051368255,0.8625413],"study_design_scores_gemma":[0.0076254066,0.0010254313,0.056373015,0.0030179806,0.000057811965,0.044124365,0.0027200372,0.20437866,0.0432257,0.05064587,0.5838602,0.002945482],"about_ca_topic_score_codex":0.000018098197,"about_ca_topic_score_gemma":0.000027256312,"teacher_disagreement_score":0.85959584,"about_ca_system_score_codex":0.000016464981,"about_ca_system_score_gemma":0.00002866466,"threshold_uncertainty_score":0.23371233},"labels":[],"label_agreement":null},{"id":"W2126431245","doi":"10.1007/s00778-006-0029-7","title":"Algorithms and analyses for maximal vector computation","year":2006,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":177,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Skyline; Curse of dimensionality; Computation; Field (mathematics); Computer science; Running time; Divide and conquer algorithms; Algorithm; Mathematics; Discrete mathematics; Theoretical computer science; Combinatorics; Artificial intelligence; Data mining; Pure mathematics","score_opus":0.04801050073090831,"score_gpt":0.3160797680561167,"score_spread":0.2680692673252084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126431245","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007514936,0.00028536268,0.98899204,0.0024064141,0.00031577033,0.00009388038,0.00000458361,0.000034172157,0.00035287256],"genre_scores_gemma":[0.5305412,0.0000774954,0.465851,0.00048690222,0.0017735184,0.000011344468,0.000020475209,0.000017416502,0.0012206425],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993457,0.000035528952,0.0001548348,0.00012518662,0.00016916204,0.0001695929],"domain_scores_gemma":[0.99961096,0.00007719451,0.000098887016,0.00012508174,0.000052909076,0.000034959066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040688994,0.00007566806,0.0000847071,0.00007739468,0.00031671114,0.0006135868,0.0004253392,0.000014121992,0.000004271776],"category_scores_gemma":[0.0000101554815,0.00004752437,0.00004640043,0.00015983018,0.00003464094,0.0005260815,0.00011313094,0.0000810377,0.0000063670973],"study_design_candidate":"design_other","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":[0.000023048324,0.000118907374,0.000401876,0.000021061856,0.00013125801,0.000041662075,0.00028291298,0.0023379114,0.0011856076,0.045242563,0.049108114,0.9011051],"study_design_scores_gemma":[0.0010253954,0.0001734617,0.019844593,0.000016682045,0.000057305286,0.0002369784,0.00006151869,0.8637421,0.00057234184,0.098279536,0.015765116,0.00022498515],"about_ca_topic_score_codex":0.000018254881,"about_ca_topic_score_gemma":0.000002583654,"teacher_disagreement_score":0.9008801,"about_ca_system_score_codex":0.00001266851,"about_ca_system_score_gemma":0.000013736972,"threshold_uncertainty_score":0.5916832},"labels":[],"label_agreement":null},{"id":"W2129088288","doi":"10.1007/s00778-012-0297-3","title":"Modeling the execution semantics of stream processing engines with SECRET","year":2012,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":false,"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; Semantics (computer science); Tuple; Key (lock); Range (aeronautics); Variation (astronomy); Window (computing); Programming language; Theoretical computer science; World Wide Web; Operating system; Engineering","score_opus":0.019849684280367718,"score_gpt":0.24530657120357555,"score_spread":0.22545688692320784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129088288","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13178492,0.0007300408,0.86679846,0.0004289753,0.00011651703,0.000044278888,0.0000011199103,0.000014981532,0.00008072075],"genre_scores_gemma":[0.96238995,0.00004020285,0.037269793,0.000033068245,0.0002363589,0.0000014175321,3.662926e-7,0.0000051765364,0.000023657632],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993444,0.00004972574,0.000156438,0.00005452873,0.0002185778,0.00017632465],"domain_scores_gemma":[0.9994917,0.000026422455,0.00013409895,0.00022380905,0.000083851344,0.000040139897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055124884,0.00007095515,0.0000836694,0.00002236911,0.000289533,0.000047602483,0.00027601363,0.000013863781,0.00000280438],"category_scores_gemma":[0.00001606244,0.000029396506,0.000023539336,0.00015548921,0.000044372053,0.00080567505,0.0000828077,0.0001534955,0.0000016504356],"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":[0.00010015958,0.0002015683,0.006000296,0.00021313326,0.0001631286,0.000018356204,0.040606774,0.6220019,0.008847545,0.17428897,0.0008109476,0.1467472],"study_design_scores_gemma":[0.00023551498,0.00006988301,0.00039687302,0.0002724215,0.000030262167,0.0013207766,0.0016942087,0.9884095,0.0028848185,0.0011776765,0.0033469477,0.00016110938],"about_ca_topic_score_codex":0.000012081161,"about_ca_topic_score_gemma":0.0000040974164,"teacher_disagreement_score":0.83060503,"about_ca_system_score_codex":0.000011201275,"about_ca_system_score_gemma":0.000039059396,"threshold_uncertainty_score":0.2226883},"labels":[],"label_agreement":null},{"id":"W2136058416","doi":"10.1007/s00778-006-0026-x","title":"Extending DBMSs with satellite databases","year":2006,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"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; Scalability; Middleware (distributed applications); Database; Architecture; Satellite; Distributed computing","score_opus":0.012294103049097956,"score_gpt":0.2241104797065471,"score_spread":0.21181637665744915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136058416","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044550795,0.0029584595,0.94359124,0.0015281404,0.0005104327,0.000084433545,0.000010675748,0.00007837615,0.006687425],"genre_scores_gemma":[0.99095005,0.00008117354,0.0076616844,0.0001500931,0.0004979842,0.000002292116,0.0000027399935,0.000007491654,0.0006464648],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990006,0.00007131828,0.00020511528,0.00014245091,0.00031093965,0.0002695545],"domain_scores_gemma":[0.9992971,0.0000512622,0.00014599109,0.00038495735,0.00006065185,0.000060033868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051762845,0.000099799865,0.00011231731,0.00004122752,0.00036348982,0.00041051712,0.00073666614,0.000013331634,0.000012239369],"category_scores_gemma":[0.000006670561,0.000051613453,0.00004102362,0.0002672469,0.000044472046,0.0005108143,0.00007174981,0.00020086524,0.00004257617],"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":[0.00009777313,0.00034406473,0.018325688,0.000045255863,0.00015838521,0.001493859,0.0012849439,0.0055979528,0.0061549633,0.608072,0.038400825,0.32002428],"study_design_scores_gemma":[0.0017286808,0.00019867279,0.06542601,0.00050730014,0.00003875882,0.012170225,0.00029613698,0.016400838,0.0028296139,0.007896343,0.89175975,0.0007476509],"about_ca_topic_score_codex":0.000056158216,"about_ca_topic_score_gemma":0.00001879866,"teacher_disagreement_score":0.9463993,"about_ca_system_score_codex":0.000024966132,"about_ca_system_score_gemma":0.00004399429,"threshold_uncertainty_score":0.3958626},"labels":[],"label_agreement":null},{"id":"W2141724398","doi":"10.1007/s00778-005-0172-6","title":"Query optimization in XML structured-document databases","year":2006,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":false,"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; XPath; Query optimization; XML validation; Streaming XML; XML database; Information retrieval; Efficient XML Interchange; Query language; XML Schema Editor; XML; Document Structure Description; Query expansion; XML Schema (W3C); XML Encryption; Database; World Wide Web","score_opus":0.010908030588630723,"score_gpt":0.2453907915984678,"score_spread":0.2344827610098371,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141724398","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011005714,0.0005964163,0.98674345,0.0006749823,0.00046728895,0.00007991905,0.0000085880165,0.000030470315,0.0003931883],"genre_scores_gemma":[0.42313746,0.00024030787,0.5748421,0.0003794322,0.00089153915,0.000010506086,0.000028930162,0.000018472889,0.00045127288],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.99902105,0.000108752254,0.00028258594,0.00014012627,0.0002407598,0.00020671826],"domain_scores_gemma":[0.9993535,0.000049666814,0.0001507112,0.00036574976,0.000042347747,0.00003799717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042021493,0.000096150514,0.00010690593,0.00008633788,0.00020300742,0.00011217045,0.00036376927,0.000015202091,0.000037740687],"category_scores_gemma":[0.000024632513,0.000059146747,0.00003139387,0.00023114399,0.000035786918,0.0010872954,0.00014724176,0.00018528839,0.0000072886387],"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":[0.000016975786,0.00003990072,0.001325732,0.000010897464,0.00001189145,0.000116657844,0.00027648348,0.5609399,0.0007250502,0.42008922,0.0039731394,0.012474128],"study_design_scores_gemma":[0.0050540366,0.00032220414,0.032753363,0.00085561874,0.000049832466,0.007973842,0.0012637082,0.35631302,0.014299236,0.0932053,0.48583502,0.0020748219],"about_ca_topic_score_codex":0.00020973348,"about_ca_topic_score_gemma":0.00015113979,"teacher_disagreement_score":0.4818619,"about_ca_system_score_codex":0.0000555899,"about_ca_system_score_gemma":0.00005940809,"threshold_uncertainty_score":0.24119344},"labels":[],"label_agreement":null},{"id":"W2141833902","doi":"10.1007/s00778-012-0278-6","title":"Scalable and dynamically balanced shared-everything OLTP with physiological partitioning","year":2012,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"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; Scalability; Thread (computing); Heap (data structure); Multi-core processor; Distributed computing; Parallel computing; Database transaction; Operating system; Programming language","score_opus":0.01529434217783311,"score_gpt":0.22644222987697848,"score_spread":0.2111478876991454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141833902","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60463494,0.0007275941,0.39169726,0.0015346851,0.00031466188,0.00008543678,0.000004543857,0.00006971178,0.00093119894],"genre_scores_gemma":[0.99308646,0.00002400667,0.006248422,0.00030148617,0.00024423553,0.0000044966423,0.000001195256,0.000004586886,0.00008511425],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99902254,0.00009444966,0.00017004649,0.00012732958,0.00022057169,0.0003650408],"domain_scores_gemma":[0.99942595,0.000049742797,0.00012053087,0.00019339821,0.00006059361,0.00014981008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005822414,0.00009959012,0.00014114952,0.000019058036,0.0004523919,0.00039797506,0.00040029408,0.000036065157,0.000020083758],"category_scores_gemma":[0.000024031231,0.0000516688,0.00003191752,0.00015721242,0.00006244627,0.00082722,0.00010583498,0.00029234352,0.000020350639],"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":[0.00049761496,0.0016052963,0.31686607,0.00025061148,0.0009279888,0.00042463568,0.023181189,0.015517805,0.079574876,0.35461658,0.06424127,0.14229605],"study_design_scores_gemma":[0.0024176058,0.00051852956,0.7311139,0.0007597424,0.000045821438,0.0066627213,0.00055904104,0.23309268,0.00046950445,0.007669544,0.015759625,0.00093127886],"about_ca_topic_score_codex":0.0000067980004,"about_ca_topic_score_gemma":0.0000012224281,"teacher_disagreement_score":0.41424784,"about_ca_system_score_codex":0.000026777127,"about_ca_system_score_gemma":0.00002515196,"threshold_uncertainty_score":0.38376826},"labels":[],"label_agreement":null},{"id":"W2143682328","doi":"10.1007/s00778-004-0128-2","title":"Supporting top-k join queries in relational databases","year":2004,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":387,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Joins; Computer science; Join (topology); Sort-merge join; Query optimization; Ranking (information retrieval); Hash join; Database; Relational database; Heuristic; Query language; Sargable; Information retrieval; Rank (graph theory); Heuristics; Relational algebra; Query expansion; Theoretical computer science; Web search query; Search engine; Programming language; Mathematics; Artificial intelligence","score_opus":0.04003804845750331,"score_gpt":0.2958259358899701,"score_spread":0.2557878874324668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143682328","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08592413,0.00024778195,0.89419013,0.01591039,0.000657874,0.00009341004,0.000006407854,0.000056268607,0.0029135987],"genre_scores_gemma":[0.7763634,0.00016512841,0.2193082,0.0016983472,0.0008088802,0.0000058208825,0.000022838836,0.000014401987,0.0016130155],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991531,0.000041552248,0.00023064358,0.00011258394,0.00024928644,0.0002128277],"domain_scores_gemma":[0.9995353,0.000043724347,0.00011685778,0.00024414019,0.000021142978,0.0000387867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094245496,0.0000639756,0.000067365305,0.00009654262,0.00020541997,0.00022674275,0.0006272252,0.0000095188625,0.00005282147],"category_scores_gemma":[0.00007608397,0.000042274296,0.000029924397,0.00024418673,0.000034217155,0.0014371225,0.0002795435,0.00021708157,0.00004982662],"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":[0.000011514079,0.00012091346,0.014382721,0.000009410037,0.000034611545,0.00041544854,0.0022386326,0.0041769226,0.00023619803,0.8991257,0.008121914,0.07112599],"study_design_scores_gemma":[0.0048954454,0.0002619804,0.2190561,0.00046893457,0.00004181938,0.0024770394,0.0018277079,0.031794924,0.0031690001,0.44939482,0.28544724,0.0011649864],"about_ca_topic_score_codex":0.000036767797,"about_ca_topic_score_gemma":0.000026290398,"teacher_disagreement_score":0.6904392,"about_ca_system_score_codex":0.000034812856,"about_ca_system_score_gemma":0.00007023131,"threshold_uncertainty_score":0.21864855},"labels":[],"label_agreement":null},{"id":"W2145957360","doi":"10.1007/s00778-011-0230-1","title":"Maximizing bichromatic reverse nearest neighbor for L p -norm in two- and three-dimensional spaces","year":2011,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Curse of dimensionality; Computer science; k-nearest neighbors algorithm; Norm (philosophy); Fixed-radius near neighbors; Best bin first; Space (punctuation); Algorithm; Nearest neighbor search; Theoretical computer science; Combinatorics; Mathematics; Data mining; Artificial intelligence; Cluster analysis","score_opus":0.046977370759670206,"score_gpt":0.2579352204925931,"score_spread":0.2109578497329229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145957360","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5514968,0.0011292583,0.4329037,0.008761338,0.0019035339,0.000807393,0.000010502421,0.00010863827,0.002878831],"genre_scores_gemma":[0.63397783,0.00008722584,0.363766,0.0011735898,0.00045760165,0.00001773359,0.0000027028195,0.00002345283,0.0004938332],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992262,0.00003655296,0.00018478569,0.00014518524,0.00017404425,0.00023319644],"domain_scores_gemma":[0.9994735,0.00008328381,0.000111718255,0.00023990606,0.000028391758,0.000063190775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084906584,0.000093595976,0.000112110996,0.00010717662,0.0002191027,0.00027093166,0.000641739,0.0000137939005,0.00003354101],"category_scores_gemma":[0.00003195816,0.000058749556,0.000035623976,0.00016901713,0.000052406405,0.00076205225,0.000293374,0.00014567154,0.000014974271],"study_design_candidate":"design_other","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":[0.00030164857,0.00066018023,0.030639822,0.00021318578,0.0004259837,0.0009030462,0.012468022,0.0006329119,0.0012680562,0.21602754,0.0412559,0.6952037],"study_design_scores_gemma":[0.0051279576,0.00044773635,0.07537672,0.00044422876,0.00008726793,0.00094190927,0.0005677615,0.68868095,0.00040717432,0.21871825,0.00848255,0.0007175011],"about_ca_topic_score_codex":0.00008908434,"about_ca_topic_score_gemma":0.000113958275,"teacher_disagreement_score":0.6944862,"about_ca_system_score_codex":0.000016075875,"about_ca_system_score_gemma":0.000028946568,"threshold_uncertainty_score":0.26126003},"labels":[],"label_agreement":null},{"id":"W2147440220","doi":"10.1007/s007780000029","title":"One-dimensional and multi-dimensional substring selectivity estimation","year":2000,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Substring; Computer science; String (physics); Context (archaeology); Matching (statistics); String searching algorithm; Constraint (computer-aided design); Theoretical computer science; Algorithm; Data structure; Mathematics; Pattern matching; Artificial intelligence; Statistics","score_opus":0.02152338838573285,"score_gpt":0.24920143496609998,"score_spread":0.22767804658036714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147440220","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6888267,0.0005003804,0.30888307,0.0013184862,0.00022804718,0.00008448188,0.000002882386,0.000062930725,0.00009301303],"genre_scores_gemma":[0.82727724,0.000041474552,0.17196177,0.00035298802,0.00016663587,0.0000018750304,0.0000023107334,0.000007700995,0.00018799887],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989618,0.00010443696,0.00017577088,0.0001875331,0.00036210864,0.00020834773],"domain_scores_gemma":[0.99943674,0.00009401051,0.000078939185,0.00022398596,0.000053709904,0.00011263141],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005727402,0.00009876985,0.000105323015,0.000052492232,0.00068650284,0.00022856896,0.0003622432,0.00003727535,0.000092281814],"category_scores_gemma":[0.000020280848,0.00006669457,0.000034985573,0.0001544467,0.000047334022,0.00073162495,0.0001546868,0.00032505294,0.00003313093],"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":[0.000038134036,0.00016292772,0.0004247605,0.0000035880678,0.000025138808,0.000024945,0.00031944597,0.029564861,0.0029081884,0.00080005685,0.001531055,0.9641969],"study_design_scores_gemma":[0.0005017431,0.00004381552,0.04055607,0.00004270785,0.0000075387893,0.0008143003,0.000002145352,0.9534601,0.0006595825,0.003173517,0.0006227945,0.00011570321],"about_ca_topic_score_codex":0.000022432174,"about_ca_topic_score_gemma":0.0000027304573,"teacher_disagreement_score":0.96408117,"about_ca_system_score_codex":0.00002884546,"about_ca_system_score_gemma":0.000062563166,"threshold_uncertainty_score":0.5280094},"labels":[],"label_agreement":null},{"id":"W2156892372","doi":"10.1007/s00778-009-0162-1","title":"Threshold-based probabilistic top-k dominating queries","year":2009,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Randomized algorithm; Scalability; Probabilistic logic; Computer science; Computation; Uncertain data; Set (abstract data type); Efficient algorithm; Dominating set; Algorithm; Theoretical computer science; Data mining; Artificial intelligence; Database","score_opus":0.015818699428412988,"score_gpt":0.24787564485482708,"score_spread":0.23205694542641409,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156892372","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04245729,0.0003537399,0.90752685,0.034562666,0.0010406319,0.00028166352,0.0000020745995,0.0002081068,0.01356695],"genre_scores_gemma":[0.94902843,0.000016560154,0.04769823,0.0021261044,0.00046322617,0.0000032609175,0.0000013971055,0.0000062928702,0.0006564743],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908096,0.000053534208,0.00018807492,0.00013885724,0.00029186884,0.0002467116],"domain_scores_gemma":[0.9993264,0.000057022626,0.00011289282,0.00039412867,0.0000513405,0.00005821304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085827,0.000096133816,0.00009421365,0.00006827714,0.00039130013,0.0007517746,0.0013023642,0.000016669088,0.00002908086],"category_scores_gemma":[0.00006427601,0.00005745108,0.000057264337,0.0002442651,0.000045532357,0.0006292971,0.000109887944,0.00021571323,0.000030155585],"study_design_candidate":"design_other","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":[0.000022368713,0.00017121155,0.0003732225,0.000015455142,0.000030872754,0.00017438312,0.0010249282,0.002529836,0.0005067175,0.27802053,0.014272625,0.70285785],"study_design_scores_gemma":[0.0019663484,0.0007369018,0.01244474,0.0001998074,0.00005723157,0.0003899255,0.00024616375,0.560142,0.0022067353,0.3867025,0.034181383,0.00072628807],"about_ca_topic_score_codex":0.0000017475049,"about_ca_topic_score_gemma":0.0000010890271,"teacher_disagreement_score":0.90657115,"about_ca_system_score_codex":0.000025842819,"about_ca_system_score_gemma":0.00004503547,"threshold_uncertainty_score":0.724938},"labels":[],"label_agreement":null},{"id":"W2157044362","doi":"10.1007/s00778-008-0128-8","title":"Top-k typicality queries and efficient query answering methods on large databases","year":2009,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"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; Discriminative model; Set (abstract data type); Tree (set theory); Information retrieval; Measure (data warehouse); Quality (philosophy); Series (stratigraphy); Data mining; Artificial intelligence; Mathematics","score_opus":0.03418460099070763,"score_gpt":0.3495786809841878,"score_spread":0.3153940799934802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157044362","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035873566,0.0003670431,0.9573062,0.0044531305,0.00039832413,0.00006200497,0.0000060499137,0.000053730448,0.0014799628],"genre_scores_gemma":[0.6142283,0.00045136965,0.3793693,0.0047743698,0.0007101229,0.0000027180422,0.0000056619433,0.000011955365,0.0004461829],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990261,0.00019574408,0.00016028677,0.00017445078,0.00020283234,0.00024058837],"domain_scores_gemma":[0.99929667,0.000112033355,0.00007292708,0.0004200904,0.00002229746,0.00007598586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018326438,0.00009570341,0.00010875339,0.00006448283,0.00036471247,0.0003854737,0.00060342555,0.000012875635,0.000017743578],"category_scores_gemma":[0.00007951713,0.000057523357,0.000035637862,0.00016837813,0.000037087753,0.0003801336,0.00027400142,0.00022113911,0.000009791759],"study_design_candidate":"design_other","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":[0.000027751672,0.00016566945,0.000320996,0.0000075106464,0.000028730585,0.000055382905,0.0006347288,0.00020131226,0.00044049768,0.32669386,0.002776769,0.66864675],"study_design_scores_gemma":[0.0022958938,0.0009368299,0.14126079,0.00031155933,0.00009617844,0.0007130667,0.00093927386,0.23940115,0.009359151,0.05078971,0.5527018,0.0011946383],"about_ca_topic_score_codex":0.000004490804,"about_ca_topic_score_gemma":0.0000012187187,"teacher_disagreement_score":0.66745216,"about_ca_system_score_codex":0.00001467214,"about_ca_system_score_gemma":0.00001538099,"threshold_uncertainty_score":0.37171316},"labels":[],"label_agreement":null},{"id":"W2170688652","doi":"10.1007/s00778-007-0067-9","title":"Applications of corpus-based semantic similarity and word segmentation to database schema matching","year":2007,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Schema matching; Computer science; Semantic similarity; Artificial intelligence; Schema (genetic algorithms); Star schema; Natural language processing; Information retrieval; Segmentation; Pattern recognition (psychology); Database schema; Data mining; Data integration","score_opus":0.1166235600128447,"score_gpt":0.4294959857511475,"score_spread":0.3128724257383028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170688652","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25725114,0.000073870804,0.7390159,0.0031461904,0.00007167492,0.0002022231,0.0000286172,0.0000068843606,0.00020354128],"genre_scores_gemma":[0.9720079,0.000036627316,0.025890436,0.0017521403,0.00010091992,0.0000056048175,0.000009905852,0.0000056362674,0.00019087114],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982775,0.00014283304,0.00049826707,0.00015467667,0.0007799368,0.00014681801],"domain_scores_gemma":[0.99824923,0.00080030964,0.0002847238,0.0004223816,0.00012847946,0.00011488975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011068163,0.00006629908,0.00012122143,0.00020601135,0.0003059042,0.00020156655,0.00051331724,0.000017180224,0.000105549974],"category_scores_gemma":[0.00036475615,0.00004171928,0.00003530759,0.0004948014,0.000071425995,0.00026181326,0.00017732287,0.00014647646,0.00004210326],"study_design_candidate":"design_other","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":[0.00023437409,0.00023857431,0.003697193,0.00004386875,0.000048859143,0.000014702019,0.0017935543,0.00083321135,0.018868158,0.0137209045,0.0099991,0.9505075],"study_design_scores_gemma":[0.005357501,0.00045217972,0.12669311,0.0004456205,0.0003885247,0.00030671526,0.035678502,0.005412393,0.06898663,0.3467853,0.40843096,0.0010625541],"about_ca_topic_score_codex":0.000045802743,"about_ca_topic_score_gemma":0.00014387032,"teacher_disagreement_score":0.94944495,"about_ca_system_score_codex":0.000019477227,"about_ca_system_score_gemma":0.000030121219,"threshold_uncertainty_score":0.38360268},"labels":[],"label_agreement":null},{"id":"W2172197636","doi":"10.1007/s00778-011-0260-8","title":"Scalability of write-ahead logging on multicore and multisocket hardware","year":2011,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":false,"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; Scalability; Multi-core processor; Serialization; Operating system; Parallel computing; Database","score_opus":0.04511224232357768,"score_gpt":0.24973414704582975,"score_spread":0.20462190472225206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2172197636","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9024221,0.00047329388,0.09427904,0.00062949676,0.00070754666,0.00015931178,0.000017501501,0.000043688462,0.0012680495],"genre_scores_gemma":[0.99565494,0.00002332106,0.004099907,0.00009033846,0.00007703335,0.000001833157,2.8923665e-7,0.0000046613936,0.00004767807],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99898744,0.000108853914,0.00029889133,0.0001672533,0.00023089927,0.00020664434],"domain_scores_gemma":[0.99914086,0.00007659063,0.00018467885,0.00039285488,0.00010640821,0.000098581666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007591964,0.00010391051,0.00017864777,0.000042500913,0.00020710568,0.0000772237,0.0006168469,0.000041919022,0.000017589866],"category_scores_gemma":[0.000056414487,0.000063039515,0.00006470856,0.00011672758,0.00010652143,0.00021501441,0.000113243244,0.00026956058,0.000010461357],"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":[0.00033798348,0.0013510663,0.22637214,0.0003046164,0.00027144293,0.00023996754,0.0394766,0.00041939577,0.0061981184,0.032421097,0.008517948,0.68408966],"study_design_scores_gemma":[0.0028323052,0.00070947735,0.8804856,0.0007618115,0.000038040966,0.0011935431,0.0010865428,0.08644866,0.008117363,0.010284371,0.007429834,0.0006124443],"about_ca_topic_score_codex":0.000053406326,"about_ca_topic_score_gemma":0.0000054649236,"teacher_disagreement_score":0.68347716,"about_ca_system_score_codex":0.000020766689,"about_ca_system_score_gemma":0.000027805956,"threshold_uncertainty_score":0.25706768},"labels":[],"label_agreement":null},{"id":"W2386452338","doi":"10.1007/s00778-017-0463-8","title":"Efficiently making (almost) any concurrency control mechanism serializable","year":2017,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Serialization; Concurrency control; Serializability; Commit; Transactional memory; Distributed transaction; Online transaction processing; Database transaction","score_opus":0.018270925180170403,"score_gpt":0.27674830958537444,"score_spread":0.258477384405204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2386452338","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017818784,0.000633671,0.966586,0.0029835464,0.006035461,0.00021572513,0.000021091859,0.000070578244,0.005635147],"genre_scores_gemma":[0.9978463,0.000023116852,0.00082132994,0.0003065338,0.00058160594,0.000005489957,3.732341e-7,0.00000903691,0.00040618188],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983852,0.00015154887,0.00035325967,0.00022442266,0.00042208904,0.0004634875],"domain_scores_gemma":[0.99806243,0.00004835814,0.00059474196,0.0009960841,0.00017852247,0.00011984779],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0015280124,0.00016028417,0.00024741137,0.000039654777,0.002172553,0.0023311467,0.0029551117,0.000058901667,0.00004634498],"category_scores_gemma":[0.000112885435,0.00010217879,0.00012233756,0.00008670208,0.00007901518,0.00068263896,0.00022326328,0.0003287914,0.00010686469],"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":[0.0000862743,0.0002266769,0.0012703473,0.000049152775,0.00024426542,0.0005133927,0.002697316,0.0015117129,0.0132036265,0.9047236,0.02325962,0.052214038],"study_design_scores_gemma":[0.013261551,0.00088589865,0.012271766,0.0015370887,0.00015831688,0.0077986657,0.00047566363,0.58479494,0.0047131325,0.102216855,0.26995108,0.0019350688],"about_ca_topic_score_codex":0.000019693678,"about_ca_topic_score_gemma":0.0000030922508,"teacher_disagreement_score":0.98002756,"about_ca_system_score_codex":0.000045228964,"about_ca_system_score_gemma":0.000117655,"threshold_uncertainty_score":0.9991265},"labels":[],"label_agreement":null},{"id":"W2755658662","doi":"10.1007/s00778-019-00548-x","title":"The ubiquity of large graphs and surprising challenges of graph processing: extended survey","year":2019,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":false,"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":"Suite; Graph; Scalability; Graph drawing; Visualization; Call graph; Data visualization","score_opus":0.02115508178165599,"score_gpt":0.263779211117652,"score_spread":0.24262412933599603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2755658662","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97707313,0.010872157,0.01053594,0.0006123199,0.00033721482,0.00010351246,0.0000034475877,0.000017381304,0.00044487312],"genre_scores_gemma":[0.99787635,0.0015956026,0.00045531598,0.000024503575,0.000015209698,6.114546e-7,1.1724429e-7,0.000005328564,0.00002697661],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998464,0.0005570263,0.00028938596,0.00013960875,0.00030292151,0.0002470809],"domain_scores_gemma":[0.9985958,0.00042138866,0.00036021325,0.00037201797,0.00019453108,0.000056075187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00607511,0.000102001664,0.00018986834,0.00008984667,0.00037550429,0.00010300818,0.00094073947,0.00003630782,0.0000032411062],"category_scores_gemma":[0.00006336103,0.000051677114,0.00008557205,0.00033507758,0.00019087331,0.00027276704,0.00018134832,0.0002671097,9.784143e-7],"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":[0.00016533502,0.00030480957,0.015720204,0.00015055858,0.00019535318,0.000009244594,0.011057681,0.000034266897,0.0042524203,0.69050604,0.00008848106,0.27751562],"study_design_scores_gemma":[0.00078861014,0.00028353062,0.37315848,0.00018092996,0.000018981309,0.00025713403,0.0011980322,0.0020374642,0.0047164536,0.6170143,0.00015453479,0.00019152297],"about_ca_topic_score_codex":0.000007987756,"about_ca_topic_score_gemma":0.000022604152,"teacher_disagreement_score":0.3574383,"about_ca_system_score_codex":0.0000035692722,"about_ca_system_score_gemma":0.00005263678,"threshold_uncertainty_score":0.28881133},"labels":[],"label_agreement":null},{"id":"W2948421209","doi":"10.1007/s00778-019-00543-2","title":"Thematic issue on data management for graphs","year":2019,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Thematic map; Data science; Computer science; Data management; Geography; Cartography; Database","score_opus":0.05563453672975735,"score_gpt":0.3060517895038253,"score_spread":0.2504172527740679,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2948421209","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047362912,0.0002446939,0.94170827,0.014735415,0.002124244,0.001084277,0.000004943605,0.00014750338,0.03521439],"genre_scores_gemma":[0.833248,0.00032351734,0.15442996,0.0031505532,0.00074210594,0.000053310567,0.000004119177,0.000034384662,0.008014005],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99923587,0.00005771357,0.00018290042,0.00015891182,0.00019951079,0.00016512169],"domain_scores_gemma":[0.9985333,0.00008663976,0.00012209968,0.0011994104,0.000022741853,0.000035777986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012308634,0.000078087774,0.000108841705,0.00007224922,0.00014232814,0.00025531475,0.0024703604,0.00001763966,0.00003056858],"category_scores_gemma":[0.000005151756,0.000041341304,0.000051556905,0.00010208858,0.000007966555,0.0002559426,0.0003382904,0.000118244534,0.00010551504],"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":[0.000010232278,0.00007938091,0.00008437195,0.000087691005,0.00014215191,0.000009388584,0.00056636863,0.000013909744,0.00007895463,0.40165484,0.27338153,0.32389116],"study_design_scores_gemma":[0.0010643312,0.00058514794,0.00058557827,0.00048212893,0.00003883558,0.0005071969,0.00050353265,0.034307387,0.00095783995,0.41183752,0.54875714,0.00037338486],"about_ca_topic_score_codex":0.0000026326718,"about_ca_topic_score_gemma":4.4519345e-7,"teacher_disagreement_score":0.8285118,"about_ca_system_score_codex":0.000014010667,"about_ca_system_score_gemma":0.000008742342,"threshold_uncertainty_score":0.45905855},"labels":[],"label_agreement":null},{"id":"W3171876400","doi":"10.1007/s00778-021-00679-0","title":"A fractional memory-efficient approach for online continuous-time influence maximization","year":2021,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Maximization; Computer science; Mathematical optimization; Mathematics","score_opus":0.010919874059083779,"score_gpt":0.2582131317671943,"score_spread":0.2472932577081105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3171876400","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1341439,0.00008488826,0.8637192,0.00043667408,0.0000464047,0.00013692048,0.000025015288,0.000027285867,0.0013796752],"genre_scores_gemma":[0.9196953,0.0000055219784,0.077435054,0.00015789513,0.0012630747,0.000024778732,0.00015082593,0.000020767626,0.0012467912],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913144,0.000088803965,0.00025726456,0.0001378537,0.00020227066,0.00018234883],"domain_scores_gemma":[0.9991004,0.00009883421,0.00020531811,0.00018881542,0.00035343744,0.00005320475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035076766,0.000102595644,0.00016856138,0.000045495108,0.00033488002,0.00012819348,0.00019559251,0.000021390913,0.0006691922],"category_scores_gemma":[0.000018465917,0.000074654214,0.00018124108,0.00020312391,0.000030640822,0.000067207795,0.00005465712,0.00024488737,0.00000772772],"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":[0.00011809207,0.0012833186,0.004177218,0.000012395496,0.0007750993,0.000006001822,0.00040212553,0.84686744,0.01123306,0.009478392,0.018928917,0.10671795],"study_design_scores_gemma":[0.0012176274,0.00007007688,0.0039509297,0.000049895934,0.00032800235,0.0001474991,0.00065927755,0.9514089,0.0061920243,0.017214058,0.018365072,0.0003966082],"about_ca_topic_score_codex":0.000012224685,"about_ca_topic_score_gemma":6.447234e-7,"teacher_disagreement_score":0.78628415,"about_ca_system_score_codex":0.000031526597,"about_ca_system_score_gemma":0.00009685852,"threshold_uncertainty_score":0.73271847},"labels":[],"label_agreement":null},{"id":"W4322741464","doi":"10.1007/s00778-023-00787-z","title":"Leveraging user itinerary to improve personalized deep matching at Fliggy","year":2023,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Science Foundation of Guangxi Province; National Natural Science Foundation of China","keywords":"Computer science; Matching (statistics); Weighting; Benchmark (surveying); Artificial intelligence; Machine learning; Data mining","score_opus":0.026442433696779455,"score_gpt":0.2688672081487491,"score_spread":0.24242477445196964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322741464","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39367315,0.0002117512,0.57770306,0.023380319,0.0016519895,0.00023594678,0.0000012838798,0.00054863153,0.0025938354],"genre_scores_gemma":[0.96220905,0.00008681321,0.025986457,0.0033063705,0.0009356843,0.00003074424,0.0000010141998,0.00003620322,0.0074076406],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985888,0.00016469164,0.00028249293,0.00021877096,0.0003477855,0.00039743073],"domain_scores_gemma":[0.99916667,0.00011627102,0.00012504593,0.00038809533,0.000054271644,0.00014961904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013461739,0.00013927366,0.0001725438,0.00016651962,0.00062164,0.0004836429,0.0010804201,0.000036787413,0.00004171755],"category_scores_gemma":[0.000019289097,0.00008888806,0.00012331782,0.00039570205,0.000015599619,0.0003495732,0.00063141953,0.00029993808,0.00021265849],"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":[0.000085743704,0.000092861985,0.0025377632,0.000091324095,0.0003972641,0.0009790786,0.089585245,0.0010308744,0.1288319,0.051058438,0.34630543,0.37900406],"study_design_scores_gemma":[0.003307039,0.000618618,0.015457814,0.0007293791,0.00006431703,0.010704515,0.0042108465,0.09693324,0.041721627,0.14948629,0.6744457,0.0023206032],"about_ca_topic_score_codex":0.00004836356,"about_ca_topic_score_gemma":0.000004489377,"teacher_disagreement_score":0.5685359,"about_ca_system_score_codex":0.000098196724,"about_ca_system_score_gemma":0.0000374553,"threshold_uncertainty_score":0.47812152},"labels":[],"label_agreement":null},{"id":"W4364362023","doi":"10.1007/s00778-023-00794-0","title":"ByShard: sharding in a Byzantine environment","year":2023,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Scalability; Distributed computing; Atomicity; Commit; Flexibility (engineering); Latency (audio); Isolation (microbiology); Byzantine fault tolerance; Protocol (science); Software deployment; Throughput; Database transaction; Computer network; Fault tolerance; Database; Operating system; Wireless","score_opus":0.016390848947298697,"score_gpt":0.22849349027064442,"score_spread":0.21210264132334572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4364362023","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50923973,0.002085848,0.43448165,0.041272298,0.0030022308,0.0005162007,0.000030398414,0.0004118315,0.008959798],"genre_scores_gemma":[0.9982363,0.00016740423,0.0005381435,0.00021026166,0.00020193092,0.000006528924,0.0000012154284,0.000006426134,0.0006318039],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99895334,0.000078286736,0.00024162677,0.0001391977,0.00029019418,0.00029733303],"domain_scores_gemma":[0.99951243,0.00004421161,0.000089194196,0.00028026692,0.000011330174,0.00006258153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011655586,0.00007915767,0.0001179201,0.00008986397,0.00017319023,0.00021135302,0.0008244491,0.000024528259,0.00003719244],"category_scores_gemma":[0.000020011834,0.000050550672,0.000059492977,0.0004262603,0.000018545541,0.0002249213,0.00018962489,0.00025288344,0.0005210594],"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":[0.00007269919,0.00043745796,0.02715839,0.000086269596,0.00026662453,0.0037946862,0.015204143,0.06339353,0.023755886,0.10228636,0.32150808,0.44203588],"study_design_scores_gemma":[0.0017506898,0.00009461881,0.10839242,0.00028701525,0.000008934044,0.0013157452,0.0003450863,0.2489909,0.0006327664,0.0054905335,0.6322161,0.00047522783],"about_ca_topic_score_codex":0.000009529307,"about_ca_topic_score_gemma":0.0000011117822,"teacher_disagreement_score":0.48899654,"about_ca_system_score_codex":0.000025970048,"about_ca_system_score_gemma":0.000022463237,"threshold_uncertainty_score":0.6697338},"labels":[],"label_agreement":null},{"id":"W4385408288","doi":"10.1007/s00778-023-00805-0","title":"Accelerating directed densest subgraph queries with software and hardware approaches","year":2023,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Complexity and Algorithms in Graphs","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; Shenzhen Science and Technology Innovation Program; National Natural Science Foundation of China; Chinese University of Hong Kong, Shenzhen","keywords":"Computer science; Speedup; Scalability; Parameterized complexity; Bipartite graph; Computation; Matching (statistics); Approximation algorithm; Linear programming; Theoretical computer science; Graph; Algorithm; Parallel computing; Mathematics","score_opus":0.08005984562599212,"score_gpt":0.2340146645626377,"score_spread":0.1539548189366456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385408288","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7074201,0.001056824,0.2834009,0.005551496,0.0005760097,0.0002341129,0.000007988479,0.0012153685,0.000537197],"genre_scores_gemma":[0.81933284,0.0002916522,0.17920403,0.00028750542,0.0004074233,0.00001922772,0.000003691547,0.000030113464,0.0004235345],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.998932,0.000113682436,0.00016265738,0.00019865637,0.0002927123,0.00030029952],"domain_scores_gemma":[0.9992285,0.00021901795,0.000101565456,0.0002805281,0.00007561862,0.00009478425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049525796,0.00013664804,0.00014186712,0.00014356663,0.0011149431,0.00076886883,0.00066124095,0.000030154823,0.000009422633],"category_scores_gemma":[0.00006854496,0.00008034425,0.000050111496,0.0008812029,0.00018629404,0.00043037647,0.00025696078,0.00035905148,0.0000070685205],"study_design_candidate":"design_other","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":[0.00009692661,0.00013521229,0.06555642,0.00012409949,0.00045149468,0.00071178755,0.02582942,0.0015028547,0.00035831693,0.057609566,0.008624384,0.8389995],"study_design_scores_gemma":[0.002751908,0.00097005785,0.5868365,0.000708388,0.0001248291,0.012418593,0.0061193067,0.20899817,0.002691992,0.16118704,0.015228858,0.0019643588],"about_ca_topic_score_codex":0.000013645755,"about_ca_topic_score_gemma":0.000039297156,"teacher_disagreement_score":0.8370352,"about_ca_system_score_codex":0.000010299646,"about_ca_system_score_gemma":0.000058856047,"threshold_uncertainty_score":0.8575353},"labels":[],"label_agreement":null},{"id":"W4386099755","doi":"10.1007/s00778-023-00809-w","title":"xDBTagger: explainable natural language interface to databases using keyword mappings and schema graph","year":2023,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"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; Pipeline (software); Schema (genetic algorithms); SQL; Artificial intelligence; Natural language; Natural language processing; Information retrieval; Database; Programming language","score_opus":0.04688202870401947,"score_gpt":0.31181788788836495,"score_spread":0.2649358591843455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386099755","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6806445,0.00093525054,0.31561193,0.0021692158,0.00042752648,0.000062245446,0.0000010218753,0.00008310599,0.00006516139],"genre_scores_gemma":[0.9465924,0.000054386754,0.05208988,0.0004517366,0.00023192608,0.000001984276,4.708818e-7,0.000010721693,0.0005664963],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989577,0.00006367297,0.00018197345,0.00020860141,0.00024503662,0.00034302336],"domain_scores_gemma":[0.9993094,0.00008073944,0.0000737453,0.0003796201,0.000045118446,0.000111362075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000747117,0.00010937866,0.0001186814,0.00019298425,0.00036750114,0.00032226188,0.00071082957,0.000017665117,0.000011164051],"category_scores_gemma":[0.00008969635,0.00007542698,0.00003910334,0.0005334483,0.000029963658,0.0005322303,0.0006945565,0.000313745,0.000029920318],"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":[0.00013142666,0.000107373875,0.0030604517,0.00021129212,0.00034323192,0.0016696744,0.1140708,0.033508502,0.40693057,0.026709212,0.033220787,0.38003668],"study_design_scores_gemma":[0.0010204224,0.00010131205,0.0014660109,0.00068606314,0.000036410704,0.0039214776,0.009868156,0.931417,0.026508125,0.004766223,0.019399889,0.00080893614],"about_ca_topic_score_codex":0.00006673081,"about_ca_topic_score_gemma":0.0000071798863,"teacher_disagreement_score":0.89790845,"about_ca_system_score_codex":0.000032243042,"about_ca_system_score_gemma":0.000036632697,"threshold_uncertainty_score":0.31075788},"labels":[],"label_agreement":null},{"id":"W4387098977","doi":"10.1007/s00778-023-00814-z","title":"A survey on transactional stream processing","year":2023,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":17,"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":"Banting and Best Diabetes Centre, University of Toronto; Singapore University of Technology and Design; National Research Foundation; Deutsche Forschungsgemeinschaft; Bundesministerium für Bildung und Forschung; Info-communications Media Development Authority; National Research Foundation Singapore; Bundesministerium für Bildung, Wissenschaft, Forschung und Technologie; Technische Universität Berlin","keywords":"Transactional leadership; Transactional analysis; Computer science; Perspective (graphical); Stream processing; Data science; Transaction processing; Database transaction; Distributed computing; Database; Artificial intelligence; Management; Economics; Psychology","score_opus":0.048473666201916135,"score_gpt":0.2954808845975803,"score_spread":0.2470072183956642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387098977","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035109177,0.00013396595,0.96165174,0.0017775942,0.000647573,0.00005949881,0.000027099835,0.0001382911,0.0004550709],"genre_scores_gemma":[0.9929062,0.00007237954,0.0050753215,0.00028269735,0.00042350317,0.000005471199,0.000008373531,0.000013005532,0.0012130506],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9991545,0.00011710331,0.0001430991,0.00011037056,0.00029042596,0.00018451014],"domain_scores_gemma":[0.9994904,0.00012790026,0.00007735787,0.00018614504,0.00006167789,0.000056532564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092148216,0.0000700497,0.00007641685,0.00006991739,0.0004643973,0.00011290957,0.00032138423,0.000015770804,0.000015718177],"category_scores_gemma":[0.000037143498,0.000040228188,0.000036619986,0.00041843747,0.000030025089,0.00040194448,0.000030280224,0.00021231729,0.00010306254],"study_design_candidate":"design_other","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":[0.00009994408,0.000119471675,0.0018325761,0.00003188914,0.0000759217,0.00021519072,0.0037435102,0.013647126,0.0012807769,0.036287002,0.03324425,0.90942234],"study_design_scores_gemma":[0.0022848377,0.00074951025,0.5470809,0.00070826506,0.000023263914,0.0024331936,0.0010446159,0.15628617,0.0036793482,0.016263377,0.26826048,0.0011860837],"about_ca_topic_score_codex":0.000020482454,"about_ca_topic_score_gemma":0.000028654806,"teacher_disagreement_score":0.957797,"about_ca_system_score_codex":0.000019991803,"about_ca_system_score_gemma":0.00008990629,"threshold_uncertainty_score":0.35718155},"labels":[],"label_agreement":null},{"id":"W4391785473","doi":"10.1007/s00778-024-00835-2","title":"Assisted design of data science pipelines","year":2024,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":6,"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":"Berlin Center for Machine Learning; Banting and Best Diabetes Centre, University of Toronto; Technische Universität Berlin","keywords":"Pipeline transport; Computer science; Data science; Engineering; Mechanical engineering","score_opus":0.16349691109568132,"score_gpt":0.37462525822397275,"score_spread":0.21112834712829143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391785473","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006856071,0.00086341816,0.9917012,0.005618825,0.00049519056,0.00003366468,0.000003287732,0.000056814763,0.00054201065],"genre_scores_gemma":[0.89051443,0.00018734258,0.10866622,0.0000932461,0.00026020006,7.1178437e-7,0.0000031787415,0.000005283742,0.0002693949],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895376,0.00013635158,0.00019434822,0.00019920067,0.00038380953,0.00013251058],"domain_scores_gemma":[0.9986504,0.0002050954,0.00008977019,0.0009136459,0.00009133512,0.0000497529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041198144,0.000052507774,0.00006370874,0.00013746011,0.00026296818,0.0005952428,0.0034386772,0.000013257358,0.000014937489],"category_scores_gemma":[0.00030155343,0.000028850958,0.000017348751,0.00078485644,0.00014908712,0.0014314261,0.0004341691,0.00024720273,0.000040270177],"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":[0.0000067517467,0.00003288495,0.00013432487,0.000016986665,0.000014749796,0.000017550132,0.0005671554,0.0008319439,0.03005883,0.040804103,0.012541042,0.9149737],"study_design_scores_gemma":[0.00005696119,0.00003392768,0.004316045,0.000058795817,0.0000106392,0.0005171837,0.000024260667,0.97239566,0.000577574,0.0025925243,0.019357288,0.000059167498],"about_ca_topic_score_codex":0.000007981723,"about_ca_topic_score_gemma":4.7902034e-7,"teacher_disagreement_score":0.9715637,"about_ca_system_score_codex":0.000016071077,"about_ca_system_score_gemma":0.00035978557,"threshold_uncertainty_score":0.6389975},"labels":[],"label_agreement":null},{"id":"W4398180243","doi":"10.1007/s00778-024-00847-y","title":"Discovering approximate implicit domain orders through order dependencies","year":2024,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; York University; University of Waterloo","funders":"","keywords":"Computer science; Domain (mathematical analysis); Order (exchange); Data mining; Theoretical computer science; Mathematics; Business","score_opus":0.13203993517966403,"score_gpt":0.4151772800383418,"score_spread":0.2831373448586778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398180243","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1957649,0.001721779,0.73569643,0.039669383,0.0028108952,0.00027293627,0.00004807636,0.00012198453,0.023893626],"genre_scores_gemma":[0.98553294,0.00045236447,0.006881802,0.0019590356,0.0006289249,0.000008130974,0.000003658604,0.000029731524,0.0045033926],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99711156,0.00027820293,0.0005554371,0.00029852337,0.0013867844,0.00036948247],"domain_scores_gemma":[0.9985407,0.0005980427,0.00013165879,0.0005670225,0.000089540525,0.00007304237],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006603232,0.00014613965,0.0001906151,0.00013586483,0.0005182965,0.0028831125,0.0014306657,0.000035328525,0.001002899],"category_scores_gemma":[0.0005151496,0.000071916664,0.00013814372,0.0008709646,0.00014647795,0.0013251614,0.00051478326,0.0004017562,0.0006925345],"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":[0.00009060428,0.00009372886,0.00023645663,0.000058149366,0.0003760916,0.00034598683,0.028478723,0.003271715,0.0016066278,0.59979296,0.25212196,0.113527015],"study_design_scores_gemma":[0.00014929533,0.000030443665,0.00022556582,0.000044541826,0.000024167426,0.00028016596,0.015817802,0.0010324664,0.00012249907,0.5741414,0.40799484,0.0001368329],"about_ca_topic_score_codex":0.000085488406,"about_ca_topic_score_gemma":0.00008479601,"teacher_disagreement_score":0.78976804,"about_ca_system_score_codex":0.000049777984,"about_ca_system_score_gemma":0.00009127191,"threshold_uncertainty_score":0.9999103},"labels":[],"label_agreement":null},{"id":"W4400404039","doi":"10.1007/s00778-024-00860-1","title":"Minimum motif-cut: a workload-aware RDF graph partitioning strategy","year":2024,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Motif (music); RDF; Computer science; Workload; Graph; Parallel computing; Theoretical computer science; Artificial intelligence; Operating system; Art; Semantic Web","score_opus":0.01798901487496369,"score_gpt":0.25051093290324294,"score_spread":0.23252191802827926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400404039","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12579353,0.008362527,0.84913224,0.0073649776,0.004234648,0.00017148482,0.000006974517,0.00047209856,0.0044615013],"genre_scores_gemma":[0.9971019,0.00019092765,0.0011352608,0.00026049174,0.0005505976,0.000005314096,5.3470905e-7,0.000012596575,0.0007423658],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99861723,0.0002044469,0.00026208573,0.00022658617,0.00030623167,0.00038339317],"domain_scores_gemma":[0.9992418,0.00015546437,0.00006993097,0.00033079265,0.000058218004,0.000143739],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001028327,0.00015010129,0.00012510283,0.0001708545,0.0006185409,0.001379666,0.0009802816,0.0000484748,0.00013631812],"category_scores_gemma":[0.000014238801,0.0000944668,0.00018911909,0.0007697914,0.00009843123,0.00066517195,0.00011592162,0.0006208968,0.00017900305],"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":[0.00006980171,0.00017254098,0.00019515224,0.00006979134,0.00044085993,0.0019051929,0.008729089,0.0072748917,0.0012169322,0.5152762,0.016637586,0.448012],"study_design_scores_gemma":[0.00031499754,0.00039892163,0.0006185207,0.0006063091,0.00004615689,0.003037249,0.0006529272,0.080242984,0.0012074221,0.90782267,0.0046879794,0.0003638732],"about_ca_topic_score_codex":0.0000019269783,"about_ca_topic_score_gemma":0.0000040843665,"teacher_disagreement_score":0.8713084,"about_ca_system_score_codex":0.000020663103,"about_ca_system_score_gemma":0.00009521174,"threshold_uncertainty_score":0.999657},"labels":[],"label_agreement":null},{"id":"W4405006607","doi":"10.1007/s00778-024-00883-8","title":"A graph pattern mining framework for large graphs on GPU","year":2024,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"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; Graph; CUDA; Theoretical computer science; Data science; Data mining; Parallel computing","score_opus":0.0195451147952551,"score_gpt":0.27693911823719536,"score_spread":0.25739400344194024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405006607","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03222211,0.0009919321,0.96011466,0.0037009541,0.002545526,0.00009922255,0.000008638523,0.000116759176,0.000200223],"genre_scores_gemma":[0.97663087,0.000081404265,0.020623937,0.0019019361,0.00059554784,0.000015221598,6.2788166e-7,0.000019908115,0.00013052707],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988235,0.000119826334,0.00019736042,0.00021722852,0.0002488949,0.00039316042],"domain_scores_gemma":[0.99886835,0.00059288717,0.000064662294,0.0003358872,0.000038413647,0.000099779834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013809261,0.00013805986,0.00012063237,0.0002136311,0.0005517372,0.000665287,0.0009939418,0.00005815097,0.00003425303],"category_scores_gemma":[0.00004665792,0.00008212563,0.0002674016,0.0005085769,0.00003430827,0.00024806065,0.00008652165,0.00053585076,0.00004040342],"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":[0.000010558651,0.00004061267,0.00007893422,0.000014706493,0.00007711641,0.00007731303,0.0029312766,0.000032932996,0.00004480335,0.8725808,0.0023687347,0.12174217],"study_design_scores_gemma":[0.0001909285,0.00020348391,0.00023666763,0.00031660352,0.000017237971,0.00030376777,0.0001738462,0.013650687,0.00025403296,0.9774175,0.0070886915,0.00014650596],"about_ca_topic_score_codex":5.004271e-7,"about_ca_topic_score_gemma":6.552924e-7,"teacher_disagreement_score":0.9444088,"about_ca_system_score_codex":0.000011193804,"about_ca_system_score_gemma":0.000032956148,"threshold_uncertainty_score":0.6415378},"labels":[],"label_agreement":null},{"id":"W4411935250","doi":"10.1007/s00778-025-00933-9","title":"Beyond influence: voting theory for opinion maximization","year":2025,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Opinion Dynamics and Social Influence","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Key Research and Development Program of Zhejiang Province; Ningbo Municipal Bureau of Science and Technology; Novo Nordisk","keywords":"Voting; Maximization; Utility maximization; Approval voting; Mathematical economics; Political science; Computer science; Psychology; Economics; Social psychology; Disapproval voting; Law; Politics","score_opus":0.006804691820581122,"score_gpt":0.29149749965931665,"score_spread":0.2846928078387355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411935250","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3203505,0.00038242136,0.6576544,0.0036919268,0.0022424227,0.000435163,0.000035604742,0.00002986228,0.015177661],"genre_scores_gemma":[0.99787694,0.000017127286,0.00052796333,0.00032106412,0.000532999,0.000011632611,0.0000074653317,0.0000073140995,0.0006974627],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99942327,0.00006393254,0.00019849525,0.00007636353,0.00008073408,0.00015722949],"domain_scores_gemma":[0.9994666,0.00014778328,0.00013050946,0.00008768747,0.00013757148,0.000029830706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061057636,0.000073378775,0.00008813824,0.00004158619,0.00063726876,0.00014918884,0.00020432619,0.000025675648,0.000053220156],"category_scores_gemma":[0.000030370724,0.000051738283,0.000089218964,0.00012994699,0.000049016675,0.0001270373,0.00003583206,0.00018357736,0.000004400661],"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":[0.000017727592,0.000017832821,0.008585564,0.0000056575086,0.000049522816,5.435335e-8,0.0003352005,0.0049374294,0.00010247522,0.956292,0.0006909895,0.02896559],"study_design_scores_gemma":[0.0005895693,0.00002771236,0.008790013,0.000087890585,0.000026790629,0.0000017075137,0.00089805375,0.010415536,0.0001489286,0.96870553,0.010179305,0.00012894202],"about_ca_topic_score_codex":0.000009656362,"about_ca_topic_score_gemma":3.565942e-7,"teacher_disagreement_score":0.6775265,"about_ca_system_score_codex":0.000020919366,"about_ca_system_score_gemma":0.00009093601,"threshold_uncertainty_score":0.49014205},"labels":[],"label_agreement":null},{"id":"W760598031","doi":"10.1007/s00778-015-0389-y","title":"Profiling relational data: a survey","year":2015,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":273,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Profiling (computer programming); Metadata; Computer science; Data mining; Data type; Information retrieval; Data science; World Wide Web","score_opus":0.8844173631534311,"score_gpt":0.5434835487839118,"score_spread":0.3409338143695193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W760598031","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.352442,0.0016693377,0.5112038,0.05794158,0.009467906,0.0007046077,0.0010885082,0.00010324621,0.065379],"genre_scores_gemma":[0.96708786,0.000056730012,0.013368911,0.0025342165,0.0015712639,0.000002907286,0.00023726223,0.000017024146,0.015123808],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964501,0.0010763827,0.0004557821,0.0001861964,0.0016773121,0.00015419841],"domain_scores_gemma":[0.9971984,0.0011507034,0.0002507955,0.00093831756,0.00032821074,0.00013355103],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051777884,0.000058432397,0.0001057201,0.00008779347,0.00026479052,0.00056203816,0.0021243063,0.000021241096,0.00021321757],"category_scores_gemma":[0.010924824,0.000029404817,0.000027865372,0.00037724889,0.00007365708,0.00092525315,0.0007525229,0.00024893065,0.0009997596],"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":[0.00008279585,0.000048899212,0.021600956,7.1028927e-7,0.000038622038,0.000014581196,0.00047931462,0.00073710264,0.000007779039,0.022833709,0.9319591,0.022196447],"study_design_scores_gemma":[0.0006290396,0.000051446168,0.087574445,0.0000096129015,0.000018795108,0.00016900337,0.00230548,0.0066900337,0.000012826525,0.15588231,0.7465175,0.00013952529],"about_ca_topic_score_codex":0.0000394526,"about_ca_topic_score_gemma":0.00009459696,"teacher_disagreement_score":0.6146459,"about_ca_system_score_codex":0.000024826468,"about_ca_system_score_gemma":0.00018176564,"threshold_uncertainty_score":0.9997781},"labels":[],"label_agreement":null}]}