{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":59,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":59,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"c4fafddebffc","filters":{"venue":"The VLDB Journal"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.009606939193727806,"gpt":0.2379098253314463,"spread":0.2283028861377185,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002041369,0.00006188159,0.00005644012,0.00003295264,0.0005590137,0.0002115889,0.0004747934,0.00002302102,0.00008125845],"category_scores_gemma":[0.000001734832,0.00004098688,0.00003809726,0.0002327128,0.00007168726,0.0001381454,0.00002381148,0.0001674633,0.0000419698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001992156,"about_ca_system_score_gemma":0.00002995795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004623651,"about_ca_topic_score_gemma":9.050422e-7,"domain_scores_codex":[0.9994842,0.00002705092,0.0001317463,0.000119519,0.0001154385,0.0001219918],"domain_scores_gemma":[0.9994978,0.00003186392,0.0000559777,0.0003057921,0.00003405972,0.00007448502],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002416276,0.00003081308,0.00005679957,0.000001278925,0.000005895106,0.00000109323,0.00009286433,0.00009874982,0.00008279792,0.0212603,0.00120863,0.9771584],"study_design_scores_gemma":[0.0002644889,0.00006770319,0.001558429,0.00001074585,0.00001168546,0.0002920273,0.00003726616,0.04288786,0.001168249,0.04698056,0.906552,0.0001690269],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001174469,0.0002231369,0.9922234,0.00367721,0.00001965458,0.0001290657,0.000001440957,0.000111159,0.002440497],"genre_scores_gemma":[0.8643743,0.0005941439,0.1298537,0.001809081,0.0005290942,0.0002177655,0.000001070125,0.00001638997,0.002604375],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9769893,"threshold_uncertainty_score":0.4299538,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Bell (Canada)","funders":"","keywords":"Computer science; Wavelet; Query optimization; Data mining; Tuple; Histogram; Algorithm; Artificial intelligence; Mathematics; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.0412518917975479,"gpt":0.2701677799750619,"spread":0.228915888177514,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007493352,0.00009056483,0.00008441041,0.00008444262,0.0005128147,0.0009499458,0.001141741,0.00001699722,0.00002060897],"category_scores_gemma":[0.0000121465,0.00005534851,0.00004212929,0.0003404355,0.00003490358,0.001317469,0.0002929477,0.0002087694,0.00002641726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002807431,"about_ca_system_score_gemma":0.00004292195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005049121,"about_ca_topic_score_gemma":5.986842e-7,"domain_scores_codex":[0.9990727,0.00005246469,0.0001716359,0.0001342281,0.0002787817,0.0002901625],"domain_scores_gemma":[0.9994665,0.00001441307,0.0001321268,0.0002799736,0.00004499448,0.00006192979],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007267495,0.00006096278,0.0003815775,0.00001414783,0.00003065054,0.0003072062,0.0007430015,0.0004504626,0.0008754768,0.005079004,0.002284011,0.9897662],"study_design_scores_gemma":[0.0003753398,0.00002968619,0.0007612113,0.00008624982,0.00001984909,0.002526341,0.0001360168,0.9563392,0.0002813176,0.01412985,0.0250828,0.0002321147],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03452689,0.0003038282,0.9598022,0.001952763,0.000404683,0.00006060367,3.262983e-7,0.00006685733,0.002881845],"genre_scores_gemma":[0.7274629,0.0004251382,0.2656185,0.002018119,0.001999093,0.000003669013,0.000001990776,0.00003561674,0.00243496],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9895341,"threshold_uncertainty_score":0.9160349,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02968092915324465,"gpt":0.2434911894461427,"spread":0.2138102602928981,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004502084,0.00009932323,0.0001068203,0.00005378461,0.0004371397,0.0001101264,0.0006410889,0.00001645706,0.0001998642],"category_scores_gemma":[0.00007004832,0.00005661947,0.00005263566,0.0002306889,0.00006640593,0.0009867345,0.0002387431,0.0002978495,0.000284647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002780593,"about_ca_system_score_gemma":0.00002113491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009409436,"about_ca_topic_score_gemma":0.000007987997,"domain_scores_codex":[0.9990461,0.0001164585,0.0001923309,0.0001438725,0.0002671566,0.000234078],"domain_scores_gemma":[0.9991105,0.00007756587,0.0001356484,0.0005016373,0.00007460163,0.0001000264],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002084389,0.0003124758,0.0004296369,0.00002695656,0.0001693307,0.0008215351,0.01147942,0.0007874581,0.002135739,0.6944815,0.2021911,0.08714402],"study_design_scores_gemma":[0.0008336324,0.0001151563,0.0002404795,0.0001161833,0.00001314252,0.00642273,0.0003643486,0.08017634,0.001075098,0.002476393,0.9078112,0.0003552806],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001812632,0.001358453,0.9909439,0.002200642,0.0005367672,0.00006773537,0.0000169109,0.00005201986,0.003010957],"genre_scores_gemma":[0.2754718,0.001671721,0.6978796,0.003845801,0.002290469,0.00002914757,0.000008005244,0.00005364561,0.01874982],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7056202,"threshold_uncertainty_score":0.3658657,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04003804845750331,"gpt":0.2958259358899701,"spread":0.2557878874324668,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000942455,0.0000639756,0.0000673653,0.00009654262,0.00020542,0.0002267427,0.0006272252,0.000009518862,0.00005282147],"category_scores_gemma":[0.00007608397,0.0000422743,0.0000299244,0.0002441867,0.00003421716,0.001437122,0.0002795435,0.0002170816,0.00004982662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003481286,"about_ca_system_score_gemma":0.00007023131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000367678,"about_ca_topic_score_gemma":0.0000262904,"domain_scores_codex":[0.9991531,0.00004155225,0.0002306436,0.0001125839,0.0002492864,0.0002128277],"domain_scores_gemma":[0.9995353,0.00004372435,0.0001168578,0.0002441402,0.00002114298,0.0000387867],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001151408,0.0001209135,0.01438272,0.000009410037,0.00003461154,0.0004154485,0.002238633,0.004176923,0.000236198,0.8991257,0.008121914,0.07112599],"study_design_scores_gemma":[0.004895445,0.0002619804,0.2190561,0.0004689346,0.00004181938,0.002477039,0.001827708,0.03179492,0.003169,0.4493948,0.2854472,0.001164986],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08592413,0.000247782,0.8941901,0.01591039,0.000657874,0.00009341004,0.000006407854,0.00005626861,0.002913599],"genre_scores_gemma":[0.7763634,0.0001651284,0.2193082,0.001698347,0.0008088802,0.000005820883,0.00002283884,0.00001440199,0.001613016],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6904392,"threshold_uncertainty_score":0.2186486,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.8844173631534311,"gpt":0.5434835487839118,"spread":0.3409338143695193,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05177788,0.0000584324,0.0001057201,0.00008779347,0.0002647905,0.0005620382,0.002124306,0.0000212411,0.0002132176],"category_scores_gemma":[0.01092482,0.00002940482,0.00002786537,0.0003772489,0.00007365708,0.0009252531,0.0007525229,0.0002489306,0.0009997596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002482647,"about_ca_system_score_gemma":0.0001817656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000394526,"about_ca_topic_score_gemma":0.00009459696,"domain_scores_codex":[0.9964501,0.001076383,0.0004557821,0.0001861964,0.001677312,0.0001541984],"domain_scores_gemma":[0.9971984,0.001150703,0.0002507955,0.0009383176,0.0003282107,0.000133551],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008279585,0.00004889921,0.02160096,7.102893e-7,0.00003862204,0.0000145812,0.0004793146,0.0007371026,0.000007779039,0.02283371,0.9319591,0.02219645],"study_design_scores_gemma":[0.0006290396,0.00005144617,0.08757444,0.000009612902,0.00001879511,0.0001690034,0.00230548,0.006690034,0.00001282652,0.1558823,0.7465175,0.0001395253],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.352442,0.001669338,0.5112038,0.05794158,0.009467906,0.0007046077,0.001088508,0.0001032462,0.065379],"genre_scores_gemma":[0.9670879,0.00005673001,0.01336891,0.002534217,0.001571264,0.000002907286,0.0002372622,0.00001702415,0.01512381],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6146459,"threshold_uncertainty_score":0.9997781,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04447157467703367,"gpt":0.2691169814537689,"spread":0.2246454067767352,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0008883012,0.0001494249,0.0001434096,0.00009007953,0.0005079797,0.001265474,0.0764215,0.0001062801,0.0003654984],"category_scores_gemma":[0.006567484,0.00009440979,0.00003946378,0.0006235365,0.0001120587,0.002623766,0.1079537,0.0008532937,0.0005456223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005442047,"about_ca_system_score_gemma":0.00006999791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003634746,"about_ca_topic_score_gemma":0.000001719874,"domain_scores_codex":[0.9981788,0.0001808294,0.0003776711,0.0003542247,0.0004253066,0.0004831326],"domain_scores_gemma":[0.9851227,0.0001808399,0.0003465494,0.01404892,0.0001931497,0.0001078148],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002153695,0.00002769973,0.0004174243,0.000001295619,0.00003546102,0.000002907961,0.00003220115,0.00001317626,0.000278916,0.0009082855,0.9080707,0.09020981],"study_design_scores_gemma":[0.0002482789,0.00003087027,0.008871217,0.00002250926,0.00001326304,0.0003710804,0.000005950905,0.6399468,0.00009704276,0.3376427,0.01259264,0.0001576105],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01298904,0.0002253221,0.8585849,0.1256743,0.001440147,0.0002122177,0.000004771426,0.0004724331,0.0003968244],"genre_scores_gemma":[0.7925283,0.0002611914,0.2049928,0.0008977062,0.0009638491,0.00001895036,0.00007970221,0.00002833476,0.0002291329],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.895478,"threshold_uncertainty_score":0.9997713,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01207445201333954,"gpt":0.2032755897971928,"spread":0.1912011377838533,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000444787,0.0001015851,0.0001195689,0.00009663794,0.0002303681,0.0003216651,0.001132337,0.00003561852,0.0001137933],"category_scores_gemma":[0.00006526765,0.00005535832,0.00009742842,0.000226372,0.0000720253,0.0003228484,0.00008262965,0.000269901,0.000215648],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001990434,"about_ca_system_score_gemma":0.00007974492,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006270313,"about_ca_topic_score_gemma":0.00000641991,"domain_scores_codex":[0.9990817,0.00009034284,0.0001767664,0.0001169642,0.0002479792,0.0002862657],"domain_scores_gemma":[0.9991785,0.0001495052,0.0000952366,0.0004046404,0.00008096073,0.00009121116],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00004753016,0.0004664236,0.02077122,0.00004758278,0.0003119765,0.0004793532,0.004189568,0.005143569,0.01103527,0.0737973,0.368668,0.5150422],"study_design_scores_gemma":[0.003938181,0.0009082152,0.3408511,0.0002737877,0.0000965185,0.004370477,0.0007513975,0.2411776,0.02077441,0.3230245,0.06226984,0.001563962],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2966215,0.001355817,0.6666414,0.03157667,0.001667102,0.0001611622,3.702606e-7,0.0002042408,0.001771801],"genre_scores_gemma":[0.9776561,0.00004202197,0.02030884,0.001494863,0.0002768064,0.000006551468,1.457938e-7,0.000006301845,0.0002083382],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6810347,"threshold_uncertainty_score":0.3101824,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04801050073090831,"gpt":0.3160797680561167,"spread":0.2680692673252084,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004068899,0.00007566806,0.0000847071,0.00007739468,0.0003167111,0.0006135868,0.0004253392,0.00001412199,0.000004271776],"category_scores_gemma":[0.00001015548,0.00004752437,0.00004640043,0.0001598302,0.00003464094,0.0005260815,0.0001131309,0.0000810377,0.000006367097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001266851,"about_ca_system_score_gemma":0.00001373697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001825488,"about_ca_topic_score_gemma":0.000002583654,"domain_scores_codex":[0.9993457,0.00003552895,0.0001548348,0.0001251866,0.000169162,0.0001695929],"domain_scores_gemma":[0.999611,0.00007719451,0.00009888702,0.0001250817,0.00005290908,0.00003495907],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002304832,0.0001189074,0.000401876,0.00002106186,0.000131258,0.00004166208,0.000282913,0.002337911,0.001185608,0.04524256,0.04910811,0.9011051],"study_design_scores_gemma":[0.001025395,0.0001734617,0.01984459,0.00001668204,0.00005730529,0.0002369784,0.00006151869,0.8637421,0.0005723418,0.09827954,0.01576512,0.0002249852],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007514936,0.0002853627,0.988992,0.002406414,0.0003157703,0.00009388038,0.00000458361,0.00003417216,0.0003528726],"genre_scores_gemma":[0.5305412,0.0000774954,0.465851,0.0004869022,0.001773518,0.00001134447,0.00002047521,0.0000174165,0.001220642],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9008801,"threshold_uncertainty_score":0.5916832,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01035243184366573,"gpt":0.2293669318428719,"spread":0.2190144999992061,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003715197,0.00007689577,0.00008500771,0.00003637455,0.0004138772,0.000120187,0.0004854962,0.00001658857,0.00001160166],"category_scores_gemma":[0.00002820672,0.0000431918,0.00005045774,0.0001487608,0.00003972677,0.0006764627,0.000131078,0.0002201795,0.00006623175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004472022,"about_ca_system_score_gemma":0.0000858348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004021532,"about_ca_topic_score_gemma":0.00001355924,"domain_scores_codex":[0.9992751,0.00004063275,0.000167109,0.0001019507,0.0002078667,0.0002072764],"domain_scores_gemma":[0.9993986,0.00003025516,0.0001047975,0.0003473458,0.00004343629,0.00007550164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007203152,0.00003726846,0.0001549671,0.000006803647,0.00003104713,0.0001717225,0.002331619,0.005091936,0.002524048,0.8805164,0.0009616829,0.1081653],"study_design_scores_gemma":[0.003772527,0.000511151,0.003410301,0.0007567705,0.00003616244,0.01997619,0.002460464,0.00449881,0.02656168,0.2778144,0.6589513,0.001250224],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0287863,0.0004614348,0.9665375,0.002359462,0.0005974802,0.00004191696,0.000001764191,0.0000522173,0.001161982],"genre_scores_gemma":[0.8522169,0.0001553954,0.1456587,0.0007159693,0.0008431707,0.000003987384,8.243567e-7,0.00001309432,0.0003919956],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8234306,"threshold_uncertainty_score":0.3183251,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02434631267444179,"gpt":0.2217052823758772,"spread":0.1973589697014354,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002027797,0.00006970706,0.0000763596,0.00004148651,0.0002670824,0.0001006634,0.0003832944,0.00001765582,0.0001374401],"category_scores_gemma":[0.00002533598,0.00004084372,0.00004175002,0.0001361394,0.00002772535,0.0006134053,0.00008397306,0.000143134,0.0001174227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000014197,"about_ca_system_score_gemma":0.000009769304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006940639,"about_ca_topic_score_gemma":0.00001013837,"domain_scores_codex":[0.9992989,0.00008147853,0.0001747481,0.00009530326,0.0001912713,0.0001583549],"domain_scores_gemma":[0.9994293,0.00004368026,0.0001173786,0.0003093054,0.00004404283,0.00005629663],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003168756,0.0000520615,0.0008676412,0.000007978183,0.00002719906,0.0000903717,0.002903177,0.0004508773,0.0004429856,0.02047416,0.05729125,0.9173892],"study_design_scores_gemma":[0.001233621,0.0002184866,0.005261986,0.0001782999,0.00002119439,0.004791351,0.0006142441,0.2647045,0.001653103,0.004479108,0.7162389,0.0006052436],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002919072,0.0005303772,0.9909993,0.002910186,0.0005542311,0.00003898393,0.00000203163,0.00003957451,0.00200626],"genre_scores_gemma":[0.919925,0.0007803214,0.07037646,0.002354438,0.001862101,0.000009728052,0.000002694906,0.00002704928,0.004662156],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9206228,"threshold_uncertainty_score":0.2054209,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01980670494016319,"gpt":0.2688788118537077,"spread":0.2490721069135445,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001406971,0.00009594926,0.0001055198,0.00007213592,0.000513994,0.0001773188,0.0003044662,0.00003024898,0.00000302325],"category_scores_gemma":[0.00003067149,0.00005758015,0.00002853469,0.0001510676,0.00005630378,0.0009144251,0.000159576,0.0002956403,0.000003677921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002137879,"about_ca_system_score_gemma":0.00007761713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004084145,"about_ca_topic_score_gemma":0.00003058575,"domain_scores_codex":[0.9990683,0.00003677432,0.0002575701,0.0001381554,0.0002367675,0.0002624508],"domain_scores_gemma":[0.9994286,0.00002862468,0.0001466574,0.000213218,0.00007636434,0.0001065162],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001087246,0.000113201,0.01165089,0.0001210151,0.00007526488,0.0005485864,0.01419888,0.006288037,0.002992651,0.2641085,0.002259334,0.6975349],"study_design_scores_gemma":[0.001393619,0.0002326494,0.002199823,0.0006617781,0.00002446861,0.01014333,0.002429916,0.7878053,0.001576525,0.03599706,0.1566245,0.0009110165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07542167,0.001331015,0.9220118,0.0004234987,0.0002193883,0.00004333434,6.144783e-7,0.00004459687,0.0005040957],"genre_scores_gemma":[0.9228728,0.00004161422,0.07626171,0.0002642481,0.0003943508,8.833927e-7,3.81403e-7,0.000008682094,0.0001552819],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8474512,"threshold_uncertainty_score":0.3953278,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Suite; Graph; Scalability; Graph drawing; Visualization; Call graph; Data visualization","retraction":null,"screen_n_in":null,"score":{"opus":0.02115508178165599,"gpt":0.263779211117652,"spread":0.242624129335996,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00607511,0.0001020017,0.0001898683,0.00008984667,0.0003755043,0.0001030082,0.0009407395,0.00003630782,0.000003241106],"category_scores_gemma":[0.00006336103,0.00005167711,0.00008557205,0.0003350776,0.0001908733,0.000272767,0.0001813483,0.0002671097,9.784143e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003569272,"about_ca_system_score_gemma":0.00005263678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007987756,"about_ca_topic_score_gemma":0.00002260415,"domain_scores_codex":[0.998464,0.0005570263,0.000289386,0.0001396087,0.0003029215,0.0002470809],"domain_scores_gemma":[0.9985958,0.0004213887,0.0003602132,0.000372018,0.0001945311,0.00005607519],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000165335,0.0003048096,0.0157202,0.0001505586,0.0001953532,0.000009244594,0.01105768,0.0000342669,0.00425242,0.690506,0.00008848106,0.2775156],"study_design_scores_gemma":[0.0007886101,0.0002835306,0.3731585,0.00018093,0.00001898131,0.000257134,0.001198032,0.002037464,0.004716454,0.6170143,0.0001545348,0.000191523],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9770731,0.01087216,0.01053594,0.0006123199,0.0003372148,0.0001035125,0.000003447588,0.0000173813,0.0004448731],"genre_scores_gemma":[0.9978763,0.001595603,0.000455316,0.00002450358,0.0000152097,6.114546e-7,1.172443e-7,0.000005328564,0.00002697661],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3574383,"threshold_uncertainty_score":0.2888113,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04986115690612704,"gpt":0.3238459435933017,"spread":0.2739847866871746,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001882621,0.00007932663,0.00008101635,0.00005978276,0.0004749341,0.0008610262,0.002102335,0.00001510426,0.00003066035],"category_scores_gemma":[0.0001002419,0.00004778722,0.00001584064,0.0001186449,0.00006614261,0.001024739,0.001170204,0.0004000725,0.00001655874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004444023,"about_ca_system_score_gemma":0.00002390558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001767287,"about_ca_topic_score_gemma":0.00001906194,"domain_scores_codex":[0.9991431,0.00005266081,0.0001702294,0.0001784717,0.0002327309,0.0002228028],"domain_scores_gemma":[0.9989365,0.0001003338,0.0001377254,0.0007490112,0.00002062609,0.0000557789],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001143074,0.00002630436,0.001274856,0.000008910653,0.00004440901,0.0001101708,0.0009470202,0.00002383387,0.00104545,0.07350478,0.01585557,0.9071473],"study_design_scores_gemma":[0.001263972,0.0001940043,0.009477008,0.0001012466,0.00004219463,0.00127342,0.0004746186,0.3167692,0.0004760506,0.06690371,0.6024582,0.0005663432],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3269864,0.0003182097,0.6145573,0.04424214,0.005006408,0.0003485657,0.0000396641,0.0002467631,0.008254587],"genre_scores_gemma":[0.9263455,0.00009927202,0.06999271,0.001832671,0.001132669,0.000001639854,0.00001516349,0.00001409732,0.000566239],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9065809,"threshold_uncertainty_score":0.8302895,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05595234486683632,"gpt":0.2594263878383082,"spread":0.2034740429714719,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005438649,0.00008815133,0.0001106276,0.00007108961,0.000431049,0.0002929886,0.001136706,0.00003449919,0.0000231561],"category_scores_gemma":[0.00007999302,0.00005218777,0.00005390697,0.0001938141,0.00007037903,0.0002613444,0.000281235,0.0002372122,0.00003928179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004012847,"about_ca_system_score_gemma":0.0001029965,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002527301,"about_ca_topic_score_gemma":0.00003296142,"domain_scores_codex":[0.9991664,0.00005463988,0.0001442669,0.0001239165,0.0002338242,0.0002769505],"domain_scores_gemma":[0.9993212,0.00009007427,0.000103924,0.0003596211,0.0000649216,0.00006027493],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002520229,0.0002511962,0.003455636,0.00009073033,0.0004377468,0.0006479661,0.02387657,0.00384739,0.03151586,0.8259058,0.01008381,0.09986209],"study_design_scores_gemma":[0.002383398,0.0002681895,0.04349416,0.0006240426,0.00004706354,0.007559909,0.006995878,0.004566762,0.02268294,0.8938857,0.01671621,0.0007757014],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2378357,0.003947163,0.6516857,0.09744944,0.001254821,0.0001155178,2.63709e-7,0.0001773678,0.007534004],"genre_scores_gemma":[0.9699957,0.0001779437,0.02760251,0.001610624,0.0003642542,0.000002302562,6.65987e-8,0.000005873689,0.0002406573],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7321601,"threshold_uncertainty_score":0.3315324,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01090803058863072,"gpt":0.2453907915984678,"spread":0.2344827610098371,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004202149,0.00009615051,0.0001069059,0.00008633788,0.0002030074,0.0001121704,0.0003637693,0.00001520209,0.00003774069],"category_scores_gemma":[0.00002463251,0.00005914675,0.00003139387,0.000231144,0.00003578692,0.001087295,0.0001472418,0.0001852884,0.000007288639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000555899,"about_ca_system_score_gemma":0.00005940809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002097335,"about_ca_topic_score_gemma":0.0001511398,"domain_scores_codex":[0.9990211,0.0001087523,0.0002825859,0.0001401263,0.0002407598,0.0002067183],"domain_scores_gemma":[0.9993535,0.00004966681,0.0001507112,0.0003657498,0.00004234775,0.00003799717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001697579,0.00003990072,0.001325732,0.00001089746,0.00001189145,0.0001166578,0.0002764835,0.5609399,0.0007250502,0.4200892,0.003973139,0.01247413],"study_design_scores_gemma":[0.005054037,0.0003222041,0.03275336,0.0008556187,0.00004983247,0.007973842,0.001263708,0.356313,0.01429924,0.0932053,0.485835,0.002074822],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01100571,0.0005964163,0.9867435,0.0006749823,0.0004672889,0.00007991905,0.000008588016,0.00003047032,0.0003931883],"genre_scores_gemma":[0.4231375,0.0002403079,0.5748421,0.0003794322,0.0008915392,0.00001050609,0.00002893016,0.00001847289,0.0004512729],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4818619,"threshold_uncertainty_score":0.2411934,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05734070335716644,"gpt":0.3061374292867121,"spread":0.2487967259295457,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.003167397,0.000171239,0.000161793,0.00008955316,0.0003358151,0.0005822746,0.04357652,0.0001050312,0.00005116991],"category_scores_gemma":[0.009567123,0.00009076298,0.00002818762,0.0003824155,0.0002678364,0.001420114,0.03313258,0.00139598,0.00004592259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002766728,"about_ca_system_score_gemma":0.0001439675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001673473,"about_ca_topic_score_gemma":0.00017775,"domain_scores_codex":[0.9981881,0.0002503957,0.0002505679,0.0003698543,0.0004656403,0.0004754432],"domain_scores_gemma":[0.9878203,0.000254127,0.0002556271,0.01144433,0.0001125994,0.0001130093],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002530233,0.0003714166,0.003883868,0.00001784806,0.0003466493,0.0005076274,0.002201933,0.00005054966,0.02575188,0.1261475,0.4449458,0.3955219],"study_design_scores_gemma":[0.0007339233,0.0002092069,0.004553399,0.00008834348,0.00006165989,0.002404583,0.0001987875,0.1460995,0.01139951,0.8222395,0.01161028,0.0004013101],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3392521,0.0001632704,0.5779714,0.08022847,0.001064211,0.0002125148,0.00003795017,0.0004736613,0.0005963978],"genre_scores_gemma":[0.8949387,0.00005016552,0.1044364,0.0003430575,0.0001778497,0.000004515639,0.000007132955,0.00001284859,0.00002931863],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.696092,"threshold_uncertainty_score":0.9987757,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03430227086175861,"gpt":0.2687840089182429,"spread":0.2344817380564843,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004390531,0.00007879466,0.0000955267,0.00004428423,0.0005078322,0.0001469659,0.0004237339,0.0000215229,0.00001297566],"category_scores_gemma":[0.00004051473,0.00004524009,0.00005364082,0.000124799,0.00004106115,0.0007673635,0.00006419055,0.0001526607,0.000009507266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000212751,"about_ca_system_score_gemma":0.00002195632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001830717,"about_ca_topic_score_gemma":0.000001352278,"domain_scores_codex":[0.9993262,0.00003417115,0.0001811028,0.0001088857,0.0001475622,0.0002020408],"domain_scores_gemma":[0.9994278,0.00004797008,0.0001410674,0.000245988,0.00008670949,0.0000504558],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007593922,0.00004226156,0.00003434497,0.00003897996,0.00001533403,0.00001897259,0.002007434,0.00004591509,0.004299584,0.07602889,0.0239795,0.8934812],"study_design_scores_gemma":[0.0002468844,0.0001345866,0.00003339293,0.000193431,0.000008236284,0.001590154,0.0002064171,0.02863702,0.01272949,0.01513624,0.940834,0.0002501458],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003111582,0.000998411,0.9949465,0.002150928,0.0001984246,0.0001119312,0.000002454474,0.00009940589,0.001180779],"genre_scores_gemma":[0.107095,0.0002221051,0.8891156,0.0008504358,0.001275421,0.00004421285,6.659638e-7,0.00001975742,0.001376837],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9168545,"threshold_uncertainty_score":0.3905886,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4798807441543463,"gpt":0.4770797275385156,"spread":0.002801016615830709,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0078893,0.0001047428,0.0001836691,0.00008003911,0.0005475497,0.0008991892,0.003927862,0.00001728822,0.001195681],"category_scores_gemma":[0.007211903,0.00005363205,0.00004274647,0.0004019612,0.00008975453,0.0009507232,0.0007711769,0.0002714593,0.0005578696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002006482,"about_ca_system_score_gemma":0.00005834699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001481652,"about_ca_topic_score_gemma":0.00006520312,"domain_scores_codex":[0.9972023,0.000427707,0.000631218,0.0003695762,0.001136882,0.0002323122],"domain_scores_gemma":[0.9954342,0.001539673,0.0003613883,0.002431924,0.0001172501,0.0001156101],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000921679,0.0002396536,0.0005343524,0.000001941033,0.00006524661,0.00005883014,0.0007895941,0.000358862,0.0006994362,0.0189341,0.5360802,0.4421456],"study_design_scores_gemma":[0.000629178,0.00009594285,0.03953699,0.00007246639,0.0001140399,0.0001060638,0.002344685,0.01327663,0.000120373,0.3403775,0.6030555,0.0002706689],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5293232,0.002423555,0.2997091,0.1126383,0.002300991,0.00120784,0.003881123,0.000291307,0.04822454],"genre_scores_gemma":[0.9837586,0.0001351775,0.008627635,0.004425716,0.0009578771,0.000002062397,0.0003376612,0.00001003771,0.001745218],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4544354,"threshold_uncertainty_score":0.9997174,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01581869942841299,"gpt":0.2478756448548271,"spread":0.2320569454264141,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085827,0.00009613382,0.00009421365,0.00006827714,0.0003913001,0.0007517746,0.001302364,0.00001666909,0.00002908086],"category_scores_gemma":[0.00006427601,0.00005745108,0.00005726434,0.0002442651,0.00004553236,0.0006292971,0.0001098879,0.0002157132,0.00003015558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002584282,"about_ca_system_score_gemma":0.00004503547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001747505,"about_ca_topic_score_gemma":0.000001089027,"domain_scores_codex":[0.999081,0.00005353421,0.0001880749,0.0001388572,0.0002918688,0.0002467116],"domain_scores_gemma":[0.9993264,0.00005702263,0.0001128928,0.0003941287,0.0000513405,0.00005821304],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002236871,0.0001712115,0.0003732225,0.00001545514,0.00003087275,0.0001743831,0.001024928,0.002529836,0.0005067175,0.2780205,0.01427262,0.7028579],"study_design_scores_gemma":[0.001966348,0.0007369018,0.01244474,0.0001998074,0.00005723157,0.0003899255,0.0002461637,0.560142,0.002206735,0.3867025,0.03418138,0.0007262881],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04245729,0.0003537399,0.9075269,0.03456267,0.001040632,0.0002816635,0.000002074599,0.0002081068,0.01356695],"genre_scores_gemma":[0.9490284,0.00001656015,0.04769823,0.002126104,0.0004632262,0.000003260918,0.000001397106,0.00000629287,0.0006564743],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9065711,"threshold_uncertainty_score":0.724938,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Scalability; Multi-core processor; Serialization; Operating system; Parallel computing; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.04511224232357768,"gpt":0.2497341470458297,"spread":0.2046219047222521,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007591964,0.0001039105,0.0001786478,0.00004250091,0.0002071057,0.0000772237,0.0006168469,0.00004191902,0.00001758987],"category_scores_gemma":[0.00005641449,0.00006303952,0.00006470856,0.0001167276,0.0001065214,0.0002150144,0.0001132432,0.0002695606,0.00001046136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002076669,"about_ca_system_score_gemma":0.00002780596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005340633,"about_ca_topic_score_gemma":0.000005464924,"domain_scores_codex":[0.9989874,0.0001088539,0.0002988913,0.0001672533,0.0002308993,0.0002066443],"domain_scores_gemma":[0.9991409,0.00007659063,0.0001846789,0.0003928549,0.0001064082,0.00009858167],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003379835,0.001351066,0.2263721,0.0003046164,0.0002714429,0.0002399675,0.0394766,0.0004193958,0.006198118,0.0324211,0.008517948,0.6840897],"study_design_scores_gemma":[0.002832305,0.0007094773,0.8804856,0.0007618115,0.00003804097,0.001193543,0.001086543,0.08644866,0.008117363,0.01028437,0.007429834,0.0006124443],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9024221,0.0004732939,0.09427904,0.0006294968,0.0007075467,0.0001593118,0.0000175015,0.00004368846,0.001268049],"genre_scores_gemma":[0.9956549,0.00002332106,0.004099907,0.00009033846,0.00007703335,0.000001833157,2.892367e-7,0.000004661394,0.00004767807],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6834772,"threshold_uncertainty_score":0.2570677,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01984968428036772,"gpt":0.2453065712035755,"spread":0.2254568869232078,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005512488,0.00007095515,0.0000836694,0.00002236911,0.000289533,0.00004760248,0.0002760136,0.00001386378,0.00000280438],"category_scores_gemma":[0.00001606244,0.00002939651,0.00002353934,0.0001554892,0.00004437205,0.0008056751,0.0000828077,0.0001534955,0.000001650436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001120127,"about_ca_system_score_gemma":0.0000390594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001208116,"about_ca_topic_score_gemma":0.000004097416,"domain_scores_codex":[0.9993444,0.00004972574,0.000156438,0.00005452873,0.0002185778,0.0001763247],"domain_scores_gemma":[0.9994917,0.00002642245,0.000134099,0.0002238091,0.00008385134,0.0000401399],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001001596,0.0002015683,0.006000296,0.0002131333,0.0001631286,0.0000183562,0.04060677,0.6220019,0.008847545,0.174289,0.0008109476,0.1467472],"study_design_scores_gemma":[0.000235515,0.00006988301,0.000396873,0.0002724215,0.00003026217,0.001320777,0.001694209,0.9884095,0.002884818,0.001177676,0.003346948,0.0001611094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1317849,0.0007300408,0.8667985,0.0004289753,0.000116517,0.00004427889,0.00000111991,0.00001498153,0.00008072075],"genre_scores_gemma":[0.9623899,0.00004020285,0.03726979,0.00003306825,0.0002363589,0.000001417532,3.662926e-7,0.000005176536,0.00002365763],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.830605,"threshold_uncertainty_score":0.2226883,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01871367238197218,"gpt":0.2452819636881325,"spread":0.2265682913061603,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001103371,0.00003526946,0.00004143695,0.0000392315,0.0001054716,0.0001658779,0.0002366564,0.000008088287,0.00001575515],"category_scores_gemma":[0.00001366982,0.00002221151,0.00001220799,0.0001104052,0.00002853675,0.0005193976,0.00007360286,0.00004246934,0.000001064819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008616592,"about_ca_system_score_gemma":0.00002012198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001131205,"about_ca_topic_score_gemma":0.000002439662,"domain_scores_codex":[0.9994171,0.00006526477,0.000113773,0.00005609897,0.0002857229,0.00006205931],"domain_scores_gemma":[0.9996618,0.00001674612,0.00008869624,0.0001262949,0.00009437023,0.00001208241],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008597644,0.0001397017,0.005293134,0.00001058842,0.00005529022,0.000008601028,0.0008980283,0.4134198,0.0005714037,0.09619103,0.01169604,0.4717078],"study_design_scores_gemma":[0.0002059308,0.00002792045,0.009616632,0.00001080289,0.00002275747,0.00002913683,0.00003698198,0.9788633,0.0001554928,0.01051249,0.0004760489,0.00004250859],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04335089,0.0003897087,0.9529162,0.001020121,0.0001872575,0.00007922156,0.000001262649,0.00001424708,0.002041116],"genre_scores_gemma":[0.9603171,0.00009348289,0.03928962,0.00003915684,0.0001461165,0.000001568885,0.00000353004,0.000002727463,0.0001067271],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9169662,"threshold_uncertainty_score":0.1599565,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Scalability; Middleware (distributed applications); Database; Architecture; Satellite; Distributed computing","retraction":null,"screen_n_in":null,"score":{"opus":0.01229410304909796,"gpt":0.2241104797065471,"spread":0.2118163766574492,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005176284,0.00009979986,0.0001123173,0.00004122752,0.0003634898,0.0004105171,0.0007366661,0.00001333163,0.00001223937],"category_scores_gemma":[0.000006670561,0.00005161345,0.00004102362,0.0002672469,0.00004447205,0.0005108143,0.00007174981,0.0002008652,0.00004257617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002496613,"about_ca_system_score_gemma":0.00004399429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005615822,"about_ca_topic_score_gemma":0.00001879866,"domain_scores_codex":[0.9990006,0.00007131828,0.0002051153,0.0001424509,0.0003109396,0.0002695545],"domain_scores_gemma":[0.9992971,0.0000512622,0.0001459911,0.0003849574,0.00006065185,0.00006003387],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009777313,0.0003440647,0.01832569,0.00004525586,0.0001583852,0.001493859,0.001284944,0.005597953,0.006154963,0.608072,0.03840083,0.3200243],"study_design_scores_gemma":[0.001728681,0.0001986728,0.06542601,0.0005073001,0.00003875882,0.01217023,0.000296137,0.01640084,0.002829614,0.007896343,0.8917598,0.0007476509],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0445508,0.00295846,0.9435912,0.00152814,0.0005104327,0.00008443354,0.00001067575,0.00007837615,0.006687425],"genre_scores_gemma":[0.99095,0.00008117354,0.007661684,0.0001500931,0.0004979842,0.000002292116,0.000002739994,0.000007491654,0.0006464648],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9463993,"threshold_uncertainty_score":0.3958626,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3025801455678561,"gpt":0.4077661213846789,"spread":0.1051859758168228,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002777442,0.00006720267,0.0001266322,0.0001303604,0.0004084485,0.000276813,0.0006001603,0.00002875357,0.0199871],"category_scores_gemma":[0.001168218,0.00003846421,0.0001227976,0.0002307146,0.0001049777,0.0006429749,0.0001409741,0.0002034185,0.0010578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002168323,"about_ca_system_score_gemma":0.00006853491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001395372,"about_ca_topic_score_gemma":0.00003004597,"domain_scores_codex":[0.9976121,0.0002375127,0.0006314425,0.0001489158,0.001239883,0.0001301435],"domain_scores_gemma":[0.9973035,0.001510576,0.0003833292,0.0003579644,0.0003674103,0.00007721853],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001034241,0.0003871441,0.02795779,0.000005219534,0.0004660455,0.00000876316,0.001960618,0.01050198,0.005718399,0.1986555,0.6547427,0.09949247],"study_design_scores_gemma":[0.0001917089,0.00001850101,0.2417914,0.000009104972,0.00001747089,0.00002413864,0.001465426,0.001197145,0.00005459741,0.7391202,0.01605517,0.0000551596],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5255728,0.0001487563,0.4582621,0.008137734,0.001128142,0.000184481,0.0002022357,0.00002368583,0.006340053],"genre_scores_gemma":[0.9938018,0.00001790979,0.004236419,0.0005221294,0.0003556575,0.000005609836,0.00003473131,0.000004032951,0.001021724],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6386875,"threshold_uncertainty_score":0.99972,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04612929082107779,"gpt":0.2739027125305562,"spread":0.2277734217094784,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000459147,0.00008635406,0.0001120532,0.0000864539,0.0001898128,0.00007687136,0.0002014204,0.00001609086,0.000004559096],"category_scores_gemma":[0.0000255198,0.00005731219,0.00002675005,0.0001663937,0.00002941489,0.0008220204,0.00004209443,0.0001784654,0.000003608148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001646498,"about_ca_system_score_gemma":0.00002866466,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000180982,"about_ca_topic_score_gemma":0.00002725631,"domain_scores_codex":[0.9992227,0.00008047922,0.0002249856,0.0001372857,0.0001526077,0.0001819285],"domain_scores_gemma":[0.9995177,0.00006739565,0.00008926132,0.0002489203,0.00002126133,0.00005546201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005708184,0.0001106775,0.00150474,0.00003911663,0.00003546909,0.000504077,0.006050105,0.002447234,0.03278927,0.0934072,0.0005136825,0.8625413],"study_design_scores_gemma":[0.007625407,0.001025431,0.05637302,0.003017981,0.00005781197,0.04412436,0.002720037,0.2043787,0.0432257,0.05064587,0.5838602,0.002945482],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.175739,0.00261762,0.8195325,0.00173229,0.0001396572,0.00007527315,0.000004721637,0.00002800559,0.0001309913],"genre_scores_gemma":[0.9088008,0.0003449896,0.09022402,0.0004130528,0.0001857701,0.00000172585,0.000002555812,0.000004942448,0.0000221016],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8595958,"threshold_uncertainty_score":0.2337123,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0426218733597992,"gpt":0.3124691026543456,"spread":0.2698472292945464,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004561003,0.00008008518,0.00009817517,0.00003157966,0.0005082678,0.0001543938,0.0004782283,0.00002866079,0.000002635441],"category_scores_gemma":[0.0004394499,0.00004461407,0.00005465537,0.0001840461,0.00002164062,0.000367068,0.00004760231,0.0002706641,0.000005696309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001513079,"about_ca_system_score_gemma":0.00004210469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002140059,"about_ca_topic_score_gemma":7.306513e-7,"domain_scores_codex":[0.9993231,0.00003576771,0.0001506342,0.0001085444,0.0001533267,0.0002285954],"domain_scores_gemma":[0.9991007,0.0003193561,0.000130795,0.0002994184,0.0000863788,0.00006338401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000009900504,0.00001437142,0.00003406098,0.000003461799,0.000008713695,0.00001426788,0.0005820711,0.0002453426,0.0008840947,0.8091173,0.004034548,0.1850519],"study_design_scores_gemma":[0.0004272451,0.0004232914,0.005038683,0.0003048783,0.00001214498,0.002719642,0.0002005978,0.004521076,0.001537386,0.8711542,0.1133644,0.0002963657],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00125997,0.0006733028,0.9924917,0.004579098,0.0004308587,0.00008990974,0.000002754778,0.0000536399,0.0004187361],"genre_scores_gemma":[0.07231183,0.00001414684,0.9252758,0.001256444,0.000938075,0.000003716235,3.371738e-7,0.000005050097,0.0001945927],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1847555,"threshold_uncertainty_score":0.3909237,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08655948616922705,"gpt":0.2882161129723615,"spread":0.2016566268031345,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005338311,0.00006060634,0.0000898587,0.00005032426,0.000192495,0.00003580347,0.0002577514,0.00001870536,0.00004243135],"category_scores_gemma":[0.00005429352,0.0000372514,0.00004927814,0.0001331154,0.00002975395,0.0007582182,0.00008102551,0.0001697699,0.000009978753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001704327,"about_ca_system_score_gemma":0.00005154855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002575648,"about_ca_topic_score_gemma":0.000009989133,"domain_scores_codex":[0.9992579,0.00006304327,0.0003176275,0.00009558431,0.0001611878,0.000104635],"domain_scores_gemma":[0.9990976,0.00002440955,0.0003592132,0.0003434748,0.0001343019,0.00004100195],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001602815,0.0004375371,0.01038033,0.00008788797,0.0004718894,0.00158406,0.03931889,0.01169236,0.1067045,0.4568323,0.007768614,0.3645613],"study_design_scores_gemma":[0.002356207,0.0009883769,0.01169497,0.001854999,0.0001387914,0.07219977,0.008891207,0.2359931,0.4922836,0.02711085,0.1446421,0.001845978],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05534787,0.0001830328,0.9424018,0.0001771396,0.001135537,0.0000360708,7.990204e-7,0.00001877298,0.000698926],"genre_scores_gemma":[0.8894024,0.00003958033,0.1099567,0.00004451106,0.0004003693,0.000002082418,0.000001113226,0.000004583418,0.0001485636],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8340546,"threshold_uncertainty_score":0.1519068,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0163908489472987,"gpt":0.2284934902706444,"spread":0.2121026413233457,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001165559,0.00007915767,0.0001179201,0.00008986397,0.0001731902,0.000211353,0.0008244491,0.00002452826,0.00003719244],"category_scores_gemma":[0.00002001183,0.00005055067,0.00005949298,0.0004262603,0.00001854554,0.0002249213,0.0001896249,0.0002528834,0.0005210594],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002597005,"about_ca_system_score_gemma":0.00002246324,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009529307,"about_ca_topic_score_gemma":0.000001111782,"domain_scores_codex":[0.9989533,0.00007828674,0.0002416268,0.0001391977,0.0002901942,0.000297333],"domain_scores_gemma":[0.9995124,0.00004421161,0.0000891942,0.0002802669,0.00001133017,0.00006258153],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007269919,0.000437458,0.02715839,0.0000862696,0.0002666245,0.003794686,0.01520414,0.06339353,0.02375589,0.1022864,0.3215081,0.4420359],"study_design_scores_gemma":[0.00175069,0.00009461881,0.1083924,0.0002870153,0.000008934044,0.001315745,0.0003450863,0.2489909,0.0006327664,0.005490534,0.6322161,0.0004752278],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5092397,0.002085848,0.4344817,0.0412723,0.003002231,0.0005162007,0.00003039841,0.0004118315,0.008959798],"genre_scores_gemma":[0.9982363,0.0001674042,0.0005381435,0.0002102617,0.0002019309,0.000006528924,0.000001215428,0.000006426134,0.0006318039],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4889965,"threshold_uncertainty_score":0.6697338,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03072226293727882,"gpt":0.2576678277286159,"spread":0.226945564791337,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001436939,0.0001642114,0.0001692265,0.0002682276,0.0004250909,0.0001593894,0.0012011,0.00002903884,0.0001040762],"category_scores_gemma":[0.00001280341,0.0001111688,0.0001130004,0.0005375416,0.00008510495,0.001007073,0.0002918619,0.0004665644,0.00002335858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001204916,"about_ca_system_score_gemma":0.00001883125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000054186,"about_ca_topic_score_gemma":0.00004458263,"domain_scores_codex":[0.9985435,0.0002206235,0.00030735,0.0002120952,0.0002394602,0.0004769692],"domain_scores_gemma":[0.9991695,0.0000723285,0.0001424231,0.0004729305,0.00003945603,0.0001033062],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001888723,0.001328395,0.204641,0.0001246022,0.0004127872,0.003212361,0.1106246,0.0006128268,0.01079484,0.284209,0.001529235,0.3823215],"study_design_scores_gemma":[0.003124814,0.0004283667,0.1469487,0.0009111011,0.00005420244,0.006062472,0.005205266,0.02442066,0.02466277,0.7824022,0.003936718,0.001842686],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2812704,0.0004303626,0.7172322,0.0001489879,0.0005865647,0.00005330385,0.000004529634,0.00005241523,0.0002212331],"genre_scores_gemma":[0.9883958,0.0002102645,0.01095205,0.0002978235,0.0001081808,0.000004636599,8.603423e-7,0.00001241388,0.0000180261],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7071253,"threshold_uncertainty_score":0.4533333,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04697737075967021,"gpt":0.2579352204925931,"spread":0.2109578497329229,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008490658,0.00009359598,0.000112111,0.0001071766,0.0002191027,0.0002709317,0.000641739,0.0000137939,0.00003354101],"category_scores_gemma":[0.00003195816,0.00005874956,0.00003562398,0.0001690171,0.00005240641,0.0007620523,0.000293374,0.0001456715,0.00001497427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001607588,"about_ca_system_score_gemma":0.00002894657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008908434,"about_ca_topic_score_gemma":0.0001139583,"domain_scores_codex":[0.9992262,0.00003655296,0.0001847857,0.0001451852,0.0001740443,0.0002331964],"domain_scores_gemma":[0.9994735,0.00008328381,0.0001117183,0.0002399061,0.00002839176,0.00006319078],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003016486,0.0006601802,0.03063982,0.0002131858,0.0004259837,0.0009030462,0.01246802,0.0006329119,0.001268056,0.2160275,0.0412559,0.6952037],"study_design_scores_gemma":[0.005127958,0.0004477364,0.07537672,0.0004442288,0.00008726793,0.0009419093,0.0005677615,0.6886809,0.0004071743,0.2187182,0.00848255,0.0007175011],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5514968,0.001129258,0.4329037,0.008761338,0.001903534,0.000807393,0.00001050242,0.0001086383,0.002878831],"genre_scores_gemma":[0.6339778,0.00008722584,0.363766,0.00117359,0.0004576017,0.00001773359,0.00000270282,0.00002345283,0.0004938332],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6944862,"threshold_uncertainty_score":0.26126,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Serialization; Concurrency control; Serializability; Commit; Transactional memory; Distributed transaction; Online transaction processing; Database transaction","retraction":null,"screen_n_in":null,"score":{"opus":0.0182709251801704,"gpt":0.2767483095853744,"spread":0.258477384405204,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001528012,0.0001602842,0.0002474114,0.00003965478,0.002172553,0.002331147,0.002955112,0.00005890167,0.00004634498],"category_scores_gemma":[0.0001128854,0.0001021788,0.0001223376,0.00008670208,0.00007901518,0.000682639,0.0002232633,0.0003287914,0.0001068647],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004522896,"about_ca_system_score_gemma":0.000117655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001969368,"about_ca_topic_score_gemma":0.000003092251,"domain_scores_codex":[0.9983852,0.0001515489,0.0003532597,0.0002244227,0.000422089,0.0004634875],"domain_scores_gemma":[0.9980624,0.00004835814,0.000594742,0.0009960841,0.0001785225,0.0001198478],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000862743,0.0002266769,0.001270347,0.00004915278,0.0002442654,0.0005133927,0.002697316,0.001511713,0.01320363,0.9047236,0.02325962,0.05221404],"study_design_scores_gemma":[0.01326155,0.0008858987,0.01227177,0.001537089,0.0001583169,0.007798666,0.0004756636,0.5847949,0.004713133,0.1022169,0.2699511,0.001935069],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01781878,0.000633671,0.966586,0.002983546,0.006035461,0.0002157251,0.00002109186,0.00007057824,0.005635147],"genre_scores_gemma":[0.9978463,0.00002311685,0.0008213299,0.0003065338,0.0005816059,0.000005489957,3.732341e-7,0.00000903691,0.0004061819],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9800276,"threshold_uncertainty_score":0.9991265,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03874119627521677,"gpt":0.2340408466965079,"spread":0.1952996504212912,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009628779,0.0001106101,0.00012362,0.0001297788,0.000300729,0.0001610042,0.0006155982,0.00002833515,0.000008530581],"category_scores_gemma":[0.00004243954,0.00006561685,0.00004831019,0.0001577373,0.00007816981,0.00001580799,0.0003223522,0.0004774125,0.000009189101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002437623,"about_ca_system_score_gemma":0.00002073305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008012759,"about_ca_topic_score_gemma":0.00002168732,"domain_scores_codex":[0.998938,0.00019616,0.0002143047,0.0001751162,0.0001879215,0.0002885264],"domain_scores_gemma":[0.9994243,0.0001138302,0.00009549522,0.0002542798,0.00002079784,0.00009123496],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000145285,0.001146803,0.06847589,0.000127733,0.000469331,0.001186582,0.1185619,0.2438882,0.001299685,0.01278096,0.001595053,0.5503225],"study_design_scores_gemma":[0.001709818,0.0002085276,0.1837326,0.0002456287,0.00003807668,0.001780496,0.0006172302,0.8024429,0.0002444639,0.006671123,0.001911159,0.0003980112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9066166,0.000717523,0.09010724,0.0009442485,0.0002924548,0.00008419785,1.386682e-7,0.00003763028,0.001199941],"genre_scores_gemma":[0.9897119,0.00001032561,0.009570578,0.0002956015,0.00006729673,0.000001489458,2.520471e-8,0.000006440448,0.0003363525],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5585546,"threshold_uncertainty_score":0.2675777,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0173761358373862,"gpt":0.2477361317347878,"spread":0.2303599958974016,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004275525,0.0000798184,0.0001099955,0.00007852236,0.0001939051,0.0003108568,0.0002683119,0.00003240485,0.00001445094],"category_scores_gemma":[0.00003703727,0.00004903989,0.00003782412,0.0001628869,0.00004716187,0.0002468652,0.00005137547,0.0001996122,0.00001914175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002459496,"about_ca_system_score_gemma":0.00002887141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006092221,"about_ca_topic_score_gemma":0.00007023061,"domain_scores_codex":[0.9991673,0.000165647,0.000252153,0.0001111797,0.0001376748,0.0001661094],"domain_scores_gemma":[0.9995567,0.00004507844,0.0001274603,0.0001733386,0.00004587057,0.00005154127],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004641247,0.00008049011,0.003662102,0.00004163759,0.00003527185,0.00001696958,0.003931032,0.0004431538,0.004000664,0.0007856808,0.0002082087,0.9867901],"study_design_scores_gemma":[0.001198721,0.0001585163,0.4607226,0.0002606325,0.000009959444,0.001919555,0.0004971633,0.5142197,0.0004574899,0.01954499,0.0007758898,0.0002347926],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6651632,0.0005884957,0.3331377,0.0005188402,0.0002358361,0.0001763884,4.863302e-7,0.00002961126,0.0001494301],"genre_scores_gemma":[0.9939563,0.00001716323,0.00575299,0.00006243857,0.00003940168,0.00001578463,1.156885e-7,0.000003412987,0.0001523931],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9865553,"threshold_uncertainty_score":0.29976,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05671574245012417,"gpt":0.2978760619772347,"spread":0.2411603195271105,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001303283,0.0000724418,0.00006386697,0.00005533796,0.0003778353,0.0007983692,0.004017516,0.00001608074,0.00006679048],"category_scores_gemma":[0.00006720414,0.00004104693,0.00002265215,0.0001542023,0.00004936005,0.00105239,0.0008659714,0.0004399029,0.0001027859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000561961,"about_ca_system_score_gemma":0.00002993734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001059159,"about_ca_topic_score_gemma":0.00001422926,"domain_scores_codex":[0.999206,0.0000493301,0.0001200446,0.0001563481,0.0002818053,0.000186488],"domain_scores_gemma":[0.998611,0.00007171022,0.00007955074,0.001169043,0.00002219071,0.00004654141],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000009602906,0.00004015142,0.0001485071,0.000002954765,0.00003825233,0.00007906924,0.0004358894,0.00004675603,0.0004484454,0.1574005,0.0621241,0.7792258],"study_design_scores_gemma":[0.0005258225,0.00008236524,0.001614916,0.00003451561,0.00001700959,0.0003225796,0.0001054684,0.07833266,0.0003774239,0.03284298,0.8854977,0.0002465367],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04552058,0.0002550732,0.8642331,0.05477501,0.0105234,0.0002549137,0.00002725918,0.0002648328,0.02414577],"genre_scores_gemma":[0.8268726,0.0003528732,0.1567263,0.006223842,0.005059696,0.000004970337,0.00003658857,0.00003576325,0.004687391],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8233736,"threshold_uncertainty_score":0.7698693,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01529434217783311,"gpt":0.2264422298769785,"spread":0.2111478876991454,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005822414,0.00009959012,0.0001411495,0.00001905804,0.0004523919,0.0003979751,0.0004002941,0.00003606516,0.00002008376],"category_scores_gemma":[0.00002403123,0.0000516688,0.00003191752,0.0001572124,0.00006244627,0.00082722,0.000105835,0.0002923435,0.00002035064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002677713,"about_ca_system_score_gemma":0.00002515196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006798,"about_ca_topic_score_gemma":0.000001222428,"domain_scores_codex":[0.9990225,0.00009444966,0.0001700465,0.0001273296,0.0002205717,0.0003650408],"domain_scores_gemma":[0.9994259,0.0000497428,0.0001205309,0.0001933982,0.00006059361,0.0001498101],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.000497615,0.001605296,0.3168661,0.0002506115,0.0009279888,0.0004246357,0.02318119,0.0155178,0.07957488,0.3546166,0.06424127,0.142296],"study_design_scores_gemma":[0.002417606,0.0005185296,0.7311139,0.0007597424,0.00004582144,0.006662721,0.000559041,0.2330927,0.0004695044,0.007669544,0.01575962,0.0009312789],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6046349,0.0007275941,0.3916973,0.001534685,0.0003146619,0.00008543678,0.000004543857,0.00006971178,0.0009311989],"genre_scores_gemma":[0.9930865,0.00002400667,0.006248422,0.0003014862,0.0002442355,0.000004496642,0.000001195256,0.000004586886,0.00008511425],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4142478,"threshold_uncertainty_score":0.3837683,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01070044184859699,"gpt":0.2297111019525497,"spread":0.2190106601039527,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007293932,0.00005548958,0.00007506197,0.00004472532,0.0003053251,0.0004776462,0.0006519731,0.00002665003,0.00001771613],"category_scores_gemma":[0.00001405517,0.00003627864,0.00002541863,0.0002898088,0.00002053878,0.001013098,0.00002460039,0.0002906159,0.00003144205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004499301,"about_ca_system_score_gemma":0.00003537703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009348732,"about_ca_topic_score_gemma":0.00001271555,"domain_scores_codex":[0.9992449,0.0001247091,0.0002313146,0.00007462643,0.0001626393,0.0001617719],"domain_scores_gemma":[0.9994748,0.00003738646,0.0001330205,0.0002224553,0.00009709059,0.00003519843],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003351953,0.00007337379,0.0006597193,0.00002158547,0.000006851696,0.000003706103,0.005132325,0.00297067,0.003129709,0.002434669,0.001301613,0.9842624],"study_design_scores_gemma":[0.000756018,0.00004855244,0.03235735,0.000491454,0.000005225683,0.0005238406,0.001320939,0.947131,0.001003844,0.01149153,0.004644669,0.0002256062],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1456317,0.001167253,0.8424468,0.007296337,0.0001793693,0.0001627598,3.203189e-7,0.00004655472,0.003068932],"genre_scores_gemma":[0.9950045,0.00003848074,0.004682118,0.0001032579,0.00003641527,0.000009604098,3.099771e-7,0.000003305148,0.0001219589],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9840368,"threshold_uncertainty_score":0.4605953,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02017665443236114,"gpt":0.2689327796126706,"spread":0.2487561251803095,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003679106,0.00007411346,0.00007623628,0.00005088691,0.0006849633,0.0001435318,0.0004229316,0.00002143049,0.00001921441],"category_scores_gemma":[0.0001058986,0.00004465009,0.00004460479,0.0001657564,0.00005664624,0.0008101279,0.0001227497,0.0003413681,0.00001578557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000013226,"about_ca_system_score_gemma":0.00006261229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004329199,"about_ca_topic_score_gemma":0.00005674579,"domain_scores_codex":[0.9993233,0.00004260556,0.0001690307,0.00009942555,0.0001774041,0.0001881998],"domain_scores_gemma":[0.9992554,0.0001002505,0.0001537269,0.0003579759,0.00007335832,0.00005935322],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001112351,0.00008880693,0.003138522,0.00001251193,0.00007201596,0.0001188487,0.004336996,0.002698199,0.4721873,0.1849025,0.0005723925,0.3318608],"study_design_scores_gemma":[0.001695947,0.0000980597,0.005532039,0.0002623406,0.00004025045,0.01267221,0.001285119,0.6334381,0.05576639,0.0128497,0.2755319,0.0008279908],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2632176,0.000130968,0.7351841,0.0002955995,0.0009515302,0.00004136288,0.000003129211,0.0000323308,0.0001433568],"genre_scores_gemma":[0.8392431,0.00001255015,0.1601798,0.00006801714,0.0003901214,0.000001339593,6.211229e-7,0.000006334915,0.0000981942],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6307398,"threshold_uncertainty_score":0.5268253,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1166235600128447,"gpt":0.4294959857511475,"spread":0.3128724257383028,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01106816,0.00006629908,0.0001212214,0.0002060113,0.0003059042,0.0002015666,0.0005133172,0.00001718022,0.00010555],"category_scores_gemma":[0.0003647562,0.00004171928,0.00003530759,0.0004948014,0.00007142599,0.0002618133,0.0001773229,0.0001464765,0.00004210326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001947723,"about_ca_system_score_gemma":0.00003012122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004580274,"about_ca_topic_score_gemma":0.0001438703,"domain_scores_codex":[0.9982775,0.000142833,0.0004982671,0.0001546767,0.0007799368,0.000146818],"domain_scores_gemma":[0.9982492,0.0008003096,0.0002847238,0.0004223816,0.0001284795,0.0001148897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002343741,0.0002385743,0.003697193,0.00004386875,0.00004885914,0.00001470202,0.001793554,0.0008332114,0.01886816,0.0137209,0.0099991,0.9505075],"study_design_scores_gemma":[0.005357501,0.0004521797,0.1266931,0.0004456205,0.0003885247,0.0003067153,0.0356785,0.005412393,0.06898663,0.3467853,0.408431,0.001062554],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2572511,0.0000738708,0.7390159,0.00314619,0.00007167492,0.0002022231,0.0000286172,0.000006884361,0.0002035413],"genre_scores_gemma":[0.9720079,0.00003662732,0.02589044,0.00175214,0.0001009199,0.000005604817,0.000009905852,0.000005636267,0.0001908711],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9494449,"threshold_uncertainty_score":0.3836027,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02152338838573285,"gpt":0.2492014349661,"spread":0.2276780465803671,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005727402,0.00009876985,0.000105323,0.00005249223,0.0006865028,0.000228569,0.0003622432,0.00003727535,0.00009228181],"category_scores_gemma":[0.00002028085,0.00006669457,0.00003498557,0.0001544467,0.00004733402,0.000731625,0.0001546868,0.0003250529,0.00003313093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002884546,"about_ca_system_score_gemma":0.00006256317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002243217,"about_ca_topic_score_gemma":0.000002730457,"domain_scores_codex":[0.9989618,0.000104437,0.0001757709,0.0001875331,0.0003621086,0.0002083477],"domain_scores_gemma":[0.9994367,0.00009401051,0.00007893919,0.000223986,0.0000537099,0.0001126314],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003813404,0.0001629277,0.0004247605,0.000003588068,0.00002513881,0.000024945,0.000319446,0.02956486,0.002908188,0.0008000568,0.001531055,0.9641969],"study_design_scores_gemma":[0.0005017431,0.00004381552,0.04055607,0.00004270785,0.000007538789,0.0008143003,0.000002145352,0.9534601,0.0006595825,0.003173517,0.0006227945,0.0001157032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6888267,0.0005003804,0.3088831,0.001318486,0.0002280472,0.00008448188,0.000002882386,0.00006293073,0.00009301303],"genre_scores_gemma":[0.8272772,0.00004147455,0.1719618,0.000352988,0.0001666359,0.00000187503,0.000002310733,0.000007700995,0.0001879989],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9640812,"threshold_uncertainty_score":0.5280094,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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)","retraction":null,"screen_n_in":null,"score":{"opus":0.02979951787720897,"gpt":0.2431261256838491,"spread":0.2133266078066401,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006531224,0.0000717366,0.0001014374,0.00007173125,0.0001855115,0.00009579099,0.0009597921,0.00003121584,0.0001712961],"category_scores_gemma":[0.00008080333,0.00004174856,0.00008996567,0.0003968528,0.00008381856,0.00008217354,0.00009540265,0.0002181682,0.00004550251],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002347937,"about_ca_system_score_gemma":0.00001888456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":5.766324e-7,"about_ca_topic_score_gemma":3.380321e-8,"domain_scores_codex":[0.9990247,0.00008568938,0.0002493031,0.00009838912,0.0003835557,0.0001583711],"domain_scores_gemma":[0.99928,0.0000746016,0.0001860824,0.0002529551,0.000149643,0.00005674397],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001135992,0.001273541,0.0005167194,0.00006985281,0.0002055051,0.0001234285,0.01013988,0.001173468,0.2872528,0.1373526,0.03148193,0.5302967],"study_design_scores_gemma":[0.0005798488,0.0003358964,0.003812732,0.00008213458,0.00002893214,0.0008990161,0.0001234778,0.6736659,0.2880214,0.01261567,0.01950936,0.0003256486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03985538,0.001708141,0.9432848,0.009464792,0.0002772679,0.000123951,0.000001631209,0.0001367651,0.005147256],"genre_scores_gemma":[0.9923286,0.0001930014,0.006628607,0.0002188408,0.00009857462,5.218289e-7,4.245384e-8,0.000004710866,0.000527109],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9524732,"threshold_uncertainty_score":0.1875572,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01945096438599307,"gpt":0.2412950354553263,"spread":0.2218440710693332,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005045711,0.00008305752,0.0001018947,0.00008786524,0.0002175004,0.0003209464,0.001003598,0.00001752062,0.00001243127],"category_scores_gemma":[0.0000106783,0.0000505585,0.0000556216,0.0002450008,0.0000514044,0.000777001,0.0001980461,0.0001662571,0.00001512636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000152957,"about_ca_system_score_gemma":0.00004164412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003725395,"about_ca_topic_score_gemma":0.00001134361,"domain_scores_codex":[0.9991414,0.00004753935,0.0002286523,0.0001118864,0.0002709929,0.0001995417],"domain_scores_gemma":[0.9994143,0.00002189594,0.0001986636,0.0002703273,0.00006002028,0.00003475557],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007836883,0.0003507258,0.002735136,0.00003375369,0.00004306653,0.00007594754,0.0005946906,0.001108448,0.00325891,0.008972893,0.00882972,0.9739889],"study_design_scores_gemma":[0.006336587,0.0005258674,0.2143378,0.0007654967,0.0001783337,0.001247729,0.000984577,0.6194605,0.03225563,0.04394982,0.07847398,0.001483723],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04379711,0.0006571636,0.9499882,0.001625226,0.0004107504,0.0001000582,0.000003850619,0.0000614379,0.003356243],"genre_scores_gemma":[0.9468489,0.00004030495,0.05090556,0.0001374917,0.000450753,0.000001444951,0.000001937194,0.000008942293,0.001604633],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9725052,"threshold_uncertainty_score":0.3094894,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04847366620191614,"gpt":0.2954808845975803,"spread":0.2470072183956642,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009214822,0.0000700497,0.00007641685,0.00006991739,0.0004643973,0.0001129096,0.0003213842,0.0000157708,0.00001571818],"category_scores_gemma":[0.0000371435,0.00004022819,0.00003661999,0.0004184375,0.00003002509,0.0004019445,0.00003028022,0.0002123173,0.0001030625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000199918,"about_ca_system_score_gemma":0.00008990629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002048245,"about_ca_topic_score_gemma":0.00002865481,"domain_scores_codex":[0.9991545,0.0001171033,0.0001430991,0.0001103706,0.000290426,0.0001845101],"domain_scores_gemma":[0.9994904,0.0001279003,0.00007735787,0.000186145,0.00006167789,0.00005653256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00009994408,0.0001194717,0.001832576,0.00003188914,0.0000759217,0.0002151907,0.00374351,0.01364713,0.001280777,0.036287,0.03324425,0.9094223],"study_design_scores_gemma":[0.002284838,0.0007495102,0.5470809,0.0007082651,0.00002326391,0.002433194,0.001044616,0.1562862,0.003679348,0.01626338,0.2682605,0.001186084],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03510918,0.000133966,0.9616517,0.001777594,0.000647573,0.00005949881,0.00002709984,0.0001382911,0.0004550709],"genre_scores_gemma":[0.9929062,0.00007237954,0.005075322,0.0002826974,0.0004235032,0.000005471199,0.000008373531,0.00001300553,0.001213051],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.957797,"threshold_uncertainty_score":0.3571815,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03418460099070763,"gpt":0.3495786809841878,"spread":0.3153940799934802,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001832644,0.00009570341,0.0001087534,0.00006448283,0.0003647125,0.0003854737,0.0006034255,0.00001287563,0.00001774358],"category_scores_gemma":[0.00007951713,0.00005752336,0.00003563786,0.0001683781,0.00003708775,0.0003801336,0.0002740014,0.0002211391,0.000009791759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001467214,"about_ca_system_score_gemma":0.00001538099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004490804,"about_ca_topic_score_gemma":0.000001218719,"domain_scores_codex":[0.9990261,0.0001957441,0.0001602868,0.0001744508,0.0002028323,0.0002405884],"domain_scores_gemma":[0.9992967,0.0001120334,0.00007292708,0.0004200904,0.00002229746,0.00007598586],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002775167,0.0001656695,0.000320996,0.000007510646,0.00002873058,0.0000553829,0.0006347288,0.0002013123,0.0004404977,0.3266939,0.002776769,0.6686468],"study_design_scores_gemma":[0.002295894,0.0009368299,0.1412608,0.0003115593,0.00009617844,0.0007130667,0.0009392739,0.2394011,0.009359151,0.05078971,0.5527018,0.001194638],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03587357,0.0003670431,0.9573062,0.004453131,0.0003983241,0.00006200497,0.000006049914,0.00005373045,0.001479963],"genre_scores_gemma":[0.6142283,0.0004513696,0.3793693,0.00477437,0.0007101229,0.000002718042,0.000005661943,0.00001195537,0.0004461829],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6674522,"threshold_uncertainty_score":0.3717132,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0234515832102263,"gpt":0.2229272232546076,"spread":0.1994756400443813,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001063981,0.00009464977,0.00006553702,0.00006663921,0.0005025943,0.0006620637,0.001397598,0.00001756113,0.0000468939],"category_scores_gemma":[0.00002007843,0.00004613274,0.000071976,0.0002333728,0.00004987862,0.0003837403,0.0001313335,0.0002386325,0.0000995493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005102058,"about_ca_system_score_gemma":0.00002746277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001985962,"about_ca_topic_score_gemma":0.000006544608,"domain_scores_codex":[0.9989637,0.0001252873,0.0001691236,0.0001325776,0.0003823318,0.0002269986],"domain_scores_gemma":[0.9992129,0.00007748162,0.0001216164,0.0005186553,0.00003463183,0.00003473166],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005336108,0.0006412743,0.001296106,0.00001264557,0.00006431521,0.0001282153,0.0004837118,0.005667223,0.001282399,0.375942,0.3447168,0.269712],"study_design_scores_gemma":[0.0005922371,0.0001784756,0.008094938,0.00003803339,0.00002212098,0.00005483617,0.00004914692,0.5234728,0.0003471537,0.01831453,0.4486172,0.0002184574],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03660053,0.000124384,0.9196177,0.02518944,0.001553098,0.0002327394,0.000002655818,0.0001180891,0.01656142],"genre_scores_gemma":[0.9831461,0.00001583918,0.01003765,0.002071194,0.000751622,0.000008051918,0.00000420153,0.00001137747,0.003953944],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9465456,"threshold_uncertainty_score":0.6384296,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Maximization; Computer science; Mathematical optimization; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01091987405908378,"gpt":0.2582131317671943,"spread":0.2472932577081105,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003507677,0.0001025956,0.0001685614,0.00004549511,0.00033488,0.0001281935,0.0001955925,0.00002139091,0.0006691922],"category_scores_gemma":[0.00001846592,0.00007465421,0.0001812411,0.0002031239,0.00003064082,0.00006720779,0.00005465712,0.0002448874,0.00000772772],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000315266,"about_ca_system_score_gemma":0.00009685852,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001222468,"about_ca_topic_score_gemma":6.447234e-7,"domain_scores_codex":[0.9991314,0.00008880396,0.0002572646,0.0001378537,0.0002022707,0.0001823488],"domain_scores_gemma":[0.9991004,0.00009883421,0.0002053181,0.0001888154,0.0003534374,0.00005320475],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001180921,0.001283319,0.004177218,0.0000123955,0.0007750993,0.000006001822,0.0004021255,0.8468674,0.01123306,0.009478392,0.01892892,0.106718],"study_design_scores_gemma":[0.001217627,0.00007007688,0.00395093,0.00004989593,0.0003280024,0.0001474991,0.0006592775,0.9514089,0.006192024,0.01721406,0.01836507,0.0003966082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1341439,0.00008488826,0.8637192,0.0004366741,0.0000464047,0.0001369205,0.00002501529,0.00002728587,0.001379675],"genre_scores_gemma":[0.9196953,0.000005521978,0.07743505,0.0001578951,0.001263075,0.00002477873,0.0001508259,0.00002076763,0.001246791],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7862841,"threshold_uncertainty_score":0.7327185,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08005984562599212,"gpt":0.2340146645626377,"spread":0.1539548189366456,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000495258,0.000136648,0.0001418671,0.0001435666,0.001114943,0.0007688688,0.0006612409,0.00003015482,0.000009422633],"category_scores_gemma":[0.00006854496,0.00008034425,0.0000501115,0.0008812029,0.000186294,0.0004303765,0.0002569608,0.0003590515,0.000007068521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001029965,"about_ca_system_score_gemma":0.00005885605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001364575,"about_ca_topic_score_gemma":0.00003929716,"domain_scores_codex":[0.998932,0.0001136824,0.0001626574,0.0001986564,0.0002927123,0.0003002995],"domain_scores_gemma":[0.9992285,0.000219018,0.0001015655,0.0002805281,0.00007561862,0.00009478425],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00009692661,0.0001352123,0.06555642,0.0001240995,0.0004514947,0.0007117876,0.02582942,0.001502855,0.0003583169,0.05760957,0.008624384,0.8389995],"study_design_scores_gemma":[0.002751908,0.0009700579,0.5868365,0.000708388,0.0001248291,0.01241859,0.006119307,0.2089982,0.002691992,0.161187,0.01522886,0.001964359],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7074201,0.001056824,0.2834009,0.005551496,0.0005760097,0.0002341129,0.000007988479,0.001215369,0.000537197],"genre_scores_gemma":[0.8193328,0.0002916522,0.179204,0.0002875054,0.0004074233,0.00001922772,0.000003691547,0.00003011346,0.0004235345],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8370352,"threshold_uncertainty_score":0.8575353,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1373293441517697,"gpt":0.3581651089396327,"spread":0.220835764787863,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009736187,0.0001192592,0.0001527771,0.00004631945,0.0006138621,0.00008723191,0.0004922206,0.00001331519,0.00001403587],"category_scores_gemma":[0.0001091021,0.00007016728,0.00009220924,0.0001344073,0.00004218199,0.001722323,0.0002027439,0.0002020409,0.0000336149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003674794,"about_ca_system_score_gemma":0.00003703491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000604868,"about_ca_topic_score_gemma":0.000001665623,"domain_scores_codex":[0.9989419,0.0001158403,0.0001924268,0.0001248083,0.0001889315,0.0004361147],"domain_scores_gemma":[0.9988298,0.0003885227,0.000159576,0.0004227292,0.00005039356,0.0001489526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004332301,0.0002132671,0.0006343068,0.00003238343,0.00008712908,0.000009657908,0.004838543,0.0001056663,0.009755337,0.8332103,0.03425666,0.1168134],"study_design_scores_gemma":[0.0005340509,0.0001221841,0.0004860908,0.00009786469,0.000028376,0.0009432368,0.0004863644,0.006132059,0.007590898,0.004409152,0.9788489,0.0003208456],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01036211,0.0004051381,0.9865683,0.001135968,0.001113215,0.0001274291,0.0000286368,0.00004602312,0.0002131422],"genre_scores_gemma":[0.5960639,0.00008523367,0.397874,0.0007233644,0.004888044,0.00003828961,0.000009419319,0.00002857038,0.0002891488],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9445922,"threshold_uncertainty_score":0.4721393,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05989600271466623,"gpt":0.2653695745818546,"spread":0.2054735718671883,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003730603,0.00007438666,0.0000884909,0.00002390027,0.0006901779,0.000463257,0.0006702052,0.00001240363,0.000003583823],"category_scores_gemma":[0.00004841847,0.00003873181,0.000007204468,0.0001425472,0.00008430439,0.001712644,0.0004737065,0.0001799504,0.000002813921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007994224,"about_ca_system_score_gemma":0.00001830082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000955006,"about_ca_topic_score_gemma":0.000007925438,"domain_scores_codex":[0.9992916,0.00005041151,0.000159765,0.0001513497,0.0001951514,0.0001517028],"domain_scores_gemma":[0.998964,0.0000666205,0.000164708,0.0006997419,0.00005243592,0.00005254174],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005055993,0.0001631959,0.03028619,0.0002590527,0.0002965659,0.001387103,0.02495763,0.001100237,0.004917883,0.1914974,0.02087028,0.7242139],"study_design_scores_gemma":[0.001969845,0.000507936,0.007333971,0.001615975,0.0001361502,0.05863261,0.005154338,0.5959258,0.004408337,0.00427085,0.3186253,0.001418902],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01906438,0.002125532,0.9760068,0.001853383,0.0003289663,0.00003890696,0.000002480309,0.0000357233,0.0005438156],"genre_scores_gemma":[0.7713348,0.0002021106,0.2273845,0.0001425308,0.0006319269,8.536715e-7,0.000001023306,0.000009736003,0.0002925005],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7522705,"threshold_uncertainty_score":0.530836,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02986945958720896,"gpt":0.2845440588140477,"spread":0.2546745992268387,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006974355,0.0001554193,0.0002039244,0.0001214938,0.0004105531,0.00008604208,0.0006235059,0.00002398758,0.00004171184],"category_scores_gemma":[0.0001575105,0.00009660173,0.00007297123,0.0004796785,0.00008230042,0.0008954771,0.000288581,0.0003862337,0.0001554273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001079769,"about_ca_system_score_gemma":0.0001729665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002113004,"about_ca_topic_score_gemma":0.0005981587,"domain_scores_codex":[0.9985479,0.0001090356,0.0003907364,0.0002297925,0.0003481337,0.0003743981],"domain_scores_gemma":[0.9988602,0.0001001947,0.0001884442,0.0006636131,0.00006569498,0.0001218258],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006342395,0.0002064871,0.000928251,0.00003513371,0.00005014677,0.001078266,0.006250481,0.005388121,0.001616867,0.9664844,0.006219442,0.01167898],"study_design_scores_gemma":[0.002009937,0.0001878743,0.002137514,0.0005303612,0.00001063345,0.004213646,0.0008074621,0.0009057648,0.003554978,0.01209026,0.9731195,0.0004320533],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06618252,0.001441083,0.9231675,0.004863376,0.001235668,0.0002236818,0.00002663408,0.00008393186,0.002775551],"genre_scores_gemma":[0.8199086,0.001928703,0.1715694,0.003593183,0.001489115,0.00005303231,0.00002533234,0.00005996596,0.001372692],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9669001,"threshold_uncertainty_score":0.3939304,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1634969110956813,"gpt":0.3746252582239727,"spread":0.2111283471282914,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004119814,0.00005250777,0.00006370874,0.0001374601,0.0002629682,0.0005952428,0.003438677,0.00001325736,0.00001493749],"category_scores_gemma":[0.0003015534,0.00002885096,0.00001734875,0.0007848564,0.0001490871,0.001431426,0.0004341691,0.0002472027,0.00004027018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001607108,"about_ca_system_score_gemma":0.0003597856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007981723,"about_ca_topic_score_gemma":4.790203e-7,"domain_scores_codex":[0.9989538,0.0001363516,0.0001943482,0.0001992007,0.0003838095,0.0001325106],"domain_scores_gemma":[0.9986504,0.0002050954,0.00008977019,0.0009136459,0.00009133512,0.0000497529],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006751747,0.00003288495,0.0001343249,0.00001698667,0.0000147498,0.00001755013,0.0005671554,0.0008319439,0.03005883,0.0408041,0.01254104,0.9149737],"study_design_scores_gemma":[0.00005696119,0.00003392768,0.004316045,0.00005879582,0.0000106392,0.0005171837,0.00002426067,0.9723957,0.000577574,0.002592524,0.01935729,0.0000591675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006856071,0.0008634182,0.9917012,0.005618825,0.0004951906,0.00003366468,0.000003287732,0.00005681476,0.0005420106],"genre_scores_gemma":[0.8905144,0.0001873426,0.1086662,0.0000932461,0.0002602001,7.117844e-7,0.000003178742,0.000005283742,0.0002693949],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9715637,"threshold_uncertainty_score":0.6389975,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}