{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":17,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":17,"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":"ea3402be1ff5","filters":{"venue":"Very Large Data Bases"}},"results":[{"id":"W2041180570","doi":"10.5555/1182635.1164189","title":"Lazy database replication with snapshot isolation","year":2006,"lang":"en","type":"article","venue":"Very Large Data Bases","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":146,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Snapshot (computer storage); Serializability; Distributed computing; Concurrency; Database; Database transaction; Concurrency control; Isolation (microbiology); Data integrity; Transaction processing; Distributed transaction","retraction":null,"screen_n_in":null,"score":{"opus":0.02553277817671872,"gpt":0.2612185157962632,"spread":0.2356857376195444,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003978205,0.0001205819,0.0001222955,0.00005181143,0.0001449253,0.0002091077,0.001094896,0.00003293064,0.00003674175],"category_scores_gemma":[0.0000455101,0.00009965023,0.00001521877,0.0004001902,0.00001919178,0.002245635,0.0003429194,0.00006899979,0.000059048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001963269,"about_ca_system_score_gemma":0.00005683388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003941773,"about_ca_topic_score_gemma":0.0002725373,"domain_scores_codex":[0.9985438,0.00004731883,0.0002185538,0.0006959118,0.0002592624,0.0002351323],"domain_scores_gemma":[0.996239,0.00005179616,0.0001199431,0.003469176,0.0000733806,0.00004670395],"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":[0.00004875265,0.0007619601,0.0230365,0.0001075176,0.00003660625,0.0001031139,0.00004752919,0.0002773299,0.003377244,0.1401359,0.8247688,0.007298661],"study_design_scores_gemma":[0.0005923561,0.00004902753,0.01319203,0.00008182238,0.0000129628,0.00003832086,0.00001332776,0.1822129,0.0008913056,0.0001392337,0.8024815,0.0002951558],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00967978,0.000370962,0.9815481,0.0003869559,0.0001598094,0.0001983691,0.005781267,0.0001760215,0.001698709],"genre_scores_gemma":[0.93562,0.00001531892,0.0216064,0.0003319687,0.0002052235,0.00002341185,0.04197833,0.00001114405,0.0002082257],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9599417,"threshold_uncertainty_score":0.4063618,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2118326624","doi":"10.5555/1182635.1164140","title":"Efficient secure query evaluation over encrypted XML databases","year":2006,"lang":"en","type":"article","venue":"Very Large Data Bases","topic":"Cryptography and Data Security","field":"Computer Science","cited_by":126,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Database; Encryption; Database security; Metadata; View; XML database; XML Encryption; Information retrieval; XML; Computer security; Database design; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.03633933031643261,"gpt":0.2968752340972579,"spread":0.2605359037808253,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001400533,0.0002562026,0.0002166503,0.0002458821,0.0002989895,0.0002704891,0.001901904,0.00006482934,0.0004208434],"category_scores_gemma":[0.0002833086,0.0002381948,0.00007619454,0.0009359709,0.00006596804,0.001613508,0.001766267,0.0001776709,0.0001064604],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003989756,"about_ca_system_score_gemma":0.0001861196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007935662,"about_ca_topic_score_gemma":0.0007172869,"domain_scores_codex":[0.9969066,0.0002492093,0.0003670876,0.001031744,0.000942048,0.0005032686],"domain_scores_gemma":[0.995765,0.0002851582,0.000146734,0.003562882,0.0001362089,0.0001039607],"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":[0.00005595697,0.002129859,0.0106027,0.00009589524,0.00006763306,0.0001101634,0.0001325429,0.0009115197,0.001188761,0.3950707,0.583452,0.006182232],"study_design_scores_gemma":[0.001301711,0.00004676167,0.02591831,0.00008465094,0.00008959457,0.00002246809,0.00004581159,0.620317,0.0009976777,0.00207143,0.3484833,0.0006212654],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2880721,0.003380074,0.6705275,0.0002411675,0.001276523,0.0007062066,0.03397528,0.0006140039,0.001207138],"genre_scores_gemma":[0.933746,0.00005573272,0.02549034,0.0006856002,0.0004088209,0.00003379257,0.03955165,0.00002040818,0.000007631003],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6456739,"threshold_uncertainty_score":0.9713302,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2784053634","doi":"10.1145/3164135.3164139","title":"The ubiquity of large graphs and surprising challenges of graph processing","year":2017,"lang":"en","type":"article","venue":"Very Large Data Bases","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Scalability; Suite; Visualization; Graph; Software; Data science; Call graph; Theoretical computer science; Data visualization; World Wide Web; Data mining; Programming language; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.07621659304314052,"gpt":0.3534706649777041,"spread":0.2772540719345635,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001026407,0.00008507412,0.0001545899,0.00006346419,0.0005536725,0.0002610306,0.001921946,0.00002821009,0.000002364511],"category_scores_gemma":[0.0004061649,0.00006119932,0.00002436123,0.0001091874,0.0001451977,0.001464177,0.001681051,0.00005177877,7.292676e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000203011,"about_ca_system_score_gemma":0.00005023013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003236485,"about_ca_topic_score_gemma":0.000237648,"domain_scores_codex":[0.9990513,0.00005607149,0.0002130753,0.0002725515,0.0002229203,0.0001840841],"domain_scores_gemma":[0.9975839,0.0001179347,0.0003115232,0.00184583,0.00009834743,0.00004242529],"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":[0.00001887845,0.0005089861,0.0220201,0.0006299675,0.00008771861,0.00001328465,0.0007096767,0.000001381732,0.0004070919,0.8814288,0.008356789,0.08581729],"study_design_scores_gemma":[0.004726885,0.0004325957,0.2168461,0.00230293,0.0003119934,0.00004665043,0.003590995,0.3251469,0.02382366,0.05175477,0.3691863,0.001830192],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2537188,0.0483197,0.6720451,0.005488787,0.00136303,0.0007840008,0.01343644,0.0004123016,0.00443185],"genre_scores_gemma":[0.9948739,0.003593921,0.001329457,0.00006610494,0.00001292615,7.379763e-7,0.0001020241,0.000005303011,0.00001560197],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8296741,"threshold_uncertainty_score":0.4258457,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2791526170","doi":"10.1145/3164135.3164147","title":"Bztree: a high-performance latch-free range index for non-volatile memory","year":2018,"lang":"en","type":"article","venue":"Very Large Data Bases","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":83,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Non-volatile memory; Block (permutation group theory); Embedded system; Throughput; Computer hardware; Tree (set theory); Semiconductor memory; Code (set theory); Data retention; Parallel computing; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.02434901392116039,"gpt":0.2591629562395728,"spread":0.2348139423184124,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005993028,0.0002284551,0.0003046284,0.00008971951,0.0003263243,0.0002234009,0.003571236,0.00009652421,0.000078312],"category_scores_gemma":[0.00013534,0.0002038107,0.0000493884,0.0004425638,0.00007553284,0.002211044,0.001371255,0.0001125937,0.0002183274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002979019,"about_ca_system_score_gemma":0.0001345889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001771142,"about_ca_topic_score_gemma":0.0002252443,"domain_scores_codex":[0.9979687,0.00003729438,0.0003432321,0.0007421113,0.0003485481,0.0005601427],"domain_scores_gemma":[0.9958624,0.000139189,0.0001447881,0.003561504,0.0001705258,0.00012165],"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":[0.00009532101,0.0002439012,0.004907455,0.0001806104,0.0000575126,0.00002021829,0.0001571629,0.00001580871,0.0002070057,0.002083582,0.9750605,0.01697096],"study_design_scores_gemma":[0.002511477,0.0002331773,0.01231917,0.0001652226,0.00001825344,0.00001377364,0.00002427443,0.4554692,0.001265264,0.000207294,0.5273058,0.0004671343],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1245265,0.0003241706,0.852271,0.0007926432,0.002621609,0.0008165466,0.01725882,0.0003724767,0.001016212],"genre_scores_gemma":[0.9879359,0.00002003254,0.008479698,0.0008682191,0.0007962204,0.00007301836,0.00116746,0.0000224285,0.0006370048],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8634093,"threshold_uncertainty_score":0.8311158,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2169424245","doi":"10.5555/1182635.1164177","title":"Answering tree pattern queries using views","year":2006,"lang":"en","type":"article","venue":"Very Large Data Bases","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Rewriting; Schema (genetic algorithms); Computer science; Time complexity; Tree (set theory); Theoretical computer science; Mathematics; Algorithm; Combinatorics; Programming language; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.06735454525073631,"gpt":0.2970910055120431,"spread":0.2297364602613068,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002889799,0.0001992186,0.0002404612,0.00008495415,0.0002425733,0.0001372061,0.0009274819,0.00003623087,0.0000361875],"category_scores_gemma":[0.00004760198,0.000176836,0.00004037855,0.0002638045,0.00004334289,0.003634158,0.001343878,0.0000844663,0.00004666755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002704023,"about_ca_system_score_gemma":0.00005624344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001181368,"about_ca_topic_score_gemma":0.001954521,"domain_scores_codex":[0.9983633,0.0000690885,0.0003268171,0.0005981681,0.0002393507,0.0004032656],"domain_scores_gemma":[0.9975984,0.00007410689,0.0001227952,0.002111033,0.00003598051,0.00005773484],"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":[0.0000680782,0.001468802,0.09738699,0.001213278,0.0002084566,0.002195649,0.0008953176,0.001579237,0.04257329,0.2594697,0.3266879,0.2662533],"study_design_scores_gemma":[0.0002345987,0.00001895295,0.00146883,0.000104321,0.000008710826,0.00004681919,0.00005160299,0.03580119,0.002380607,0.00009010437,0.9594672,0.0003270556],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01522439,0.001085741,0.979726,0.00007329804,0.0004768892,0.0001167807,0.002740716,0.0002085587,0.0003476289],"genre_scores_gemma":[0.4697219,0.00014285,0.5188168,0.001414038,0.001689664,0.00003989722,0.007317288,0.00009753936,0.0007600453],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6327793,"threshold_uncertainty_score":0.7211164,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2108075439","doi":"","title":"Approximate joins: concepts and techniques","year":2005,"lang":"en","type":"article","venue":"Very Large Data Bases","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Joins; Multitude; Computer science; Database; Quality (philosophy); Data quality; Character (mathematics); Service (business); Relational database; Missing data; Data science; Data mining; World Wide Web; Business; Marketing","retraction":null,"screen_n_in":null,"score":{"opus":0.2365840025725053,"gpt":0.4607702635409333,"spread":0.224186260968428,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003856645,0.0001260537,0.0002134087,0.0001463361,0.0001617881,0.0004400091,0.001418007,0.00004111492,0.0008855336],"category_scores_gemma":[0.001758456,0.00009404742,0.00002534918,0.0002678238,0.0001180869,0.002311572,0.002198617,0.00007824468,0.0004176799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001094035,"about_ca_system_score_gemma":0.0000240456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003720919,"about_ca_topic_score_gemma":0.0001823869,"domain_scores_codex":[0.997833,0.0001688038,0.0004116658,0.0006506177,0.0006721424,0.0002638179],"domain_scores_gemma":[0.9972637,0.0004654627,0.0001218718,0.002003961,0.00005401519,0.00009098494],"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":[0.00001416099,0.0001302958,0.0005217004,0.00001256216,0.00001253064,0.00001040675,0.00008042766,4.638468e-7,0.00009157779,0.01568962,0.8023581,0.1810782],"study_design_scores_gemma":[0.0001752135,0.00002317092,0.0004111849,0.00001660637,0.00001178612,0.000004337811,0.0004267237,0.001060392,0.001178982,0.001975029,0.9945806,0.0001360034],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2004807,0.01323976,0.4310565,0.04598019,0.002408485,0.004996289,0.1685955,0.003369529,0.129873],"genre_scores_gemma":[0.8628125,0.002198087,0.09010569,0.02685067,0.001046362,0.00008473015,0.008422949,0.00005652888,0.00842254],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6623317,"threshold_uncertainty_score":0.9695972,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W145033769","doi":"","title":"The Long-Term Preservation of Authentic Electronic Records","year":2001,"lang":"en","type":"article","venue":"Very Large Data Bases","topic":"Digital and Traditional Archives Management","field":"Arts and Humanities","cited_by":26,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Term (time); Computer science; Phase (matter); Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.0536414918134093,"gpt":0.2481834449299291,"spread":0.1945419531165198,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001304375,0.00006704856,0.00006448727,0.00003322423,0.0002226536,0.0001424378,0.0004149695,0.000003980226,0.0004945939],"category_scores_gemma":[0.00002871879,0.0000445662,0.00003091226,0.0000286394,0.00009030137,0.0008416435,0.0001923367,0.00004422605,0.00006034899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007954057,"about_ca_system_score_gemma":0.00002019083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005273371,"about_ca_topic_score_gemma":0.001075896,"domain_scores_codex":[0.9993543,0.00002148949,0.0001456447,0.0001388609,0.0001481623,0.0001915168],"domain_scores_gemma":[0.9993661,0.0001196136,0.0000598129,0.0004125831,0.00002347434,0.0000184052],"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":[0.00005375346,0.0002771876,0.002514748,0.00004151201,0.00008968535,0.000006517906,0.0002259675,0.000001064528,0.000002545632,0.9522069,0.02947642,0.01510372],"study_design_scores_gemma":[0.0001632883,0.00008519227,0.03728514,0.00003399456,0.00003360152,0.00000147395,0.00008068855,0.0003169343,0.000009489163,0.02392634,0.9379806,0.00008324432],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7823752,0.0005272601,0.0005378766,0.001313732,0.0006608811,0.0003962299,0.004453107,0.00009535839,0.2096403],"genre_scores_gemma":[0.9814216,0.0003252968,0.000004197402,0.0001252377,0.0002026824,0.0000100123,0.003275563,0.000007087019,0.01462826],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9282805,"threshold_uncertainty_score":0.5415457,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2400761516","doi":"","title":"Towards Dynamic Green-Sizing for Database Servers.","year":2015,"lang":"en","type":"article","venue":"Very Large Data Bases","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Server; Computer science; Frequency scaling; Memory management; Exploit; Workload; Database server; Power (physics); Dynamic demand; Database; Transaction processing; Operating system; Database transaction; Semiconductor memory","retraction":null,"screen_n_in":null,"score":{"opus":0.07489147399189085,"gpt":0.3030708951274435,"spread":0.2281794211355527,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001230615,0.0001752009,0.0001808759,0.0001151901,0.0001814685,0.000209599,0.002797502,0.00003655222,0.000006393287],"category_scores_gemma":[0.0002373603,0.0001573593,0.00005295061,0.0003257419,0.00002405526,0.0002756603,0.004386585,0.00009531269,0.00006202178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006148537,"about_ca_system_score_gemma":0.0001263711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003119458,"about_ca_topic_score_gemma":0.0001470117,"domain_scores_codex":[0.9981399,0.00006815625,0.0002174076,0.0007146493,0.0003607987,0.0004990508],"domain_scores_gemma":[0.997059,0.0001157845,0.00008480327,0.002473817,0.00007614536,0.0001903849],"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":[0.0001242956,0.001262694,0.001422644,0.000685576,0.0003371476,0.0004502252,0.001162114,0.002497134,0.0002006105,0.03550287,0.6938351,0.2625196],"study_design_scores_gemma":[0.0006479413,0.00005761545,0.0001058957,0.00004398663,0.00001841925,0.000008482337,0.0001036605,0.6521362,0.00004131038,0.0002760866,0.3463635,0.0001968577],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0437214,0.001167377,0.9461105,0.002994859,0.001456083,0.0004696037,0.002565597,0.0006573946,0.0008572186],"genre_scores_gemma":[0.7665501,0.00003932124,0.2199212,0.004825714,0.0007792387,0.00005020996,0.005563473,0.00007388271,0.002196906],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7261893,"threshold_uncertainty_score":0.6416928,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2889053599","doi":"10.5555/3236187.3269462","title":"Efficient construction of approximate ad-hoc ML models through materialization and reuse","year":2018,"lang":"en","type":"article","venue":"Very Large Data Bases","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Online analytical processing; Reuse; Dimension (graph theory); Cluster analysis; Data warehouse; Data mining; Construct (python library); Variety (cybernetics); Mixture model; Data modeling; Machine learning; Artificial intelligence; Database; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.04435581347020066,"gpt":0.2676946544767879,"spread":0.2233388410065872,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002797947,0.00009798915,0.0001218214,0.00006537694,0.0001067553,0.0001785723,0.001038089,0.00002646972,0.00002721712],"category_scores_gemma":[0.00004554371,0.00008822668,0.00001032386,0.0002315282,0.0001070423,0.001705019,0.002208212,0.00002289819,0.00001240146],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006925625,"about_ca_system_score_gemma":0.00001542013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001708505,"about_ca_topic_score_gemma":0.000003632128,"domain_scores_codex":[0.9990007,0.00004123656,0.0001925751,0.0004124481,0.0001831187,0.0001699489],"domain_scores_gemma":[0.9981805,0.00001868836,0.0001072831,0.001609816,0.00005686275,0.00002686286],"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":[0.0002173772,0.00110049,0.000525477,0.000838341,0.0002123488,0.00004077152,0.002870074,0.0005514217,0.004961374,0.8115037,0.1088829,0.06829573],"study_design_scores_gemma":[0.0004481464,0.00007473589,0.00006025383,0.00005447022,0.00002141638,0.000007159435,0.0000712256,0.9639546,0.003698264,0.003755713,0.02769329,0.0001607811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06484899,0.0001753722,0.9318442,0.0001152202,0.0006737309,0.0001664619,0.001794881,0.0001158671,0.0002652736],"genre_scores_gemma":[0.3167988,0.000747927,0.677894,0.0003709241,0.0002378528,0.00001203448,0.003831743,0.00002557194,0.00008111493],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9634031,"threshold_uncertainty_score":0.359778,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1489499991","doi":"","title":"Personalizing XML text search in PIMENT","year":2005,"lang":"en","type":"article","venue":"Very Large Data Bases","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Information retrieval; Web search query; Ranking (information retrieval); Personalization; Query expansion; Web query classification; XML; World Wide Web; Search engine","retraction":null,"screen_n_in":null,"score":{"opus":0.05606628651388298,"gpt":0.314073539819003,"spread":0.2580072533051201,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005749163,0.0001254731,0.0001568628,0.0001148924,0.0001180589,0.0000718627,0.0009247722,0.00002683346,0.0001149562],"category_scores_gemma":[0.00006427996,0.000112864,0.00002224149,0.0003047367,0.00002685145,0.002698162,0.001425607,0.0001222137,0.000251418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005687829,"about_ca_system_score_gemma":0.00008448499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002122492,"about_ca_topic_score_gemma":0.0004927487,"domain_scores_codex":[0.9984688,0.00007987262,0.0002139019,0.0005327221,0.0003057395,0.0003989956],"domain_scores_gemma":[0.9982904,0.0001060178,0.00003732303,0.001461966,0.00002537011,0.00007889525],"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":[0.00008545736,0.001646064,0.02199726,0.0003469097,0.00009558901,0.0007709741,0.003944493,0.001057654,0.004624621,0.5564882,0.1982534,0.2106893],"study_design_scores_gemma":[0.0003584599,0.00002097895,0.0008618812,0.00007913305,0.000001927063,0.00001862885,0.0002295564,0.04290469,0.001301448,0.00001534707,0.954021,0.0001869264],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04145268,0.004117252,0.9456884,0.002099383,0.0004208088,0.0003794426,0.003984612,0.0002631028,0.001594383],"genre_scores_gemma":[0.7168172,0.0003128143,0.2769735,0.002191531,0.0005816447,0.00003517702,0.002110366,0.00003153838,0.0009462823],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7557676,"threshold_uncertainty_score":0.4602462,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3204354173","doi":"","title":"Enabling NUMA-aware Main Memory Spatial Join Processing: An Experimental Study.","year":2020,"lang":"en","type":"article","venue":"Very Large Data Bases","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Join (topology); Parallel computing; Computer architecture","retraction":null,"screen_n_in":null,"score":{"opus":0.08098202661924112,"gpt":0.3075131336643204,"spread":0.2265311070450793,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004210277,0.0002210366,0.0002138001,0.00008517055,0.0002815753,0.0008524313,0.003199899,0.00002895831,0.000147623],"category_scores_gemma":[0.00006305146,0.0002084389,0.00002863471,0.0003940598,0.00002676532,0.005453504,0.00368386,0.0001305918,0.0001054145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002138562,"about_ca_system_score_gemma":0.00008053022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000105615,"about_ca_topic_score_gemma":0.000054339,"domain_scores_codex":[0.9977088,0.0001225554,0.0002660569,0.001019382,0.0004858584,0.0003973403],"domain_scores_gemma":[0.9981418,0.00002819275,0.00009303888,0.001519609,0.00002557086,0.0001918144],"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":[0.0003844718,0.02359642,0.01052692,0.0007274693,0.0004343455,0.006630842,0.0206987,0.000129027,0.01102185,0.002907956,0.4928862,0.4300557],"study_design_scores_gemma":[0.002977578,0.001252461,0.0007717625,0.00006591137,0.00006102136,0.00001231565,0.01148248,0.8866907,0.006865416,0.00003712278,0.08867477,0.001108503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1599634,0.0009747074,0.8276687,0.001834992,0.00120774,0.001528584,0.004709537,0.001511191,0.0006011074],"genre_scores_gemma":[0.986749,0.000006890447,0.008129829,0.001695795,0.0005506756,0.00002122596,0.002751569,0.00002413895,0.00007086087],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8865616,"threshold_uncertainty_score":0.8499893,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2398890672","doi":"","title":"Towards Adaptive Resource Allocation for Database Workloads.","year":2015,"lang":"en","type":"article","venue":"Very Large Data Bases","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Workload; Scalability; Resource allocation; Distributed computing; Performance tuning; Performance metric; Real-time computing; Database; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.09405781546455771,"gpt":0.2961469118723735,"spread":0.2020890964078157,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001331364,0.0001659517,0.0001634105,0.0001093706,0.0001733724,0.0001934536,0.002352533,0.00004055252,0.000005029818],"category_scores_gemma":[0.0003872971,0.0001483201,0.00004198938,0.0003725401,0.00003034479,0.0002155566,0.002923069,0.00009623655,0.00005929705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000532253,"about_ca_system_score_gemma":0.0001275542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000867416,"about_ca_topic_score_gemma":0.00002495592,"domain_scores_codex":[0.998181,0.0001031127,0.0002219249,0.0007171328,0.0003900501,0.0003867941],"domain_scores_gemma":[0.9970974,0.000174236,0.0001005145,0.002354484,0.000101273,0.000172125],"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":[0.00008499965,0.0003670233,0.00009712827,0.00004221838,0.00007138597,0.00003295694,0.0004319365,0.001788893,0.00002316287,0.02990672,0.8832182,0.0839354],"study_design_scores_gemma":[0.0005318312,0.00008316578,0.00004977719,0.00004919581,0.00001714861,0.000004034215,0.0001933852,0.4322317,0.0001140034,0.0002601481,0.5662957,0.0001699033],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004710716,0.0007523192,0.9883717,0.002058695,0.0004870346,0.0004088381,0.0008463324,0.0003666349,0.001997679],"genre_scores_gemma":[0.6703752,0.00002663767,0.3144881,0.005505641,0.001514999,0.0001116197,0.005467345,0.00006799208,0.002442562],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6738837,"threshold_uncertainty_score":0.6048319,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2144006311","doi":"","title":"MIX: a meta-data indexing system for XML","year":2005,"lang":"en","type":"article","venue":"Very Large Data Bases","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"XPath; Computer science; XML database; Information retrieval; Streaming XML; XML validation; Efficient XML Interchange; XML Encryption; Document Structure Description; XML Schema (W3C); Database; XML Schema Editor; Search engine indexing; Simple API for XML; XML Signature; XML; Data mining; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.1406926542850825,"gpt":0.3255385009971596,"spread":0.1848458467120771,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001164063,0.000238136,0.0004339493,0.0001006641,0.0002978565,0.0001666496,0.003304062,0.00005257002,0.0000260708],"category_scores_gemma":[0.0003209049,0.0001899239,0.00007452263,0.0002672982,0.00002978397,0.006495252,0.003888593,0.00009641505,0.00009422521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003963274,"about_ca_system_score_gemma":0.0001140357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008680221,"about_ca_topic_score_gemma":0.0003010734,"domain_scores_codex":[0.9976406,0.00008849091,0.0004171431,0.001050472,0.0003152743,0.0004880183],"domain_scores_gemma":[0.9931808,0.0003456032,0.0001765612,0.006104672,0.00007511656,0.0001172523],"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":[0.0000611797,0.0003621624,0.0002221844,0.0008321407,0.001245087,0.0001111019,0.0001951468,0.0002356892,0.000517257,0.5398684,0.4235606,0.03278907],"study_design_scores_gemma":[0.0003429971,0.00002070603,0.00001086052,0.00005978731,0.0001314427,0.00003654487,0.00007999533,0.09418365,0.0006554053,0.00001829614,0.9042274,0.0002329277],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00016119,0.002752511,0.954648,0.0003771423,0.0004886719,0.0003593486,0.04071652,0.0003299447,0.0001666651],"genre_scores_gemma":[0.08524068,0.00007817583,0.8907365,0.001138366,0.001289617,0.0001758338,0.02068594,0.00005630132,0.0005985371],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5398501,"threshold_uncertainty_score":0.7744872,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2400133291","doi":"","title":"Robust concurrency control in main-memory DBMS: What main memory giveth, the application taketh away.","year":2014,"lang":"en","type":"article","venue":"Very Large Data Bases","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":1,"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; Concurrency control; Multiversion concurrency control; Non-lock concurrency control; Concurrency; Database; Optimistic concurrency control; Memory management; Distributed concurrency control; Parallel computing; Programming language; Operating system; Database transaction; Overlay","retraction":null,"screen_n_in":null,"score":{"opus":0.02795687589826629,"gpt":0.2522051176409221,"spread":0.2242482417426558,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002458649,0.0002604309,0.0003660843,0.00008964975,0.0002385793,0.0005458048,0.003013921,0.0001059726,0.00003525372],"category_scores_gemma":[0.0002536797,0.0001992632,0.00006261361,0.0005065601,0.0001011645,0.002444535,0.0005519386,0.000291854,0.0001492314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000064857,"about_ca_system_score_gemma":0.0001426839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000274458,"about_ca_topic_score_gemma":0.0005256052,"domain_scores_codex":[0.9971336,0.0004977112,0.0004988267,0.0008759934,0.0004330328,0.0005608531],"domain_scores_gemma":[0.9959404,0.0006230848,0.0002330356,0.003012757,0.00007429891,0.0001164426],"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":[0.0001335218,0.001522653,0.003580573,0.0004599122,0.0001615178,0.0001834511,0.001553247,0.00488682,0.00220381,0.09917124,0.4819439,0.4041994],"study_design_scores_gemma":[0.002330725,0.00005487871,0.002481906,0.000246073,0.00002253952,0.00003807161,0.0006860857,0.6262369,0.0001271081,0.0004552014,0.3668339,0.0004866209],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003435135,0.002186651,0.9875183,0.001722318,0.001049328,0.0007568942,0.002601953,0.000142328,0.000587063],"genre_scores_gemma":[0.9936885,0.0001848714,0.001095637,0.002961618,0.0003643695,0.0001524161,0.001380181,0.00002040368,0.0001519771],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9902534,"threshold_uncertainty_score":0.8125716,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3204354299","doi":"","title":"A Data Discovery Platform Empowered by Knowledge GraphTechnologies: Challenges and Opportunities.","year":2021,"lang":"en","type":"article","venue":"Very Large Data Bases","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":0,"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":"Knowledge extraction; Computer science; Data science; Knowledge management; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.2241899612295714,"gpt":0.3216368435572881,"spread":0.09744688232771662,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0004824869,0.000234067,0.0003199592,0.0001165319,0.0001680249,0.0003967033,0.00411381,0.0001241912,0.00001593511],"category_scores_gemma":[0.0005744661,0.0002020284,0.00002771643,0.0001967104,0.0001598667,0.004985867,0.0112462,0.0001651378,0.00001443424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001239594,"about_ca_system_score_gemma":0.0002260132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001695238,"about_ca_topic_score_gemma":0.0005261635,"domain_scores_codex":[0.9978898,0.00005947616,0.000260667,0.001126801,0.0002149674,0.0004482617],"domain_scores_gemma":[0.9939222,0.0004460079,0.00008491211,0.005411199,0.00005272322,0.0000829791],"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":[0.00002176012,0.000833668,0.0004901874,0.0003045017,0.0002337728,0.001028829,0.0005514847,1.381859e-7,0.0002253689,0.1700453,0.5884025,0.2378625],"study_design_scores_gemma":[0.0006310628,0.00007702503,0.0006378284,0.000134712,0.00003904611,0.0001447056,0.005316155,0.006736267,0.0009613959,0.002123018,0.982687,0.0005117789],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.04158713,0.7618311,0.1169702,0.01658742,0.002575241,0.0005377049,0.04829686,0.002490912,0.00912336],"genre_scores_gemma":[0.5386922,0.4071991,0.02360753,0.001981314,0.000242318,0.00004421069,0.02633686,0.00007020742,0.001826303],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.4971051,"threshold_uncertainty_score":0.9967507,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W10721341","doi":"10.5694/j.1326-5377.1999.tb123814.x","title":"Letter from the Research Track Co-Chair.","year":2011,"lang":"en","type":"letter","venue":"Very Large Data Bases","topic":"","field":"","cited_by":0,"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; Track (disk drive); Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.2888122786995828,"gpt":0.3825250955688818,"spread":0.09371281686929894,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004528549,0.0008867782,0.0008313657,0.0004820978,0.0007790113,0.0006355981,0.009971872,0.001226807,0.01959693],"category_scores_gemma":[0.001715472,0.0006221976,0.0002285328,0.0007054814,0.0008721873,0.001329381,0.003680039,0.008576539,0.1339368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001826892,"about_ca_system_score_gemma":0.0004071049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005170978,"about_ca_topic_score_gemma":0.001062897,"domain_scores_codex":[0.9883922,0.003213226,0.0007219753,0.002481314,0.002905869,0.002285422],"domain_scores_gemma":[0.9806074,0.005178859,0.0003168143,0.013456,0.0002912998,0.0001496542],"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":[0.00009682273,0.000166326,0.0008031362,0.00006498151,0.0003307845,0.002494287,0.0001078812,7.226332e-8,0.0000952132,0.00001593881,0.9957238,0.0001007323],"study_design_scores_gemma":[0.0005568041,0.0000427969,0.0006906559,0.0002682327,0.0001960434,0.00001988737,0.00003638267,0.00002707687,0.0002771605,0.000152681,0.9969636,0.0007686333],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"commentary","genre_scores_codex":[0.0006360112,0.001976038,0.00002814889,0.37958,0.001065625,0.0009804757,0.6117315,0.0003880545,0.003614146],"genre_scores_gemma":[0.0002251156,0.000123136,0.0001300995,0.6402591,0.02165707,0.00009954958,0.3337784,0.0005426742,0.003184774],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.2779531,"threshold_uncertainty_score":0.9996229,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2400495833","doi":"","title":"Composing Scalability for Transactions on Multicore Platforms.","year":2013,"lang":"en","type":"article","venue":"Very Large Data Bases","topic":"Distributed and Parallel Computing Systems","field":"Computer Science","cited_by":0,"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":"Multi-core processor; Scalability; Computer science; Distributed computing; Computer architecture; Parallel computing; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.05550861582558886,"gpt":0.2846928815528709,"spread":0.229184265727282,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003427635,0.0001451554,0.0001791651,0.00005424487,0.0003058911,0.0002954263,0.001304169,0.00005205363,0.00004252932],"category_scores_gemma":[0.00006261862,0.0001222768,0.00006285639,0.0001798185,0.00002652394,0.00108698,0.0001009935,0.0001016008,0.0001483289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002904382,"about_ca_system_score_gemma":0.00004640244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001041372,"about_ca_topic_score_gemma":0.0000196969,"domain_scores_codex":[0.9986795,0.00003099004,0.0002481589,0.0005099709,0.0001828084,0.0003486003],"domain_scores_gemma":[0.9978614,0.0004634354,0.00006712827,0.001429105,0.0000778874,0.0001010171],"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":[0.0002310807,0.007906181,0.01368135,0.001287933,0.0005724569,0.00004526263,0.001871487,0.02728889,0.002201183,0.04272703,0.5146087,0.3875784],"study_design_scores_gemma":[0.0006313561,0.00009826117,0.00197614,0.0000788386,0.00001014617,0.000008444546,0.00003176486,0.9500132,0.0004157138,0.0005801736,0.04591828,0.0002376801],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04386107,0.00003728916,0.9526885,0.0002143199,0.0005737279,0.0004525894,0.001850239,0.0002276229,0.00009463171],"genre_scores_gemma":[0.97627,0.000001930815,0.0223083,0.0003082028,0.00006867896,0.00003341036,0.0009463527,0.000008576999,0.00005455478],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9324089,"threshold_uncertainty_score":0.4986304,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}