{"meta":{"query_hash":"ea3402be1ff5","filters":{"venue":"Very Large Data Bases"},"cohort_total":17,"direct_labels_cover":0,"predictions_cover":17,"exported":17,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/ea3402be1ff5","api":"https://metacan.xera.ac/api/v1/cohort?venue=Very+Large+Data+Bases"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Track (disk drive); Operating system","score_opus":0.2888122786995828,"score_gpt":0.38252509556888176,"score_spread":0.09371281686929894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W10721341","genre_codex":"dataset","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006360112,0.001976038,0.00002814889,0.37957996,0.0010656248,0.0009804757,0.6117315,0.00038805447,0.0036141456],"genre_scores_gemma":[0.00022511561,0.00012313598,0.0001300995,0.64025915,0.021657066,0.00009954958,0.33377844,0.00054267416,0.0031847742],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9883922,0.0032132256,0.00072197535,0.0024813144,0.0029058687,0.0022854223],"domain_scores_gemma":[0.9806074,0.0051788595,0.00031681434,0.013455995,0.00029129977,0.00014965421],"candidate_categories":["metaepi_narrow","open_science","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0045285486,0.0008867782,0.0008313657,0.00048209782,0.00077901135,0.0006355981,0.009971872,0.0012268075,0.01959693],"category_scores_gemma":[0.0017154716,0.0006221976,0.00022853282,0.0007054814,0.0008721873,0.0013293809,0.0036800392,0.008576539,0.13393681],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000096822725,0.00016632598,0.00080313615,0.00006498151,0.0003307845,0.002494287,0.00010788116,7.226332e-8,0.000095213196,0.00001593881,0.99572384,0.00010073226],"study_design_scores_gemma":[0.0005568041,0.0000427969,0.0006906559,0.00026823272,0.00019604343,0.00001988737,0.00003638267,0.000027076874,0.00027716052,0.00015268096,0.9969636,0.0007686333],"about_ca_topic_score_codex":0.0051709777,"about_ca_topic_score_gemma":0.001062897,"teacher_disagreement_score":0.2779531,"about_ca_system_score_codex":0.00018268915,"about_ca_system_score_gemma":0.0004071049,"threshold_uncertainty_score":0.99962294},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Term (time); Computer science; Phase (matter); Data science","score_opus":0.0536414918134093,"score_gpt":0.24818344492992914,"score_spread":0.19454195311651984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W145033769","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7823752,0.0005272601,0.0005378766,0.0013137321,0.00066088105,0.00039622988,0.0044531072,0.000095358395,0.20964032],"genre_scores_gemma":[0.98142165,0.00032529677,0.0000041974017,0.00012523774,0.0002026824,0.000010012297,0.0032755632,0.0000070870187,0.014628257],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993543,0.000021489486,0.00014564472,0.00013886091,0.00014816227,0.00019151684],"domain_scores_gemma":[0.9993661,0.0001196136,0.0000598129,0.00041258312,0.000023474338,0.000018405195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013043749,0.00006704856,0.00006448727,0.000033224227,0.00022265357,0.00014243784,0.00041496955,0.000003980226,0.0004945939],"category_scores_gemma":[0.000028718794,0.000044566197,0.000030912262,0.000028639397,0.00009030137,0.00084164354,0.00019233668,0.00004422605,0.00006034899],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005375346,0.00027718756,0.0025147481,0.000041512012,0.000089685345,0.0000065179056,0.00022596745,0.0000010645275,0.0000025456325,0.95220685,0.029476421,0.015103722],"study_design_scores_gemma":[0.0001632883,0.000085192274,0.03728514,0.000033994558,0.000033601522,0.0000014739501,0.00008068855,0.00031693425,0.000009489163,0.023926344,0.9379806,0.00008324432],"about_ca_topic_score_codex":0.000052733714,"about_ca_topic_score_gemma":0.0010758963,"teacher_disagreement_score":0.92828053,"about_ca_system_score_codex":0.000007954057,"about_ca_system_score_gemma":0.000020190831,"threshold_uncertainty_score":0.5415457},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.056066286513882985,"score_gpt":0.31407353981900304,"score_spread":0.2580072533051201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1489499991","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041452676,0.0041172523,0.94568837,0.0020993834,0.0004208088,0.00037944264,0.003984612,0.0002631028,0.0015943828],"genre_scores_gemma":[0.7168172,0.0003128143,0.27697346,0.0021915315,0.00058164465,0.000035177025,0.0021103665,0.00003153838,0.0009462823],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99846876,0.00007987262,0.00021390195,0.0005327221,0.00030573946,0.00039899565],"domain_scores_gemma":[0.9982904,0.00010601776,0.00003732303,0.0014619661,0.000025370111,0.00007889525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005749163,0.00012547312,0.00015686284,0.00011489242,0.000118058946,0.0000718627,0.0009247722,0.000026833459,0.00011495616],"category_scores_gemma":[0.00006427996,0.000112864036,0.00002224149,0.0003047367,0.000026851452,0.0026981619,0.0014256065,0.00012221372,0.00025141798],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008545736,0.0016460643,0.021997262,0.0003469097,0.000095589014,0.00077097415,0.0039444934,0.0010576537,0.0046246215,0.5564882,0.19825342,0.21068932],"study_design_scores_gemma":[0.0003584599,0.000020978945,0.0008618812,0.000079133046,0.0000019270633,0.000018628847,0.00022955642,0.042904694,0.0013014481,0.000015347068,0.95402104,0.00018692637],"about_ca_topic_score_codex":0.00021224919,"about_ca_topic_score_gemma":0.0004927487,"teacher_disagreement_score":0.7557676,"about_ca_system_score_codex":0.000056878293,"about_ca_system_score_gemma":0.000084484986,"threshold_uncertainty_score":0.46024618},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Snapshot (computer storage); Serializability; Distributed computing; Concurrency; Database; Database transaction; Concurrency control; Isolation (microbiology); Data integrity; Transaction processing; Distributed transaction","score_opus":0.025532778176718715,"score_gpt":0.26121851579626315,"score_spread":0.23568573761954442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041180570","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00967978,0.00037096202,0.98154813,0.00038695586,0.00015980937,0.00019836912,0.0057812673,0.00017602154,0.0016987091],"genre_scores_gemma":[0.93562,0.00001531892,0.021606397,0.00033196865,0.0002052235,0.000023411845,0.041978326,0.000011144054,0.00020822567],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985438,0.00004731883,0.00021855377,0.0006959118,0.00025926236,0.00023513235],"domain_scores_gemma":[0.996239,0.000051796163,0.000119943055,0.003469176,0.0000733806,0.00004670395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039782046,0.00012058193,0.00012229552,0.000051811432,0.00014492526,0.00020910773,0.0010948965,0.000032930642,0.00003674175],"category_scores_gemma":[0.0000455101,0.00009965023,0.000015218767,0.00040019024,0.000019191782,0.0022456353,0.00034291937,0.00006899979,0.000059048005],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048752652,0.0007619601,0.0230365,0.00010751757,0.00003660625,0.000103113896,0.000047529193,0.00027732988,0.003377244,0.14013591,0.82476884,0.007298661],"study_design_scores_gemma":[0.0005923561,0.00004902753,0.013192031,0.00008182238,0.000012962804,0.000038320864,0.00001332776,0.18221295,0.00089130556,0.0001392337,0.80248153,0.0002951558],"about_ca_topic_score_codex":0.00039417733,"about_ca_topic_score_gemma":0.00027253732,"teacher_disagreement_score":0.95994174,"about_ca_system_score_codex":0.000019632687,"about_ca_system_score_gemma":0.00005683388,"threshold_uncertainty_score":0.40636185},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.2365840025725053,"score_gpt":0.4607702635409333,"score_spread":0.224186260968428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108075439","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20048073,0.013239764,0.43105653,0.045980193,0.0024084847,0.004996289,0.16859552,0.003369529,0.12987296],"genre_scores_gemma":[0.86281246,0.002198087,0.09010569,0.026850669,0.0010463619,0.00008473015,0.008422949,0.000056528883,0.00842254],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99783295,0.00016880377,0.00041166577,0.0006506177,0.0006721424,0.0002638179],"domain_scores_gemma":[0.9972637,0.00046546268,0.000121871766,0.0020039612,0.00005401519,0.00009098494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038566452,0.0001260537,0.00021340873,0.00014633607,0.00016178815,0.00044000914,0.0014180073,0.00004111492,0.00088553363],"category_scores_gemma":[0.0017584559,0.00009404742,0.00002534918,0.00026782378,0.000118086886,0.0023115715,0.0021986165,0.00007824468,0.0004176799],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014160986,0.00013029581,0.0005217004,0.000012562163,0.000012530635,0.0000104067485,0.000080427664,4.638468e-7,0.000091577785,0.015689623,0.8023581,0.18107818],"study_design_scores_gemma":[0.00017521351,0.000023170918,0.00041118494,0.00001660637,0.000011786124,0.0000043378113,0.00042672365,0.0010603921,0.0011789819,0.0019750288,0.99458057,0.00013600338],"about_ca_topic_score_codex":0.000037209193,"about_ca_topic_score_gemma":0.00018238685,"teacher_disagreement_score":0.6623317,"about_ca_system_score_codex":0.000010940354,"about_ca_system_score_gemma":0.000024045597,"threshold_uncertainty_score":0.9695972},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.036339330316432605,"score_gpt":0.2968752340972579,"score_spread":0.2605359037808253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118326624","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28807214,0.003380074,0.67052746,0.0002411675,0.001276523,0.0007062066,0.033975277,0.0006140039,0.0012071383],"genre_scores_gemma":[0.93374604,0.00005573272,0.025490338,0.00068560016,0.0004088209,0.000033792567,0.039551653,0.00002040818,0.000007631003],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99690664,0.00024920935,0.00036708757,0.0010317444,0.000942048,0.0005032686],"domain_scores_gemma":[0.99576503,0.00028515817,0.000146734,0.0035628818,0.00013620885,0.000103960716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014005326,0.00025620265,0.0002166503,0.0002458821,0.0002989895,0.00027048914,0.0019019037,0.000064829335,0.00042084337],"category_scores_gemma":[0.0002833086,0.00023819479,0.00007619454,0.00093597086,0.00006596804,0.0016135076,0.0017662675,0.0001776709,0.00010646036],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005595697,0.002129859,0.0106027005,0.00009589524,0.00006763306,0.0001101634,0.00013254289,0.00091151975,0.0011887609,0.39507073,0.583452,0.0061822324],"study_design_scores_gemma":[0.0013017108,0.000046761674,0.02591831,0.000084650936,0.00008959457,0.000022468093,0.000045811586,0.62031704,0.0009976777,0.0020714304,0.34848326,0.0006212654],"about_ca_topic_score_codex":0.00079356617,"about_ca_topic_score_gemma":0.0007172869,"teacher_disagreement_score":0.6456739,"about_ca_system_score_codex":0.000039897557,"about_ca_system_score_gemma":0.00018611962,"threshold_uncertainty_score":0.97133017},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.1406926542850825,"score_gpt":0.32553850099715964,"score_spread":0.18484584671207713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144006311","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016118996,0.0027525113,0.954648,0.00037714234,0.0004886719,0.00035934863,0.040716518,0.0003299447,0.00016666512],"genre_scores_gemma":[0.085240684,0.00007817583,0.8907365,0.001138366,0.0012896166,0.00017583385,0.020685945,0.000056301324,0.0005985371],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976406,0.00008849091,0.00041714308,0.0010504719,0.00031527432,0.00048801833],"domain_scores_gemma":[0.9931808,0.00034560316,0.00017656123,0.006104672,0.000075116564,0.00011725228],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011640632,0.00023813601,0.00043394935,0.00010066407,0.0002978565,0.00016664957,0.0033040622,0.000052570023,0.000026070804],"category_scores_gemma":[0.00032090486,0.0001899239,0.00007452263,0.00026729822,0.00002978397,0.0064952523,0.003888593,0.00009641505,0.00009422521],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000611797,0.00036216236,0.0002221844,0.0008321407,0.0012450867,0.00011110189,0.00019514676,0.00023568921,0.000517257,0.53986835,0.42356065,0.032789066],"study_design_scores_gemma":[0.0003429971,0.000020706031,0.000010860515,0.000059787315,0.00013144266,0.00003654487,0.000079995334,0.094183646,0.00065540534,0.000018296136,0.9042274,0.00023292773],"about_ca_topic_score_codex":0.00008680221,"about_ca_topic_score_gemma":0.00030107342,"teacher_disagreement_score":0.53985006,"about_ca_system_score_codex":0.00003963274,"about_ca_system_score_gemma":0.00011403568,"threshold_uncertainty_score":0.7744872},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06735454525073631,"score_gpt":0.29709100551204315,"score_spread":0.22973646026130684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169424245","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015224387,0.0010857407,0.979726,0.00007329804,0.00047688922,0.00011678068,0.0027407159,0.00020855872,0.00034762887],"genre_scores_gemma":[0.4697219,0.00014285003,0.51881677,0.0014140379,0.0016896639,0.000039897215,0.007317288,0.000097539356,0.0007600453],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983633,0.0000690885,0.00032681713,0.00059816806,0.0002393507,0.00040326564],"domain_scores_gemma":[0.99759835,0.00007410689,0.00012279519,0.0021110328,0.00003598051,0.00005773484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028897988,0.00019921857,0.00024046117,0.000084954154,0.00024257325,0.00013720614,0.00092748186,0.00003623087,0.000036187495],"category_scores_gemma":[0.000047601978,0.00017683602,0.000040378553,0.0002638045,0.000043342894,0.003634158,0.0013438785,0.0000844663,0.00004666755],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000068078196,0.0014688023,0.097386986,0.0012132778,0.00020845661,0.0021956493,0.0008953176,0.0015792368,0.042573288,0.2594697,0.32668793,0.26625326],"study_design_scores_gemma":[0.00023459875,0.000018952946,0.0014688297,0.00010432103,0.000008710826,0.000046819194,0.00005160299,0.035801187,0.0023806072,0.000090104375,0.95946723,0.00032705558],"about_ca_topic_score_codex":0.0011813685,"about_ca_topic_score_gemma":0.0019545208,"teacher_disagreement_score":0.6327793,"about_ca_system_score_codex":0.000027040232,"about_ca_system_score_gemma":0.000056243436,"threshold_uncertainty_score":0.72111636},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Workload; Scalability; Resource allocation; Distributed computing; Performance tuning; Performance metric; Real-time computing; Database; Operating system","score_opus":0.09405781546455771,"score_gpt":0.29614691187237346,"score_spread":0.20208909640781575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2398890672","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004710716,0.00075231923,0.98837173,0.0020586946,0.0004870346,0.00040883807,0.0008463324,0.00036663486,0.0019976792],"genre_scores_gemma":[0.67037517,0.000026637668,0.31448805,0.005505641,0.0015149992,0.0001116197,0.0054673455,0.000067992085,0.0024425618],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998181,0.000103112674,0.00022192494,0.00071713276,0.0003900501,0.00038679413],"domain_scores_gemma":[0.9970974,0.00017423605,0.00010051452,0.0023544836,0.00010127303,0.00017212504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013313644,0.00016595167,0.0001634105,0.0001093706,0.00017337242,0.00019345363,0.002352533,0.000040552517,0.000005029818],"category_scores_gemma":[0.0003872971,0.00014832012,0.00004198938,0.00037254012,0.000030344794,0.00021555656,0.002923069,0.00009623655,0.000059297054],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008499965,0.0003670233,0.00009712827,0.000042218377,0.00007138597,0.00003295694,0.00043193647,0.0017888932,0.000023162867,0.029906724,0.88321817,0.0839354],"study_design_scores_gemma":[0.0005318312,0.00008316578,0.000049777187,0.000049195805,0.000017148608,0.0000040342147,0.0001933852,0.4322317,0.00011400337,0.00026014805,0.56629574,0.0001699033],"about_ca_topic_score_codex":0.0000867416,"about_ca_topic_score_gemma":0.00002495592,"teacher_disagreement_score":0.6738837,"about_ca_system_score_codex":0.000053225303,"about_ca_system_score_gemma":0.00012755425,"threshold_uncertainty_score":0.6048319},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; 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","score_opus":0.027956875898266287,"score_gpt":0.25220511764092207,"score_spread":0.22424824174265579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2400133291","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034351354,0.0021866509,0.9875183,0.0017223182,0.0010493282,0.0007568942,0.0026019532,0.000142328,0.00058706297],"genre_scores_gemma":[0.9936885,0.0001848714,0.0010956366,0.0029616177,0.00036436945,0.00015241613,0.0013801806,0.000020403677,0.00015197712],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971336,0.0004977112,0.0004988267,0.0008759934,0.00043303284,0.0005608531],"domain_scores_gemma":[0.9959404,0.0006230848,0.00023303562,0.0030127573,0.000074298914,0.00011644264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024586488,0.00026043085,0.00036608434,0.00008964975,0.0002385793,0.0005458048,0.0030139207,0.00010597264,0.00003525372],"category_scores_gemma":[0.00025367973,0.00019926316,0.00006261361,0.0005065601,0.00010116453,0.0024445353,0.0005519386,0.000291854,0.00014923139],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013352181,0.0015226528,0.003580573,0.0004599122,0.00016151778,0.00018345109,0.0015532465,0.0048868195,0.0022038103,0.09917124,0.48194388,0.40419936],"study_design_scores_gemma":[0.0023307248,0.000054878707,0.0024819055,0.00024607303,0.000022539523,0.00003807161,0.00068608567,0.6262369,0.00012710805,0.0004552014,0.3668339,0.00048662088],"about_ca_topic_score_codex":0.00027445797,"about_ca_topic_score_gemma":0.0005256052,"teacher_disagreement_score":0.9902534,"about_ca_system_score_codex":0.000064857,"about_ca_system_score_gemma":0.00014268386,"threshold_uncertainty_score":0.8125716},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Multi-core processor; Scalability; Computer science; Distributed computing; Computer architecture; Parallel computing; Database","score_opus":0.05550861582558886,"score_gpt":0.28469288155287087,"score_spread":0.229184265727282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2400495833","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04386107,0.000037289163,0.9526885,0.0002143199,0.00057372794,0.0004525894,0.0018502388,0.00022762292,0.00009463171],"genre_scores_gemma":[0.97627,0.0000019308145,0.0223083,0.00030820278,0.00006867896,0.000033410357,0.00094635267,0.000008576999,0.000054554777],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867946,0.00003099004,0.00024815887,0.0005099709,0.00018280838,0.00034860033],"domain_scores_gemma":[0.99786144,0.00046343543,0.00006712827,0.0014291048,0.0000778874,0.00010101706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034276347,0.00014515535,0.00017916512,0.000054244865,0.0003058911,0.00029542632,0.0013041692,0.000052053627,0.000042529322],"category_scores_gemma":[0.000062618616,0.00012227682,0.00006285639,0.00017981853,0.000026523936,0.0010869802,0.00010099348,0.00010160075,0.0001483289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023108072,0.007906181,0.013681349,0.001287933,0.0005724569,0.000045262626,0.0018714869,0.027288886,0.0022011825,0.042727035,0.51460874,0.38757843],"study_design_scores_gemma":[0.0006313561,0.000098261175,0.0019761396,0.000078838595,0.000010146167,0.000008444546,0.000031764856,0.9500132,0.00041571382,0.0005801736,0.045918282,0.0002376801],"about_ca_topic_score_codex":0.00010413722,"about_ca_topic_score_gemma":0.000019696896,"teacher_disagreement_score":0.9324089,"about_ca_system_score_codex":0.000029043817,"about_ca_system_score_gemma":0.000046402438,"threshold_uncertainty_score":0.4986304},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.07489147399189085,"score_gpt":0.3030708951274435,"score_spread":0.22817942113555267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2400761516","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043721404,0.0011673765,0.9461105,0.002994859,0.001456083,0.00046960372,0.0025655972,0.00065739464,0.0008572186],"genre_scores_gemma":[0.7665501,0.000039321236,0.21992116,0.0048257136,0.0007792387,0.000050209957,0.005563473,0.00007388271,0.0021969057],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981399,0.00006815625,0.00021740762,0.00071464933,0.00036079867,0.00049905083],"domain_scores_gemma":[0.99705905,0.00011578452,0.000084803265,0.0024738172,0.000076145356,0.00019038492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012306151,0.00017520088,0.00018087588,0.00011519013,0.00018146854,0.00020959896,0.0027975019,0.00003655222,0.000006393287],"category_scores_gemma":[0.00023736035,0.00015735935,0.000052950607,0.00032574192,0.000024055256,0.0002756603,0.0043865847,0.00009531269,0.000062021776],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001242956,0.0012626942,0.0014226439,0.000685576,0.00033714762,0.00045022523,0.001162114,0.002497134,0.00020061054,0.035502866,0.6938351,0.26251963],"study_design_scores_gemma":[0.0006479413,0.000057615453,0.00010589572,0.00004398663,0.000018419249,0.000008482337,0.0001036605,0.6521362,0.000041310384,0.00027608656,0.34636354,0.00019685768],"about_ca_topic_score_codex":0.00031194577,"about_ca_topic_score_gemma":0.00014701165,"teacher_disagreement_score":0.7261893,"about_ca_system_score_codex":0.00006148537,"about_ca_system_score_gemma":0.00012637113,"threshold_uncertainty_score":0.6416928},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Scalability; Suite; Visualization; Graph; Software; Data science; Call graph; Theoretical computer science; Data visualization; World Wide Web; Data mining; Programming language; Database","score_opus":0.07621659304314052,"score_gpt":0.3534706649777041,"score_spread":0.27725407193456353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2784053634","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2537188,0.048319705,0.67204505,0.0054887873,0.0013630303,0.0007840008,0.013436444,0.00041230163,0.0044318503],"genre_scores_gemma":[0.99487394,0.0035939212,0.0013294574,0.00006610494,0.000012926151,7.379763e-7,0.000102024074,0.0000053030108,0.000015601969],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990513,0.00005607149,0.00021307534,0.00027255152,0.00022292031,0.00018408409],"domain_scores_gemma":[0.9975839,0.000117934695,0.00031152315,0.0018458297,0.00009834743,0.000042425287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010264072,0.00008507412,0.00015458986,0.00006346419,0.0005536725,0.00026103063,0.0019219457,0.000028210092,0.000002364511],"category_scores_gemma":[0.0004061649,0.000061199324,0.00002436123,0.00010918739,0.00014519772,0.0014641768,0.0016810506,0.000051778767,7.2926764e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018878449,0.00050898606,0.022020098,0.00062996754,0.00008771861,0.000013284654,0.0007096767,0.0000013817317,0.00040709187,0.88142884,0.008356789,0.08581729],"study_design_scores_gemma":[0.0047268854,0.00043259567,0.21684611,0.0023029295,0.00031199338,0.000046650428,0.0035909954,0.3251469,0.023823658,0.051754765,0.3691863,0.0018301924],"about_ca_topic_score_codex":0.000032364846,"about_ca_topic_score_gemma":0.00023764804,"teacher_disagreement_score":0.82967407,"about_ca_system_score_codex":0.00000203011,"about_ca_system_score_gemma":0.00005023013,"threshold_uncertainty_score":0.42584568},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; 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","score_opus":0.024349013921160394,"score_gpt":0.2591629562395728,"score_spread":0.2348139423184124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791526170","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.124526545,0.00032417057,0.85227096,0.0007926432,0.0026216088,0.00081654656,0.017258823,0.00037247673,0.0010162118],"genre_scores_gemma":[0.9879359,0.000020032538,0.008479698,0.0008682191,0.0007962204,0.00007301836,0.0011674601,0.000022428496,0.0006370048],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979687,0.000037294383,0.0003432321,0.0007421113,0.00034854806,0.00056014274],"domain_scores_gemma":[0.99586236,0.000139189,0.00014478806,0.0035615044,0.00017052585,0.000121650024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005993028,0.00022845512,0.0003046284,0.00008971951,0.0003263243,0.00022340087,0.003571236,0.00009652421,0.000078312],"category_scores_gemma":[0.00013534001,0.00020381068,0.000049388404,0.00044256385,0.00007553284,0.0022110443,0.0013712551,0.00011259369,0.00021832745],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009532101,0.00024390117,0.004907455,0.00018061041,0.0000575126,0.000020218293,0.00015716293,0.000015808706,0.00020700574,0.0020835819,0.97506046,0.016970964],"study_design_scores_gemma":[0.002511477,0.0002331773,0.01231917,0.00016522262,0.00001825344,0.000013773644,0.000024274434,0.45546916,0.001265264,0.00020729404,0.5273058,0.00046713435],"about_ca_topic_score_codex":0.00017711424,"about_ca_topic_score_gemma":0.00022524425,"teacher_disagreement_score":0.86340934,"about_ca_system_score_codex":0.00002979019,"about_ca_system_score_gemma":0.00013458892,"threshold_uncertainty_score":0.83111584},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Online 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","score_opus":0.04435581347020066,"score_gpt":0.26769465447678786,"score_spread":0.2233388410065872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889053599","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06484899,0.00017537217,0.93184423,0.00011522015,0.0006737309,0.00016646189,0.001794881,0.00011586709,0.00026527356],"genre_scores_gemma":[0.31679884,0.000747927,0.677894,0.00037092413,0.00023785277,0.000012034481,0.0038317428,0.000025571935,0.00008111493],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900067,0.000041236563,0.00019257513,0.00041244808,0.00018311871,0.00016994892],"domain_scores_gemma":[0.9981805,0.000018688363,0.00010728309,0.0016098155,0.000056862755,0.000026862865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027979474,0.00009798915,0.00012182135,0.00006537694,0.00010675533,0.00017857227,0.0010380889,0.000026469723,0.000027217116],"category_scores_gemma":[0.00004554371,0.00008822668,0.000010323864,0.00023152819,0.00010704229,0.0017050186,0.0022082117,0.000022898186,0.000012401455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021737718,0.0011004895,0.000525477,0.00083834096,0.00021234875,0.000040771516,0.0028700742,0.0005514217,0.004961374,0.8115037,0.10888291,0.06829573],"study_design_scores_gemma":[0.00044814637,0.00007473589,0.00006025383,0.000054470216,0.000021416376,0.0000071594354,0.0000712256,0.96395457,0.0036982642,0.0037557133,0.027693294,0.00016078107],"about_ca_topic_score_codex":0.000017085054,"about_ca_topic_score_gemma":0.0000036321285,"teacher_disagreement_score":0.9634031,"about_ca_system_score_codex":0.0000069256253,"about_ca_system_score_gemma":0.000015420132,"threshold_uncertainty_score":0.359778},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Join (topology); Parallel computing; Computer architecture","score_opus":0.08098202661924112,"score_gpt":0.3075131336643204,"score_spread":0.2265311070450793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204354173","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15996343,0.0009747074,0.8276687,0.0018349919,0.0012077397,0.0015285838,0.0047095367,0.001511191,0.00060110743],"genre_scores_gemma":[0.986749,0.000006890447,0.008129829,0.0016957948,0.00055067556,0.000021225957,0.0027515693,0.000024138953,0.00007086087],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977088,0.00012255544,0.00026605686,0.0010193817,0.00048585836,0.0003973403],"domain_scores_gemma":[0.99814177,0.000028192751,0.00009303888,0.0015196088,0.000025570858,0.0001918144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004210277,0.00022103664,0.00021380009,0.00008517055,0.0002815753,0.00085243135,0.0031998993,0.000028958306,0.00014762295],"category_scores_gemma":[0.00006305146,0.00020843893,0.000028634708,0.00039405975,0.000026765318,0.005453504,0.0036838602,0.00013059175,0.00010541449],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003844718,0.023596423,0.01052692,0.0007274693,0.00043434548,0.006630842,0.0206987,0.00012902704,0.011021846,0.0029079563,0.49288625,0.43005574],"study_design_scores_gemma":[0.0029775782,0.0012524615,0.00077176245,0.00006591137,0.000061021365,0.000012315651,0.011482479,0.8866907,0.0068654157,0.000037122776,0.08867477,0.0011085027],"about_ca_topic_score_codex":0.00010561502,"about_ca_topic_score_gemma":0.000054338998,"teacher_disagreement_score":0.88656163,"about_ca_system_score_codex":0.000021385618,"about_ca_system_score_gemma":0.00008053022,"threshold_uncertainty_score":0.8499893},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Knowledge extraction; Computer science; Data science; Knowledge management; Data mining","score_opus":0.22418996122957144,"score_gpt":0.32163684355728805,"score_spread":0.09744688232771662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204354299","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041587126,0.7618311,0.11697024,0.016587418,0.0025752413,0.0005377049,0.048296858,0.0024909119,0.00912336],"genre_scores_gemma":[0.5386922,0.40719905,0.023607532,0.001981314,0.00024231801,0.000044210694,0.026336864,0.000070207425,0.0018263028],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978898,0.000059476162,0.000260667,0.0011268014,0.00021496744,0.0004482617],"domain_scores_gemma":[0.9939222,0.0004460079,0.00008491211,0.0054111993,0.000052723222,0.000082979095],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00048248688,0.00023406699,0.0003199592,0.000116531875,0.0001680249,0.00039670325,0.00411381,0.00012419121,0.000015935113],"category_scores_gemma":[0.0005744661,0.00020202842,0.000027716434,0.00019671042,0.00015986666,0.0049858666,0.011246196,0.00016513781,0.000014434239],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021760117,0.00083366805,0.00049018743,0.00030450168,0.00023377282,0.0010288295,0.0005514847,1.381859e-7,0.00022536887,0.17004532,0.58840245,0.23786253],"study_design_scores_gemma":[0.0006310628,0.00007702503,0.0006378284,0.00013471195,0.00003904611,0.00014470557,0.005316155,0.006736267,0.0009613959,0.0021230183,0.982687,0.00051177887],"about_ca_topic_score_codex":0.000016952376,"about_ca_topic_score_gemma":0.0005261635,"teacher_disagreement_score":0.49710506,"about_ca_system_score_codex":0.000012395937,"about_ca_system_score_gemma":0.00022601319,"threshold_uncertainty_score":0.99675065},"labels":[],"label_agreement":null}]}