{"meta":{"query_hash":"ee4a48787628","filters":{"venue":"ACM Transactions on Database Systems"},"cohort_total":43,"direct_labels_cover":0,"predictions_cover":43,"exported":43,"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/ee4a48787628","api":"https://metacan.xera.ac/api/v1/cohort?venue=ACM+Transactions+on+Database+Systems"},"results":[{"id":"W1967155922","doi":"10.1145/1670243.1670250","title":"Automatic virtual machine configuration for database workloads","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); University of Waterloo","funders":"","keywords":"Computer science; Online transaction processing; Workload; Database; Software deployment; Virtual machine; Virtualization; Temporal isolation among virtual machines; Distributed computing; Hypervisor; Operating system; Cloud computing; Transaction processing; Database transaction","score_opus":0.03302318292325333,"score_gpt":0.2566651177257133,"score_spread":0.22364193480245997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967155922","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":[0.024441043,0.00016163003,0.97146916,0.0006465008,0.0013528413,0.0008215113,0.00028994985,0.0005787486,0.00023861609],"genre_scores_gemma":[0.9739885,0.000017923381,0.023518765,0.00022011744,0.00015349603,0.00022825137,0.00014456839,0.000025034582,0.0017033434],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99800485,0.0001425056,0.0004585648,0.0005954639,0.00044414468,0.0003544666],"domain_scores_gemma":[0.99711716,0.00042582938,0.00014054154,0.002098234,0.000070457136,0.00014779947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004996076,0.0002444762,0.00026234426,0.00025044224,0.0007159286,0.0001251014,0.0011491547,0.00005769289,0.000027916953],"category_scores_gemma":[0.000061705956,0.00021987871,0.000120576704,0.00045361868,0.000054165663,0.00010073048,0.000048890863,0.0001977414,0.00014573602],"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":[0.0002091562,0.002950878,0.00008596054,0.0012824369,0.00090752513,0.00037875236,0.0038650571,0.32304564,0.0052441065,0.040915087,0.034771763,0.58634365],"study_design_scores_gemma":[0.0009951721,0.00021506823,0.00003684181,0.00022254574,0.00003401243,0.00011708588,0.000117312455,0.9816348,0.0007927602,0.000022200658,0.015495075,0.00031714662],"about_ca_topic_score_codex":0.00021798306,"about_ca_topic_score_gemma":0.000016028602,"teacher_disagreement_score":0.94954747,"about_ca_system_score_codex":0.00007644699,"about_ca_system_score_gemma":0.000064389955,"threshold_uncertainty_score":0.89663935},"labels":[],"label_agreement":null},{"id":"W1971512992","doi":"10.1145/1005566.1005570","title":"A compressed accessibility map for XML","year":2004,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Access Control and Trust","field":"Social Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Efficient XML Interchange; XML validation; XML Schema (W3C); XML database; XML; Streaming XML; XML framework; XML Encryption; Simple API for XML; Database; Document Structure Description; XML Schema Editor; XML Signature; Information retrieval; Data mining; World Wide Web","score_opus":0.05599528690366123,"score_gpt":0.3495931178292262,"score_spread":0.29359783092556496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971512992","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":[0.009226237,0.00033280512,0.97660035,0.0036907452,0.0024935293,0.0021413034,0.002136396,0.00036374308,0.0030148956],"genre_scores_gemma":[0.99683064,0.000027512251,0.0015508245,0.00012489808,0.0002742641,0.00043693956,0.00007490009,0.000016143647,0.0006639049],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984678,0.00013647671,0.00029570257,0.00038098372,0.00035923146,0.00035979802],"domain_scores_gemma":[0.9984637,0.00034663582,0.000095080235,0.0008033956,0.00011923869,0.00017195987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006328559,0.00014404733,0.00023186542,0.00008795118,0.0010292175,0.00018479557,0.0006838304,0.00009784161,0.000119323275],"category_scores_gemma":[0.00013015886,0.00013104847,0.00012480185,0.00022849678,0.0001517162,0.0005905725,0.00000770482,0.0001524934,0.000102606704],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004975177,0.013919374,0.0040264074,0.0052386653,0.0026720774,0.000176199,0.035577882,0.07392809,0.009219999,0.6264123,0.01550098,0.2083529],"study_design_scores_gemma":[0.016786646,0.00048922276,0.0018441353,0.0009839437,0.0005595184,0.000010326189,0.01777449,0.002575349,0.0036657196,0.0152446795,0.93806195,0.0020040115],"about_ca_topic_score_codex":0.0107234195,"about_ca_topic_score_gemma":0.003779888,"teacher_disagreement_score":0.9876044,"about_ca_system_score_codex":0.00015365338,"about_ca_system_score_gemma":0.0002189167,"threshold_uncertainty_score":0.9958643},"labels":[],"label_agreement":null},{"id":"W1971604907","doi":"10.1145/1189769.1189770","title":"Expressive power of an algebra for data mining","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Tuple; Relational algebra; Data mining; Data model (GIS); Relational database; Information retrieval; Theoretical computer science; Algebra over a field; Artificial intelligence; Mathematics; Discrete mathematics","score_opus":0.04314760138777388,"score_gpt":0.2949769826758806,"score_spread":0.25182938128810667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971604907","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":[0.004055239,0.000082500774,0.98626477,0.00014909256,0.0003580807,0.00040366474,0.008426124,0.00012208078,0.00013843954],"genre_scores_gemma":[0.33107996,0.000005790021,0.6659688,0.000036372017,0.00009165509,0.0002497769,0.0023307153,0.00002191763,0.00021501088],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851424,0.00004759452,0.0003683181,0.00061611267,0.00023632051,0.00021742148],"domain_scores_gemma":[0.9948097,0.000276077,0.00015554162,0.0045970688,0.00008547681,0.00007614528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035919674,0.00014044449,0.00018945993,0.00012616652,0.00020467355,0.00012672748,0.0026053933,0.00004701279,0.0000091201955],"category_scores_gemma":[0.000031862884,0.00013413896,0.00004006085,0.00029540487,0.000041501044,0.0012561426,0.00006890023,0.000077576486,0.000012674595],"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":[0.0001548535,0.0064767944,0.00008766302,0.00084008777,0.00054158,0.00005567795,0.0027321,0.009246011,0.047039393,0.11308687,0.10017843,0.71956056],"study_design_scores_gemma":[0.001605773,0.00041153101,0.00014565632,0.0003625962,0.000093164985,0.00008052662,0.0011100565,0.88527346,0.016097445,0.00050724414,0.09357873,0.0007337999],"about_ca_topic_score_codex":0.00065141247,"about_ca_topic_score_gemma":0.000041105817,"teacher_disagreement_score":0.87602746,"about_ca_system_score_codex":0.000015901518,"about_ca_system_score_gemma":0.00006219418,"threshold_uncertainty_score":0.5470028},"labels":[],"label_agreement":null},{"id":"W1973115038","doi":"10.1145/937598.937601","title":"Are quorums an alternative for data replication?","year":2003,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":144,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Replication (statistics); Scalability; Overhead (engineering); Replicate; Distributed computing; Consistency (knowledge bases); Eventual consistency; Selection (genetic algorithm); Data access; Data consistency; Consistency model; Database; Programming language; Artificial intelligence","score_opus":0.1108332601636947,"score_gpt":0.3436451194508417,"score_spread":0.23281185928714698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973115038","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":[0.00047662805,0.00018661296,0.9896952,0.00036267107,0.0014736042,0.000891305,0.006437166,0.00021524214,0.00026159696],"genre_scores_gemma":[0.9465595,0.000032814187,0.050208434,0.00027361495,0.00015676889,0.00070038013,0.0012045901,0.00003777323,0.0008261548],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99746805,0.00021141283,0.00044370687,0.0012078546,0.00034006077,0.0003289267],"domain_scores_gemma":[0.98983574,0.00020056467,0.000308832,0.0092917355,0.00018182457,0.00018131883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010192634,0.0002115714,0.00027013183,0.000109611574,0.0003662662,0.0002860872,0.0029407775,0.00006847743,0.0000086001255],"category_scores_gemma":[0.0002264319,0.00019783867,0.00005821977,0.00040042688,0.0000319423,0.0015708968,0.00003012916,0.00015208937,0.00006759712],"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":[0.00023583941,0.0058505023,0.0009087333,0.0014754372,0.0011978914,0.00015396437,0.0018328663,0.03085976,0.0047455574,0.708931,0.09163543,0.15217301],"study_design_scores_gemma":[0.0015546263,0.0001926529,0.00012842102,0.00032055992,0.00004436214,0.00014060538,0.0006725869,0.32645002,0.0023421422,0.00063141726,0.6668081,0.0007144853],"about_ca_topic_score_codex":0.00030002606,"about_ca_topic_score_gemma":0.000102716214,"teacher_disagreement_score":0.94608283,"about_ca_system_score_codex":0.0000621909,"about_ca_system_score_gemma":0.00007522446,"threshold_uncertainty_score":0.8067627},"labels":[],"label_agreement":null},{"id":"W1983304353","doi":"10.1145/974750.974757","title":"A normal form for XML documents","year":2004,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":285,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Functional dependency; XML validation; Document Structure Description; XML; Information retrieval; XML database; XML Schema Editor; Relational database; Theoretical computer science; Programming language; World Wide Web","score_opus":0.02221699491570806,"score_gpt":0.2760328890509727,"score_spread":0.2538158941352646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983304353","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":[0.00067595695,0.00014662617,0.993596,0.00037395387,0.0018198737,0.0009840283,0.0017117347,0.0003106361,0.00038114545],"genre_scores_gemma":[0.5487428,0.00009324779,0.44684348,0.0003675771,0.00031548017,0.0016401536,0.00044138328,0.00006469709,0.0014912025],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980268,0.000037934748,0.00046454443,0.0005977801,0.00038391346,0.0004890615],"domain_scores_gemma":[0.9973009,0.0001398641,0.00013826422,0.0021309354,0.000100687794,0.00018934884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034249076,0.00026639854,0.00028724378,0.0001938456,0.00047900356,0.00012413654,0.0008698718,0.00006958968,0.000007994171],"category_scores_gemma":[0.0000434353,0.00023814703,0.00013755183,0.00036741025,0.000043556818,0.0021905268,0.000040784606,0.0001654078,0.00018855139],"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":[0.00029625645,0.0012253121,0.000030853807,0.0013175139,0.00044275864,0.00012793684,0.00204528,0.03442099,0.008022746,0.89798254,0.0028756405,0.051212147],"study_design_scores_gemma":[0.006950865,0.001130311,0.000031295007,0.0010167172,0.000077598284,0.00045684894,0.00079025334,0.0064333463,0.021517951,0.0028076451,0.9573278,0.001459415],"about_ca_topic_score_codex":0.0006409155,"about_ca_topic_score_gemma":0.00015468402,"teacher_disagreement_score":0.9544521,"about_ca_system_score_codex":0.00017165995,"about_ca_system_score_gemma":0.00012657206,"threshold_uncertainty_score":0.9711354},"labels":[],"label_agreement":null},{"id":"W1984237017","doi":"10.1145/1735886.1735887","title":"Transparent anonymization","year":2010,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Nanyang Technological University; Glaucoma Research Foundation","keywords":"Computer science; Data publishing; Adversary; Exploit; Guard (computer science); Generalization; Data anonymization; Privacy protection; Computer security; Adversary model; Information privacy; Data mining; Publishing","score_opus":0.04600808504767626,"score_gpt":0.28701188294021884,"score_spread":0.2410037978925426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984237017","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":[0.0019837175,0.00004971215,0.9857735,0.0066375863,0.0029458997,0.0003601294,0.0005101888,0.0013719072,0.0003673399],"genre_scores_gemma":[0.7360292,0.00006628558,0.2633832,0.00008669206,0.00006232577,0.00013622432,0.00012435515,0.000022029164,0.00008970593],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981528,0.000079299716,0.00034824852,0.00064937794,0.00043032956,0.00033993498],"domain_scores_gemma":[0.98288345,0.00020499158,0.00009243881,0.01664094,0.000067331595,0.00011085122],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0004301431,0.00020781049,0.00019327246,0.00027972995,0.0002613746,0.00021211112,0.020498741,0.00015049858,0.00006448062],"category_scores_gemma":[0.0018315539,0.00019720732,0.00006403113,0.0006727477,0.00007735948,0.0010761643,0.0012565233,0.0005939155,0.0002122406],"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":[0.000111786,0.002721023,0.00073238014,0.0007580377,0.00048550506,0.0002529097,0.0005748806,0.0066074557,0.17164637,0.05826668,0.250581,0.507262],"study_design_scores_gemma":[0.0021849517,0.00033699532,0.00055006583,0.0003834698,0.000088433386,0.0003720433,0.00018016464,0.73702085,0.09398346,0.0196188,0.14352022,0.0017605291],"about_ca_topic_score_codex":0.00018752198,"about_ca_topic_score_gemma":0.00012068327,"teacher_disagreement_score":0.73404545,"about_ca_system_score_codex":0.00004373892,"about_ca_system_score_gemma":0.0000657661,"threshold_uncertainty_score":0.9848008},"labels":[],"label_agreement":null},{"id":"W1993831977","doi":"10.1145/1242524.1242529","title":"Estimating the selectivity of approximate string queries","year":2007,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":41,"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":"Substring; String (physics); Estimator; Approximate string matching; Computer science; Inverse; String searching algorithm; String metric; Algorithm; String kernel; Data structure; Mathematics; Statistics; Pattern matching; Artificial intelligence","score_opus":0.025787043361268296,"score_gpt":0.2745853299599472,"score_spread":0.24879828659867892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993831977","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":[0.00885549,0.00009512026,0.9896277,0.000068143076,0.00074493844,0.00023717017,0.0001272055,0.0001291744,0.00011506328],"genre_scores_gemma":[0.8386069,0.000005119525,0.16124564,0.0000145030235,0.00005704597,0.000018311865,0.0000121938965,0.0000079230995,0.00003234365],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987236,0.0000849596,0.00031563142,0.00030008826,0.00033620765,0.00023946105],"domain_scores_gemma":[0.99776936,0.00042186852,0.00014559332,0.0015387947,0.00006458361,0.00005981061],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011084728,0.00012711054,0.00016199276,0.00010105733,0.00037248788,0.000093272436,0.000979523,0.000037439535,0.0000043208006],"category_scores_gemma":[0.000056157387,0.000087908054,0.000047921178,0.00045050195,0.00005093674,0.0006701408,0.00005683245,0.00020773684,0.0000070320825],"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":[0.00016116122,0.001163655,0.00067495304,0.0011055368,0.00031226958,0.00007373625,0.0036174944,0.11682294,0.033196736,0.05399875,0.0009992147,0.78787357],"study_design_scores_gemma":[0.0004520912,0.00012411799,0.0005994808,0.00043990664,0.000026277788,0.00010765125,0.00039189146,0.95498556,0.03957935,0.0003621578,0.0026030594,0.0003284636],"about_ca_topic_score_codex":0.0006743145,"about_ca_topic_score_gemma":0.00004156485,"teacher_disagreement_score":0.8381626,"about_ca_system_score_codex":0.00003277867,"about_ca_system_score_gemma":0.000041864834,"threshold_uncertainty_score":0.35847867},"labels":[],"label_agreement":null},{"id":"W1997533292","doi":"10.1145/503099.503102","title":"SchemaSQL","year":2001,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":94,"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; SQL; Data definition language; Relational database; Schema (genetic algorithms); Database schema; Programming language; Database; Conceptual schema; Semi-structured model; Database model; Information retrieval; Database design","score_opus":0.03070971332297829,"score_gpt":0.26929298189477086,"score_spread":0.23858326857179257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997533292","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":[0.0008409894,0.00036155863,0.9938166,0.0004602707,0.0015398451,0.00034414808,0.00031909184,0.000519447,0.0017980083],"genre_scores_gemma":[0.6717315,0.00062025484,0.31795505,0.00056607154,0.00048347446,0.0005370624,0.00022573676,0.00008302446,0.0077978545],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99801666,0.00010682618,0.00040367333,0.00062542903,0.00043353593,0.00041387018],"domain_scores_gemma":[0.9962888,0.00016940026,0.0001083085,0.003151397,0.000081241684,0.00020088269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003310457,0.00025018677,0.00027090282,0.00021356138,0.0003621707,0.0001043427,0.0009507589,0.00006789153,0.00006069724],"category_scores_gemma":[0.000051625786,0.00022283295,0.00009445187,0.00068100187,0.000051650804,0.0014634238,0.000044348104,0.00024329033,0.00068992085],"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":[0.00016741449,0.0012931594,0.00032829584,0.0005400669,0.0003855712,0.0011082568,0.0010570952,0.011691247,0.01455998,0.78603876,0.012031141,0.170799],"study_design_scores_gemma":[0.00065918843,0.000113278715,0.00003555637,0.0002532297,0.00001523682,0.0005862983,0.00029565496,0.009710787,0.0030146355,0.0001300703,0.9846652,0.0005208767],"about_ca_topic_score_codex":0.00034551503,"about_ca_topic_score_gemma":0.000050303188,"teacher_disagreement_score":0.972634,"about_ca_system_score_codex":0.00007634498,"about_ca_system_score_gemma":0.000064036525,"threshold_uncertainty_score":0.9086864},"labels":[],"label_agreement":null},{"id":"W1998597078","doi":"10.1145/1670243.1670248","title":"An information-theoretic analysis of worst-case redundancy in database design","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Seventh Framework Programme; Engineering and Physical Sciences Research Council","keywords":"Computer science; Redundancy (engineering); Schema (genetic algorithms); Functional dependency; Database schema; Theoretical computer science; Data integrity; Relational database; Data mining; Database design; Information retrieval; Database","score_opus":0.03518479320693964,"score_gpt":0.27502739543239096,"score_spread":0.23984260222545134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998597078","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":[0.011781416,0.0001537483,0.9843577,0.000040384657,0.0004133509,0.0006364483,0.0023793748,0.00016087454,0.0000766585],"genre_scores_gemma":[0.85504115,0.00015825518,0.14385447,0.000050129318,0.000022942371,0.00017722016,0.0006477304,0.000016298398,0.00003182571],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99685854,0.00050618156,0.0011176692,0.00056443247,0.0005468594,0.00040633685],"domain_scores_gemma":[0.99469906,0.00047078222,0.0003570997,0.004064915,0.00017665603,0.0002314862],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009919658,0.0003148786,0.0006242088,0.0017044155,0.00034619437,0.0000622431,0.0009734325,0.00008703383,0.000044588767],"category_scores_gemma":[0.00013111168,0.0002967949,0.00014625912,0.0035127662,0.00016995013,0.005274704,0.000042299336,0.00027936415,0.000046755165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045296107,0.0021476343,0.00097202155,0.0009529034,0.0014798151,0.0041617127,0.011907882,0.8090082,0.0027750575,0.14929564,0.00069473806,0.016151452],"study_design_scores_gemma":[0.0027713587,0.00068070064,0.00050855073,0.0008077925,0.00063424703,0.003970108,0.003683454,0.97049534,0.006467935,0.00014293884,0.008164986,0.0016725911],"about_ca_topic_score_codex":0.00230234,"about_ca_topic_score_gemma":0.0003577521,"teacher_disagreement_score":0.8432597,"about_ca_system_score_codex":0.00010717641,"about_ca_system_score_gemma":0.0001853559,"threshold_uncertainty_score":0.99994844},"labels":[],"label_agreement":null},{"id":"W2002932370","doi":"10.1145/1061318.1061324","title":"Concise descriptions of subsets of structured sets","year":2005,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Automatic summarization; Theoretical computer science; Set (abstract data type); Minimum description length; Online analytical processing; Hierarchy; Cover (algebra); Context (archaeology); Representation (politics); Data mining; Algorithm; Artificial intelligence; Data warehouse","score_opus":0.0319806076430219,"score_gpt":0.26392649524481654,"score_spread":0.23194588760179463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002932370","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":[0.0072392235,0.00017764317,0.988696,0.0002694101,0.00075598236,0.0003559746,0.002066163,0.00010177541,0.00033782385],"genre_scores_gemma":[0.93713695,0.000054774995,0.06227939,0.00004152769,0.00003382045,0.000026404783,0.00014217719,0.000010027648,0.000274936],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986135,0.00007531949,0.00043749445,0.0003142164,0.00036562956,0.00019384299],"domain_scores_gemma":[0.9977255,0.00008150355,0.00016832791,0.0018568452,0.00008732885,0.00008051918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025893215,0.0001438858,0.00023869913,0.0002566489,0.00009024883,0.000052149666,0.0012502788,0.000041695435,0.000055421144],"category_scores_gemma":[0.000020673519,0.00013407115,0.00008135671,0.00047591567,0.000058678448,0.0010214109,0.000040340565,0.00011151256,0.00004463801],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015203257,0.0026490092,0.00040135498,0.0017044778,0.0011116978,0.00006369471,0.0028446284,0.034048356,0.053113393,0.10429019,0.03320691,0.7664143],"study_design_scores_gemma":[0.009017816,0.00093302835,0.0035825386,0.0017297661,0.00061939564,0.00020203323,0.0019615141,0.5726355,0.17950723,0.0011988304,0.22604635,0.002566045],"about_ca_topic_score_codex":0.00018681026,"about_ca_topic_score_gemma":0.00007351698,"teacher_disagreement_score":0.9298977,"about_ca_system_score_codex":0.000030353907,"about_ca_system_score_gemma":0.000039565217,"threshold_uncertainty_score":0.5467262},"labels":[],"label_agreement":null},{"id":"W2006315879","doi":"10.1145/1093382.1093388","title":"Capturing summarizability with integrity constraints in OLAP","year":2005,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":93,"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":"Online analytical processing; Computer science; Heuristics; Dimension (graph theory); Theoretical computer science; Set (abstract data type); Data integrity; Aggregate (composite); Intrinsic dimension; Class (philosophy); Space (punctuation); Data mining; Curse of dimensionality; Data warehouse; Database; Artificial intelligence; Mathematics; Programming language","score_opus":0.025716485551273413,"score_gpt":0.2608755870518358,"score_spread":0.23515910150056235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006315879","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":[0.011812294,0.00012837029,0.98491424,0.00051871873,0.0004514868,0.0005695849,0.0006889716,0.0002506555,0.000665672],"genre_scores_gemma":[0.8872782,0.00001678746,0.112203375,0.00007676168,0.000071509,0.00013672301,0.000061034527,0.000016818012,0.0001388063],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99765646,0.0002085011,0.0005311031,0.0007557658,0.00040495477,0.0004432112],"domain_scores_gemma":[0.9970111,0.00028652855,0.00012130225,0.0023256124,0.00008139173,0.00017404789],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069151237,0.0002889453,0.00036500418,0.00024048678,0.0001956644,0.00009045378,0.00074570527,0.00008462978,0.00003376377],"category_scores_gemma":[0.00006898868,0.00023578215,0.000060169416,0.0005382316,0.0001786434,0.0017148954,0.000042458832,0.0006039899,0.00008557451],"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":[0.0007115612,0.0043351916,0.009759254,0.0021094952,0.00049006724,0.0008357693,0.007334107,0.07752611,0.0054613193,0.3286915,0.0011062566,0.56163937],"study_design_scores_gemma":[0.019891167,0.0018652991,0.008575709,0.010381871,0.00019819709,0.0036545931,0.013966869,0.21385184,0.045105077,0.0008533834,0.67281234,0.008843631],"about_ca_topic_score_codex":0.0019133574,"about_ca_topic_score_gemma":0.0034662394,"teacher_disagreement_score":0.87546587,"about_ca_system_score_codex":0.000260889,"about_ca_system_score_gemma":0.00016089954,"threshold_uncertainty_score":0.9614917},"labels":[],"label_agreement":null},{"id":"W2010916971","doi":"10.1145/1132863.1132868","title":"Integrating XML data sources using approximate joins","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Joins; XML validation; XML; Efficient XML Interchange; Document Structure Description; XML Schema (W3C); XML database; Information retrieval; Streaming XML; Data mining; Set (abstract data type); Tree (set theory); XML Encryption; Database; Programming language; World Wide Web","score_opus":0.06748389564404962,"score_gpt":0.2828255905583581,"score_spread":0.2153416949143085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010916971","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":[0.0013125552,0.00015538283,0.99469465,0.00017508202,0.0010015122,0.00033521865,0.0013698388,0.00036650922,0.00058926665],"genre_scores_gemma":[0.42338413,0.00004943761,0.5715017,0.00015713707,0.00060290727,0.00006935373,0.0026921383,0.0000648788,0.0014783306],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99787056,0.0001120941,0.00042576808,0.00078604557,0.0004300545,0.0003754994],"domain_scores_gemma":[0.99526185,0.00010962173,0.00015022987,0.0043661483,0.00003814234,0.00007399989],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006450247,0.00023561936,0.00022583989,0.0002625086,0.00044415417,0.0007688176,0.0034121242,0.000044645814,0.000015532833],"category_scores_gemma":[0.000025801766,0.00020906924,0.00005082696,0.00060868874,0.00004508615,0.002746512,0.0002513643,0.00021733633,0.00006603077],"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":[0.00010255687,0.0052051735,0.0013173877,0.0030049514,0.0013968394,0.00091357203,0.0015998346,0.11404436,0.02703342,0.26122507,0.048338108,0.53581876],"study_design_scores_gemma":[0.0003427732,0.000027522106,0.000017546754,0.00020354768,0.000044369754,0.00004203835,0.00030992922,0.97489977,0.0006996151,0.00015273098,0.022913016,0.00034716577],"about_ca_topic_score_codex":0.002600541,"about_ca_topic_score_gemma":0.0001590475,"teacher_disagreement_score":0.8608554,"about_ca_system_score_codex":0.00004848087,"about_ca_system_score_gemma":0.000042604617,"threshold_uncertainty_score":0.8525596},"labels":[],"label_agreement":null},{"id":"W2036787492","doi":"10.1145/2560796","title":"Sharing across Multiple MapReduce Jobs","year":2014,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Cloud computing; Merge (version control); Key (lock); Batch processing; Database; Distributed computing; Context (archaeology); Parallel computing; Operating system","score_opus":0.028705162256593777,"score_gpt":0.26509984859053803,"score_spread":0.23639468633394425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036787492","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":[0.107475765,0.000052309904,0.88900065,0.00043341602,0.0015850607,0.00024675924,0.000042405096,0.00051873224,0.000644923],"genre_scores_gemma":[0.98955756,0.0000025803158,0.008496407,0.00014569971,0.00016727293,0.000050931398,0.000008037788,0.00001922568,0.0015523003],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805176,0.000111770765,0.00031861642,0.00069701625,0.00037341716,0.000447442],"domain_scores_gemma":[0.99668074,0.0002675963,0.0000894425,0.0027730612,0.000041407173,0.00014776643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000758142,0.00020195649,0.00020462401,0.00011107734,0.0005337259,0.00033169193,0.0019984066,0.00005377473,0.0000065727986],"category_scores_gemma":[0.00006396704,0.000184924,0.000099974684,0.00038279625,0.00003338352,0.000059259917,0.0001585537,0.00024398517,0.00028198934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037967016,0.0007830719,0.0010319871,0.0005185667,0.00026316,0.000050685165,0.0031754372,0.6682317,0.0020608674,0.011209021,0.0025623387,0.31007516],"study_design_scores_gemma":[0.00067062984,0.0000751398,0.00040242838,0.0002116357,0.000012664242,0.00003613405,0.00025305717,0.9493737,0.0009071147,0.000067026966,0.047653574,0.00033685687],"about_ca_topic_score_codex":0.00057518407,"about_ca_topic_score_gemma":0.000041051906,"teacher_disagreement_score":0.8820818,"about_ca_system_score_codex":0.000059435126,"about_ca_system_score_gemma":0.000011750584,"threshold_uncertainty_score":0.7540982},"labels":[],"label_agreement":null},{"id":"W2042315498","doi":"10.1145/581751.581752","title":"Searching for dependencies at multiple abstraction levels","year":2002,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":38,"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; Functional dependency; Dependency (UML); Tuple; Online analytical processing; Dependency theory (database theory); Generalization; Abstraction; Scope (computer science); Data mining; Extension (predicate logic); Theoretical computer science; Database; Data warehouse; Relational database; Artificial intelligence; Programming language","score_opus":0.09694704259971397,"score_gpt":0.2879969122087368,"score_spread":0.19104986960902282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042315498","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":[0.0027855374,0.0003029949,0.9915824,0.0002811724,0.0015430155,0.0008352023,0.0019931553,0.000362182,0.0003143602],"genre_scores_gemma":[0.87088895,0.00007693413,0.12498213,0.00007769648,0.00018317417,0.00051669753,0.00011768849,0.00004031917,0.003116393],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977934,0.00010997089,0.00046416852,0.00068119843,0.00047049622,0.00048077514],"domain_scores_gemma":[0.99681956,0.0008098679,0.00016213296,0.0019202088,0.000108561726,0.00017964905],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004537154,0.00026407157,0.00027963685,0.00022059429,0.00089537323,0.00012760276,0.0006824078,0.000081743536,0.000058523914],"category_scores_gemma":[0.00016070374,0.0002453422,0.00013508409,0.00028885956,0.000049861403,0.0017596552,0.0000510284,0.00020379793,0.00025910485],"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":[0.00047344455,0.0026563487,0.00053237827,0.0040880484,0.0010765464,0.00033759794,0.0077641476,0.15010504,0.19769089,0.17091312,0.024888162,0.43947428],"study_design_scores_gemma":[0.00236962,0.00032278823,0.00022152984,0.0005045617,0.00004686559,0.0005155481,0.0008952114,0.32636064,0.031136502,0.00015339346,0.63632256,0.0011507415],"about_ca_topic_score_codex":0.00042985642,"about_ca_topic_score_gemma":0.00060685107,"teacher_disagreement_score":0.86810344,"about_ca_system_score_codex":0.00020995559,"about_ca_system_score_gemma":0.000025980014,"threshold_uncertainty_score":0.9999999},"labels":[],"label_agreement":null},{"id":"W2051445745","doi":"10.1145/507234.507237","title":"A logical foundation for deductive object-oriented databases","year":2002,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Logic, Reasoning, and Knowledge","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Programming language; Deductive database; Syntax; Semantics (computer science); Class (philosophy); Object (grammar); Well-founded semantics; Logic programming; Inheritance (genetic algorithm); Operational semantics; Database; Natural language processing; Artificial intelligence; Denotational semantics","score_opus":0.07233550198391613,"score_gpt":0.2909125887188853,"score_spread":0.21857708673496917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051445745","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":[0.0010627767,0.00029076863,0.99302584,0.00027301948,0.0020890536,0.00086600886,0.0004319747,0.00036825016,0.0015922791],"genre_scores_gemma":[0.9390233,0.000119720135,0.05722579,0.00014022346,0.00033798633,0.0007038194,0.0003458615,0.000029776393,0.0020734929],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979281,0.00016627004,0.00036840024,0.0007753781,0.00033546664,0.0004264227],"domain_scores_gemma":[0.9972386,0.0005636734,0.00013141557,0.0016993016,0.00018988388,0.00017713352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036293437,0.0002606291,0.00028229158,0.00021338335,0.00053098757,0.00016801924,0.000859645,0.0000709223,0.00013587593],"category_scores_gemma":[0.00026996664,0.00022225223,0.00013910104,0.0005790183,0.000076012315,0.0010754286,0.000037170183,0.00020199607,0.00046116553],"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":[0.00034970077,0.006668591,0.0002646906,0.00086586276,0.0008095978,0.00012898556,0.0061402353,0.0028707003,0.005544625,0.69570386,0.037628666,0.24302451],"study_design_scores_gemma":[0.004924118,0.0014026706,0.00022091474,0.00050392863,0.00023410418,0.00047644955,0.0014086447,0.41077933,0.007911345,0.0010789789,0.56923246,0.0018270419],"about_ca_topic_score_codex":0.00015108314,"about_ca_topic_score_gemma":0.000064679625,"teacher_disagreement_score":0.93796057,"about_ca_system_score_codex":0.0001243935,"about_ca_system_score_gemma":0.000046679055,"threshold_uncertainty_score":0.9063183},"labels":[],"label_agreement":null},{"id":"W2053495332","doi":"10.1145/2487259.2487260","title":"Analysis and optimization for boolean expression indexing","year":2013,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Regular expression; Theoretical computer science; Search engine indexing; Boolean expression; Tree (set theory); Matching (statistics); Search tree; Data structure; Tree structure; String searching algorithm; Data mining; Algorithm; Pattern matching; Boolean function; Binary tree; Search algorithm; Artificial intelligence; Mathematics","score_opus":0.020552758876912467,"score_gpt":0.24775622824136947,"score_spread":0.227203469364457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053495332","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":[0.0003914545,0.000041582414,0.9981969,0.00022730627,0.00026217703,0.000530267,0.00015028393,0.00012709828,0.000072907314],"genre_scores_gemma":[0.38741016,0.00008587718,0.61034596,0.00013289087,0.00007654499,0.0005278687,0.0005072822,0.000019338942,0.0008940978],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990009,0.000045182387,0.00020568036,0.00039599263,0.00017922376,0.00017301424],"domain_scores_gemma":[0.9986489,0.00011061675,0.000073706135,0.0010358325,0.000050739596,0.00008023167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022166144,0.000116476396,0.00015047041,0.00037008352,0.00023895894,0.0004355764,0.00054704177,0.00003344342,0.000034759116],"category_scores_gemma":[0.000018121833,0.00010305583,0.000055849938,0.0005670465,0.000015545751,0.0017034339,0.00003776483,0.00006387971,0.000017911809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003034396,0.00050477654,0.0005412012,0.00054273335,0.0012337852,0.000008495736,0.00063190656,0.5774015,0.002565795,0.0054659275,0.0058434093,0.4052301],"study_design_scores_gemma":[0.00029476287,0.000034088855,0.00007666843,0.00004643125,0.000092548355,0.0000013838508,0.00010575532,0.9966292,0.000662424,0.000037874648,0.0018685496,0.00015030759],"about_ca_topic_score_codex":0.00022573664,"about_ca_topic_score_gemma":0.000009032257,"teacher_disagreement_score":0.41922766,"about_ca_system_score_codex":0.000017265134,"about_ca_system_score_gemma":0.000007827476,"threshold_uncertainty_score":0.42024946},"labels":[],"label_agreement":null},{"id":"W2054655669","doi":"10.1145/383891.383892","title":"Querying ATSQL databases with temporal logic","year":2001,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":66,"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; SQL; Temporal logic; Expressive power; Temporal database; Extension (predicate logic); Database; Translation (biology); Programming language; Representation (politics); Theoretical computer science","score_opus":0.05051783123629092,"score_gpt":0.2832165114231688,"score_spread":0.23269868018687787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054655669","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":[0.0015298729,0.00045258933,0.99336153,0.0004382894,0.00093397003,0.00061496696,0.0010749204,0.00067210017,0.00092173915],"genre_scores_gemma":[0.63271093,0.00035034423,0.362985,0.00047102314,0.00030364413,0.000455109,0.0007520039,0.00008498662,0.0018869787],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.996909,0.00020597583,0.00056506175,0.0010162072,0.0006709408,0.0006327672],"domain_scores_gemma":[0.9951604,0.00029455256,0.00022558017,0.003909136,0.00013011484,0.0002802348],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046370117,0.00044241772,0.00045854686,0.00031684586,0.00061127247,0.00015950312,0.0010832931,0.00006306586,0.00005807579],"category_scores_gemma":[0.000054044143,0.00034273596,0.000094414216,0.00097632443,0.00011961156,0.0026799666,0.00007553676,0.0003623097,0.0002616735],"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":[0.0013215748,0.0034304822,0.0068886154,0.0019166598,0.0012139607,0.0070673516,0.0020417355,0.053253096,0.008963967,0.79291844,0.011071814,0.10991228],"study_design_scores_gemma":[0.0025178562,0.0007072717,0.00019051135,0.0016262704,0.00009034803,0.0034178062,0.002001602,0.016396103,0.0027364527,0.00012832256,0.9682288,0.0019586475],"about_ca_topic_score_codex":0.0019248932,"about_ca_topic_score_gemma":0.0006468459,"teacher_disagreement_score":0.957157,"about_ca_system_score_codex":0.00011559072,"about_ca_system_score_gemma":0.00014303131,"threshold_uncertainty_score":0.9999025},"labels":[],"label_agreement":null},{"id":"W2057058417","doi":"10.1145/1132863.1132873","title":"Approximation and streaming algorithms for histogram construction problems","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":127,"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":"Histogram; Computer science; Algorithm; Approximation algorithm; Artificial intelligence; Image (mathematics)","score_opus":0.02572179603381434,"score_gpt":0.24387751952964024,"score_spread":0.2181557234958259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057058417","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":[0.00040142136,0.0001422532,0.9964413,0.00022782749,0.00089992036,0.0009294755,0.00042675782,0.00028056552,0.00025046442],"genre_scores_gemma":[0.13963802,0.0000806913,0.8568093,0.000044233442,0.00028793243,0.00083543133,0.0011547323,0.00003623059,0.0011133852],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986616,0.000043073753,0.00031510144,0.00050168304,0.00023451632,0.0002440513],"domain_scores_gemma":[0.9987986,0.00010185329,0.0001238786,0.00086040853,0.000058727765,0.00005650604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003257952,0.00017198076,0.00016530845,0.0002337342,0.0003266283,0.00035590515,0.00045043003,0.000049421207,0.0000028581578],"category_scores_gemma":[0.000011210091,0.00016762518,0.000047749647,0.00030285385,0.000053497384,0.0012535109,0.000024142077,0.00009314338,0.000010055696],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012913839,0.0003195914,0.00004943895,0.0005670656,0.000074845964,0.000005080026,0.00011455901,0.0026903746,0.00092593,0.065313466,0.0015979789,0.92832875],"study_design_scores_gemma":[0.0021095963,0.00027476126,0.00016153058,0.00028510173,0.00010278438,0.00010480394,0.00037208805,0.8973469,0.0013001052,0.0034491203,0.093767315,0.0007258623],"about_ca_topic_score_codex":0.00053497526,"about_ca_topic_score_gemma":0.000037662005,"teacher_disagreement_score":0.9276029,"about_ca_system_score_codex":0.000055049266,"about_ca_system_score_gemma":0.000018198409,"threshold_uncertainty_score":0.68355566},"labels":[],"label_agreement":null},{"id":"W2057545667","doi":"10.1145/1508857.1508858","title":"The design of a query monitoring system","year":2009,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":169,"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; Query optimization; Online aggregation; Joins; Query expansion; Sargable; Query plan; View; Data mining; Database; Query language; Cardinality (data modeling); Web query classification; Information retrieval; Web search query; Search engine; Database design","score_opus":0.034277973946782773,"score_gpt":0.26691792212526705,"score_spread":0.23263994817848427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057545667","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":[0.00023762105,0.0009048817,0.9957117,0.00016963374,0.0018076301,0.0005636912,0.00015986351,0.00029212242,0.00015286708],"genre_scores_gemma":[0.89589626,0.0001979321,0.10331655,0.000015865968,0.00015765999,0.00013685574,0.000008568523,0.000017669181,0.00025263944],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978104,0.000306349,0.00060007954,0.00042628727,0.0004950376,0.00036184842],"domain_scores_gemma":[0.99604,0.00063913915,0.00023918416,0.0028399755,0.00012545043,0.000116261945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000897679,0.00022921657,0.00030832968,0.00013736081,0.0005864384,0.00010255478,0.0011528513,0.000058679063,8.329911e-7],"category_scores_gemma":[0.000063740394,0.00016013613,0.00009449712,0.000507527,0.000056359084,0.00082320237,0.00002343531,0.00020756545,0.000035025594],"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":[0.00031087612,0.0005485391,0.000073803094,0.0008985326,0.0003593489,0.00019177562,0.0014526799,0.10107427,0.03651766,0.6661947,0.0014231578,0.19095469],"study_design_scores_gemma":[0.007183939,0.004470237,0.0012908102,0.017059451,0.00040899456,0.0026880421,0.02259827,0.3994166,0.26888517,0.0011387292,0.26950455,0.0053552333],"about_ca_topic_score_codex":0.00018195108,"about_ca_topic_score_gemma":0.0000040974764,"teacher_disagreement_score":0.8956586,"about_ca_system_score_codex":0.00011335769,"about_ca_system_score_gemma":0.000091061556,"threshold_uncertainty_score":0.65301615},"labels":[],"label_agreement":null},{"id":"W2080555007","doi":"10.1145/1806907.1806909","title":"Continuous online index tuning in moving object databases","year":2010,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Media Development Authority - Singapore","keywords":"Computer science; Granularity; B-tree; Overhead (engineering); Search engine indexing; Tree (set theory); Grid; Data mining; Workload; Set (abstract data type); Object (grammar); Database; Binary tree; Information retrieval; Algorithm; Artificial intelligence; Mathematics","score_opus":0.028133624355503567,"score_gpt":0.2745241931610565,"score_spread":0.2463905688055529,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080555007","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":[0.019594105,0.00006175797,0.9753745,0.0002885505,0.0023856896,0.0004255073,0.0011648091,0.0003261243,0.00037890938],"genre_scores_gemma":[0.9424059,0.000051332758,0.05584538,0.00017270264,0.0001817105,0.000075714976,0.00062698364,0.00002855332,0.0006117696],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979141,0.00010532319,0.00044424334,0.0006881533,0.00041628085,0.00043192485],"domain_scores_gemma":[0.9966849,0.00026524274,0.000116354095,0.0027601346,0.000044837605,0.00012849823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006626886,0.00024608086,0.00028443828,0.0005483517,0.00019972934,0.00031134373,0.0018878041,0.000054277723,0.00004220869],"category_scores_gemma":[0.00011514653,0.00023855134,0.000060255043,0.0008076304,0.00004824142,0.0020975284,0.00013852917,0.00064709794,0.00008572257],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013111303,0.0048387917,0.010828291,0.000864495,0.00042575103,0.0017121821,0.001355733,0.008771725,0.0320848,0.04095716,0.0060519218,0.891978],"study_design_scores_gemma":[0.0037382885,0.00020945509,0.005206101,0.0010222481,0.000070832575,0.00021710199,0.0017647233,0.8333502,0.002093875,0.00014667907,0.1503901,0.0017903981],"about_ca_topic_score_codex":0.0026110387,"about_ca_topic_score_gemma":0.0022811606,"teacher_disagreement_score":0.92281175,"about_ca_system_score_codex":0.00003500802,"about_ca_system_score_gemma":0.00006131239,"threshold_uncertainty_score":0.9727841},"labels":[],"label_agreement":null},{"id":"W2090154982","doi":"10.1145/357775.357778","title":"Emancipating instances from the tyranny of classes in information modeling","year":2000,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":165,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Schema (genetic algorithms); Interoperability; Relational database; Class (philosophy); Semi-structured model; Theoretical computer science; Information schema; Data mining; Information retrieval; Artificial intelligence; Database model; World Wide Web","score_opus":0.0253603979568016,"score_gpt":0.2532512764296321,"score_spread":0.2278908784728305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090154982","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":[0.052137308,0.0003822394,0.9452373,0.0001507476,0.00037136851,0.00031891945,0.0009451286,0.000078608246,0.0003784151],"genre_scores_gemma":[0.9708082,0.00021212212,0.028597485,0.00008528831,0.000043833898,0.00010346669,0.00011324133,0.000007672573,0.000028656277],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984024,0.00013366234,0.0006614886,0.00024256397,0.00035021172,0.0002096507],"domain_scores_gemma":[0.9980676,0.00030411597,0.00014432204,0.0013765318,0.00006365553,0.000043732653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003939334,0.00015421964,0.00023430327,0.00011200574,0.00019394449,0.00006741563,0.00067572383,0.000046350153,0.000028921011],"category_scores_gemma":[0.000053115542,0.00011398153,0.000051233157,0.00050930784,0.000037852384,0.0030386322,0.000017916218,0.00020036008,0.000043790766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009462928,0.000147798,0.0002718998,0.00022460021,0.000065094355,0.000008372151,0.00595067,0.78144634,0.0004318575,0.018251533,0.00014405086,0.19296312],"study_design_scores_gemma":[0.000909591,0.000072840245,0.00018361885,0.0013355629,0.000016366928,0.000014625696,0.003518402,0.9565792,0.00089211104,0.00025440677,0.035839535,0.00038374966],"about_ca_topic_score_codex":0.0051009567,"about_ca_topic_score_gemma":0.00090760173,"teacher_disagreement_score":0.91867095,"about_ca_system_score_codex":0.000047181627,"about_ca_system_score_gemma":0.00006565318,"threshold_uncertainty_score":0.7711155},"labels":[],"label_agreement":null},{"id":"W2104120015","doi":"10.1145/1538909.1538910","title":"Anonymization-based attacks in privacy-preserving data publishing","year":2009,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Research Grants Council, University Grants Committee","keywords":"Computer science; Adversary; Data publishing; Overhead (engineering); Confidentiality; Computer security; Information loss; k-anonymity; Information sensitivity; Publishing; Information privacy; Internet privacy; Artificial intelligence","score_opus":0.07597995798891426,"score_gpt":0.3100199144698071,"score_spread":0.23403995648089282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104120015","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":[0.00089870073,0.00026232848,0.95396984,0.040324792,0.00085398793,0.0006420161,0.0011926785,0.0013831935,0.00047245758],"genre_scores_gemma":[0.6262185,0.00007419529,0.37150156,0.00066515146,0.00007683741,0.000068305766,0.0013166728,0.00003264089,0.000046116456],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957877,0.0003162991,0.00077789195,0.0015428392,0.00086566585,0.0007096135],"domain_scores_gemma":[0.9515556,0.0007805563,0.0002336292,0.047150657,0.00011994955,0.00015961478],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0018347789,0.00036417233,0.00039094026,0.0009261411,0.00031741682,0.0016035474,0.08681242,0.000246255,0.000038649097],"category_scores_gemma":[0.022976963,0.00037547157,0.000058390116,0.0023976546,0.00006300142,0.009644433,0.010421426,0.00090594665,0.00006136835],"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":[0.0001445512,0.0026592424,0.0029719733,0.00061086845,0.00018039739,0.0005499058,0.00034433018,0.051640924,0.003405142,0.0049160756,0.6869829,0.24559365],"study_design_scores_gemma":[0.0010332994,0.00008540906,0.00052816246,0.00056476815,0.0000148911195,0.000025122386,0.000072413,0.97899896,0.0011142219,0.0043157795,0.0127068525,0.0005400992],"about_ca_topic_score_codex":0.0007617353,"about_ca_topic_score_gemma":0.0001806129,"teacher_disagreement_score":0.92735803,"about_ca_system_score_codex":0.00023810442,"about_ca_system_score_gemma":0.00026608806,"threshold_uncertainty_score":0.9998697},"labels":[],"label_agreement":null},{"id":"W2112527958","doi":"10.1145/1538909.1538913","title":"Snapshot isolation and integrity constraints in replicated databases","year":2009,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Seventh Framework Programme; Federación Española de Enfermedades Raras","keywords":"Computer science; Serializability; Correctness; Replica; Data integrity; Snapshot (computer storage); Database; Isolation (microbiology); Distributed computing; Rollback; Concurrency control; Two-phase locking; Distributed database; Fault tolerance; Database transaction; Distributed transaction; Transaction processing; Programming language","score_opus":0.044649816998303886,"score_gpt":0.2969985777953138,"score_spread":0.2523487607970099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112527958","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":[0.01262687,0.0002612675,0.98370206,0.00081281766,0.00040707417,0.0004929023,0.00093019067,0.00016101683,0.00060581503],"genre_scores_gemma":[0.99159276,0.000061549894,0.007766127,0.00015517182,0.000027692085,0.00004173311,0.00031235427,0.00000614226,0.000036484813],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99812216,0.00016216609,0.0004981329,0.00066489604,0.00026114634,0.00029150915],"domain_scores_gemma":[0.9978519,0.00015605034,0.00011646892,0.0016723892,0.00006724177,0.00013592502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005919423,0.00020580302,0.00028652107,0.00021528467,0.00015033464,0.00016501399,0.00059116987,0.00007451172,0.000020069905],"category_scores_gemma":[0.000079902864,0.00019352575,0.00004022391,0.00062361226,0.00006644613,0.0009343825,0.000016430773,0.00037031044,0.00002410201],"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":[0.00042858903,0.004380023,0.004930387,0.0008123831,0.00026255776,0.00064412644,0.0024998847,0.0057104286,0.049087305,0.27072895,0.0118585825,0.6486568],"study_design_scores_gemma":[0.012954013,0.0016789454,0.056685567,0.0065754796,0.00014019173,0.002595461,0.002579472,0.8087973,0.0119340625,0.0021525945,0.089015886,0.004891015],"about_ca_topic_score_codex":0.0006153391,"about_ca_topic_score_gemma":0.000098575794,"teacher_disagreement_score":0.9789659,"about_ca_system_score_codex":0.00006525768,"about_ca_system_score_gemma":0.000059433605,"threshold_uncertainty_score":0.78917503},"labels":[],"label_agreement":null},{"id":"W2118265701","doi":"10.1145/1189769.1189772","title":"Adaptive rank-aware query optimization in relational databases","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Query optimization; Query plan; Ranking (information retrieval); Rank (graph theory); Cardinality (data modeling); Key (lock); Query language; Relational database; Join (topology); Operator (biology); Sargable; Theoretical computer science; Database; Data mining; Information retrieval; Web search query; Search engine","score_opus":0.038032297023068214,"score_gpt":0.24930291190045173,"score_spread":0.21127061487738352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118265701","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":[0.00010442628,0.00011437908,0.99602854,0.0003234512,0.00073115434,0.00043201793,0.0012357614,0.00021021794,0.0008200286],"genre_scores_gemma":[0.520306,0.00015710159,0.46957666,0.0002039517,0.00034746574,0.00037051967,0.0062790653,0.000054945824,0.0027042818],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811184,0.00014849528,0.00042827308,0.0005855631,0.00044676187,0.00027907116],"domain_scores_gemma":[0.99811226,0.00021498789,0.0001114411,0.0014460988,0.000057598158,0.000057588484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040055026,0.00020059015,0.00018994838,0.00045329373,0.00019306924,0.00014886916,0.00080485485,0.0000437803,0.000051681192],"category_scores_gemma":[0.00002117737,0.00020170935,0.0000532522,0.00082270475,0.00003540338,0.0025984556,0.00005280482,0.00019844262,0.000110399975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003330093,0.00043855843,0.00018533446,0.00005436694,0.000036951184,0.00007391315,0.00004323764,0.9410409,0.000025304538,0.04748416,0.004152541,0.0064314427],"study_design_scores_gemma":[0.00091086427,0.00004338362,0.000403984,0.00019795704,0.00001876389,0.000016480863,0.00011528522,0.98843056,0.000096008356,0.00011695161,0.009310028,0.00033972738],"about_ca_topic_score_codex":0.002186456,"about_ca_topic_score_gemma":0.00030073203,"teacher_disagreement_score":0.5264519,"about_ca_system_score_codex":0.00009749365,"about_ca_system_score_gemma":0.000056915113,"threshold_uncertainty_score":0.82254684},"labels":[],"label_agreement":null},{"id":"W2121433213","doi":"10.1145/1386118.1386119","title":"Probabilistic top- <i>k</i> and ranking-aggregate queries","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":87,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Ranking (information retrieval); Probabilistic logic; Aggregate (composite); Uncertain data; Semantics (computer science); Tuple; Probabilistic database; Search engine indexing; Materialized view; Dimension (graph theory); Information retrieval; Online aggregation; Data mining; Theoretical computer science; Web search query; Sargable; Search engine; Relational database; Artificial intelligence; View; Database theory; Programming language","score_opus":0.027337698147204898,"score_gpt":0.23315272567843237,"score_spread":0.20581502753122746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121433213","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":[0.0062033897,0.0003322276,0.9901506,0.0005983687,0.0009733832,0.00047599987,0.00025288065,0.0003506879,0.00066250825],"genre_scores_gemma":[0.9537305,0.0008514009,0.041115217,0.0003447139,0.00015438489,0.00023866768,0.00013510282,0.00003346149,0.0033965183],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985796,0.000080229685,0.00025486507,0.000511805,0.00030751916,0.00026597723],"domain_scores_gemma":[0.9980938,0.00012304002,0.000069430076,0.0015692523,0.00003872811,0.00010573954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026147993,0.0001838085,0.00019594282,0.00015533055,0.0004232176,0.00020126459,0.0008605283,0.000035997484,0.00001258119],"category_scores_gemma":[0.000034357763,0.00016426615,0.0000423391,0.00037288267,0.00011025054,0.001219848,0.00006301071,0.00014517382,0.00008805279],"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":[0.0003199324,0.0030912985,0.0016549565,0.0036947916,0.0012540238,0.0028169316,0.007839781,0.008262914,0.0027766565,0.33467585,0.047010966,0.5866019],"study_design_scores_gemma":[0.0067403885,0.0010815513,0.0014419389,0.0014808222,0.00027217672,0.0024643522,0.000808921,0.24120818,0.005371025,0.00312376,0.7324467,0.003560237],"about_ca_topic_score_codex":0.00024506304,"about_ca_topic_score_gemma":0.000022105087,"teacher_disagreement_score":0.94903535,"about_ca_system_score_codex":0.000024898718,"about_ca_system_score_gemma":0.000034601664,"threshold_uncertainty_score":0.6698579},"labels":[],"label_agreement":null},{"id":"W2130696419","doi":"10.1145/1189769.1189774","title":"Towards multidimensional subspace skyline analysis","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":117,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Skyline; Linear subspace; Subspace topology; Computer science; Semantics (computer science); Theoretical computer science; Space (punctuation); Object (grammar); Online analytical processing; Algorithm; Data mining; Mathematics; Artificial intelligence; Pure mathematics; Programming language","score_opus":0.017999956148877616,"score_gpt":0.25174250827514694,"score_spread":0.23374255212626932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130696419","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":[0.0012007792,0.00012988341,0.9949945,0.0008265504,0.00077737856,0.00024357522,0.00075702445,0.000305299,0.000764971],"genre_scores_gemma":[0.75475967,0.00005672727,0.23685196,0.00018517257,0.00025129982,0.00011272143,0.0016106354,0.00002807265,0.0061437422],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99797577,0.0001000853,0.00035425994,0.0006358626,0.00060827204,0.000325754],"domain_scores_gemma":[0.99727774,0.00010262226,0.0000992791,0.0023437361,0.000075415825,0.00010118339],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044213198,0.00021809503,0.00027795904,0.000581536,0.00024892157,0.00021744437,0.0011436949,0.000048204343,0.00006639199],"category_scores_gemma":[0.000013856007,0.00019594686,0.00017784929,0.0018119045,0.000034565805,0.0009259198,0.0000625519,0.00015812159,0.00025346674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015019596,0.005940149,0.0015207926,0.00050385133,0.006224702,0.00092953374,0.0004159285,0.416884,0.0055620763,0.29399687,0.0696414,0.19823052],"study_design_scores_gemma":[0.0013507016,0.00010502368,0.0026034534,0.00007437368,0.00065016805,0.000026055504,0.00011210462,0.86800706,0.0024098342,0.00019709002,0.1236247,0.0008394453],"about_ca_topic_score_codex":0.0029060368,"about_ca_topic_score_gemma":0.0002966779,"teacher_disagreement_score":0.7581426,"about_ca_system_score_codex":0.000054080352,"about_ca_system_score_gemma":0.000035683974,"threshold_uncertainty_score":0.7990481},"labels":[],"label_agreement":null},{"id":"W2139000699","doi":"10.1145/2338626.2338633","title":"Reordering rows for better compression","year":2012,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Speedup; Lexicographical order; Row; Sorting; Compression (physics); Algorithm; Data compression; Heuristic; Heuristics; Huffman coding; Compression ratio; Encoding (memory); Parallel computing; Mathematics; Combinatorics; Artificial intelligence; Database","score_opus":0.040661275768922964,"score_gpt":0.289049769394661,"score_spread":0.248388493625738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139000699","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":[0.0011248515,0.0005091833,0.9932705,0.00027759193,0.002815309,0.00068102794,0.00075845665,0.00030096382,0.0002620797],"genre_scores_gemma":[0.52009904,0.00005060507,0.47692302,0.00032283572,0.0006335341,0.00087068055,0.00024445713,0.00005681237,0.0007990473],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982471,0.00010129533,0.00039550388,0.00043037403,0.00029655185,0.00052916683],"domain_scores_gemma":[0.9972442,0.00030687638,0.00012801442,0.002045617,0.00006650452,0.00020880773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047227577,0.00023710754,0.00027269666,0.00015422366,0.00043771035,0.00007377272,0.00063018594,0.00006882168,0.000017671382],"category_scores_gemma":[0.00004469308,0.00020444884,0.00010311916,0.0002472866,0.000032865664,0.0020335675,0.000048481783,0.00017690138,0.00011728398],"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":[0.00045059933,0.0027556806,0.0010200002,0.0038939412,0.0007478192,0.00005142975,0.005046713,0.016620731,0.085584626,0.4106841,0.061889302,0.41125503],"study_design_scores_gemma":[0.0008524553,0.00010074793,0.000067927926,0.00044194222,0.0000265961,0.000088661065,0.0002477753,0.012352915,0.011695952,0.00006860908,0.97350734,0.00054910185],"about_ca_topic_score_codex":0.00011047737,"about_ca_topic_score_gemma":0.000012567047,"teacher_disagreement_score":0.911618,"about_ca_system_score_codex":0.00006316912,"about_ca_system_score_gemma":0.000025814166,"threshold_uncertainty_score":0.8337182},"labels":[],"label_agreement":null},{"id":"W2150433972","doi":"10.1145/958942.958944","title":"Efficient dynamic mining of constrained frequent sets","year":2003,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":85,"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 Manitoba; University of British Columbia","funders":"","keywords":"Computer science; Context (archaeology); Computation; Exploit; Process (computing); Set (abstract data type); Data mining; Function (biology); Component (thermodynamics); Association rule learning; Algorithm","score_opus":0.02206422575661429,"score_gpt":0.26971647157293405,"score_spread":0.24765224581631975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150433972","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":[0.01539448,0.00010066815,0.98171115,0.0001643064,0.0005305423,0.0003058216,0.0011047663,0.00012402049,0.0005642615],"genre_scores_gemma":[0.7912593,0.000010543888,0.2084568,0.000025509764,0.000005340512,0.000087211636,0.00005373254,0.000010640742,0.00009091013],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851036,0.00010243975,0.00040005497,0.00043867884,0.0003018392,0.00024664417],"domain_scores_gemma":[0.9976213,0.00022503351,0.00013662426,0.0018293519,0.00007089886,0.000116813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043222588,0.00015841583,0.00020866506,0.00017140503,0.00018475046,0.000068802925,0.00079398433,0.0000469855,0.000022887167],"category_scores_gemma":[0.00005486202,0.0001510834,0.00006799591,0.00051644625,0.00007300417,0.00012208584,0.000015603966,0.00012565145,0.00004884077],"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":[0.000041832005,0.0057409666,0.00012103153,0.0011016758,0.000890603,0.0001555559,0.0052094436,0.23856023,0.06855043,0.30965224,0.003375816,0.3666002],"study_design_scores_gemma":[0.0009237067,0.00014609184,0.000053018826,0.00033853122,0.00004754161,0.00018886467,0.00095314044,0.9841938,0.0050246506,0.0000798514,0.0076071597,0.0004436333],"about_ca_topic_score_codex":0.00010340165,"about_ca_topic_score_gemma":0.000010891232,"teacher_disagreement_score":0.77586484,"about_ca_system_score_codex":0.000052921856,"about_ca_system_score_gemma":0.00011409091,"threshold_uncertainty_score":0.61610025},"labels":[],"label_agreement":null},{"id":"W2171332293","doi":"10.1145/1366102.1366103","title":"Conditional functional dependencies for capturing data inconsistencies","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":458,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"Engineering and Physical Sciences Research Council","keywords":"Computer science; Functional dependency; Data integrity; Consistency (knowledge bases); Relational database; SQL; Data mining; Set (abstract data type); Schema (genetic algorithms); Database; Programming language; Theoretical computer science; Algorithm; Information retrieval; Artificial intelligence","score_opus":0.5917106512846138,"score_gpt":0.4156652633131301,"score_spread":0.17604538797148367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171332293","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":[0.0026714308,0.00017669193,0.95701265,0.000971684,0.0018697069,0.0006627008,0.035718504,0.00011759937,0.0007990051],"genre_scores_gemma":[0.97667843,0.000065417655,0.008499217,0.00051145913,0.00028301758,0.0002859965,0.006512661,0.000022694401,0.0071410956],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99593365,0.0002293184,0.0008280448,0.0009323349,0.0017569346,0.000319692],"domain_scores_gemma":[0.99266,0.0029671756,0.00021845188,0.0037110313,0.00029129686,0.00015204735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030932971,0.00021369765,0.00032669856,0.0004035097,0.0010836925,0.00023164196,0.0021356468,0.00007091129,0.00050959556],"category_scores_gemma":[0.0017802466,0.00017775469,0.00012498145,0.00042363376,0.00023715956,0.0016488457,0.00014348348,0.00018256904,0.00062977045],"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":[0.0007931147,0.0017419991,0.0007502174,0.00047557245,0.0010463743,0.00019186626,0.0012660634,0.036083452,0.0013499265,0.060434796,0.87849313,0.017373497],"study_design_scores_gemma":[0.0021829044,0.0001645838,0.0025568346,0.00013962218,0.00016321427,0.00055515254,0.010516756,0.013975479,0.00066068384,0.0054544746,0.9628404,0.0007898973],"about_ca_topic_score_codex":0.0004541447,"about_ca_topic_score_gemma":0.0005062943,"teacher_disagreement_score":0.974007,"about_ca_system_score_codex":0.000074699645,"about_ca_system_score_gemma":0.00019609793,"threshold_uncertainty_score":0.8334996},"labels":[],"label_agreement":null},{"id":"W2553567329","doi":"10.1145/3004295","title":"Smart Meter Data Analytics","year":2016,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Data analysis; Analytics; Smart meter; Big data; Data science; Data mining; Smart grid; Electrical engineering","score_opus":0.09289352135828077,"score_gpt":0.27501557937919624,"score_spread":0.18212205802091547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2553567329","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":[0.00029182297,0.000091177455,0.9963562,0.0010158616,0.000627715,0.00011614583,0.0008728725,0.00015404396,0.00047414622],"genre_scores_gemma":[0.9443691,0.00011060898,0.051683776,0.00013926547,0.0001462817,0.000024469759,0.00011613678,0.000026763108,0.003383645],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820656,0.000094766954,0.0003734519,0.000659561,0.0003603356,0.00030535023],"domain_scores_gemma":[0.9939816,0.00027224724,0.00011173696,0.005429799,0.00006633112,0.00013829327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005697055,0.00017146837,0.00023672158,0.00018659575,0.00021920931,0.0001887553,0.0026286356,0.000047231875,0.000113784554],"category_scores_gemma":[0.000079280435,0.00011063295,0.000085881344,0.0005172396,0.000042670898,0.0013242817,0.00013360697,0.000105558414,0.00038353252],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000709379,0.00069141027,0.00067663635,0.00019719837,0.0015592047,0.00016326469,0.00030501038,0.0023086723,0.011267976,0.021871569,0.024214145,0.936674],"study_design_scores_gemma":[0.0015255451,0.0002804157,0.00024095173,0.00064264226,0.00036760935,0.0002031356,0.00023302478,0.5039417,0.003748482,0.00026479017,0.48732126,0.0012304152],"about_ca_topic_score_codex":0.00027077986,"about_ca_topic_score_gemma":0.00010199096,"teacher_disagreement_score":0.94467247,"about_ca_system_score_codex":0.000042408374,"about_ca_system_score_gemma":0.000044437864,"threshold_uncertainty_score":0.49296623},"labels":[],"label_agreement":null},{"id":"W2740924709","doi":"10.1145/3068335","title":"DBSCAN Revisited, Revisited","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":2625,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of Alberta","funders":"","keywords":"Computer science; DBSCAN; Data mining; Heuristics; Information retrieval; Algorithm; Artificial intelligence; Cluster analysis","score_opus":0.03953632886572851,"score_gpt":0.28752780225235086,"score_spread":0.24799147338662236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2740924709","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":[0.00016504682,0.00018165381,0.9903804,0.0012666179,0.0012918526,0.00047784034,0.0007400021,0.00034418885,0.0051523754],"genre_scores_gemma":[0.8985859,0.0010683418,0.08268696,0.000776584,0.0007595212,0.00024798347,0.0007591086,0.00008249852,0.015033076],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99810266,0.00009774519,0.00033760883,0.00068082864,0.0004349471,0.00034617627],"domain_scores_gemma":[0.99195564,0.00007793935,0.00022322458,0.0075181434,0.00006713059,0.00015791472],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00061441766,0.00022527268,0.00026611713,0.00022134457,0.000998598,0.0015399139,0.0043667434,0.000051836516,0.000059631337],"category_scores_gemma":[0.00009353485,0.0002058787,0.000100106554,0.0002482905,0.000057475037,0.0025277876,0.00015371818,0.00022194604,0.00073983375],"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":[0.00006677807,0.00084321736,0.00051055505,0.0011211472,0.0006515729,0.00061403355,0.00029671265,0.00046478692,0.0013027439,0.13139783,0.11034694,0.75238365],"study_design_scores_gemma":[0.0019656844,0.00021177807,0.001192581,0.001360079,0.00014276197,0.000096235235,0.00011870378,0.07697163,0.0010766507,0.0004371409,0.91517633,0.0012504549],"about_ca_topic_score_codex":0.00028839524,"about_ca_topic_score_gemma":0.000009941318,"teacher_disagreement_score":0.90769345,"about_ca_system_score_codex":0.000043674238,"about_ca_system_score_gemma":0.00002565339,"threshold_uncertainty_score":0.9994966},"labels":[],"label_agreement":null},{"id":"W2766916843","doi":"10.1145/3110214","title":"Blazes","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Air Force Office of Scientific Research; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Computer science; Debugging; Consistency (knowledge bases); Scalability; Distributed computing; Programming language; Database; Artificial intelligence","score_opus":0.03784811562260383,"score_gpt":0.288350591027029,"score_spread":0.25050247540442516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766916843","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":[0.0011345412,0.0001610415,0.9904814,0.0008971845,0.0028152145,0.00027749233,0.000586703,0.00023899565,0.0034074332],"genre_scores_gemma":[0.9933432,0.000034987053,0.004463505,0.000064683816,0.00011943703,0.000094982744,0.000021968306,0.000012761537,0.0018444876],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99848974,0.00006487535,0.0002932953,0.00049458834,0.00035418762,0.00030334268],"domain_scores_gemma":[0.9941479,0.00007443516,0.00018343874,0.0053713005,0.000073533396,0.00014939772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034400498,0.00018011744,0.0002295065,0.00008164046,0.0010273645,0.0009159747,0.0030497336,0.00006728541,0.00001710329],"category_scores_gemma":[0.000058707286,0.00015964718,0.00009152583,0.000108092994,0.000062263716,0.0011771882,0.00004545047,0.00018743597,0.00051200524],"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":[0.00014766573,0.0023737405,0.0012409749,0.0011764874,0.00091993756,0.000967527,0.001696343,0.0103409905,0.010644764,0.34876516,0.06897842,0.552748],"study_design_scores_gemma":[0.0028140636,0.00028906585,0.0028763313,0.0011936749,0.000058608977,0.0003626321,0.00030914307,0.1048558,0.005530099,0.0005801246,0.8795756,0.0015548627],"about_ca_topic_score_codex":0.00076923723,"about_ca_topic_score_gemma":0.00005450941,"teacher_disagreement_score":0.99220866,"about_ca_system_score_codex":0.000038888087,"about_ca_system_score_gemma":0.00004956889,"threshold_uncertainty_score":0.8832765},"labels":[],"label_agreement":null},{"id":"W3166524313","doi":"10.1145/3446980","title":"Optimizing One-time and Continuous Subgraph Queries using Worst-case Optimal Joins","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Joins; Query plan; Query optimization; Spatial query; Vertex (graph theory); Computation; Theoretical computer science; Graph; Sargable; Algorithm; Database; Web search query; Search engine; Information retrieval","score_opus":0.03081097010833498,"score_gpt":0.24837275789465005,"score_spread":0.21756178778631508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3166524313","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":[0.10831484,0.00076961884,0.8892211,0.00014625039,0.0006534746,0.00022803988,0.0003627335,0.00022473774,0.000079233934],"genre_scores_gemma":[0.71295655,0.000095259566,0.28636277,0.00009397152,0.00007702625,0.00003515057,0.000041289048,0.000031882682,0.00030607937],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99797666,0.00031632895,0.00038016395,0.00067082455,0.00026308215,0.00039296746],"domain_scores_gemma":[0.9978201,0.00027716413,0.000106171356,0.0014689871,0.0001176569,0.00020991277],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047324187,0.0002602813,0.000370788,0.0002523635,0.0006795399,0.00046421264,0.0004497603,0.000086330816,0.000038078488],"category_scores_gemma":[0.00004116816,0.0002724144,0.00012001678,0.00071717706,0.00012355852,0.0010392133,0.000063515916,0.0002886171,0.000024964],"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":[0.00057523226,0.0059473417,0.00029174425,0.0021662991,0.0040434874,0.061251465,0.023373138,0.27235684,0.33331475,0.15568367,0.0005319668,0.14046405],"study_design_scores_gemma":[0.0039643953,0.0005440626,0.000043521544,0.0020166321,0.00051410496,0.04488315,0.0068621775,0.8578889,0.07536444,0.00086952775,0.004284169,0.002764938],"about_ca_topic_score_codex":0.00024085597,"about_ca_topic_score_gemma":0.00003325362,"teacher_disagreement_score":0.60464174,"about_ca_system_score_codex":0.00003210181,"about_ca_system_score_gemma":0.00008976243,"threshold_uncertainty_score":0.9999728},"labels":[],"label_agreement":null},{"id":"W3172623769","doi":"10.1145/3451159","title":"Graph Indexing for Efficient Evaluation of Label-constrained Reachability Queries","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reachability; Computer science; Vertex (graph theory); Search engine indexing; Transitive closure; Combinatorics; Graph; Theoretical computer science; Discrete mathematics; Mathematics; Information retrieval","score_opus":0.06869570056074788,"score_gpt":0.31231993113975526,"score_spread":0.2436242305790074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3172623769","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":[0.008771741,0.00014588065,0.98769695,0.00030312815,0.0009872316,0.0007476862,0.0009864005,0.000095355936,0.0002656474],"genre_scores_gemma":[0.92510027,0.000017880031,0.07392434,0.00003331338,0.00004246864,0.0003211238,0.00038139563,0.000012020295,0.00016717747],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980745,0.00023527484,0.0003884325,0.0004942946,0.00060482573,0.00020270809],"domain_scores_gemma":[0.9974092,0.00026920994,0.00012584918,0.001737981,0.0004003355,0.000057400863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020407997,0.00013577375,0.00020719548,0.00017023853,0.00018077352,0.000113639464,0.00059961376,0.000040773146,0.000017799006],"category_scores_gemma":[0.00018964923,0.00013325983,0.00008556974,0.0006016582,0.00006142744,0.00045419598,0.000039101706,0.00009076017,0.000005651945],"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":[0.00010007975,0.0029554563,0.000114156355,0.00200018,0.00068578176,0.000019735517,0.0018205876,0.061248068,0.014671631,0.14905459,0.00090929074,0.7664204],"study_design_scores_gemma":[0.0031149425,0.00018901909,0.00017523709,0.00042589408,0.00025222223,0.000021194806,0.0015114158,0.9653699,0.022258537,0.0017218023,0.004492366,0.00046748485],"about_ca_topic_score_codex":0.0001316686,"about_ca_topic_score_gemma":0.000053816122,"teacher_disagreement_score":0.91632855,"about_ca_system_score_codex":0.000058026908,"about_ca_system_score_gemma":0.00015914126,"threshold_uncertainty_score":0.5434178},"labels":[],"label_agreement":null},{"id":"W3212747350","doi":"10.1145/3483940","title":"On Directed Densest Subgraph Discovery","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"University of Hong Kong; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Scalability; Induced subgraph isomorphism problem; Enhanced Data Rates for GSM Evolution; Core (optical fiber); Graph; Directed graph; Subgraph isomorphism problem; Efficient algorithm; Theoretical computer science; Algorithm; Artificial intelligence; Database; Line graph","score_opus":0.019904467790991108,"score_gpt":0.25218275451067046,"score_spread":0.23227828671967934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212747350","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":[0.012054928,0.00036479614,0.9830376,0.00046252043,0.0025490555,0.00026155598,0.00031291554,0.00064075907,0.00031589856],"genre_scores_gemma":[0.985059,0.0002131761,0.012486079,0.00045911616,0.000090136346,0.000104633626,0.000116720024,0.000035161018,0.0014359761],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99771655,0.00024187792,0.00033843747,0.00082269916,0.00046731028,0.00041313047],"domain_scores_gemma":[0.9959985,0.0007171803,0.000094783005,0.0029226264,0.00010059355,0.00016633327],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00013510398,0.00027037284,0.00027302853,0.00021737987,0.000321721,0.00029210778,0.0009613929,0.000080238184,0.000021401558],"category_scores_gemma":[0.000083091385,0.00025273595,0.00015803747,0.0014464317,0.00005215285,0.0010918563,0.000037138812,0.00041123174,0.00015396516],"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":[0.000665136,0.0059878933,0.0008496029,0.0008463941,0.0014392749,0.007877939,0.00096253195,0.3689574,0.05521684,0.3702691,0.033239495,0.15368837],"study_design_scores_gemma":[0.016292524,0.0035501367,0.007492193,0.009009319,0.00074636424,0.006353679,0.0014907301,0.44467002,0.30235082,0.027663868,0.16754675,0.012833593],"about_ca_topic_score_codex":0.000059618516,"about_ca_topic_score_gemma":0.000097662734,"teacher_disagreement_score":0.9730041,"about_ca_system_score_codex":0.000060477203,"about_ca_system_score_gemma":0.00007412403,"threshold_uncertainty_score":0.9999925},"labels":[],"label_agreement":null},{"id":"W4245823248","doi":"10.1145/1114244.1114250","title":"Optimization of query streams using semantic prefetching","year":2005,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":20,"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; Latency (audio); Context (archaeology); Server; Query optimization; STREAMS; Data mining; Information retrieval; Database; Computer network","score_opus":0.03100413104897517,"score_gpt":0.2743439780064526,"score_spread":0.24333984695747743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245823248","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":[0.005187922,0.00023880553,0.99275404,0.00008781331,0.000634576,0.00037309722,0.00042268937,0.00018401183,0.000117018375],"genre_scores_gemma":[0.5395878,0.00005879476,0.46001422,0.000027251706,0.0001004866,0.000028035578,0.00006343139,0.000021883618,0.000098088654],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811745,0.0001482074,0.0005933121,0.00046890628,0.00039000044,0.00028214738],"domain_scores_gemma":[0.99746877,0.00015168039,0.00026259443,0.0019076125,0.00010375125,0.000105571766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035866164,0.00022054913,0.0003170143,0.00026172717,0.00024042801,0.000056787907,0.0005715459,0.00006488009,0.000019494453],"category_scores_gemma":[0.00004167211,0.0002058556,0.00008649836,0.00047362366,0.000044897773,0.0019479892,0.000040088104,0.0001710344,0.00001973159],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011598041,0.00013011521,0.00002452559,0.00017063401,0.000042646334,0.000005240195,0.00025016489,0.97812897,0.002674367,0.005745394,0.000029746332,0.012786627],"study_design_scores_gemma":[0.00042872477,0.00006001836,0.000007439775,0.00060419954,0.000031657135,0.00009179618,0.00028355894,0.9860477,0.0074232835,0.000011807067,0.0047110673,0.00029877096],"about_ca_topic_score_codex":0.0008427167,"about_ca_topic_score_gemma":0.00008003106,"teacher_disagreement_score":0.53439987,"about_ca_system_score_codex":0.0001055091,"about_ca_system_score_gemma":0.000090114765,"threshold_uncertainty_score":0.83945477},"labels":[],"label_agreement":null},{"id":"W4256119157","doi":"10.1145/1189769.1189778","title":"Peer data exchange","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Data exchange; Tuple; Peer-to-peer; Schema (genetic algorithms); Data sharing; Generalization; Data source; Theoretical computer science; Information retrieval; Distributed computing; World Wide Web","score_opus":0.0697215860345619,"score_gpt":0.28923607189616385,"score_spread":0.21951448586160194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256119157","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":[0.00053002464,0.0006093375,0.99077266,0.0025725788,0.0018000704,0.00022923129,0.00066140614,0.00042705113,0.0023976301],"genre_scores_gemma":[0.93294966,0.00008065848,0.055089135,0.00024775916,0.00041028255,0.000089319605,0.0006456998,0.000027297783,0.010460201],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982386,0.00008967936,0.00026136267,0.0005947225,0.0005194093,0.00029620674],"domain_scores_gemma":[0.99464583,0.00020394285,0.000063333115,0.004943543,0.000081334074,0.00006198424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005387742,0.00016043936,0.00018216867,0.0001478942,0.00020086658,0.000213933,0.0029523754,0.000060374055,0.000037789177],"category_scores_gemma":[0.00006090681,0.00013796671,0.000040949817,0.00033267657,0.000039420946,0.00093207706,0.00010071645,0.00014944877,0.00035783544],"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":[0.00006604196,0.0019999722,0.00080955046,0.0007583306,0.00031301126,0.0006518948,0.00081538316,0.0043379236,0.0036780224,0.08136776,0.7225571,0.18264496],"study_design_scores_gemma":[0.0010997005,0.0001183415,0.00093518314,0.00017482534,0.0000641161,0.00026735946,0.00039649932,0.08375075,0.0024527607,0.0006909032,0.9092853,0.0007642432],"about_ca_topic_score_codex":0.0029777293,"about_ca_topic_score_gemma":0.00045093204,"teacher_disagreement_score":0.93568355,"about_ca_system_score_codex":0.000030055819,"about_ca_system_score_gemma":0.00004478833,"threshold_uncertainty_score":0.56261194},"labels":[],"label_agreement":null},{"id":"W4309617049","doi":"10.1145/3571281","title":"Efficiently Cleaning Structured Event Logs: A Graph Repair Approach","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Beijing National Research Center For Information Science And Technology; National Natural Science Foundation of China","keywords":"Computer science; Workflow; Event (particle physics); Pruning; Data mining; Graph; Profiling (computer programming); Information retrieval; Theoretical computer science; Database; Programming language","score_opus":0.11679595709416458,"score_gpt":0.35897822892552084,"score_spread":0.24218227183135627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309617049","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":[0.009426407,0.00025694203,0.9766492,0.00040243688,0.003217915,0.0012736254,0.0063290126,0.000424474,0.0020199372],"genre_scores_gemma":[0.99131215,0.000013613272,0.0043960162,0.00042837326,0.000065088156,0.0004227625,0.0005775493,0.000028971428,0.0027555074],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.99336386,0.0013303277,0.0010241437,0.0011261149,0.002727783,0.00042777462],"domain_scores_gemma":[0.99491006,0.0006978599,0.0003144542,0.0038078288,0.00009119069,0.00017860868],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.006514168,0.0002537365,0.0003957864,0.0007524402,0.0013073109,0.00027657722,0.0022303027,0.00004586341,0.0008134438],"category_scores_gemma":[0.0004147896,0.00021756743,0.0003174985,0.0018732569,0.00008820976,0.00042233584,0.00021483855,0.00049361284,0.00019454381],"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":[0.000536886,0.0025119146,0.00012515136,0.00026310002,0.00056906365,0.00012182899,0.0034137687,0.77707064,0.00047766796,0.02937876,0.13830233,0.047228917],"study_design_scores_gemma":[0.0019629227,0.0005214039,0.0003274187,0.00006897005,0.00019563844,0.00017329857,0.06328368,0.05944963,0.00015046407,0.0020557586,0.8708953,0.00091548136],"about_ca_topic_score_codex":0.00056761334,"about_ca_topic_score_gemma":0.000067476576,"teacher_disagreement_score":0.98188573,"about_ca_system_score_codex":0.0001570881,"about_ca_system_score_gemma":0.000069767644,"threshold_uncertainty_score":0.99999285},"labels":[],"label_agreement":null},{"id":"W4392139269","doi":"10.1145/3649133","title":"Sharing Queries with Nonequivalent User-defined Aggregate Functions","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Rewriting; Computer science; Aggregate (composite); Class (philosophy); Query language; Function (biology); Materialized view; Extension (predicate logic); Theoretical computer science; Database query; Reuse; Programming language; Information retrieval; Artificial intelligence; View","score_opus":0.026689537956721236,"score_gpt":0.25969814733779084,"score_spread":0.2330086093810696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392139269","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":[0.0017038558,0.0014527371,0.98943156,0.0005756618,0.0028644858,0.00055311056,0.0014757869,0.001372248,0.0005705667],"genre_scores_gemma":[0.82893884,0.000545865,0.146542,0.00019841851,0.00059243885,0.0015360363,0.0006412209,0.00020287152,0.020802304],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.997222,0.000085910935,0.0005085885,0.0011038552,0.00056215486,0.00051747874],"domain_scores_gemma":[0.9963498,0.00024462916,0.00009933066,0.0029845347,0.00010120208,0.00022049408],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00033945104,0.00040294233,0.00036267555,0.00040793073,0.0004947246,0.000514912,0.0008564417,0.00007569491,0.000058303536],"category_scores_gemma":[0.000030121726,0.00031590596,0.00012491259,0.0010722404,0.00010222318,0.0026526165,0.00008316986,0.00040808838,0.0005402532],"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":[0.00027079182,0.00061070634,0.00016923591,0.0033158038,0.0012572415,0.0014907201,0.0021334507,0.042498145,0.00746313,0.89009404,0.0063391034,0.044357628],"study_design_scores_gemma":[0.00086130056,0.0005219868,0.00004554172,0.003799129,0.0001407849,0.0010675277,0.0010519436,0.042274367,0.004984148,0.0001667974,0.9438603,0.0012261815],"about_ca_topic_score_codex":0.0009955425,"about_ca_topic_score_gemma":0.0003425584,"teacher_disagreement_score":0.93752116,"about_ca_system_score_codex":0.00016079207,"about_ca_system_score_gemma":0.00013686133,"threshold_uncertainty_score":0.9999293},"labels":[],"label_agreement":null},{"id":"W4410830018","doi":"10.1145/3736756","title":"Efficient Parallel Boolean Expression Matching","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Algorithms and Data Compression","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":"Science and Technology Commission of Shanghai Municipality","keywords":"Computer science; Boolean expression; Expression (computer science); Matching (statistics); Regular expression; Theoretical computer science; Boolean function; Algorithm; Programming language; Mathematics","score_opus":0.01736739543533445,"score_gpt":0.26725246816992965,"score_spread":0.2498850727345952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410830018","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":[0.0016940505,0.00031778714,0.99416494,0.00036211658,0.0018820649,0.00033977453,0.00017786272,0.00033431573,0.0007270937],"genre_scores_gemma":[0.8214864,0.00005934491,0.17612056,0.0003174818,0.000090130525,0.000179313,0.00009734052,0.000022279086,0.0016271556],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982031,0.00013985946,0.0003548158,0.00061147864,0.000384871,0.00030585867],"domain_scores_gemma":[0.99701834,0.00020575617,0.0000833636,0.0025286477,0.000047613452,0.00011630875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003399167,0.00020764483,0.00021421767,0.00026324965,0.0005152252,0.00023963972,0.0014881358,0.00007260138,0.000019566934],"category_scores_gemma":[0.000019353547,0.00017195172,0.000082073224,0.00044512318,0.000026470632,0.00032125955,0.00012352125,0.00027763552,0.00012537042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016208495,0.0017984641,0.000034296652,0.0006424569,0.00017312437,0.00014134911,0.0011415291,0.7311589,0.030494003,0.06144535,0.02155403,0.15125439],"study_design_scores_gemma":[0.0016865161,0.00009962344,0.00015005597,0.0024118584,0.000039640487,0.000046987137,0.00052077085,0.92754424,0.008398479,0.0009625379,0.057430796,0.000708504],"about_ca_topic_score_codex":0.00028356165,"about_ca_topic_score_gemma":0.0000060811985,"teacher_disagreement_score":0.81979233,"about_ca_system_score_codex":0.000066088294,"about_ca_system_score_gemma":0.00007072005,"threshold_uncertainty_score":0.70119876},"labels":[],"label_agreement":null},{"id":"W4415991463","doi":"10.1145/3774322","title":"Proof-of-Execution: Low-Latency Consensus via Speculative Execution","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Protocol (science); Latency (audio); Key (lock); Distributed transaction; Transaction processing; Two-phase commit protocol; Database transaction","score_opus":0.01594775058131951,"score_gpt":0.2646067206446487,"score_spread":0.24865897006332918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415991463","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":[0.002652278,0.00049511425,0.990003,0.0005185842,0.0024171053,0.00087473897,0.000675356,0.00018571255,0.0021781044],"genre_scores_gemma":[0.9938766,0.000015578038,0.004797615,0.00005215321,0.00004592785,0.00013823246,0.00008583268,0.000010855332,0.0009772062],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99762917,0.00021956296,0.00075082586,0.00064072653,0.00042315826,0.00033654177],"domain_scores_gemma":[0.99719644,0.00018724614,0.00024546278,0.001974835,0.00028840388,0.0001075913],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043636173,0.00026825778,0.0004166359,0.00029325334,0.00028144885,0.000099276745,0.0009331523,0.00012949016,0.000015460908],"category_scores_gemma":[0.00004776638,0.00025306994,0.00014900413,0.0012342267,0.00010710796,0.00036150674,0.000034017125,0.00025787935,0.00005325044],"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":[0.0007942349,0.0064961603,0.00051892945,0.006581675,0.0023925097,0.0005400547,0.0031908478,0.107231714,0.056337167,0.53254086,0.027961342,0.25541452],"study_design_scores_gemma":[0.0076793674,0.0009605011,0.0015956651,0.00967422,0.00037227376,0.0005209135,0.0016436207,0.72549427,0.15805763,0.004589951,0.08665077,0.002760835],"about_ca_topic_score_codex":0.00051307364,"about_ca_topic_score_gemma":0.000028131037,"teacher_disagreement_score":0.99122435,"about_ca_system_score_codex":0.0001386735,"about_ca_system_score_gemma":0.00018541493,"threshold_uncertainty_score":0.99999213},"labels":[],"label_agreement":null},{"id":"W4417496854","doi":"10.1145/3785662","title":"Semi-Oblivious Chase Termination for Linear Existential Rules and Beyond: An Experimental Analysis","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; European Commission","keywords":"Existentialism; Chase; Set (abstract data type); Generalization; Linearization; Class (philosophy); Focus (optics)","score_opus":0.023561886560447394,"score_gpt":0.30921964395633783,"score_spread":0.28565775739589044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417496854","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":[0.009767524,0.00017434634,0.9870277,0.00021963038,0.0007089726,0.0005413606,0.0011965707,0.00016064543,0.00020327274],"genre_scores_gemma":[0.93248063,0.000048306454,0.063268416,0.0001886226,0.00010591331,0.00040413128,0.001724005,0.000015399153,0.0017645571],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862945,0.000073881754,0.00028195715,0.00058567047,0.00021861786,0.00021044063],"domain_scores_gemma":[0.99843156,0.0000911571,0.00007519678,0.0012664833,0.000049589176,0.00008603382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003309369,0.00017251018,0.00022500473,0.00066050753,0.00034280948,0.0003591552,0.00073500484,0.000047361154,0.000009650723],"category_scores_gemma":[0.000012962694,0.00016941434,0.00009862363,0.0006345482,0.000038526476,0.0013236965,0.00005379794,0.00007860427,0.0000083736695],"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":[0.00055532646,0.009360514,0.00035791608,0.0020159981,0.007024628,0.00020140628,0.0046804273,0.010674972,0.028546542,0.16964263,0.009514221,0.7574254],"study_design_scores_gemma":[0.0016109127,0.00030326328,0.000114892275,0.0000802726,0.00060871296,0.000009322295,0.0009705128,0.97539127,0.0075085014,0.00015949694,0.012803142,0.0004396963],"about_ca_topic_score_codex":0.00016666038,"about_ca_topic_score_gemma":0.00004062989,"teacher_disagreement_score":0.9647163,"about_ca_system_score_codex":0.000040483683,"about_ca_system_score_gemma":0.000023774295,"threshold_uncertainty_score":0.6908516},"labels":[],"label_agreement":null},{"id":"W7117687674","doi":"10.1145/3786785","title":"Finding Smallest Witnesses for Conjunctive Queries","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Conjunctive query; Rewriting; Property (philosophy); Logarithm; Class (philosophy); Time complexity; Polynomial; Constant (computer programming)","score_opus":0.03221601730685047,"score_gpt":0.2997566851307163,"score_spread":0.2675406678238658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117687674","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":[0.00047670913,0.00059868535,0.9917354,0.00057207997,0.0028584623,0.0009822942,0.0017051703,0.00031267022,0.00075854757],"genre_scores_gemma":[0.7676578,0.00017676184,0.2222365,0.00046748633,0.0001986453,0.0023718171,0.00039096473,0.000049342434,0.0064506438],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981236,0.00009608636,0.00046311165,0.00069465174,0.00023288622,0.0003896591],"domain_scores_gemma":[0.99681604,0.00080665183,0.00014105512,0.001954442,0.00018680829,0.000095032956],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037240295,0.00029031895,0.00038337213,0.00032007665,0.0006745776,0.00014928463,0.0007913326,0.00008149658,0.000009746082],"category_scores_gemma":[0.00018342915,0.00026268006,0.000117956166,0.0006269781,0.000103911865,0.00095094315,0.000052830525,0.00017908431,0.000030688774],"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":[0.00014409816,0.00018454215,0.00008755943,0.0006409598,0.0002569256,0.000019141266,0.0004249484,0.0032234015,0.0019887493,0.9771493,0.0052195424,0.0106608],"study_design_scores_gemma":[0.002901043,0.00040855963,0.00013856146,0.0018559776,0.00013097415,0.000084570995,0.004092677,0.014489755,0.02398592,0.0021461567,0.94849426,0.0012715217],"about_ca_topic_score_codex":0.00038762117,"about_ca_topic_score_gemma":0.00021914837,"teacher_disagreement_score":0.9750032,"about_ca_system_score_codex":0.00011466446,"about_ca_system_score_gemma":0.00020311613,"threshold_uncertainty_score":0.99998254},"labels":[],"label_agreement":null}]}