{"meta":{"query_hash":"8458b7f752df","filters":{"venue":"Distributed and Parallel Databases"},"cohort_total":20,"direct_labels_cover":1,"predictions_cover":20,"exported":20,"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/8458b7f752df","api":"https://metacan.xera.ac/api/v1/cohort?venue=Distributed+and+Parallel+Databases"},"results":[{"id":"W139568493","doi":"10.1023/a:1019258807615","title":"A Graphical Approach to Allocating Class Fragments in Distributed Objectbase Systems","year":2001,"lang":"en","type":"article","venue":"Distributed and Parallel Databases","topic":"VLSI and FPGA Design Techniques","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Overhead (engineering); Scheme (mathematics); Mathematical optimization; Optimization algorithm; Mathematics","score_opus":0.025049053546780962,"score_gpt":0.24733264465686508,"score_spread":0.2222835911100841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W139568493","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":[0.21910393,0.0015577812,0.77146506,0.000062209416,0.00010699677,0.00068127865,0.0054412954,0.0007171545,0.0008642562],"genre_scores_gemma":[0.98839736,0.00047013117,0.0026468474,0.00004536405,0.000057363468,0.00024943711,0.008095315,0.000029691268,0.000008514507],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984839,0.00006437889,0.000389978,0.00037311207,0.0001960115,0.0004926412],"domain_scores_gemma":[0.99914235,0.00008332727,0.000033637712,0.00046556565,0.00003514919,0.00023996315],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021980454,0.0002842884,0.00034607737,0.00016615853,0.000092494476,0.00008481353,0.0002599589,0.0001026073,0.0000073503998],"category_scores_gemma":[0.00010372447,0.00027488515,0.0000446763,0.00068910135,0.000042274944,0.00020307497,0.00011043875,0.00025428357,0.000009318905],"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":[0.00076552073,0.0032065688,0.4057593,0.0029463132,0.0007766916,0.0014177934,0.0012827634,0.27019915,0.019607047,0.040826812,0.24173059,0.011481429],"study_design_scores_gemma":[0.005092418,0.0003566656,0.06481698,0.0014705197,0.00017385563,0.0005141491,0.0032607024,0.7205172,0.0017082458,0.0005848915,0.19767517,0.0038291868],"about_ca_topic_score_codex":0.00034792803,"about_ca_topic_score_gemma":0.00004910807,"teacher_disagreement_score":0.7692934,"about_ca_system_score_codex":0.000074946285,"about_ca_system_score_gemma":0.0000150769,"threshold_uncertainty_score":0.9999703},"labels":[],"label_agreement":null},{"id":"W1991438431","doi":"10.1007/s10619-006-6575-6","title":"The cgmCUBE project: Optimizing parallel data cube generation for ROLAP","year":2006,"lang":"en","type":"article","venue":"Distributed and Parallel Databases","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; Concordia University; Carleton University","funders":"","keywords":"Online analytical processing; Computer science; Data cube; Data warehouse; Cube (algebra); Very large database; Database; Data structure; Data mining; Programming language","score_opus":0.07826883404703516,"score_gpt":0.31089565877940334,"score_spread":0.23262682473236818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991438431","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":[0.0005737997,0.0030485576,0.9804829,0.0007162155,0.0002648957,0.00062849646,0.01405763,0.00014175838,0.00008575857],"genre_scores_gemma":[0.015049855,0.0016041783,0.8767207,0.00022829608,0.00095685234,0.0004221757,0.10464561,0.000032897788,0.00033938832],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981128,0.00007824524,0.00040407619,0.0007341669,0.00022100704,0.0004496904],"domain_scores_gemma":[0.99769187,0.00030322603,0.00017591342,0.0016555921,0.000106240186,0.00006718123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046949292,0.00024132179,0.00022621555,0.000038369264,0.0011011326,0.0002691194,0.0007215488,0.000041982363,0.0000017085508],"category_scores_gemma":[0.0001520038,0.00016871236,0.00004422291,0.00021599286,0.000107647385,0.001777648,0.0007137407,0.00010326113,0.0000044487065],"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":[0.00006729612,0.00009625475,0.00034641693,0.00006479688,0.000047218986,0.000015103916,0.00005558245,0.0026934328,0.0006588929,0.7839752,0.2029935,0.008986319],"study_design_scores_gemma":[0.0005737941,0.000035661877,0.00017712082,0.000024847797,0.000016470483,0.00002626538,0.00009264968,0.22909041,0.00012582226,0.0002810517,0.7692848,0.0002711352],"about_ca_topic_score_codex":0.00061501114,"about_ca_topic_score_gemma":0.0007213662,"teacher_disagreement_score":0.78369415,"about_ca_system_score_codex":0.000018309382,"about_ca_system_score_gemma":0.000096021875,"threshold_uncertainty_score":0.84691334},"labels":[],"label_agreement":null},{"id":"W1993755977","doi":"10.1007/s10619-010-7076-1","title":"Query processing in sensor networks","year":2010,"lang":"en","type":"article","venue":"Distributed and Parallel Databases","topic":"Energy Efficient Wireless Sensor Networks","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Data structure; Programming language","score_opus":0.014371540501215427,"score_gpt":0.2452749747759609,"score_spread":0.2309034342747455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993755977","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":[0.19506526,0.0005792924,0.803202,0.0003115066,0.0002998694,0.00010511543,0.000091690374,0.00018854436,0.00015673002],"genre_scores_gemma":[0.95525324,0.00010529847,0.043583687,0.00018630538,0.00012516115,0.000014072597,0.00069466466,0.000010939555,0.000026604703],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986295,0.000054888493,0.0002454171,0.0004766745,0.00015939017,0.0004341402],"domain_scores_gemma":[0.99911654,0.000121320205,0.000081811275,0.0004980745,0.000046896334,0.00013538345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021264744,0.00018493498,0.00019531845,0.00007934173,0.00015612053,0.00016717134,0.0004007083,0.00008202388,0.000008639234],"category_scores_gemma":[0.0000641143,0.00016922355,0.000029641067,0.00046803567,0.00009645675,0.00046335816,0.00024363853,0.00040658764,0.00000505992],"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":[0.00008325194,0.0006458043,0.122297004,0.00010152486,0.000023277717,0.0006091582,0.00027703904,0.7003681,0.0022216039,0.079908624,0.0071589085,0.0863057],"study_design_scores_gemma":[0.00049570185,0.000016507387,0.030322744,0.00007132029,0.000005081295,0.000062692554,0.00003277483,0.9551351,0.00010888212,0.000043416807,0.013350058,0.00035572573],"about_ca_topic_score_codex":0.00012976072,"about_ca_topic_score_gemma":0.0005025571,"teacher_disagreement_score":0.760188,"about_ca_system_score_codex":0.000009637759,"about_ca_system_score_gemma":0.000035837485,"threshold_uncertainty_score":0.6900736},"labels":[],"label_agreement":null},{"id":"W2008361063","doi":"10.1007/s10619-009-7052-9","title":"Guest editorial: special issue on ranking in databases","year":2009,"lang":"en","type":"editorial","venue":"Distributed and Parallel Databases","topic":"Web visibility and informetrics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Ranking (information retrieval); Database; Information retrieval; Data science","score_opus":0.024128819301910822,"score_gpt":0.2946601032873167,"score_spread":0.2705312839854059,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008361063","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000022311131,0.00046849783,0.0070021944,0.00015645602,0.968822,0.00039008562,0.021733696,0.00017386385,0.0012308721],"genre_scores_gemma":[0.000020343465,0.0019618042,0.0017690441,0.00012152637,0.94510144,0.000020708756,0.05089046,0.000021617607,0.000093065784],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952721,0.0001850917,0.00088286033,0.001328024,0.001545669,0.0007862514],"domain_scores_gemma":[0.9952261,0.0022460874,0.00036469934,0.0016613606,0.0002456543,0.00025611903],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001075285,0.0006792401,0.0008893218,0.00055256503,0.00027924243,0.00050657144,0.0015298005,0.00049433357,0.000049109967],"category_scores_gemma":[0.0044334135,0.0006436629,0.00013325621,0.0012048311,0.00012731494,0.0016414544,0.0007110576,0.0014537984,0.00013653497],"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":[0.00013099346,0.0002568542,0.00007221518,0.00010103926,0.0000195835,0.00008205622,0.000048098904,0.00003789445,7.8880504e-7,0.0017899766,0.99321455,0.004245941],"study_design_scores_gemma":[0.0012778658,0.00021726318,0.00021322118,0.00039823836,0.000024356668,0.0000025601566,0.000019644147,0.00019014614,0.000022455524,0.00014240551,0.9967716,0.00072026113],"about_ca_topic_score_codex":0.0006737067,"about_ca_topic_score_gemma":0.0004353412,"teacher_disagreement_score":0.029156763,"about_ca_system_score_codex":0.00015827236,"about_ca_system_score_gemma":0.0004533327,"threshold_uncertainty_score":0.9996015},"labels":[],"label_agreement":null},{"id":"W2016326061","doi":"10.1023/b:dapd.0000013069.97679.62","title":"An Adaptive Data-Shipping Architecture for Client Caching Data Management Systems","year":2004,"lang":"en","type":"article","venue":"Distributed and Parallel Databases","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Distributed computing; Cache; Robustness (evolution); Architecture; Data management; Database; Computer network","score_opus":0.09128449405044331,"score_gpt":0.32144718531403554,"score_spread":0.23016269126359223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016326061","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":[0.0015070277,0.001635266,0.9282715,0.0002912292,0.00038358208,0.0007963408,0.066841185,0.00019663054,0.00007725989],"genre_scores_gemma":[0.7898236,0.00017121465,0.093347356,0.00018196205,0.00025008267,0.00011702171,0.1160682,0.00002405083,0.00001653285],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970985,0.000103124796,0.000460635,0.0014314414,0.0003481441,0.0005581256],"domain_scores_gemma":[0.99546695,0.00011130017,0.00019758588,0.0038932208,0.00007385245,0.0002570825],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00073261635,0.00032231148,0.00037417343,0.00007738052,0.0004935938,0.0005358897,0.003201032,0.000057966874,0.0000011599902],"category_scores_gemma":[0.000049315444,0.00028110153,0.00003534345,0.00028562653,0.00006658804,0.0018718828,0.0015868105,0.00018128456,0.0000063793163],"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":[0.00031600642,0.0009870976,0.0006206861,0.0010530247,0.0006409367,0.00035573376,0.00054100953,0.21512201,0.00014041188,0.7107523,0.024734152,0.04473662],"study_design_scores_gemma":[0.0034638268,0.00029913007,0.0016644229,0.0008287836,0.00014087616,0.00016780307,0.001252328,0.60875374,0.000021283779,0.0012049053,0.3810396,0.0011632994],"about_ca_topic_score_codex":0.0006214988,"about_ca_topic_score_gemma":0.00018166436,"teacher_disagreement_score":0.8349241,"about_ca_system_score_codex":0.000045402245,"about_ca_system_score_gemma":0.00006688944,"threshold_uncertainty_score":0.9999641},"labels":[],"label_agreement":null},{"id":"W2047284331","doi":"10.1007/s10619-007-7018-8","title":"Adaptive processing of historical spatial range queries in peer-to-peer sensor networks","year":2007,"lang":"en","type":"article","venue":"Distributed and Parallel Databases","topic":"Energy Efficient Wireless Sensor Networks","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University; University of Alberta","funders":"","keywords":"Computer science; Query optimization; Flooding (psychology); Spatial query; Online aggregation; Data mining; Distributed computing; Query expansion; Energy consumption; Web search query; Web query classification; Information retrieval; Search engine","score_opus":0.026885808651503078,"score_gpt":0.26124794385443934,"score_spread":0.23436213520293625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047284331","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":[0.041921217,0.0007696034,0.9559956,0.0005558714,0.00023047926,0.0001586544,0.00017811677,0.00008241025,0.00010801103],"genre_scores_gemma":[0.9531768,0.00003058827,0.04593536,0.00010752345,0.00013707513,0.000009301294,0.0004667109,0.000012911895,0.00012373146],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979596,0.00007743852,0.0004458662,0.00049714284,0.0005099763,0.00050995214],"domain_scores_gemma":[0.99869674,0.00028932633,0.0001505918,0.00038220774,0.0002900679,0.00019105416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060802005,0.00022382924,0.00035309512,0.00014833517,0.00011711387,0.00005223391,0.00036719328,0.000087942004,0.0000039619545],"category_scores_gemma":[0.00020563537,0.00021014243,0.000047087433,0.0007018094,0.00008686787,0.00030053803,0.00025604412,0.000224973,0.0000015931149],"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":[0.00134275,0.0010282992,0.098309934,0.00013389719,0.000066422,0.0007171064,0.0022172993,0.75599015,0.00028900552,0.018706668,0.018728139,0.102470316],"study_design_scores_gemma":[0.0019932366,0.00034491558,0.090273835,0.00040062546,0.000032689783,0.000055977853,0.00043022295,0.8427085,0.0006008756,0.00004609609,0.062054127,0.0010588777],"about_ca_topic_score_codex":0.0013683978,"about_ca_topic_score_gemma":0.0014011757,"teacher_disagreement_score":0.9112556,"about_ca_system_score_codex":0.00012137578,"about_ca_system_score_gemma":0.00004517069,"threshold_uncertainty_score":0.856936},"labels":[],"label_agreement":null},{"id":"W2070626055","doi":"10.1007/s10619-005-4257-4","title":"Preventive Replication in a Database Cluster","year":2005,"lang":"en","type":"article","venue":"Distributed and Parallel Databases","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Replica; Computer science; Replication (statistics); Database transaction; Benchmark (surveying); Distributed database; Database; Throughput; Cluster (spacecraft); Consistency (knowledge bases); Data consistency; Distributed computing; Parallel computing; Computer network; Operating system; Mathematics; Artificial intelligence; Geography","score_opus":0.022992260274848044,"score_gpt":0.2855527655536087,"score_spread":0.2625605052787607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070626055","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":[0.03788013,0.0013093934,0.9535551,0.0020163874,0.00008755315,0.00041644397,0.0041621886,0.00013351992,0.00043925553],"genre_scores_gemma":[0.9708322,0.0002442283,0.021636495,0.000471898,0.000095887255,0.000112782385,0.0064412397,0.000008659138,0.00015656982],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998389,0.0000954998,0.00035511397,0.00066960225,0.00018137546,0.0003094129],"domain_scores_gemma":[0.9985345,0.00009151983,0.000110294815,0.0010923961,0.000053342184,0.0001179214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040053864,0.00017024417,0.00020682752,0.00007228922,0.00010348734,0.000112641275,0.00043603292,0.00003984063,0.000014594227],"category_scores_gemma":[0.00011093472,0.00015663335,0.000035863803,0.0003825039,0.00004360262,0.0012419826,0.0002793861,0.0001330664,0.000047016332],"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":[0.0003404335,0.0025788373,0.06182885,0.00042720424,0.00015511127,0.00020962539,0.0017860538,0.0040199747,0.0023564547,0.46251678,0.23736376,0.22641692],"study_design_scores_gemma":[0.0029546476,0.00006723877,0.053465296,0.00034541587,0.000017549199,0.000107931686,0.00014988985,0.18251327,0.0007245965,0.00050118106,0.75835556,0.0007974313],"about_ca_topic_score_codex":0.00015727888,"about_ca_topic_score_gemma":0.00025157374,"teacher_disagreement_score":0.9329521,"about_ca_system_score_codex":0.000037297235,"about_ca_system_score_gemma":0.000037955717,"threshold_uncertainty_score":0.63873225},"labels":[],"label_agreement":null},{"id":"W2072466548","doi":"10.1007/s10619-006-6284-1","title":"Incremental click-stream tree model: Learning from new users for web page prediction","year":2006,"lang":"en","type":"article","venue":"Distributed and Parallel Databases","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Clickstream; Tree (set theory); Web log analysis software; Data mining; Process (computing); Online model; Web server; Recommender system; Data stream; Web page; Document Object Model; Machine learning; Database; World Wide Web; Information retrieval; Static web page; The Internet; Web API","score_opus":0.040724674281577715,"score_gpt":0.262250113213566,"score_spread":0.22152543893198828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072466548","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":[0.053903237,0.0003216872,0.94049186,0.0002257389,0.000096469324,0.00028476786,0.004029019,0.0004069753,0.0002402487],"genre_scores_gemma":[0.9284468,0.00011355505,0.058370966,0.000062511375,0.0001861349,0.000061173734,0.012619536,0.00001284097,0.00012642787],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988468,0.000045868514,0.0002819525,0.00042266783,0.0001491167,0.0002535681],"domain_scores_gemma":[0.9993393,0.000102246326,0.000113452246,0.00031609033,0.000029076362,0.00009985787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013298677,0.00017753622,0.00019662116,0.000050498777,0.00021335961,0.00016943707,0.00026199373,0.000054552092,0.0000061999194],"category_scores_gemma":[0.000018789557,0.00016246365,0.000064698026,0.0001098547,0.000022491515,0.0006258385,0.00015545925,0.00010163352,0.000002313375],"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":[0.00015877312,0.00045645435,0.13452008,0.0000989927,0.00018381505,0.000024673276,0.00037703547,0.004323555,0.012855462,0.051430143,0.75705373,0.038517278],"study_design_scores_gemma":[0.0018972406,0.00018492443,0.011441342,0.000102437436,0.000044381977,0.000011411455,0.00012580949,0.88188064,0.0024317014,0.0043561524,0.0970637,0.00046027268],"about_ca_topic_score_codex":0.0037113186,"about_ca_topic_score_gemma":0.00054709835,"teacher_disagreement_score":0.8821209,"about_ca_system_score_codex":0.00002989479,"about_ca_system_score_gemma":0.000048433223,"threshold_uncertainty_score":0.66250753},"labels":[],"label_agreement":null},{"id":"W2078842512","doi":"10.1007/s10619-005-3296-1","title":"Stream Cube: An Architecture for Multi-Dimensional Analysis of Data Streams","year":2005,"lang":"en","type":"article","venue":"Distributed and Parallel Databases","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":155,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Science Foundation","keywords":"Computer science; Data cube; Data stream mining; Data stream; Data structure; Volume (thermodynamics); Online analytical processing; Computation; Stream processing; Data mining; Algorithm; Parallel computing; Data warehouse","score_opus":0.10197947995303348,"score_gpt":0.3616370861324058,"score_spread":0.25965760617937234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078842512","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":[0.03369131,0.00023516995,0.8506371,0.00022237503,0.000019392388,0.00019781497,0.11481182,0.00017796739,0.000007082804],"genre_scores_gemma":[0.1482135,0.000040341656,0.72196805,0.00008972347,0.000037032525,0.000020205996,0.12961447,0.000008435046,0.000008220772],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826515,0.00006358415,0.00034895414,0.0007975914,0.00023001099,0.00029469587],"domain_scores_gemma":[0.99708515,0.00025324008,0.00017175938,0.0022340484,0.00009580702,0.00015997993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002988997,0.00022156847,0.00038640102,0.00022082159,0.00012569736,0.00008041713,0.0015769122,0.000052663472,0.000017066306],"category_scores_gemma":[0.00013257314,0.00019125448,0.00007159979,0.00058744557,0.000108158085,0.0012476561,0.0009794796,0.00009897045,0.0000012269993],"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":[0.00029463635,0.0032590851,0.025671804,0.00014911247,0.0026808807,0.000033847704,0.00047328236,0.01004978,0.0016691607,0.04151941,0.07079311,0.8434059],"study_design_scores_gemma":[0.00084784866,0.00017611135,0.009802936,0.000043106767,0.00054367655,0.0000125279275,0.00004427719,0.9455583,0.0014071128,0.00015866809,0.040978163,0.00042726842],"about_ca_topic_score_codex":0.0003020335,"about_ca_topic_score_gemma":0.0010301818,"teacher_disagreement_score":0.93550855,"about_ca_system_score_codex":0.000012298218,"about_ca_system_score_gemma":0.000059310198,"threshold_uncertainty_score":0.7799131},"labels":[],"label_agreement":null},{"id":"W2080139625","doi":"10.1007/s10619-011-7085-8","title":"Scaling XML query processing: distribution, localization and pruning","year":2011,"lang":"en","type":"article","venue":"Distributed and Parallel Databases","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Query optimization; XML database; Query plan; Sargable; Scalability; Query expansion; Query language; Information retrieval; Database; Data mining; XML; Web search query; Search engine; World Wide Web","score_opus":0.04172179025022446,"score_gpt":0.25388811319574134,"score_spread":0.21216632294551688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080139625","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":[0.0052334,0.0018638402,0.9905394,0.00005741089,0.00007073598,0.00013650158,0.0018318208,0.00017674857,0.00009019042],"genre_scores_gemma":[0.8819481,0.000651539,0.10773816,0.00016236005,0.00008177478,0.000045059514,0.009323536,0.000017178647,0.000032263677],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987922,0.000053717715,0.00027516842,0.00045204457,0.00014846481,0.00027843722],"domain_scores_gemma":[0.9992123,0.00005306655,0.00013037329,0.0003493515,0.00010440392,0.00015048632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018844962,0.00018718824,0.00019537692,0.00003718495,0.00045232408,0.0000740509,0.00014192957,0.000040206167,0.0000070467204],"category_scores_gemma":[0.0001319949,0.00016353418,0.000020108988,0.00026866316,0.00014243138,0.0015258571,0.00028533992,0.00009128649,0.0000035870048],"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":[0.00006753677,0.00017249194,0.029759817,0.00040882188,0.000040860414,0.00008048478,0.0014908364,0.000189833,0.00015427925,0.92320776,0.0035296406,0.04089764],"study_design_scores_gemma":[0.0021379173,0.00019664638,0.044292454,0.0011774715,0.000093144365,0.00045590583,0.002268852,0.19426547,0.0026855913,0.0030902494,0.74734753,0.00198876],"about_ca_topic_score_codex":0.00020153262,"about_ca_topic_score_gemma":0.000023323046,"teacher_disagreement_score":0.9201175,"about_ca_system_score_codex":0.000014330506,"about_ca_system_score_gemma":0.00004496163,"threshold_uncertainty_score":0.666873},"labels":[],"label_agreement":null},{"id":"W2121550967","doi":"10.1007/s10619-006-0445-0","title":"Parallel Bifold: Large-scale parallel pattern mining with constraints","year":2006,"lang":"en","type":"article","venue":"Distributed and Parallel Databases","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Data mining; Set (abstract data type); Scale (ratio); Cluster (spacecraft); Space (punctuation); Geography","score_opus":0.01781232993566086,"score_gpt":0.2489065911592234,"score_spread":0.23109426122356252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121550967","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":[0.016167125,0.0004128234,0.9727748,0.0007705698,0.000060154416,0.00024775334,0.008802668,0.0002628821,0.0005011994],"genre_scores_gemma":[0.41845062,0.00016816828,0.5576675,0.0006024899,0.0002136932,0.00022271948,0.022382865,0.000038149057,0.00025381256],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99777645,0.000054615626,0.00038161257,0.00082669564,0.0003120087,0.0006486381],"domain_scores_gemma":[0.998469,0.00015403541,0.00017089653,0.000911841,0.00008353042,0.00021070546],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021245153,0.0003399021,0.00032975007,0.000081271224,0.0004574084,0.00032101726,0.0006744595,0.000063382584,0.000052267926],"category_scores_gemma":[0.000016738088,0.00028327806,0.000055622495,0.00040358622,0.00023002242,0.0007102828,0.00035810712,0.00016622206,0.00004780817],"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":[0.00018160525,0.0034945956,0.2849434,0.00031163607,0.00044811104,0.00089076365,0.0014233383,0.0044536744,0.00033350463,0.21215062,0.29470742,0.19666134],"study_design_scores_gemma":[0.009351198,0.0004542967,0.2149667,0.00051517,0.00019808614,0.00073865126,0.0019329237,0.31213197,0.00019536844,0.0016086568,0.45469555,0.0032114105],"about_ca_topic_score_codex":0.00037765794,"about_ca_topic_score_gemma":0.00038315303,"teacher_disagreement_score":0.41510734,"about_ca_system_score_codex":0.000017944498,"about_ca_system_score_gemma":0.00007455934,"threshold_uncertainty_score":0.9999619},"labels":[],"label_agreement":null},{"id":"W2126220026","doi":"10.1007/s10619-009-7043-x","title":"Continuously monitoring top-k uncertain data streams: a probabilistic threshold method","year":2009,"lang":"en","type":"article","venue":"Distributed and Parallel Databases","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Data stream mining; Computer science; Probabilistic logic; Uncertain data; Quantile; Data mining; Data structure; Algorithm; Artificial intelligence; Mathematics; Statistics","score_opus":0.07410263996446681,"score_gpt":0.33747829743305896,"score_spread":0.26337565746859215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126220026","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":[0.0034460472,0.0010048726,0.9884417,0.0011194451,0.00020566833,0.00032912593,0.0048404275,0.00028205887,0.00033065886],"genre_scores_gemma":[0.23431115,0.0011206763,0.72472394,0.00060311554,0.000578763,0.00004743572,0.038298827,0.00002417998,0.00029194515],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980981,0.00006719214,0.00028414052,0.00085070654,0.00027768684,0.00042218182],"domain_scores_gemma":[0.99769545,0.00014775842,0.00009947382,0.0018553237,0.000048934588,0.00015303589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047871468,0.00024211334,0.00026652878,0.000066070694,0.00020958125,0.00045258814,0.0017261797,0.000033928307,0.000010370016],"category_scores_gemma":[0.00015590807,0.00020883472,0.000031661497,0.00036423263,0.00004463297,0.0018312003,0.0010563271,0.00014365013,0.000013006116],"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":[0.00006876405,0.00068562693,0.01818039,0.00013445059,0.0001606991,0.00048457677,0.0001908808,0.00076578883,0.00016777722,0.16306162,0.06739528,0.74870414],"study_design_scores_gemma":[0.0038442197,0.0005500984,0.03974839,0.00063711696,0.00027682437,0.0001229615,0.00061187235,0.6518872,0.00056761946,0.019252213,0.28011462,0.002386888],"about_ca_topic_score_codex":0.00013347626,"about_ca_topic_score_gemma":0.000011820981,"teacher_disagreement_score":0.74631727,"about_ca_system_score_codex":0.000016947248,"about_ca_system_score_gemma":0.000036367834,"threshold_uncertainty_score":0.85160327},"labels":[],"label_agreement":null},{"id":"W2133443743","doi":"10.1007/s10619-007-7023-y","title":"PnP: sequential, external memory, and parallel iceberg cube computation","year":2008,"lang":"en","type":"article","venue":"Distributed and Parallel Databases","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; Concordia University; Carleton University","funders":"","keywords":"Computer science; Speedup; Cube (algebra); Scalability; Iceberg; Auxiliary memory; Data cube; Computation; Parallel computing; Pruning; Data structure; Algorithm; Data mining; Mathematics; Computer hardware; Database; Operating system; Geology; Combinatorics","score_opus":0.04727396136730296,"score_gpt":0.2760956854569131,"score_spread":0.22882172408961013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133443743","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":[0.041886166,0.001140817,0.9545969,0.0004329301,0.00020024908,0.00019887694,0.0010909612,0.0001673793,0.00028575285],"genre_scores_gemma":[0.74035126,0.005464917,0.23731446,0.0009589551,0.00036657625,0.00005946828,0.0146716805,0.00003293827,0.0007797514],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848604,0.000070443,0.00026349624,0.0005626366,0.0002832551,0.00033413433],"domain_scores_gemma":[0.99917185,0.00008473512,0.00011028121,0.0004099729,0.00004919726,0.00017398731],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016939739,0.00022641168,0.00022409447,0.00008228196,0.00041348638,0.0002446251,0.0004155506,0.00003402287,0.000022340215],"category_scores_gemma":[0.000028328572,0.00020953867,0.000040012415,0.0002175629,0.00015700297,0.0015384245,0.0006129684,0.00011596903,0.00003155679],"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":[0.00038052376,0.0016845751,0.055490673,0.0006750182,0.00071272097,0.0041466407,0.0019918233,0.006216718,0.0012367553,0.20905465,0.45695254,0.26145735],"study_design_scores_gemma":[0.0084101865,0.00044308926,0.18302725,0.0003155707,0.0001950985,0.0013415226,0.00041528002,0.59273577,0.0005218074,0.005567924,0.20428382,0.0027427063],"about_ca_topic_score_codex":0.00025912447,"about_ca_topic_score_gemma":0.000025693882,"teacher_disagreement_score":0.7172824,"about_ca_system_score_codex":0.0000123872605,"about_ca_system_score_gemma":0.000029596202,"threshold_uncertainty_score":0.85447395},"labels":[],"label_agreement":null},{"id":"W2135133299","doi":"10.1023/b:dapd.0000018572.20283.e0","title":"Parallel ROLAP Data Cube Construction on Shared-Nothing Multiprocessors","year":2004,"lang":"en","type":"article","venue":"Distributed and Parallel Databases","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Dalhousie University","funders":"","keywords":"Computer science; Online analytical processing; Row; Parallel computing; Data cube; Speedup; Data warehouse; Data structure; Cube (algebra); Database; Data mining; Programming language; Mathematics","score_opus":0.05168987859294967,"score_gpt":0.2929623151742056,"score_spread":0.24127243658125597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135133299","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":[0.006025551,0.0007575395,0.9755785,0.00091686647,0.0002915357,0.00025247302,0.015765183,0.00030561574,0.00010674927],"genre_scores_gemma":[0.13764042,0.0008619745,0.81734216,0.00090452074,0.0002875966,0.00007172326,0.042813566,0.000037855276,0.000040211078],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99774235,0.00005043742,0.00039857774,0.0010134277,0.00034619943,0.000448983],"domain_scores_gemma":[0.99764293,0.00013720052,0.00019567527,0.0017341385,0.000080383455,0.00020968016],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022941669,0.00032531787,0.00032644972,0.000087851535,0.0004876997,0.0001509865,0.00076974375,0.00006350089,0.000015555774],"category_scores_gemma":[0.00025290862,0.00028322544,0.000040536812,0.0003258585,0.00015987904,0.0031947843,0.00086214073,0.00023974144,0.000051182684],"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":[0.00019136265,0.00032273433,0.0024306676,0.00022839374,0.00011146293,0.00022378036,0.0007712019,0.013861897,0.00030153332,0.9591617,0.0053996444,0.016995642],"study_design_scores_gemma":[0.0058384803,0.00027384533,0.0052406397,0.00096562883,0.00006327842,0.0005200447,0.0012452482,0.034719486,0.00097339053,0.002435504,0.94587004,0.0018543851],"about_ca_topic_score_codex":0.00042025337,"about_ca_topic_score_gemma":0.00010634873,"teacher_disagreement_score":0.9567262,"about_ca_system_score_codex":0.00003970029,"about_ca_system_score_gemma":0.00010241775,"threshold_uncertainty_score":0.999962},"labels":[],"label_agreement":null},{"id":"W2299020861","doi":"10.1007/s10619-017-7196-y","title":"TAPER: query-aware, partition-enhancement for large, heterogenous graphs","year":2017,"lang":"en","type":"article","venue":"Distributed and Parallel Databases","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Newcastle University","keywords":"Computer science; Graph partition; Scalability; Partition (number theory); Workload; Space partitioning; Hash function; Parallel computing; USable; Theoretical computer science; Graph; Algorithm; Database; Mathematics","score_opus":0.03487313379500431,"score_gpt":0.29416619769974,"score_spread":0.2592930639047357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2299020861","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":[0.02767796,0.00039358353,0.96474254,0.0004053062,0.00030387347,0.0002937017,0.006024629,0.00009002161,0.00006835607],"genre_scores_gemma":[0.9866313,0.00033988003,0.009311448,0.00023323174,0.000058386602,0.00015765785,0.0032006106,0.000008539234,0.000058942955],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987404,0.000040326744,0.00020430032,0.00044916707,0.00014081702,0.00042501124],"domain_scores_gemma":[0.99857146,0.000092327304,0.00014682561,0.00096573954,0.00007530998,0.00014835793],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00026278492,0.00018509409,0.00020208559,0.00004058781,0.0014042129,0.00035336072,0.0006869503,0.00003620269,0.00002072851],"category_scores_gemma":[0.00004905297,0.00016358994,0.000095837,0.00006422812,0.00009230076,0.0007954099,0.000292699,0.00007497862,0.000014584275],"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":[0.00008698239,0.00063397817,0.0065004295,0.00011578082,0.00015095192,0.000057692163,0.00021561205,0.000029908842,0.00029476586,0.9666251,0.010623931,0.014664858],"study_design_scores_gemma":[0.012564576,0.0014416905,0.038242906,0.0005400495,0.00026392366,0.00023940504,0.0005690995,0.09932504,0.019208131,0.33005345,0.4938019,0.0037498418],"about_ca_topic_score_codex":0.00003903067,"about_ca_topic_score_gemma":0.000046791967,"teacher_disagreement_score":0.9589533,"about_ca_system_score_codex":0.000007326878,"about_ca_system_score_gemma":0.000024841058,"threshold_uncertainty_score":0.9998958},"labels":[],"label_agreement":null},{"id":"W3088726914","doi":"10.1007/s10619-020-07313-y","title":"Introduction to the special issue on Self-managing and Hardware-Optimized Database Systems 2019","year":2020,"lang":"en","type":"article","venue":"Distributed and Parallel Databases","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"University of Waterloo; University of California, Davis; Institute of Computing Technology, Chinese Academy of Sciences; University of Pittsburgh; Chinese Academy of Sciences; Oracle","keywords":"Computer science; Database; Data structure; Computer architecture; Operating system","score_opus":0.01679472336439665,"score_gpt":0.23503290242983793,"score_spread":0.2182381790654413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088726914","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":[0.013432209,0.0014345193,0.8370569,0.14166088,0.0019865222,0.001223158,0.0017880754,0.0006513546,0.0007663863],"genre_scores_gemma":[0.5014858,0.0051413868,0.17387937,0.047127455,0.24579564,0.00051703484,0.020884937,0.00028955468,0.0048787943],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984949,0.00012729666,0.00021077355,0.00064978946,0.00025034387,0.00026687176],"domain_scores_gemma":[0.99898106,0.00012208387,0.0000737382,0.00059158466,0.000033793258,0.0001977498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029725456,0.00019139485,0.0002082765,0.000049055707,0.00037273116,0.0003356459,0.00045571136,0.00001927052,0.0000127172725],"category_scores_gemma":[0.0000988241,0.00013637729,0.000029197208,0.00032230886,0.000031103307,0.00007782555,0.0008115674,0.00015151173,0.00008102456],"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":[0.00008317706,0.0000585783,0.000077393146,0.000079250975,0.00006154649,0.000033343636,0.00062506105,0.057237282,0.000009731558,0.010359739,0.92176795,0.009606977],"study_design_scores_gemma":[0.0003965056,0.00007638138,0.00023671048,0.000035716792,0.000021550635,0.000010575335,0.00021379664,0.21293917,0.000011914306,0.00000568068,0.785882,0.00016997519],"about_ca_topic_score_codex":0.0001332745,"about_ca_topic_score_gemma":0.0000045581205,"teacher_disagreement_score":0.66317755,"about_ca_system_score_codex":0.000016514148,"about_ca_system_score_gemma":0.000012160907,"threshold_uncertainty_score":0.55613047},"labels":[],"label_agreement":null},{"id":"W4287307637","doi":"10.1007/s10619-022-07415-9","title":"Scalable probabilistic truss decomposition using central limit theorem and H-index","year":2022,"lang":"en","type":"article","venue":"Distributed and Parallel Databases","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Truss; Probabilistic logic; Computer science; Scalability; Algorithm; Discrete mathematics; Mathematical optimization; Mathematics; Theoretical computer science; Artificial intelligence; Structural engineering","score_opus":0.023529447674205426,"score_gpt":0.2592946132143147,"score_spread":0.23576516554010926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287307637","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":[0.4049857,0.000497689,0.59207195,0.00016462075,0.0001549918,0.00018659026,0.0018000688,0.00009052829,0.00004786251],"genre_scores_gemma":[0.99166405,0.000038667135,0.0070608123,0.000121394434,0.000029536064,0.000021377671,0.0010477655,0.000006386646,0.000010030649],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876344,0.00017599868,0.00016435186,0.00039597342,0.00017076285,0.00032945292],"domain_scores_gemma":[0.99935174,0.00012677125,0.00006561842,0.0002982117,0.000022701473,0.00013492999],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024393726,0.00014622945,0.0001552192,0.000055974455,0.00076098484,0.00013876097,0.0002717157,0.000017767392,0.000040815386],"category_scores_gemma":[0.00002575158,0.00013762168,0.00003441615,0.00027942212,0.000107597676,0.0004276234,0.00048106388,0.00014299488,0.0000010594842],"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":[0.00020758153,0.0005250002,0.020290913,0.00010695104,0.00008127795,0.00016419089,0.0006178394,0.018735083,0.0008504321,0.94632804,0.00080530957,0.011287353],"study_design_scores_gemma":[0.001535854,0.00021228343,0.023202006,0.000054921282,0.00005898236,0.0005314091,0.0005169058,0.9079427,0.00029542626,0.05790239,0.0070697414,0.00067737955],"about_ca_topic_score_codex":0.000060128725,"about_ca_topic_score_gemma":0.0000056151634,"teacher_disagreement_score":0.8892076,"about_ca_system_score_codex":0.000026866712,"about_ca_system_score_gemma":0.000034908793,"threshold_uncertainty_score":0.58529574},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4405880184","doi":"10.1007/s10619-024-07450-8","title":"Infomod: information-theoretic machine learning model diagnostics","year":2024,"lang":"en","type":"article","venue":"Distributed and Parallel Databases","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Automatic summarization; Computer science; SPARK (programming language); Debugging; Process (computing); Machine learning; Artificial intelligence; Ranging; Test data; Data mining; Programming language","score_opus":0.01595322642870192,"score_gpt":0.25958549389043345,"score_spread":0.24363226746173153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405880184","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":[0.0015333446,0.0014740947,0.9942979,0.00060377584,0.00019693843,0.00010848644,0.00081591116,0.00050723716,0.00046230125],"genre_scores_gemma":[0.92196196,0.0017931056,0.06916732,0.000313899,0.00008437326,0.000029529809,0.006547315,0.000017584929,0.00008489645],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988517,0.00006975053,0.0002718606,0.00027672562,0.00024177728,0.0002881825],"domain_scores_gemma":[0.9988809,0.00055033015,0.000062368,0.00033274107,0.00005259276,0.00012104284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002694633,0.00019877522,0.00016669436,0.00012369646,0.00028131678,0.00047470361,0.00040252658,0.000047536534,0.000027944123],"category_scores_gemma":[0.0007550444,0.00017617606,0.000045111457,0.0003575732,0.00008458475,0.0021157109,0.0005146616,0.00042872512,0.00007791847],"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":[0.000009948129,0.000016569596,0.0018230833,0.00012931402,0.000029958863,0.00004264705,0.0005468507,0.38964677,0.0000053036447,0.59373605,0.0031160114,0.01089747],"study_design_scores_gemma":[0.00019108166,0.000022455932,0.00015763167,0.00007584573,0.000019194635,0.000027690263,0.00003772495,0.94830775,0.000013938463,0.0035454002,0.047381617,0.00021967903],"about_ca_topic_score_codex":0.00006155226,"about_ca_topic_score_gemma":0.000005829277,"teacher_disagreement_score":0.9251306,"about_ca_system_score_codex":0.000025170284,"about_ca_system_score_gemma":0.00008031782,"threshold_uncertainty_score":0.71842515},"labels":[],"label_agreement":null},{"id":"W4406162498","doi":"10.1007/s10619-024-07452-6","title":"Indexing temporal relations for range-duration queries","year":2025,"lang":"en","type":"article","venue":"Distributed and Parallel Databases","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Università degli Studi di Padova","keywords":"Search engine indexing; Computer science; Data structure; Range (aeronautics); Duration (music); Information retrieval; Data mining; Programming language","score_opus":0.02640828025020287,"score_gpt":0.2848948208440601,"score_spread":0.25848654059385723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406162498","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":[0.00067842304,0.00028469943,0.9943663,0.0019082695,0.00015987943,0.00023551795,0.001816469,0.00011501868,0.00043543294],"genre_scores_gemma":[0.5084632,0.00036569452,0.41350865,0.0011785892,0.00020753985,0.00039386482,0.07113906,0.000017362461,0.004726061],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993157,0.00002153697,0.00017201602,0.0002531282,0.00007450849,0.00016313212],"domain_scores_gemma":[0.99946433,0.00011538497,0.00005304766,0.00029044654,0.000042092004,0.00003467742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017042569,0.000092236696,0.00010016858,0.000074408745,0.00030119406,0.00021096894,0.00023405212,0.000020534222,0.000007252578],"category_scores_gemma":[0.0001099519,0.00008541193,0.00002714769,0.00026154652,0.00003621555,0.0011336651,0.00020157962,0.000045737223,0.0000045902693],"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":[0.000022066775,0.00005312148,0.01800357,0.000058983,0.000043777945,0.0000038008434,0.00005555782,0.00006483351,0.000015677026,0.85632515,0.109101295,0.016252177],"study_design_scores_gemma":[0.0011137186,0.000036273683,0.018307064,0.00008377077,0.000038404884,0.0000017234375,0.00016300805,0.108963385,0.0000940402,0.009143189,0.8617762,0.00027923143],"about_ca_topic_score_codex":0.00005865975,"about_ca_topic_score_gemma":0.00007725712,"teacher_disagreement_score":0.847182,"about_ca_system_score_codex":0.000011084265,"about_ca_system_score_gemma":0.000033938173,"threshold_uncertainty_score":0.34829974},"labels":[],"label_agreement":null},{"id":"W7117103606","doi":"10.1007/s10619-025-07455-x","title":"Revisiting shared registers and leaderless consensus in WAN environments","year":2025,"lang":"en","type":"article","venue":"Distributed and Parallel Databases","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Latency (audio); Throughput; Overhead (engineering); Protocol (science); Process (computing); Communications protocol; Distributed database","score_opus":0.029226334190379503,"score_gpt":0.2739984755017218,"score_spread":0.24477214131134228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117103606","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":[0.20244919,0.011609473,0.76992726,0.0063843695,0.00035433704,0.0007628359,0.006690975,0.0001831168,0.0016384177],"genre_scores_gemma":[0.99493897,0.00033857377,0.002942839,0.0003116697,0.000021881142,0.000026563828,0.0012242058,0.000005441769,0.00018986853],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985963,0.000088417,0.00034067422,0.00053232553,0.00013119048,0.00031109422],"domain_scores_gemma":[0.9992031,0.00014495318,0.00009500386,0.00044942248,0.000014922255,0.000092630435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023321595,0.00018304108,0.00028328272,0.00007612633,0.0001570488,0.0001757918,0.00027760435,0.00004782351,0.0000031998159],"category_scores_gemma":[0.00008429666,0.00017633247,0.000026715354,0.0002812249,0.00011325505,0.00026205427,0.00027379577,0.00013349936,0.000004107217],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035171752,0.00061493396,0.39512965,0.0020175679,0.00033496573,0.0014530547,0.00171797,0.0011106846,0.0037511187,0.37435403,0.063722976,0.15544133],"study_design_scores_gemma":[0.0058936565,0.00006415704,0.40691924,0.0028126559,0.000051534513,0.00014449566,0.0016268655,0.063957475,0.0003483693,0.0009222291,0.5159166,0.0013427412],"about_ca_topic_score_codex":0.00016388098,"about_ca_topic_score_gemma":0.000034881345,"teacher_disagreement_score":0.79248977,"about_ca_system_score_codex":0.00002877446,"about_ca_system_score_gemma":0.000029597053,"threshold_uncertainty_score":0.719063},"labels":[],"label_agreement":null}]}