{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":329,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":329,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"416db036aa93","filters":{"venue":"Proceedings of the VLDB Endowment"}},"results":[{"id":"W2591700809","doi":"10.14778/3137628.3137631","title":"HoloClean","year":2017,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":454,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency","keywords":"Leverage (statistics); Computer science; Probabilistic logic; Inference; Tuple; Data mining; Statistical model; Machine learning; Artificial intelligence; Mathematics","authors":[{"name":"Theodoros Rekatsinas","is_ca":false},{"name":"Xu Chu","is_ca":true},{"name":"Ihab F. Ilyas","is_ca":true},{"name":"Christopher Ré","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2284211371904144,"gpt":0.4286142488382545,"spread":0.2001931116478401,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002889255,0.00009153604,0.0001748362,0.00006363964,0.0004877773,0.000574952,0.003819774,0.00002560655,0.0001365203],"category_scores_gemma":[0.002600801,0.00005030314,0.0001240365,0.0001049913,0.0002273848,0.0005424615,0.001896428,0.00007774967,0.0001689178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002283535,"about_ca_system_score_gemma":0.00001058732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008488551,"about_ca_topic_score_gemma":0.000009997489,"domain_scores_codex":[0.9979413,0.000008699308,0.000385802,0.0002964365,0.001182719,0.0001850265],"domain_scores_gemma":[0.9982606,0.00006705589,0.0006783588,0.0007305088,0.0002083848,0.00005513363],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000058013,0.000232636,0.03047157,0.0000459695,0.00006966102,9.36723e-7,0.001220038,0.000004676824,0.008127528,0.494772,0.3383624,0.1266346],"study_design_scores_gemma":[0.0007907638,0.00009693258,0.1417979,0.00007219232,0.0000428309,0.000004126095,0.002640583,0.0001000451,0.08212352,0.2827421,0.4893618,0.0002272432],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.581025,0.00004108088,0.00008783965,0.02444974,0.001043692,0.000571433,0.00002828331,0.0000391925,0.3927137],"genre_scores_gemma":[0.9901442,0.00001429161,0.0004617177,0.0003847261,0.0000597516,0.00001297408,2.207737e-7,0.000005049163,0.008917073],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4091192,"threshold_uncertainty_score":0.7098153,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1991635064","doi":"10.14778/2047485.2047492","title":"A data-based approach to social influence maximization","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":426,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Maximization; Submodular set function; Computer science; Scalability; Perspective (graphical); Set (abstract data type); Function (biology); Expectation–maximization algorithm; Social graph; Social network (sociolinguistics); Mathematical optimization; Theoretical computer science; Artificial intelligence; Social media; Mathematics; Maximum likelihood; World Wide Web; Statistics","authors":[{"name":"Amit Goyal","is_ca":true},{"name":"Francesco Bonchi","is_ca":false},{"name":"Laks V. S. Lakshmanan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05672051885013572,"gpt":0.261899610639344,"spread":0.2051790917892083,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001897652,0.0001078313,0.000147904,0.00005497216,0.0001026118,0.0000262754,0.0008376284,0.00001696663,0.00003992527],"category_scores_gemma":[0.000007701671,0.00008083672,0.0000703746,0.0003376387,0.00003948303,0.000129089,0.0004174236,0.0000717825,0.000003525869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002244541,"about_ca_system_score_gemma":0.00001825403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001718112,"about_ca_topic_score_gemma":8.928153e-7,"domain_scores_codex":[0.9991882,0.000005196845,0.0002068232,0.000237837,0.0002049617,0.0001569235],"domain_scores_gemma":[0.9994437,0.000005939384,0.0001827156,0.0001961257,0.0001363718,0.00003515072],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000259692,0.003268426,0.311396,0.0002379323,0.000737233,1.195329e-7,0.007647622,0.001433757,0.0393011,0.5405243,0.05879339,0.03640039],"study_design_scores_gemma":[0.002720632,0.0003543933,0.116855,0.0003289368,0.001238319,0.000001704302,0.002716396,0.05931924,0.663236,0.120175,0.03104957,0.002004891],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.74912,0.00002038936,0.06211278,0.0005928532,0.00007950699,0.00201412,0.0001760467,0.000237267,0.185647],"genre_scores_gemma":[0.9810469,1.998131e-7,0.01863574,0.00008277109,0.00007859983,0.000078779,0.00001437151,0.00001094837,0.00005167943],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6239349,"threshold_uncertainty_score":0.3296426,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2128248866","doi":"10.14778/1687627.1687734","title":"k-automorphism","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":407,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Popularity; Computer science; Extension (predicate logic); Personally identifiable information; Automorphism; Computer security; Data mining; Theoretical computer science; Mathematics; Discrete mathematics; Programming language","authors":[{"name":"Lei Zou","is_ca":false},{"name":"Lei Chen","is_ca":false},{"name":"M. TAMER ÖZSU","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01853108214018638,"gpt":0.2408935676521065,"spread":0.2223624855119201,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0003042698,0.000130169,0.0001490177,0.00008489699,0.00009359395,0.00008655194,0.02850315,0.00005899453,0.000006290463],"category_scores_gemma":[0.003006293,0.00008920152,0.0000746543,0.0004999337,0.00007725148,0.0004739609,0.03116168,0.0001736706,0.00001451667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007222279,"about_ca_system_score_gemma":0.00002003547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008046096,"about_ca_topic_score_gemma":1.692123e-7,"domain_scores_codex":[0.9987389,0.000003494471,0.0002292386,0.0003238241,0.0004218366,0.0002826886],"domain_scores_gemma":[0.9975823,0.00002279592,0.0001979971,0.002054665,0.0001035331,0.00003875111],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000007845016,0.0002073187,0.00117547,0.00003345601,0.00003094878,0.000001732359,0.0001937856,0.000002300903,0.100619,0.2712224,0.5662294,0.06027627],"study_design_scores_gemma":[0.0002340483,0.00009770848,0.003649854,0.00005788151,0.000006760562,0.00001921213,0.0000180252,0.004077854,0.3287898,0.6580924,0.004819984,0.0001364022],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.2511491,0.0009786943,0.0184659,0.6290764,0.001755621,0.001854536,0.00001950955,0.00382399,0.09287623],"genre_scores_gemma":[0.8742734,0.00003880802,0.1249027,0.0006267154,0.00002639373,0.00001270469,2.452746e-7,0.000005003081,0.0001139947],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6284497,"threshold_uncertainty_score":0.9767531,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1967167578","doi":"10.14778/1453856.1453980","title":"Discovering data quality rules","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":268,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Data quality; Consistency (knowledge bases); Context (archaeology); Quality (philosophy); Data mining; Data integrity; Set (abstract data type); Data consistency; Process (computing); Database; Artificial intelligence; Programming language; Engineering","authors":[{"name":"Fei Chiang","is_ca":true},{"name":"Renée J. Miller","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4977714110126681,"gpt":0.451736219472416,"spread":0.04603519154025215,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004397595,0.000130477,0.0002713974,0.00008478633,0.0002555672,0.0001441013,0.004305646,0.00002819983,0.0001026041],"category_scores_gemma":[0.002536684,0.00007487221,0.00009972433,0.0003850528,0.0002239154,0.001027157,0.004286827,0.0001019861,0.0001080641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003656344,"about_ca_system_score_gemma":0.00002847438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002921453,"about_ca_topic_score_gemma":0.00002114362,"domain_scores_codex":[0.9965878,0.00003038975,0.0007538665,0.0005427183,0.001848247,0.000237037],"domain_scores_gemma":[0.9979997,0.0002321048,0.0005117372,0.00102122,0.0001685729,0.00006665223],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001759446,0.0008405626,0.07481226,0.0002131513,0.0002167386,0.000003071587,0.006253954,0.00005269947,0.01485065,0.4062716,0.4563141,0.03999534],"study_design_scores_gemma":[0.001276041,0.00009761946,0.193402,0.0001276646,0.0000712369,0.00002542461,0.007961334,0.0005190978,0.03693907,0.1190325,0.6399669,0.000581099],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9511541,0.0001286295,0.0004584321,0.005143543,0.0004836817,0.0004645401,0.0003122495,0.00004861448,0.04180622],"genre_scores_gemma":[0.9942297,0.00008732842,0.0019098,0.0003389185,0.00007437031,0.00001265945,0.000009695446,0.000007553263,0.003329965],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2872391,"threshold_uncertainty_score":0.8001034,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1982177147","doi":"10.14778/2002974.2002976","title":"gStore","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":263,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"SPARQL; RDF; Computer science; Information retrieval; Named graph; RDF Schema; Linked data; RDF query language; Scalability; RDF/XML; Pruning; Database; Semantic Web; Web search query; Web query classification; Search engine","authors":[{"name":"Lei Zou","is_ca":false},{"name":"Jinghui Mo","is_ca":false},{"name":"Lei Chen","is_ca":false},{"name":"M. TAMER ÖZSU","is_ca":true},{"name":"Dongyan Zhao","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03354416418142819,"gpt":0.1981530133423381,"spread":0.1646088491609099,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001443584,0.00007600151,0.00009837752,0.00003412347,0.0000550835,0.00002318322,0.001268918,0.00002497789,0.00001279026],"category_scores_gemma":[0.00004235516,0.00004504311,0.0000656561,0.0001573988,0.00005501151,0.0001973509,0.0004484648,0.00005672749,0.00001302117],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001831989,"about_ca_system_score_gemma":0.0000129936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005067094,"about_ca_topic_score_gemma":0.000001377173,"domain_scores_codex":[0.9993467,0.000002160139,0.0001345906,0.0001614137,0.0001948608,0.0001602484],"domain_scores_gemma":[0.9996161,0.00001043795,0.0001088263,0.0001591509,0.00007678627,0.00002862939],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001123495,0.0001523143,0.03272223,0.00005737561,0.00004083428,0.000001073483,0.006593833,3.738356e-7,0.01666407,0.9240162,0.006840174,0.01290024],"study_design_scores_gemma":[0.0003984756,0.0001541466,0.08009625,0.00006930476,0.00002064928,0.00002966485,0.0005568363,0.0003625821,0.8206781,0.09256896,0.004855524,0.0002095442],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6743295,0.0004640163,0.00353139,0.003103982,0.001500434,0.0005940977,0.000001088068,0.000379041,0.3160965],"genre_scores_gemma":[0.9817498,0.00001167217,0.01773129,0.0001543643,0.00002174989,0.00001263175,1.87641e-8,0.000003192883,0.0003152723],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8314473,"threshold_uncertainty_score":0.2357987,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2170712852","doi":"10.14778/2536258.2536262","title":"Discovering denial constraints","year":2013,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":252,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Rotation formalisms in three dimensions; Scalability; Inference; Data integrity; Set (abstract data type); Functional dependency; Constraint (computer-aided design); Theoretical computer science; Rank (graph theory); Semantics (computer science); Function (biology); Data mining; Artificial intelligence; Programming language; Database; Relational database","authors":[{"name":"Xu Chu","is_ca":true},{"name":"Ihab F. Ilyas","is_ca":false},{"name":"Paolo Papotti","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08220481571088507,"gpt":0.3393964871060694,"spread":0.2571916713951843,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001305985,0.0001071175,0.0001825213,0.00008216985,0.0001122423,0.0003418665,0.001353482,0.00002590699,0.000868397],"category_scores_gemma":[0.0009329253,0.00005968237,0.0001148648,0.0003120233,0.0002400005,0.0006437655,0.0009307045,0.00008061975,0.0003529665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003492704,"about_ca_system_score_gemma":0.00001526653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001441624,"about_ca_topic_score_gemma":0.0000064045,"domain_scores_codex":[0.997828,0.00001201534,0.0004927954,0.0002883651,0.001155006,0.0002238247],"domain_scores_gemma":[0.9990573,0.0001238607,0.0003090717,0.0002336129,0.0002084695,0.00006767515],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004327157,0.0003753887,0.02458625,0.0001030803,0.0001466641,7.799481e-7,0.003554245,0.00004184867,0.07121547,0.4192651,0.2756597,0.2050082],"study_design_scores_gemma":[0.002179143,0.0002256634,0.1044187,0.0002417505,0.00009922904,0.00002333847,0.02333618,0.0007154183,0.2072443,0.4940276,0.1667424,0.0007462656],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9038038,0.00002545494,0.0003354985,0.005718539,0.0005744038,0.0007748185,0.00002142963,0.00003255562,0.08871349],"genre_scores_gemma":[0.9960927,0.00000693625,0.0008359857,0.0003572128,0.00005345259,0.00004491731,4.54364e-7,0.000005284103,0.002603044],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.204262,"threshold_uncertainty_score":0.9508338,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2406955896","doi":"10.14778/2732219.2732227","title":"Multi-core, main-memory joins","year":2013,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":247,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Computer science; Hash join; Joins; Merge sort; Parallel computing; Join (topology); sort; Merge (version control); Hash function; Merge algorithm; SIMD; Theoretical computer science; Sorting algorithm; Database; Programming language; Mathematics","authors":[{"name":"Çagri Balkesen","is_ca":false},{"name":"Gustavo Alonso","is_ca":false},{"name":"Jens Teubner","is_ca":false},{"name":"M. TAMER ÖZSU","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02508474588165716,"gpt":0.2397200588904825,"spread":0.2146353130088254,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001533138,0.0001712422,0.0001798211,0.0001008997,0.0001148744,0.00008625915,0.002377629,0.00005808849,0.00001778731],"category_scores_gemma":[0.0002036774,0.000114009,0.00008094415,0.0004083772,0.0001604684,0.0009050202,0.001970917,0.000181897,0.00008834002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001070652,"about_ca_system_score_gemma":0.00002149247,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005671849,"about_ca_topic_score_gemma":0.000001836605,"domain_scores_codex":[0.9986787,0.000002545661,0.0002637907,0.0003662337,0.0003469688,0.0003417549],"domain_scores_gemma":[0.9990351,0.00002954086,0.000246015,0.0004837526,0.0001519597,0.00005363136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000005622714,0.000372277,0.002475321,0.000132,0.00006200668,0.00000252169,0.001093522,0.00004898954,0.7358164,0.1632742,0.03409733,0.06261987],"study_design_scores_gemma":[0.00126318,0.0001760992,0.01330714,0.0001462955,0.00001930143,0.00006153323,0.000941706,0.01063828,0.8745214,0.09271867,0.005639162,0.0005671781],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8213486,0.0009483462,0.1331439,0.01520786,0.002027973,0.005024507,0.00004097075,0.003246342,0.01901154],"genre_scores_gemma":[0.7174404,0.00003140084,0.2813375,0.000275948,0.00002286394,0.000148039,3.528418e-7,0.00001224741,0.0007312035],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1481936,"threshold_uncertainty_score":0.4649151,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2548122763","doi":"10.14778/2994509.2994514","title":"ActiveClean","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":244,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"MNIST database; Computer science; Context (archaeology); Support vector machine; Data mining; Convergence (economics); Process (computing); Class (philosophy); Iterative and incremental development; Machine learning; Artificial intelligence; Deep learning","authors":[{"name":"Sanjay Krishnan","is_ca":false},{"name":"Jiannan Wang","is_ca":true},{"name":"Eugene Wu","is_ca":false},{"name":"Michael J. Franklin","is_ca":false},{"name":"Ken Goldberg","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.009115700324434017,"gpt":0.2121947867126384,"spread":0.2030790863882044,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002455014,0.00006172685,0.00006522557,0.00003417992,0.00006358518,0.00003427575,0.0009108183,0.00001755708,0.00001058924],"category_scores_gemma":[0.0001236381,0.00002905918,0.0000414636,0.0001489794,0.00003619854,0.0003022806,0.0003272137,0.00004717764,0.00002646544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003386122,"about_ca_system_score_gemma":0.00001160415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009090244,"about_ca_topic_score_gemma":2.792583e-7,"domain_scores_codex":[0.999399,0.000006654332,0.0001172592,0.0001828491,0.0001766334,0.0001175978],"domain_scores_gemma":[0.9995267,0.00003516491,0.0001479358,0.0001874553,0.00007123804,0.00003150084],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000005092331,0.00004358792,0.005162852,0.00001270583,0.00001072455,3.301596e-8,0.0002485394,2.972087e-7,0.3499639,0.3406787,0.002692454,0.3011811],"study_design_scores_gemma":[0.0006386968,0.0001065241,0.07652286,0.0001276876,0.00001114911,0.0000107853,0.00007034253,0.0008733721,0.8030983,0.02366083,0.09468397,0.0001954392],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3562582,0.0002442886,0.2771933,0.1524427,0.001813846,0.001391986,0.00001480555,0.0009568534,0.2096839],"genre_scores_gemma":[0.9882314,0.0000155887,0.01057301,0.00009126191,0.00002797692,0.00001227271,9.592381e-8,0.000003741714,0.001044702],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6319731,"threshold_uncertainty_score":0.1692542,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2621145626","doi":"10.14778/3099622.3099626","title":"Attribute-driven community search","year":2017,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":241,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Node (physics); Theoretical computer science; Relevance (law); Graph; Community structure; Cohesion (chemistry); Data mining; Mathematics; Combinatorics","authors":[{"name":"Xin Huang","is_ca":false},{"name":"Laks V. S. Lakshmanan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04102465157361466,"gpt":0.3032241378313941,"spread":0.2621994862577794,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003992121,0.0001178787,0.0002042,0.00003298868,0.0009214783,0.0001283639,0.001490695,0.00001998553,0.0001045891],"category_scores_gemma":[0.00001603418,0.00008449266,0.0001849713,0.00007309437,0.0001575961,0.0001373857,0.001180349,0.0003128576,0.000007502631],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003620216,"about_ca_system_score_gemma":0.00001500255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001413415,"about_ca_topic_score_gemma":0.000009821865,"domain_scores_codex":[0.9992111,0.0000151905,0.0001915436,0.0001225815,0.0002438831,0.0002156724],"domain_scores_gemma":[0.9989951,0.00002920504,0.0002797107,0.000463671,0.0001853656,0.00004698851],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001227167,0.0002732651,0.9129953,0.00003240821,0.0002106703,5.489399e-8,0.000570152,0.00001904423,0.02006343,0.05141855,0.007716234,0.006688601],"study_design_scores_gemma":[0.00103002,0.0001501722,0.2870824,0.0002759038,0.00023448,0.000001382974,0.001667131,0.001562728,0.6484465,0.05085787,0.008218663,0.0004727438],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9562356,0.0000103338,0.0001491237,0.0007569417,0.00004505531,0.0002888524,0.0000146492,0.00003533994,0.04246411],"genre_scores_gemma":[0.9987271,0.000003187533,0.0006295879,0.00001723156,0.0001229577,0.0000324204,0.000002595528,0.00001094974,0.0004539333],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.628383,"threshold_uncertainty_score":0.7087359,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2544486974","doi":"10.14778/2994509.2994518","title":"Detecting data errors","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":237,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"University of California Berkeley","keywords":"Computer science; Raw data; Outlier; Data mining; Set (abstract data type); Variety (cybernetics); Data quality; Ground truth; Anomaly detection; Quality (philosophy); Big data; Data science; Machine learning; Artificial intelligence; Engineering","authors":[{"name":"Ziawasch Abedjan","is_ca":false},{"name":"Xu Chu","is_ca":true},{"name":"Dong Deng","is_ca":false},{"name":"Raul Castro Fernandez","is_ca":false},{"name":"Ihab F. Ilyas","is_ca":true},{"name":"Mourad Ouzzani","is_ca":false},{"name":"Paolo Papotti","is_ca":false},{"name":"Michael Stonebraker","is_ca":false},{"name":"Nan Tang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3097609978046282,"gpt":0.4126229492891771,"spread":0.1028619514845489,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00496573,0.0001076389,0.0001800164,0.0001027757,0.0001386065,0.0001218161,0.004188958,0.00002737488,0.0001856214],"category_scores_gemma":[0.00501184,0.00004614924,0.00007127508,0.0004263165,0.0001240579,0.0007866435,0.003694214,0.00005910585,0.0001515044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003851822,"about_ca_system_score_gemma":0.00001678737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004514522,"about_ca_topic_score_gemma":0.00001874168,"domain_scores_codex":[0.9973492,0.00001971414,0.0005474916,0.0004984864,0.001347826,0.000237257],"domain_scores_gemma":[0.9980723,0.0003440704,0.000466794,0.0008638618,0.0001922365,0.00006070064],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007913954,0.0001948257,0.01391979,0.00005613091,0.0001070928,6.834094e-7,0.0009899496,0.000002379312,0.0868101,0.07285151,0.2312869,0.5937015],"study_design_scores_gemma":[0.001125774,0.0001114514,0.009615254,0.0002392657,0.0000709224,0.00000861578,0.004676851,0.0001844982,0.1827602,0.1383543,0.6625121,0.0003408301],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8245145,0.0002048905,0.003952549,0.05824431,0.002426374,0.001678293,0.000400624,0.0001991761,0.1083793],"genre_scores_gemma":[0.9943935,0.00001976695,0.00126447,0.0003069742,0.0000648686,0.00001158121,6.593079e-7,0.000007325316,0.003930863],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5933607,"threshold_uncertainty_score":0.7784196,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2970992672","doi":"10.14778/3352063.3352116","title":"Data lake management","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":236,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"TD Bank Group; University of Toronto","funders":"","keywords":"Metadata; Data management; Metadata management; Data science; Data management plan; Computer science; Data integration; Software versioning; Data mapping; Data extraction; Data element; Research data; Data virtualization; Data curation; Database; World Wide Web; Software","authors":[{"name":"Fatemeh Nargesian","is_ca":true},{"name":"Erkang Zhu","is_ca":true},{"name":"Renée J. Miller","is_ca":false},{"name":"Ken Q. Pu","is_ca":false},{"name":"Patricia C. Arocena","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.190965546163535,"gpt":0.3896089267691528,"spread":0.1986433806056178,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003986794,0.0001340955,0.0002335676,0.0001350364,0.0000818218,0.000221756,0.005522825,0.00002794514,0.0008325573],"category_scores_gemma":[0.0002932887,0.00007762691,0.00008796646,0.0005859726,0.0000711519,0.0006484029,0.005744299,0.00009131345,0.000896293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002484521,"about_ca_system_score_gemma":0.00000963265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001333288,"about_ca_topic_score_gemma":0.00002571617,"domain_scores_codex":[0.9966341,0.00001660896,0.0005898306,0.000625041,0.001880161,0.0002542783],"domain_scores_gemma":[0.9979554,0.0001045313,0.0003983375,0.001337419,0.0001476777,0.00005667681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006041762,0.0002915908,0.01453879,0.0001911041,0.000173583,8.728077e-7,0.0003863852,0.00002188333,0.00112191,0.3760752,0.5550478,0.05209047],"study_design_scores_gemma":[0.0004677484,0.0000371259,0.01089679,0.00005279854,0.00004019351,0.000001624575,0.001976713,0.0002219013,0.001609044,0.03270717,0.9518612,0.0001277166],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2131897,0.000132185,0.0002619935,0.01205264,0.002108751,0.0025781,0.0005677844,0.00009785569,0.769011],"genre_scores_gemma":[0.9499258,0.00007182606,0.002698324,0.00122611,0.00006681453,0.00003066623,0.00002150233,0.00001461448,0.04594429],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7367362,"threshold_uncertainty_score":0.9998816,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2148524305","doi":"10.14778/1687627.1687771","title":"Framework for evaluating clustering algorithms in duplicate detection","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":232,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Scalability; Cluster analysis; Data mining; Data deduplication; Process (computing); Algorithm; Machine learning; Database","authors":[{"name":"Oktie Hassanzadeh","is_ca":true},{"name":"Fei Chiang","is_ca":true},{"name":"Hyun‐Chul Lee","is_ca":false},{"name":"Renée J. Miller","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2418184006816228,"gpt":0.4629068859449667,"spread":0.2210884852633439,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005075376,0.0001091063,0.0002029045,0.0001135759,0.0001278313,0.0001587514,0.0008756947,0.00004947625,0.00001426738],"category_scores_gemma":[0.002896374,0.00007238074,0.0001082241,0.0005809948,0.00003186712,0.000297467,0.000285715,0.000116083,0.000009187585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008238278,"about_ca_system_score_gemma":0.000007840089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002863098,"about_ca_topic_score_gemma":0.0000124774,"domain_scores_codex":[0.9978746,0.00001702597,0.000615692,0.0003701682,0.0008803767,0.0002421305],"domain_scores_gemma":[0.9988445,0.000290364,0.0004058883,0.0002213299,0.0001998074,0.00003808988],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001424575,0.0001694117,0.0004795575,0.0000515358,0.00001755442,1.209039e-7,0.001515742,0.0005510604,0.02940103,0.02867866,0.0007374,0.9382555],"study_design_scores_gemma":[0.0009947035,0.000488859,0.0156783,0.0002255205,0.00003471868,0.000003028395,0.002768579,0.04831654,0.1217076,0.8047684,0.004770796,0.0002428983],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6674408,0.0001613238,0.3053354,0.01622593,0.001238609,0.004116622,0.00002894418,0.0001130461,0.005339356],"genre_scores_gemma":[0.9677308,0.000009590512,0.03142178,0.0004800568,0.00006276392,0.00009428709,4.545223e-7,0.000005713973,0.0001945318],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9380126,"threshold_uncertainty_score":0.3467439,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2131164945","doi":"10.14778/2367502.2367512","title":"Solving big data challenges for enterprise application performance management","year":2012,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":232,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Scalability; Big data; Data science; Context (archaeology); Analytics; Instrumentation (computer programming); Data management; Enterprise system; System monitoring; Database; Data mining; Operating system","authors":[{"name":"Tilmann Rabl","is_ca":true},{"name":"Sergio Gómez-Villamor","is_ca":false},{"name":"Mohammad Sadoghi","is_ca":true},{"name":"Víctor Muntés-Mulero","is_ca":false},{"name":"Hans‐Arno Jacobsen","is_ca":true},{"name":"Serge Mankovskii","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0504586435494311,"gpt":0.2445988120777852,"spread":0.1941401685283541,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008809931,0.0001428866,0.0001352056,0.00007748249,0.0001846294,0.00005755069,0.002611291,0.00002620164,4.464295e-7],"category_scores_gemma":[0.0000153469,0.0001012193,0.00006350873,0.0001803034,0.0000296357,0.0001113316,0.003052684,0.00006653109,0.000005970372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005730093,"about_ca_system_score_gemma":0.000004858753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004316537,"about_ca_topic_score_gemma":3.160828e-7,"domain_scores_codex":[0.9986486,0.000004967377,0.0002523644,0.0003754897,0.0003473158,0.0003712794],"domain_scores_gemma":[0.9989534,0.0000296101,0.0002397541,0.0006539021,0.0000636092,0.00005970939],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001463677,0.0003582774,0.002619779,0.0008979289,0.000117672,4.889231e-8,0.001931207,0.0001315,0.0008722499,0.05681726,0.00227077,0.9339687],"study_design_scores_gemma":[0.00250801,0.0003141684,0.03949105,0.0009266238,0.0002833625,0.0000233279,0.001932313,0.474215,0.03387995,0.004166326,0.4411833,0.001076529],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.655544,0.008390632,0.2229202,0.01774422,0.0053523,0.007983917,0.00001634658,0.0009174457,0.08113093],"genre_scores_gemma":[0.9845365,0.0002106015,0.01436515,0.000108363,0.000286751,0.0001456365,0.000001048362,0.00001133142,0.0003346382],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9328921,"threshold_uncertainty_score":0.4852472,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2126547925","doi":"10.14778/1920841.1920906","title":"MRShare","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":226,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Cloud computing; Batch processing; Context (archaeology); Distributed computing; Work (physics); Core (optical fiber); Database; Operating system","authors":[{"name":"Tomasz Nykiel","is_ca":true},{"name":"Michalis Potamias","is_ca":false},{"name":"Chaitanya Mishra","is_ca":false},{"name":"George Kollios","is_ca":false},{"name":"Nick Koudas","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.00697231335455234,"gpt":0.1997996891760867,"spread":0.1928273758215344,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002550583,0.0000976347,0.00009825522,0.00004920797,0.0001224923,0.00008758754,0.001674938,0.00002970877,0.00001305193],"category_scores_gemma":[0.0000473151,0.00006109384,0.00009173327,0.000269053,0.00004210942,0.00002692252,0.001153652,0.0001825974,0.0000162326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001449014,"about_ca_system_score_gemma":0.00001002284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002088127,"about_ca_topic_score_gemma":0.000001980927,"domain_scores_codex":[0.9990791,0.000002451865,0.0001650133,0.0002293113,0.0003246512,0.0001994395],"domain_scores_gemma":[0.9994557,0.00001774385,0.0001382958,0.0002484497,0.00009119038,0.00004857686],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000009839376,0.0004079017,0.01109603,0.0002186367,0.0001042343,0.000001731585,0.003184283,0.0002091081,0.1863864,0.6587075,0.03838572,0.1012887],"study_design_scores_gemma":[0.001717699,0.00027508,0.04126248,0.0003179252,0.0000616391,0.00008286138,0.0004586955,0.05616618,0.5817854,0.04708451,0.2698802,0.0009073716],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9452204,0.00003054032,0.0002851711,0.006609385,0.0009145095,0.0002850375,7.886839e-7,0.0001654886,0.04648865],"genre_scores_gemma":[0.9932321,9.289201e-7,0.005277921,0.0002243837,0.00009662097,0.00001277568,5.494284e-8,0.00000563298,0.001149583],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.611623,"threshold_uncertainty_score":0.3112479,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2293703278","doi":"10.14778/3402707.3402744","title":"Publishing set-valued data via differential privacy","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":221,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Differential privacy; Computer science; Data publishing; Data mining; Scalability; Context (archaeology); Data anonymization; Set (abstract data type); Information privacy; Information retrieval; Theoretical computer science; Publishing; Database; Computer security","authors":[{"name":"Rui Chen","is_ca":true},{"name":"Noman Mohammed","is_ca":true},{"name":"Benjamin C. M. Fung","is_ca":true},{"name":"Bipin C. Desai","is_ca":true},{"name":"Li Xiong","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09995646936477759,"gpt":0.2744083175834562,"spread":0.1744518482186786,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0007836958,0.0002447771,0.0002623517,0.0001545944,0.0001783764,0.0005190451,0.1031015,0.0001258516,0.00004012382],"category_scores_gemma":[0.01089578,0.0001728468,0.00007911601,0.0006397457,0.0001704245,0.004645349,0.2920184,0.0004204892,0.00001360174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009029468,"about_ca_system_score_gemma":0.00004559404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000186633,"about_ca_topic_score_gemma":0.000002300416,"domain_scores_codex":[0.9974089,0.00001540294,0.0004538022,0.000827536,0.0007850889,0.0005093186],"domain_scores_gemma":[0.9915843,0.00004407513,0.0004808494,0.007611141,0.000193217,0.00008640517],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006733322,0.0007428727,0.01430419,0.0003292755,0.0003607973,0.000005118408,0.002959404,3.544156e-7,0.06076613,0.09714977,0.7552817,0.06803305],"study_design_scores_gemma":[0.001096923,0.0001434653,0.009421084,0.000224236,0.00007516977,0.00004923243,0.0001709238,0.05237533,0.3627039,0.5688383,0.004299026,0.0006024253],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5678421,0.0006575212,0.2858705,0.08721219,0.0065385,0.004067027,0.0003283499,0.005286196,0.04219767],"genre_scores_gemma":[0.7982678,0.00002402643,0.2014234,0.0001243139,0.00006184972,0.00002887456,0.000008562542,0.00001779102,0.00004337865],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7509827,"threshold_uncertainty_score":0.9974359,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2212315060","doi":"10.14778/2856318.2856323","title":"Approximate closest community search in networks","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Caching and Content Delivery","field":"Computer Science","cited_by":217,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Truss; Computer science; Approximation algorithm; Greedy algorithm; Set (abstract data type); Graph; Efficient algorithm; Theoretical computer science; Mathematical optimization; Mathematics; Combinatorics; Algorithm","authors":[{"name":"Xin Huang","is_ca":true},{"name":"Laks V. S. Lakshmanan","is_ca":true},{"name":"Jeffrey Xu Yu","is_ca":false},{"name":"Hong Cheng","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05422769107867213,"gpt":0.2469106196643252,"spread":0.1926829285856531,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001346144,0.0001024941,0.0001484435,0.00007331387,0.0001023339,0.00009381591,0.001531793,0.00003721478,6.610103e-7],"category_scores_gemma":[0.00006138361,0.00007303118,0.00006101358,0.0003813476,0.00005598464,0.0002628202,0.001057972,0.0004145954,0.000003663639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001030643,"about_ca_system_score_gemma":0.00003404179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008669284,"about_ca_topic_score_gemma":0.00001775596,"domain_scores_codex":[0.9989927,0.00003895423,0.0002087159,0.0001533329,0.0003514692,0.0002547886],"domain_scores_gemma":[0.9993865,0.00004217857,0.00008796383,0.0002519308,0.0001537572,0.00007765728],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003983334,0.003895231,0.3617154,0.0005708845,0.0002297787,0.00001280246,0.04613966,0.01878104,0.03827805,0.4338373,0.02230639,0.07383508],"study_design_scores_gemma":[0.005202832,0.0008092553,0.02996845,0.0007908072,0.00003948416,0.0001036247,0.006622553,0.877474,0.04458502,0.03193763,0.00149377,0.0009725695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9864669,0.000186424,0.00212052,0.001173174,0.0002944132,0.0003084979,8.952773e-7,0.00007872068,0.009370391],"genre_scores_gemma":[0.9988436,0.00001598276,0.000771196,0.0001697008,0.00003006535,0.0000184576,3.153482e-7,0.000005782942,0.0001449477],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8586929,"threshold_uncertainty_score":0.2978125,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W808055529","doi":"10.14778/2850578.2850581","title":"From competition to complementarity","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":216,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Complementarity (molecular biology); Computer science; Maximization; Competition (biology); Mathematical optimization; Cellular automaton; Set (abstract data type); Margin (machine learning); Theoretical computer science; Artificial intelligence; Machine learning; Mathematics","authors":[{"name":"Wei Lu","is_ca":true},{"name":"Wei Chen","is_ca":false},{"name":"Laks V. S. Lakshmanan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0274108720421482,"gpt":0.2739003839945476,"spread":0.2464895119523994,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001659081,0.0001021819,0.0001680766,0.0000366609,0.00005494357,0.00003417901,0.0003500013,0.00001002839,0.000248222],"category_scores_gemma":[0.000004862364,0.00007728636,0.00009467141,0.000188131,0.00002664167,0.0000660825,0.0003275182,0.0000708693,0.00001701224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006660913,"about_ca_system_score_gemma":0.00001322288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002687273,"about_ca_topic_score_gemma":0.00001908755,"domain_scores_codex":[0.9992025,0.000005731352,0.0002135987,0.0001673506,0.0002655124,0.0001452768],"domain_scores_gemma":[0.9994872,0.00001335083,0.000136297,0.0001168008,0.0001604417,0.00008586152],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00008203529,0.0006288564,0.4073399,0.00001583208,0.0003945342,9.84115e-8,0.00310975,0.0001018984,0.04268632,0.3564099,0.1794319,0.009798964],"study_design_scores_gemma":[0.001377281,0.0002068868,0.01831036,0.0001815042,0.0002436925,4.54109e-7,0.004154325,0.000972848,0.3997891,0.4613099,0.1129638,0.0004898339],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.961085,0.00001375396,0.001761724,0.001652821,0.0001151243,0.0004903999,0.00005702271,0.00005710674,0.03476708],"genre_scores_gemma":[0.9941154,2.711365e-7,0.005347482,0.0001109262,0.0002593559,0.00004595522,0.00001492134,0.000007818317,0.00009788688],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3890295,"threshold_uncertainty_score":0.4062371,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2291620117","doi":"10.14778/2850469.2850471","title":"K-core decomposition of large networks on a single PC","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":214,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Decomposition; Implementation; Core (optical fiber); Metric (unit); Graph; Multi-core processor; Vertex (graph theory); Theoretical computer science; Parallel computing; Algorithm","authors":[{"name":"Wissam Khaouid","is_ca":true},{"name":"Marina Barsky","is_ca":true},{"name":"Venkatesh Srinivasan","is_ca":true},{"name":"Alex Thomo","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03872705365176489,"gpt":0.2674381582051575,"spread":0.2287111045533927,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004854322,0.0001043164,0.0001476297,0.00006495639,0.00006162973,0.00003066371,0.0007489573,0.00003748217,0.00000230686],"category_scores_gemma":[0.00003253711,0.00007150745,0.00009612005,0.0003256519,0.00004476551,0.0001916101,0.0002917486,0.00009273659,0.000003084686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003742294,"about_ca_system_score_gemma":0.00001228692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004021636,"about_ca_topic_score_gemma":3.415276e-7,"domain_scores_codex":[0.999089,0.000008435948,0.0002071204,0.0001882059,0.0003082777,0.000198966],"domain_scores_gemma":[0.9993529,0.00002716046,0.0002195235,0.0001602786,0.0001722473,0.00006793695],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009773434,0.001020113,0.001915587,0.00005892437,0.00006399117,0.00000102843,0.002683525,0.0009016492,0.03965887,0.9423572,0.002753726,0.008487668],"study_design_scores_gemma":[0.00212539,0.001475176,0.001559494,0.0004379577,0.00004336684,0.00003017535,0.0004968683,0.05340236,0.7251322,0.2134905,0.001447493,0.0003590166],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9472895,0.0002370289,0.03318288,0.001154628,0.001051487,0.0006156883,0.000007126313,0.0001291706,0.01633245],"genre_scores_gemma":[0.9958159,0.000003565747,0.003884388,0.000171841,0.00004873957,0.00001191627,4.93178e-7,0.000005771841,0.00005734892],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7288666,"threshold_uncertainty_score":0.2915989,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2111607365","doi":"10.14778/1687627.1687727","title":"Distance-join","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":207,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Reachability; Join (topology); Graph; Theoretical computer science; Query optimization; Shortest path problem; Data mining; Mathematics; Combinatorics","authors":[{"name":"Lei Zou","is_ca":false},{"name":"Lei Chen","is_ca":false},{"name":"M. TAMER ÖZSU","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.006708040847259433,"gpt":0.2017328283834329,"spread":0.1950247875361735,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002380526,0.00009968995,0.0001139967,0.00004226512,0.0001025072,0.00006288253,0.001150644,0.00002235302,0.000005090124],"category_scores_gemma":[0.00002376777,0.00006389889,0.00009797885,0.0003516093,0.00004410175,0.0002768878,0.0001550382,0.00008518712,0.000006999832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002200326,"about_ca_system_score_gemma":0.00000958292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001856344,"about_ca_topic_score_gemma":1.220936e-7,"domain_scores_codex":[0.9991654,0.000004138079,0.0001675892,0.0002033222,0.0002597719,0.0001998134],"domain_scores_gemma":[0.9995786,0.0000124418,0.0001231679,0.0001677677,0.00007104229,0.00004697769],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000005583996,0.00008432592,0.0002975663,0.000009975845,0.000007881727,3.385319e-7,0.0005244343,0.000004427763,0.01656543,0.9604617,0.001017672,0.02102064],"study_design_scores_gemma":[0.0004583646,0.0001904768,0.006579966,0.00008686649,0.00001124568,0.00001658393,0.0001006456,0.001393803,0.3070242,0.6775364,0.006393623,0.0002077344],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5986049,0.001445427,0.1071811,0.03910148,0.002734032,0.002176824,0.00001096872,0.0009812367,0.247764],"genre_scores_gemma":[0.9914644,0.00001197622,0.007607733,0.0004128946,0.00003723623,0.00000730535,7.754238e-8,0.000002892321,0.000455514],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3928594,"threshold_uncertainty_score":0.2605721,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2294111665","doi":"10.14778/2732951.2732960","title":"Scalable logging through emerging non-volatile memory","year":2014,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":206,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Commit; Scalability; Computer science; Logging; Dram; Bottleneck; Embedded system; Overhead (engineering); Cache; Operating system; Computer hardware; Database; Forestry","authors":[{"name":"Tianzheng Wang","is_ca":true},{"name":"Ryan Johnson","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.009201764651845435,"gpt":0.2140710501752543,"spread":0.2048692855234089,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001940666,0.0001741041,0.0002076383,0.00003844881,0.0001550614,0.00002263235,0.0003183558,0.00003879784,0.00001997051],"category_scores_gemma":[0.00004329647,0.0001345571,0.00008979337,0.0001876901,0.00003839089,0.0002772388,0.0001583296,0.0001982115,0.00001044745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000529348,"about_ca_system_score_gemma":0.000004195781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006243041,"about_ca_topic_score_gemma":3.668105e-7,"domain_scores_codex":[0.9990234,0.000003300463,0.000263407,0.000185475,0.0002022166,0.0003222413],"domain_scores_gemma":[0.9996544,0.00004177193,0.00009565453,0.0001193565,0.0000462632,0.00004252495],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001448583,0.0000304635,0.0009134886,0.0006078284,0.00004886808,3.573366e-7,0.001410668,0.05018933,0.9315732,0.001758967,0.00262349,0.01082893],"study_design_scores_gemma":[0.0003271814,0.00003021841,0.0002418198,0.0001959442,0.00002127989,0.000007456677,0.0002239712,0.04334547,0.9474207,0.003379397,0.004614752,0.000191773],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.938687,0.0001706074,0.002993606,0.0001668234,0.000660261,0.0002932851,0.00000109827,0.0002785905,0.05674876],"genre_scores_gemma":[0.9965774,0.00002353102,0.002780261,0.00009665233,0.00017426,0.00001587193,3.578977e-7,0.00003306024,0.0002986309],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05789041,"threshold_uncertainty_score":0.5487079,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2281494333","doi":"10.14778/2732977.2732980","title":"An experimental comparison of pregel-like graph processing systems","year":2014,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":194,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; PageRank; Graph; Global Positioning System; Theoretical computer science; Operating system","authors":[{"name":"Minyang Han","is_ca":true},{"name":"Khuzaima Daudjee","is_ca":true},{"name":"Khaled Ammar","is_ca":true},{"name":"M. TAMER ÖZSU","is_ca":true},{"name":"Xingfang Wang","is_ca":true},{"name":"Tianqi Jin","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01446843168368664,"gpt":0.2619565896032245,"spread":0.2474881579195378,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005404567,0.000166133,0.0002948778,0.0001039607,0.0001590739,0.0001137468,0.001488606,0.00004601939,0.000001874752],"category_scores_gemma":[0.00001424586,0.0001154004,0.0001043307,0.000378179,0.0001356247,0.0005377532,0.0002542168,0.0001047914,0.000001290614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000232192,"about_ca_system_score_gemma":0.0000162564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001706076,"about_ca_topic_score_gemma":2.42743e-7,"domain_scores_codex":[0.9985229,0.0000259634,0.0004213991,0.0003184341,0.0004688017,0.0002425093],"domain_scores_gemma":[0.9990125,0.00002345284,0.0004659955,0.0002550271,0.0001629223,0.00008010418],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003878691,0.001202476,0.009021328,0.0004813844,0.00004875325,1.468379e-7,0.01126399,0.0004860153,0.5828564,0.3839421,0.0002863892,0.01037217],"study_design_scores_gemma":[0.0005098546,0.0004999023,0.0006072192,0.0002745086,0.00001900689,0.000009795583,0.001905418,0.06426916,0.9246236,0.006785608,0.0002866952,0.0002092025],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9746047,0.001003672,0.01968969,0.00009614123,0.0007305464,0.0006141273,0.000002396478,0.0001428028,0.003115919],"genre_scores_gemma":[0.9953004,0.000002031,0.00453549,0.00002842945,0.00004443857,0.00004208576,3.511678e-7,0.00001007792,0.00003666986],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3771565,"threshold_uncertainty_score":0.4705893,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2798664493","doi":"10.14778/3192965.3192973","title":"Table union search on open data","year":2018,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":193,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Table (database); Computer science; Benchmark (surveying); Data mining; Set (abstract data type); Semantic search; Domain (mathematical analysis); Ontology; Decision table; Probabilistic logic; Information retrieval; Search engine; Artificial intelligence; Mathematics; Programming language","authors":[{"name":"Fatemeh Nargesian","is_ca":true},{"name":"Erkang Zhu","is_ca":true},{"name":"Ken Q. Pu","is_ca":false},{"name":"Renée J. Miller","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4805425545209558,"gpt":0.4884253644300699,"spread":0.007882809909114052,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.01025841,0.0001084626,0.000195496,0.0001102498,0.0002647666,0.0006400906,0.01024161,0.00002553353,0.0004610213],"category_scores_gemma":[0.001331878,0.00006089952,0.0000335905,0.0007900212,0.0002026631,0.001010727,0.01295218,0.0001049761,0.0004453454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003409791,"about_ca_system_score_gemma":0.00004092453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004345713,"about_ca_topic_score_gemma":0.00004147274,"domain_scores_codex":[0.9969523,0.0000432489,0.0004378641,0.000614234,0.001692751,0.0002595937],"domain_scores_gemma":[0.9979764,0.000156895,0.0002506188,0.001158114,0.0003871694,0.00007080311],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007519912,0.0002059809,0.0009332173,0.00001290875,0.00002840523,1.563479e-7,0.0004069704,0.000003335607,0.002379407,0.1044471,0.8579091,0.0335983],"study_design_scores_gemma":[0.000430178,0.0002302428,0.001860879,0.00006300217,0.0000130843,0.00000114046,0.001742479,0.0004170132,0.04895037,0.02350083,0.922684,0.000106814],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1439259,0.00005370688,0.0005731527,0.06921851,0.001668451,0.002985392,0.0004888851,0.0000736525,0.7810124],"genre_scores_gemma":[0.9754143,0.00002897564,0.001730507,0.003336686,0.0001356275,0.00002306954,0.00001300143,0.00001198877,0.01930586],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8314884,"threshold_uncertainty_score":0.9951134,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2751694342","doi":"10.14778/3137628.3137630","title":"Trajectory similarity join in spatial networks","year":2017,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":179,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"Beijing Nova Program; King Abdullah University of Science and Technology; National Natural Science Foundation of China; Innovationsfonden","keywords":"Join (topology); Computer science; Pruning; Similarity (geometry); Trajectory; Nearest neighbor search; Heuristic; Matching (statistics); Data mining; Scheduling (production processes); Algorithm; Theoretical computer science; Artificial intelligence; Mathematics; Mathematical optimization","authors":[{"name":"Shuo Shang","is_ca":true},{"name":"Lisi Chen","is_ca":false},{"name":"Zhewei Wei","is_ca":false},{"name":"Christian S. Jensen","is_ca":false},{"name":"Kai Zheng","is_ca":false},{"name":"Panos Kalnis","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01795752554889163,"gpt":0.2326463657509419,"spread":0.2146888402020503,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004762782,0.0001147106,0.000147587,0.00005779784,0.0002043526,0.0003233687,0.002783312,0.0000347733,0.000006704161],"category_scores_gemma":[0.00006288499,0.00008335499,0.00006796947,0.00009639008,0.00007470499,0.0008001223,0.001557235,0.0001495145,0.000003372309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004123908,"about_ca_system_score_gemma":0.00001220457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002954345,"about_ca_topic_score_gemma":0.00005232555,"domain_scores_codex":[0.9989737,0.000005084467,0.0002060454,0.0002776475,0.0002881765,0.0002493987],"domain_scores_gemma":[0.9992309,0.00001206393,0.0002590413,0.0004156951,0.00004380436,0.00003855012],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00008183008,0.001203579,0.2482929,0.0003980296,0.0001467031,0.00001722348,0.002130505,0.0006340799,0.005901243,0.2337164,0.03370338,0.4737741],"study_design_scores_gemma":[0.002774164,0.0001968186,0.7102966,0.0003220814,0.00004247234,0.000006086137,0.0001228642,0.2255824,0.03072217,0.01845042,0.01079493,0.0006890012],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.611132,0.0006899948,0.1207894,0.0340441,0.009884554,0.005164852,0.00003494446,0.0006155878,0.2176446],"genre_scores_gemma":[0.9957062,0.00003447791,0.003697341,0.0001359032,0.0001067913,0.00002028274,4.767567e-7,0.000005522338,0.0002929757],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4730851,"threshold_uncertainty_score":0.5172132,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2005499394","doi":"10.14778/2168651.2168658","title":"Dense subgraph maintenance under streaming edge weight updates for real-time story identification","year":2012,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":172,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Enhanced Data Rates for GSM Evolution; Identification (biology); Social media; Globe; Scale (ratio); Point (geometry); Data science; Edge device; Range (aeronautics); Social network (sociolinguistics); World Wide Web; Artificial intelligence; Geography; Mathematics; Engineering","authors":[{"name":"Albert Angel","is_ca":true},{"name":"Nikos Sarkas","is_ca":true},{"name":"Nick Koudas","is_ca":true},{"name":"Divesh Srivastava","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0132090247020189,"gpt":0.2384151435654986,"spread":0.2252061188634797,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006221068,0.0001234175,0.0001312776,0.00007071628,0.0002387768,0.00009514148,0.000970941,0.0000363739,0.000003709798],"category_scores_gemma":[0.00004234499,0.00009408485,0.00008700402,0.0002870941,0.00006796048,0.0006674593,0.0002703213,0.00007253347,0.000019318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007704707,"about_ca_system_score_gemma":0.00002182009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001834517,"about_ca_topic_score_gemma":6.298242e-7,"domain_scores_codex":[0.9989182,0.000006334805,0.0002469689,0.0002812808,0.0002249435,0.000322222],"domain_scores_gemma":[0.9990567,0.00007127695,0.0002969279,0.0003005978,0.0001982198,0.00007630842],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001292214,0.0004172147,0.002134425,0.0001158259,0.00009172467,5.46532e-8,0.001879664,0.000008658285,0.347117,0.5531856,0.04869983,0.046337],"study_design_scores_gemma":[0.001516584,0.0001499862,0.07202521,0.0003276091,0.0002020034,0.00003702205,0.001259285,0.03445954,0.7972062,0.04403552,0.04781608,0.0009650009],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7876935,0.0008398109,0.1883656,0.01246155,0.001818225,0.003366261,0.000218545,0.0006089368,0.004627535],"genre_scores_gemma":[0.9329337,0.00009321036,0.06498047,0.00009990918,0.0001632036,0.0003291957,0.00001156774,0.00001868499,0.001370076],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5091501,"threshold_uncertainty_score":0.3836669,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2133246278","doi":"10.14778/1453856.1453895","title":"Efficient search for the top-k probable nearest neighbors in uncertain databases","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":149,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Data mining; Query optimization; Online aggregation; k-nearest neighbors algorithm; Query language; Semantics (computer science); Information retrieval; Sargable; Object (grammar); Point (geometry); Database; Feature (linguistics); Web query classification; Web search query; Search engine; Artificial intelligence","authors":[{"name":"George Beskales","is_ca":true},{"name":"Mohamed A. Soliman","is_ca":true},{"name":"Ihab F. Ilyas","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05346318793657699,"gpt":0.2715280562480217,"spread":0.2180648683114447,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006452869,0.0001281898,0.0001361242,0.00008646279,0.000266293,0.00009554292,0.001869526,0.00001552029,0.000005675796],"category_scores_gemma":[0.00006846619,0.00007130609,0.00006995328,0.0006123806,0.0001055648,0.0002618988,0.001130636,0.0001058427,0.000005242524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006247049,"about_ca_system_score_gemma":0.00004495695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001971336,"about_ca_topic_score_gemma":0.000007067521,"domain_scores_codex":[0.9985974,0.000007216346,0.0002319851,0.0003326134,0.0004692359,0.0003615712],"domain_scores_gemma":[0.9993073,0.0001152242,0.0001000381,0.0003355957,0.0001031643,0.00003867878],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001579421,0.001646169,0.07907028,0.0006771564,0.0001951438,0.000008744637,0.006120609,0.02463807,0.003978821,0.796243,0.04499962,0.04226441],"study_design_scores_gemma":[0.004220396,0.0003902789,0.04706459,0.0004220211,0.00006859218,0.00002580775,0.001528066,0.7831204,0.0797512,0.002918605,0.07962988,0.0008601595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8509537,0.00151265,0.08600765,0.03346977,0.002081388,0.0124648,0.0001696182,0.0003754961,0.01296495],"genre_scores_gemma":[0.9737758,0.00007928286,0.02437377,0.0003293639,0.00009826134,0.0002922222,0.000005310293,0.00001474321,0.001031264],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7933244,"threshold_uncertainty_score":0.3474076,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2263157912","doi":"10.14778/2777598.2777604","title":"Giraph unchained","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Graph Theory and Algorithms","field":"Computer Science","cited_by":145,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Asynchronous communication; Computer science; Scalability; Computation; Synchronization (alternating current); Distributed computing; Bulk synchronous parallel; Graph; Parallel computing; Model of computation; Theoretical computer science; Algorithm; Computer network; Operating system","authors":[{"name":"Minyang Han","is_ca":true},{"name":"Khuzaima Daudjee","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01784287209176177,"gpt":0.2045423580511298,"spread":0.186699485959368,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005284773,0.0001049482,0.0001204823,0.00006554927,0.00006842081,0.00005789895,0.001294556,0.00002751794,0.000003592986],"category_scores_gemma":[0.00006864707,0.00006644407,0.00008978057,0.0004470847,0.00006702289,0.0002758444,0.0004647293,0.00008348611,0.00001221543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002863823,"about_ca_system_score_gemma":0.00002752375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007572339,"about_ca_topic_score_gemma":1.953481e-7,"domain_scores_codex":[0.9990572,0.000007187637,0.0001711054,0.0002034064,0.0003593831,0.000201657],"domain_scores_gemma":[0.99939,0.00001632228,0.0001321786,0.0001803482,0.0001832018,0.00009794727],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001310532,0.0001099081,0.001106457,0.00002251225,0.00003021914,6.090736e-7,0.002252881,0.00002505738,0.01006072,0.9759554,0.004424277,0.005998838],"study_design_scores_gemma":[0.00131237,0.000283117,0.0008901194,0.00007830159,0.00002107766,0.00003574569,0.0006269273,0.005190035,0.3124523,0.6690939,0.009709193,0.0003068535],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.782061,0.000887935,0.02929216,0.01640356,0.00435679,0.001724463,0.000009095242,0.0008121827,0.1644528],"genre_scores_gemma":[0.9900244,0.000004040994,0.00901067,0.0002543683,0.00005022741,0.00001886357,1.070539e-7,0.000005529686,0.0006317592],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3068615,"threshold_uncertainty_score":0.2709511,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3085364681","doi":"10.14778/3415478.3415562","title":"Data collection and quality challenges for deep learning","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":145,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Feature engineering; Deep learning; Data collection; Big data; Data science; Software; Data mining","authors":[{"name":"Steven Euijong Whang","is_ca":true},{"name":"Jae-Gil Lee","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1284582489283515,"gpt":0.3110977474383105,"spread":0.182639498509959,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002457347,0.00005433211,0.00008237451,0.00001586779,0.0001602956,0.00003964957,0.0005892426,0.00002226572,9.328311e-7],"category_scores_gemma":[0.00009299544,0.00004134062,0.00002502368,0.0001489436,0.00002322384,0.0001835234,0.0005234082,0.0000624755,4.671265e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001281825,"about_ca_system_score_gemma":0.000006592554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008911918,"about_ca_topic_score_gemma":0.000001719747,"domain_scores_codex":[0.999429,0.000004350586,0.0001365836,0.0002497307,0.0001021425,0.00007821957],"domain_scores_gemma":[0.9996014,0.00003064546,0.000139619,0.0001184174,0.00007515113,0.0000347991],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004798514,0.0001197802,0.001822355,0.0005275249,0.00006703479,2.937659e-8,0.004295507,0.00001438758,0.07864595,0.6292531,0.002535056,0.2826712],"study_design_scores_gemma":[0.001327588,0.0009906711,0.01302388,0.00007684271,0.00006673175,0.00001298656,0.002236707,0.2485432,0.4241993,0.03144207,0.2775256,0.0005544057],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03894528,0.001535561,0.8831534,0.06631579,0.0001273695,0.002198731,0.0000148469,0.0006774585,0.007031583],"genre_scores_gemma":[0.9614473,0.0004223336,0.03774157,0.0001573281,0.00003922248,0.0001076324,6.897483e-7,0.000004764426,0.00007916247],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.922502,"threshold_uncertainty_score":0.1685822,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4255889623","doi":"10.1145/3186728.3164139","title":"The ubiquity of large graphs and surprising challenges of graph processing","year":2017,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":145,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Suite; Scalability; Visualization; Graph; Software; Data science; Theoretical computer science; World Wide Web; Data mining; Programming language; Database","authors":[{"name":"Siddhartha Sahu","is_ca":true},{"name":"Amine Mhedhbi","is_ca":true},{"name":"Semih Salihoğlu","is_ca":true},{"name":"Jimmy Lin","is_ca":true},{"name":"M. TAMER ÖZSU","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03165215848905461,"gpt":0.305877498930536,"spread":0.2742253404414814,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007855187,0.00008632643,0.000161366,0.00005110719,0.0004098463,0.0001434559,0.001314347,0.00002591054,4.53932e-7],"category_scores_gemma":[0.000162956,0.00004995234,0.00006014198,0.0001197699,0.000218605,0.0004013394,0.0008019978,0.00005769977,1.094842e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006420699,"about_ca_system_score_gemma":0.00002178222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002105556,"about_ca_topic_score_gemma":0.00001080466,"domain_scores_codex":[0.9990892,0.000007113375,0.0002628044,0.0001679305,0.0003205966,0.0001523309],"domain_scores_gemma":[0.998675,0.00002990881,0.0007150983,0.0002859041,0.0002618183,0.00003225958],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000008498459,0.0001253394,0.008416948,0.0004422858,0.00004221077,9.78765e-8,0.002462541,9.151604e-7,0.008176235,0.9540617,0.0002186925,0.02604456],"study_design_scores_gemma":[0.001969244,0.000305938,0.09130651,0.00160589,0.0001393901,0.00001542921,0.004136856,0.01293743,0.6419738,0.2406629,0.00443533,0.0005112909],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9529137,0.007738642,0.006533025,0.01093903,0.0005543471,0.0009844365,0.00003565786,0.0001126667,0.02018849],"genre_scores_gemma":[0.9978432,0.001203145,0.0008784781,0.0000247605,0.000007285321,0.000003024291,1.350831e-7,0.000004299002,0.00003566345],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7133988,"threshold_uncertainty_score":0.3152248,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3198515637","doi":"10.14778/3476249.3476283","title":"SlimChain","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Blockchain Technology Applications and Security","field":"Computer Science","cited_by":143,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Blockchain; Scalability; Distributed computing; Database transaction; Computer network; Robustness (evolution); Distributed data store; Node (physics); Computer security; Database","authors":[{"name":"Cheng Xu","is_ca":true},{"name":"Ce Zhang","is_ca":false},{"name":"Jianliang Xu","is_ca":false},{"name":"Jian Pei","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.007848441708610996,"gpt":0.2075309755193116,"spread":0.1996825338107006,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001627938,0.00006597559,0.00009182382,0.00003088128,0.00009842859,0.00003018246,0.0009497809,0.00004653624,0.000008127463],"category_scores_gemma":[0.00004350924,0.0000478496,0.00006192339,0.0004660283,0.00005450807,0.00007211336,0.0006840191,0.0001087616,0.000006728069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002371147,"about_ca_system_score_gemma":0.00002778956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005134527,"about_ca_topic_score_gemma":0.000001277784,"domain_scores_codex":[0.9993379,0.000003078526,0.0001421733,0.0002138519,0.0001632977,0.0001397087],"domain_scores_gemma":[0.9994472,0.0000148877,0.00009312364,0.0002575285,0.0001619952,0.00002532627],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[5.057543e-7,0.00007241115,0.0006725701,0.00001272317,0.00001083479,2.986194e-7,0.0002218188,9.307327e-7,0.03515789,0.9556906,0.001527817,0.006631651],"study_design_scores_gemma":[0.0001783872,0.00001798329,0.00121148,0.00001932072,0.000006553452,0.00003002522,0.0001271186,0.001319286,0.8341488,0.1458716,0.01698284,0.00008663263],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8050135,0.001633377,0.0297914,0.09343117,0.0007254562,0.0009512082,0.000007036478,0.0007373251,0.06770957],"genre_scores_gemma":[0.9825384,0.00003128308,0.01667801,0.0003071565,0.00001593176,0.00004477183,1.341835e-7,0.000003255321,0.0003810245],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.809819,"threshold_uncertainty_score":0.195125,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963174348","doi":"10.14778/2994509.2994534","title":"LSH ensemble","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":136,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Jaccard index; Computer science; Data mining; Domain (mathematical analysis); Locality-sensitive hashing; Data structure; Data set; Set (abstract data type); Hash function; Mathematics; Cluster analysis; Hash table; Artificial intelligence","authors":[{"name":"Erkang Zhu","is_ca":true},{"name":"Fatemeh Nargesian","is_ca":true},{"name":"Ken Q. Pu","is_ca":false},{"name":"Renée J. Miller","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01131773862150246,"gpt":0.2360180883857376,"spread":0.2247003497642351,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000185335,0.00009858549,0.0001151825,0.00004465561,0.00006265881,0.00003412601,0.001077037,0.00002741466,0.000007321221],"category_scores_gemma":[0.0001139504,0.00004764201,0.00008073931,0.000247322,0.0000565943,0.0005505309,0.0005385869,0.00004971574,0.00001444116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005022846,"about_ca_system_score_gemma":0.00001560587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000370667,"about_ca_topic_score_gemma":1.579966e-7,"domain_scores_codex":[0.9991205,0.000003087012,0.0001775863,0.0002209275,0.0002731289,0.000204796],"domain_scores_gemma":[0.999418,0.00003544148,0.0001481641,0.0002022782,0.0001529271,0.00004322637],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000007125408,0.00004081479,0.0008684829,0.0000181603,0.00001025701,3.289275e-7,0.0001135073,6.117543e-8,0.678563,0.1562902,0.004964155,0.1591239],"study_design_scores_gemma":[0.0001654469,0.00006468075,0.0004327887,0.00007612592,0.00000323255,0.000007140899,0.000007675085,0.00001165163,0.9174836,0.06580421,0.01586788,0.00007553816],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04250883,0.0004496242,0.8830945,0.01294032,0.0005182425,0.0009562579,0.000004291896,0.0007452253,0.05878263],"genre_scores_gemma":[0.9593542,0.0001255179,0.03851346,0.0002420546,0.00003889057,0.00002536894,2.208931e-8,0.000007568619,0.001692888],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9168454,"threshold_uncertainty_score":0.2001421,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2080132606","doi":"10.14778/1938545.1938547","title":"Automatic wrappers for large scale web extraction","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":135,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Noise (video); Scale (ratio); Noisy data; Extraction (chemistry); Data extraction; Data mining; Information extraction; Training set; Artificial intelligence; Machine learning; Information retrieval; Pattern recognition (psychology)","authors":[{"name":"Nilesh Dalvi","is_ca":false},{"name":"Ravi Kumar","is_ca":false},{"name":"Mohamed A. Soliman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02415002081639386,"gpt":0.2448207655012949,"spread":0.2206707446849011,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004121945,0.00009426787,0.000134771,0.00008097065,0.000130293,0.0000503766,0.0008487081,0.00003029341,0.00002556905],"category_scores_gemma":[0.00004494737,0.0000645535,0.0001346095,0.0002744832,0.00002162676,0.0003980818,0.0002116503,0.00005681924,0.00001135651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002894376,"about_ca_system_score_gemma":0.00002188755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001733837,"about_ca_topic_score_gemma":0.000002911289,"domain_scores_codex":[0.9991307,0.000003793631,0.0002048558,0.0002304081,0.0002151883,0.0002150059],"domain_scores_gemma":[0.9994513,0.00002002495,0.0001993546,0.0001863106,0.00009833239,0.00004472669],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008868141,0.002929436,0.0420534,0.001262166,0.0008989658,0.000001503001,0.03905774,0.00001217746,0.3998624,0.2733877,0.08925852,0.1511873],"study_design_scores_gemma":[0.001972075,0.0003952651,0.0101086,0.0003335241,0.0002984758,0.00002913727,0.003211157,0.3443504,0.609665,0.01227753,0.01675934,0.000599567],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9398059,0.0001177666,0.03362151,0.002135886,0.0008084552,0.0009767832,0.00004161059,0.0004205003,0.02207159],"genre_scores_gemma":[0.9490006,0.000009229226,0.05049328,0.00008504764,0.00002995853,0.00005939276,7.845499e-7,0.000006423864,0.0003152729],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3443382,"threshold_uncertainty_score":0.2632415,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2110020044","doi":"10.14778/1453856.1453922","title":"A practical scalable distributed B-tree","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":135,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Distributed computing; Scalability; Tree (set theory); Fault tolerance; Distributed transaction; Concurrency; Transaction processing; Database transaction; Operating system; Database","authors":[{"name":"Marcos K. Aguilera","is_ca":false},{"name":"Wojciech Golab","is_ca":true},{"name":"Mehul A. Shah","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02628965727836388,"gpt":0.2516244494746975,"spread":0.2253347921963336,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002576579,0.0001498588,0.0002248191,0.00003509383,0.0002112618,0.00007329936,0.001002706,0.0000550194,0.000007378488],"category_scores_gemma":[0.0001446194,0.00009982893,0.0001229257,0.0005594726,0.0001070968,0.0004971574,0.0004543816,0.000155721,0.00002786018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000741856,"about_ca_system_score_gemma":0.00007026755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003974651,"about_ca_topic_score_gemma":0.000001160828,"domain_scores_codex":[0.9984473,0.000008557899,0.0003387552,0.0003205759,0.0005545869,0.0003302435],"domain_scores_gemma":[0.9990719,0.0000360399,0.0002584814,0.0002664722,0.0002662021,0.0001009235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000648429,0.001228532,0.02776888,0.0002313777,0.0001749007,0.00002607135,0.001459321,0.00005134414,0.03679095,0.5540692,0.3743352,0.003799375],"study_design_scores_gemma":[0.00539162,0.0006968215,0.0888715,0.0007559718,0.0001050511,0.002329148,0.0006004749,0.04249629,0.4776981,0.01492701,0.3644607,0.001667369],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5560932,0.0008310526,0.2756563,0.04826988,0.003262614,0.003596234,0.0002148662,0.001165575,0.1109103],"genre_scores_gemma":[0.9893275,0.00002154893,0.009862182,0.0001293186,0.00005450629,0.00004553307,0.000001534617,0.000007172541,0.0005507433],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5391422,"threshold_uncertainty_score":0.4070906,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3012550338","doi":"10.14778/3389133.3389134","title":"Dash","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":135,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Hash function; Scalability; Emulation; Hash table; Factor (programming language); Double hashing; Table (database)","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.02138445553614614,"gpt":0.2242101176233977,"spread":0.2028256620872516,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007203795,0.0000934175,0.0001155613,0.0000264413,0.00005675162,0.00004124529,0.002319901,0.00002752929,0.000004226365],"category_scores_gemma":[0.0002050888,0.00006256819,0.0000497191,0.0004225217,0.00007289151,0.000439658,0.001797208,0.0001153019,0.00001879037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003003384,"about_ca_system_score_gemma":0.00001177812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002610886,"about_ca_topic_score_gemma":1.164684e-7,"domain_scores_codex":[0.9991623,0.000001513839,0.0001537922,0.0002530019,0.0002625879,0.0001668248],"domain_scores_gemma":[0.9995285,0.00001435676,0.0001436229,0.0002039782,0.00006704888,0.00004251173],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000009833822,0.00005757588,0.001500656,0.00009057555,0.00002969021,0.000001509741,0.001278287,0.00003327442,0.1765566,0.7617239,0.02259623,0.03612184],"study_design_scores_gemma":[0.0003344827,0.0001359461,0.0005142897,0.00003400526,0.000008792299,0.000008631237,0.0002381814,0.002446759,0.9199743,0.04287207,0.03324641,0.0001861637],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2572214,0.001645049,0.3888936,0.2632277,0.001684886,0.003401158,0.00005580996,0.006458937,0.07741145],"genre_scores_gemma":[0.9240246,0.00002126965,0.07505194,0.0007989347,0.00002745344,0.00001913702,1.603173e-7,0.000005905706,0.0000505319],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7434176,"threshold_uncertainty_score":0.4310992,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2619906413","doi":"10.14778/3099622.3099623","title":"Revisiting the stop-and-stare algorithms for influence maximization","year":2017,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":132,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Education, India","keywords":"Maximization; Scalability; Computer science; Set (abstract data type); Scaling; Order (exchange); Approximation algorithm; Mathematical optimization; Algorithm; Mathematics; Economics","authors":[{"name":"Keke Huang","is_ca":false},{"name":"Sibo Wang","is_ca":false},{"name":"Glenn S. Bevilacqua","is_ca":true},{"name":"Xiaokui Xiao","is_ca":false},{"name":"Laks V. S. Lakshmanan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0194310404711445,"gpt":0.2842343860065044,"spread":0.2648033455353598,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002605816,0.00009609535,0.0001362804,0.00001762968,0.00061038,0.0001610268,0.0005178602,0.00001364628,0.000009800626],"category_scores_gemma":[0.00004187058,0.00005684004,0.00009772077,0.00004711254,0.00008218846,0.0001541217,0.0003102323,0.00007150877,3.785159e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001626297,"about_ca_system_score_gemma":0.000007866463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001175948,"about_ca_topic_score_gemma":5.201175e-7,"domain_scores_codex":[0.9993892,0.000003392644,0.0001811813,0.0001541285,0.0001335819,0.0001385254],"domain_scores_gemma":[0.9991361,0.00003365391,0.0004275284,0.0001943326,0.0001875476,0.00002078535],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004279401,0.00006747612,0.333974,0.0001999182,0.0003641763,5.769846e-8,0.001663497,0.0002631289,0.01556448,0.3004269,0.002358389,0.3450752],"study_design_scores_gemma":[0.002577603,0.0001964491,0.1952994,0.001528036,0.001132183,0.000004924774,0.003998016,0.06199943,0.3047284,0.378433,0.04891759,0.001184975],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.973484,0.0002410249,0.007414202,0.007660427,0.0001011298,0.001970093,0.00003764958,0.00007542432,0.009016015],"genre_scores_gemma":[0.9959675,0.00001038993,0.0034641,0.00003508741,0.000245358,0.0001111222,0.000001620419,0.000009367188,0.0001554287],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3438902,"threshold_uncertainty_score":0.4694611,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2162783807","doi":"10.14778/2021017.2021025","title":"Keyword search in graphs","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":132,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Substructure; Clique; Computer science; Graph; Combinatorics; Theoretical computer science; Time complexity; Mathematics; Algorithm","authors":[{"name":"Mehdi Kargar","is_ca":true},{"name":"Aijun An","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03651081320407087,"gpt":0.2195111061961708,"spread":0.1830002929920999,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004017705,0.00008809684,0.0001010769,0.0001424784,0.00004286028,0.00005669384,0.001791588,0.00001831342,0.00001677695],"category_scores_gemma":[0.00001333902,0.00006020477,0.00005333316,0.0005919952,0.00004607272,0.000541179,0.001069795,0.00009520025,0.0000154169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002281415,"about_ca_system_score_gemma":0.000009097477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001255494,"about_ca_topic_score_gemma":0.000003667571,"domain_scores_codex":[0.9990399,0.000004473394,0.0001784105,0.0002336189,0.000306961,0.0002365752],"domain_scores_gemma":[0.9996407,0.000007751302,0.00007084211,0.000193883,0.00005158335,0.00003522365],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001416894,0.0003261295,0.03940989,0.00008708902,0.0000343614,0.000002583907,0.003961796,0.00000168828,0.002874808,0.9028099,0.003258864,0.04721879],"study_design_scores_gemma":[0.002839522,0.0005142487,0.2403772,0.0004110273,0.00004117369,0.00001632068,0.001511221,0.01001033,0.4510853,0.2804068,0.01185708,0.00092981],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6515311,0.0002331193,0.003539546,0.003061783,0.001140578,0.001670766,0.000006637375,0.0002657971,0.3385507],"genre_scores_gemma":[0.9822847,0.00003951294,0.01686749,0.0001187717,0.00001440654,0.00002554233,2.550495e-7,0.000005443708,0.0006438605],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.622403,"threshold_uncertainty_score":0.3329246,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2160152607","doi":"10.14778/1687627.1687754","title":"Efficient method for maximizing bichromatic reverse nearest neighbor","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":129,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; k-nearest neighbors algorithm; Point (geometry); Best bin first; Exponential function; Algorithm; Exponential growth; Theoretical computer science; Mathematics; Artificial intelligence","authors":[{"name":"Raymond Chi-Wing Wong","is_ca":false},{"name":"M. TAMER ÖZSU","is_ca":true},{"name":"Philip S. Yu","is_ca":false},{"name":"Ada Wai-Chee Fu","is_ca":false},{"name":"Lian Liu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01458119393423405,"gpt":0.2572641271071092,"spread":0.2426829331728751,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006653243,0.00015014,0.0001924429,0.00009486605,0.0001523825,0.0001758173,0.001484499,0.00002654132,0.000004913277],"category_scores_gemma":[0.00009940144,0.0001026985,0.0001301104,0.0004159688,0.00002353691,0.000234822,0.0004301501,0.00006970707,0.000006988207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005380619,"about_ca_system_score_gemma":0.00001566073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001456355,"about_ca_topic_score_gemma":2.686304e-7,"domain_scores_codex":[0.9987003,0.000006684613,0.0002858811,0.0003376298,0.0003645704,0.0003049485],"domain_scores_gemma":[0.9992753,0.00004986282,0.0002402601,0.0002728761,0.0001051833,0.0000565302],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003504273,0.0005335892,0.0001066098,0.0003703237,0.00008671777,0.000001635318,0.001463111,0.0008019512,0.0363678,0.7219895,0.02968973,0.208554],"study_design_scores_gemma":[0.002142952,0.000513093,0.003280138,0.0003813149,0.0001333378,0.00001635071,0.0003618814,0.8581399,0.08078135,0.02961672,0.02408257,0.0005503957],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02502903,0.0002592309,0.9225783,0.02990946,0.001468002,0.003988468,0.00002602421,0.0004478864,0.01629365],"genre_scores_gemma":[0.23785,0.00001037679,0.760218,0.001074257,0.0001026116,0.00006662645,0.00000152704,0.00001157998,0.0006650704],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.857338,"threshold_uncertainty_score":0.4187925,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2112840274","doi":"10.14778/1920841.1920870","title":"Sampling the repairs of functional dependency violations under hard constraints","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":127,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Dependency (UML); Class (philosophy); Functional dependency; Context (archaeology); Sampling (signal processing); Relation (database); Data integrity; Variety (cybernetics); Space (punctuation); Data mining; Metric (unit); Theoretical computer science; Relational database; Database; Artificial intelligence","authors":[{"name":"George Beskales","is_ca":true},{"name":"Ihab F. Ilyas","is_ca":true},{"name":"Lukasz Golab","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1812498346188758,"gpt":0.3696657815601582,"spread":0.1884159469412824,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003644981,0.0001058837,0.0001723385,0.0001013614,0.0002576671,0.0001093144,0.001103403,0.00004486698,0.0007046714],"category_scores_gemma":[0.001882149,0.00005459006,0.0001697858,0.0004129858,0.0004269395,0.0002808494,0.0005194222,0.0002137205,0.00003287273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002048068,"about_ca_system_score_gemma":0.00005185003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004213702,"about_ca_topic_score_gemma":0.000041651,"domain_scores_codex":[0.9975303,0.00001934611,0.0006479094,0.000293113,0.001337835,0.0001714298],"domain_scores_gemma":[0.9980634,0.000503447,0.0005448339,0.0003689323,0.0004717317,0.00004766303],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000406563,0.0001996949,0.01277916,0.00002871053,0.0001087568,7.878107e-8,0.000861121,0.0001811694,0.08822781,0.8685724,0.01487159,0.01412882],"study_design_scores_gemma":[0.000885231,0.00008789302,0.2274871,0.0000849232,0.0001446285,0.00002148475,0.01379489,0.0007074735,0.03541622,0.6822823,0.03880276,0.0002850734],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9262955,0.00003980305,0.008185695,0.0141309,0.002090576,0.001087377,0.0001220881,0.00005823748,0.04798984],"genre_scores_gemma":[0.9962366,0.000007060673,0.00241368,0.0002966667,0.00006387834,0.00002466461,0.000001866997,0.000005380852,0.000950246],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.214708,"threshold_uncertainty_score":0.7715657,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2112485457","doi":"10.14778/1687553.1687567","title":"SQL/MapReduce","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":127,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"ASTER","funders":"","keywords":"Computer science; SQL; User-defined function; Database; Schema (genetic algorithms); Scalability; NoSQL; Programming language; Query by Example; Information retrieval","authors":[{"name":"Eric Friedman","is_ca":true},{"name":"Peter M. Pawlowski","is_ca":true},{"name":"John Cieslewicz","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.007158007447369725,"gpt":0.213177163393006,"spread":0.2060191559456363,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001584952,0.0001038212,0.0001308662,0.00003589507,0.00009432597,0.00003192481,0.0007032271,0.00002080275,0.000003663551],"category_scores_gemma":[0.00004157975,0.00006595921,0.00006772858,0.0002463196,0.00003353394,0.0005157662,0.0002496926,0.00007139684,0.000008250227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003173475,"about_ca_system_score_gemma":0.00001737993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001138572,"about_ca_topic_score_gemma":3.770277e-7,"domain_scores_codex":[0.9991041,0.000002977394,0.0002009987,0.0002206678,0.0002774581,0.000193755],"domain_scores_gemma":[0.9994609,0.00001042687,0.0001609584,0.0002192288,0.0001013213,0.00004717627],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00000512731,0.00005884986,0.0001797322,0.00002298997,0.000008067452,3.353711e-7,0.0005211383,0.000009028319,0.08138123,0.8991455,0.00402295,0.01464509],"study_design_scores_gemma":[0.0005473328,0.0002320386,0.004775483,0.0002083285,0.0000124734,0.00005018084,0.0002590401,0.0007015427,0.8459881,0.03051051,0.1164014,0.0003135896],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5029984,0.002710842,0.2237486,0.04296666,0.003924058,0.00352778,0.00005251259,0.001339072,0.218732],"genre_scores_gemma":[0.9544168,0.00002069933,0.04440263,0.0003687771,0.000072006,0.00001430739,2.881128e-7,0.00000426927,0.0007002581],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8686349,"threshold_uncertainty_score":0.2689739,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2970828623","doi":"10.14778/3342263.3342645","title":"Efficient algorithms for densest subgraph discovery","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":115,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Induced subgraph isomorphism problem; Intuition; Computer science; Subgraph isomorphism problem; Graph; Algorithm; Color-coding; Efficient algorithm; Theoretical computer science; Artificial intelligence; Line graph","authors":[{"name":"Yixiang Fang","is_ca":false},{"name":"Kaiqiang Yu","is_ca":false},{"name":"Reynold Cheng","is_ca":false},{"name":"Laks V. S. Lakshmanan","is_ca":true},{"name":"Xuemin Lin","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01307049411882908,"gpt":0.2375503892464292,"spread":0.2244798951276001,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002558508,0.0001201804,0.0001464833,0.00005796587,0.0001106982,0.0001638606,0.001266123,0.00002853155,0.000002470348],"category_scores_gemma":[0.00002714729,0.00008098593,0.0001265006,0.0003459824,0.00004304125,0.0001957762,0.0004372188,0.00006559136,0.00001470716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003672066,"about_ca_system_score_gemma":0.00002880273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002165705,"about_ca_topic_score_gemma":4.30241e-7,"domain_scores_codex":[0.9988986,0.00000206414,0.0002182576,0.0003518796,0.0002872511,0.0002418988],"domain_scores_gemma":[0.9992806,0.00005470656,0.0001805778,0.0003013,0.0001376661,0.00004518603],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002552519,0.0007830472,0.004875159,0.0002989809,0.0001269396,2.279367e-7,0.00154999,0.000533874,0.0851652,0.8348223,0.01042683,0.06139191],"study_design_scores_gemma":[0.002906623,0.0006408296,0.01424708,0.0003904539,0.0001027835,0.00004434141,0.0007752433,0.5267554,0.3926595,0.01994577,0.04054733,0.0009846651],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8442253,0.0002037985,0.1422397,0.004165852,0.001301415,0.002864289,0.0001296975,0.000196548,0.004673449],"genre_scores_gemma":[0.8976334,0.00001020788,0.1006229,0.0001706586,0.00006740246,0.0002434801,0.000002723724,0.00001392484,0.001235227],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8148766,"threshold_uncertainty_score":0.3302511,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2571118757","doi":"10.14778/3015274.3015276","title":"Mostly-optimistic concurrency control for highly contended dynamic workloads on a thousand cores","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":113,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Concurrency control; Server; Parallel computing; Concurrency; Cache; Distributed computing; Cache coherence; Lock (firearm); Deadlock; Out-of-order execution; Serialization; Operating system; CPU cache; Database transaction; Cache algorithms; Database","authors":[{"name":"Tianzheng Wang","is_ca":true},{"name":"Hideaki Kimura","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01018218956139474,"gpt":0.2339998161680842,"spread":0.2238176266066894,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003453586,0.0002291472,0.0003610725,0.00005467453,0.0001387084,0.0001026934,0.001190371,0.00006489713,0.000004073122],"category_scores_gemma":[0.0001750818,0.0001207017,0.000179368,0.0001909494,0.000110221,0.000213188,0.0001275743,0.00007953036,0.000006892104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001150072,"about_ca_system_score_gemma":0.00004643147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006334392,"about_ca_topic_score_gemma":0.000001336979,"domain_scores_codex":[0.9983288,0.00001097251,0.0004317517,0.0004376986,0.0003912149,0.0003995704],"domain_scores_gemma":[0.99866,0.0002108793,0.0004082284,0.0002706223,0.0003541246,0.00009616707],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003662731,0.0003741017,0.001573476,0.0002322303,0.0002022657,0.000001499414,0.0003936431,0.0000472342,0.09846205,0.8396074,0.009755659,0.04898416],"study_design_scores_gemma":[0.08865922,0.01068121,0.02884931,0.01110188,0.0007503956,0.0001987048,0.0007438637,0.1768942,0.3712588,0.1887504,0.1167854,0.005326575],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2023318,0.001689224,0.7294819,0.03651856,0.005851727,0.009331218,0.001171501,0.0008308275,0.01279321],"genre_scores_gemma":[0.9975842,0.00001640853,0.001159628,0.0002157243,0.00004757536,0.0002776519,7.779945e-7,0.00001341575,0.0006845674],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7952524,"threshold_uncertainty_score":0.4922074,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2154768509","doi":"10.14778/1453856.1453934","title":"Efficient network aware search in collaborative tagging sites","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":112,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Popularity; Cluster analysis; Seekers; Context (archaeology); Upper and lower bounds; Heuristic; Space (punctuation); Information retrieval; Data mining; Machine learning; Artificial intelligence; Mathematics; Geography","authors":[{"name":"Sihem Amer Yahia","is_ca":false},{"name":"Michael Benedikt","is_ca":false},{"name":"Laks V. S. Lakshmanan","is_ca":true},{"name":"Julia Stoyanovich","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01881665465521546,"gpt":0.234770653360951,"spread":0.2159539987057356,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004507724,0.000127004,0.0001617635,0.0001044174,0.000209384,0.00008293162,0.001223513,0.00002281735,0.000006480933],"category_scores_gemma":[0.00002787121,0.00009111875,0.00004750331,0.001356482,0.00008518548,0.0002350158,0.001141363,0.0001244018,0.000012019],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007358609,"about_ca_system_score_gemma":0.00003586738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002436385,"about_ca_topic_score_gemma":0.000002508333,"domain_scores_codex":[0.9986108,0.00001107836,0.0002300781,0.0003123915,0.0004804363,0.0003552412],"domain_scores_gemma":[0.999478,0.00003446865,0.0001174334,0.0001795552,0.0001457147,0.00004486928],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001379444,0.002117882,0.3075927,0.0006833361,0.0003070988,0.00007817216,0.03836222,0.07795362,0.01675978,0.4020542,0.1266204,0.02733276],"study_design_scores_gemma":[0.003544638,0.0004587737,0.06893806,0.0007742585,0.00003844188,0.00003655937,0.003186815,0.8175385,0.08590493,0.0046848,0.0136972,0.001197056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9747671,0.0003598276,0.00432007,0.004400143,0.0004886439,0.001326805,0.000009366853,0.000155966,0.01417211],"genre_scores_gemma":[0.9895294,0.00004859355,0.00972097,0.0001813168,0.00006970335,0.00003373873,0.000001108805,0.000007004335,0.0004082226],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7395849,"threshold_uncertainty_score":0.3715715,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2106019582","doi":"10.14778/2168651.2168659","title":"ReStore","year":2012,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":110,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Workflow; Dataflow; Reuse; Compiler; Implementation; Distributed computing; Operating system; Database; Parallel computing; Programming language","authors":[{"name":"Iman Elghandour","is_ca":true},{"name":"Ashraf Aboulnaga","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01353766561554491,"gpt":0.214237238605279,"spread":0.2006995729897341,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003976145,0.00009276303,0.00009712346,0.00004705067,0.00011129,0.00004214681,0.001120659,0.00002209936,0.000003579471],"category_scores_gemma":[0.00003120966,0.00005749734,0.00008428506,0.000273333,0.00003477031,0.00004614578,0.001031963,0.00008366512,0.00001575536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000470994,"about_ca_system_score_gemma":0.000006161911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001392122,"about_ca_topic_score_gemma":1.222684e-7,"domain_scores_codex":[0.9990551,0.000004963289,0.0001607754,0.000150987,0.0003411742,0.0002869682],"domain_scores_gemma":[0.9995247,0.00001724453,0.0001370614,0.0002016133,0.00005328462,0.00006611553],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001025185,0.0005322625,0.0612186,0.0001832841,0.0001077233,4.186104e-7,0.00724387,0.0002104505,0.01208643,0.8255869,0.04391252,0.04890731],"study_design_scores_gemma":[0.002030363,0.0003621193,0.1902403,0.0005743729,0.0001257511,0.00009711232,0.001399259,0.02019307,0.2969293,0.02123257,0.4655862,0.001229626],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9262439,0.0004253931,0.0007928025,0.004179642,0.001007963,0.0003272264,3.336213e-7,0.0001770926,0.06684566],"genre_scores_gemma":[0.9938557,0.000002775768,0.004481283,0.0002197078,0.0001489635,0.00001074469,2.884124e-8,0.000005476519,0.001275351],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8043543,"threshold_uncertainty_score":0.2344673,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2156972533","doi":"10.14778/1920841.1920874","title":"SECRET","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Semantics (computer science); Key (lock); Variation (astronomy); Range (aeronautics); Window (computing); World Wide Web; Programming language; Computer security; Engineering","authors":[{"name":"Irina Botan","is_ca":false},{"name":"Roozbeh Derakhshan","is_ca":false},{"name":"Nihal Dindar","is_ca":false},{"name":"Laura M. Haas","is_ca":false},{"name":"Renée J. Miller","is_ca":true},{"name":"Nesime Tatbul","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.004724064018066928,"gpt":0.2012143182637794,"spread":0.1964902542457125,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001909494,0.00008440694,0.0001025615,0.00002915083,0.00008796471,0.00002889835,0.0006923235,0.00002504261,0.0000115589],"category_scores_gemma":[0.0000602712,0.000051671,0.00005470856,0.0001768017,0.00005752678,0.0004168763,0.0005016081,0.0001326866,0.000009644829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001001267,"about_ca_system_score_gemma":0.00001747913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002632655,"about_ca_topic_score_gemma":0.000005604445,"domain_scores_codex":[0.9992595,0.000001738615,0.0001610836,0.0001832469,0.0002369283,0.0001574476],"domain_scores_gemma":[0.9994668,0.0000141569,0.0001429391,0.0002274675,0.0001034573,0.00004512004],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00000171374,0.0000179469,0.0009403786,0.00002377364,0.000005811545,1.415648e-7,0.0002592755,7.534778e-7,0.211792,0.7832291,0.001404011,0.002325126],"study_design_scores_gemma":[0.0003081737,0.00004991636,0.002313363,0.00005412216,0.000006324271,0.00004152394,0.0001267801,0.0005778935,0.7238536,0.01219036,0.2602943,0.0001835694],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8400179,0.0001891433,0.06407565,0.00690811,0.004650925,0.001296728,0.00003563113,0.0004597484,0.08236623],"genre_scores_gemma":[0.9273098,0.000006218129,0.07184654,0.0001370672,0.00009145513,0.00002926734,3.273509e-7,0.000006250909,0.0005731018],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7710387,"threshold_uncertainty_score":0.2107082,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2970408474","doi":"10.14778/3342263.3342274","title":"PrivateSQL","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Differential privacy; SQL; Relational database; Schema (genetic algorithms); Conjunctive query; Information retrieval; Workload; View; Relation (database); Database; Data mining; Database design","authors":[{"name":"Ios Kotsogiannis","is_ca":false},{"name":"Yuchao Tao","is_ca":false},{"name":"Xi He","is_ca":true},{"name":"Maryam Fanaeepour","is_ca":false},{"name":"Ashwin Machanavajjhala","is_ca":false},{"name":"Michael Hay","is_ca":false},{"name":"Gerome Miklau","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01425645443807064,"gpt":0.2277791953859026,"spread":0.213522740947832,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0003227665,0.0001264296,0.0001547589,0.00007572629,0.00005288661,0.00008255759,0.03186454,0.00005822518,0.00002008319],"category_scores_gemma":[0.00253939,0.00008459246,0.00007231721,0.0004693443,0.00006399529,0.0005183493,0.08297414,0.0001712531,0.00008141132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007163962,"about_ca_system_score_gemma":0.00002121823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001251597,"about_ca_topic_score_gemma":1.899982e-7,"domain_scores_codex":[0.9987121,0.000003517092,0.0002201496,0.0003604113,0.0004239339,0.0002799548],"domain_scores_gemma":[0.9970193,0.00003769351,0.0002091807,0.002599954,0.0001025973,0.00003125459],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001494774,0.0002145655,0.05689414,0.0002606339,0.00009295889,7.541e-7,0.0003117923,0.000005619709,0.2883253,0.3100969,0.3262359,0.01754658],"study_design_scores_gemma":[0.0003620205,0.00008518571,0.003918224,0.0001060104,0.000006606029,0.00001174945,0.00004447728,0.00546892,0.6329242,0.3464052,0.01048303,0.0001844065],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8757601,0.0002330854,0.002119391,0.0722217,0.001336068,0.001320873,0.000008229378,0.001089553,0.04591101],"genre_scores_gemma":[0.9072232,0.00002524901,0.09218266,0.0001967847,0.00001738778,0.0000245996,2.745681e-7,0.000009083087,0.0003207305],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3445989,"threshold_uncertainty_score":0.9733735,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2295468252","doi":"10.14778/2856318.2856325","title":"Combining quantitative and logical data cleaning","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":104,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Tech University; McMaster University; University of Toronto","funders":"","keywords":"Computer science; Metric (unit); Inference; Functional dependency; Set (abstract data type); Distortion (music); Statistical inference; Data mining; Algorithm; Theoretical computer science; Dependency (UML); Quality (philosophy); Data quality; Artificial intelligence; Relational database; Mathematics","authors":[{"name":"Nataliya Prokoshyna","is_ca":true},{"name":"Jaroslaw Szlichta","is_ca":true},{"name":"Fei Chiang","is_ca":true},{"name":"Renée J. Miller","is_ca":true},{"name":"Divesh Srivastava","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.6149975953066957,"gpt":0.4683191180089634,"spread":0.1466784772977324,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005978244,0.00009779505,0.0002128958,0.00007374395,0.0001076004,0.0002372084,0.001859741,0.0000260165,0.00001893997],"category_scores_gemma":[0.004737836,0.00005502174,0.00003024039,0.0003319944,0.0001894309,0.0006538076,0.00362099,0.0001004695,0.00003071725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002155951,"about_ca_system_score_gemma":0.0000188333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005733418,"about_ca_topic_score_gemma":0.000007735977,"domain_scores_codex":[0.9977972,0.00003188147,0.0004340434,0.0004197052,0.001146495,0.0001707099],"domain_scores_gemma":[0.9986349,0.0003081137,0.000333269,0.000377103,0.0002460384,0.0001006124],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001273223,0.0001800719,0.01047531,0.00003278647,0.00006513477,0.000001081392,0.005801457,0.00001746467,0.00139098,0.8257729,0.1355931,0.02054241],"study_design_scores_gemma":[0.002681357,0.0007681448,0.01429369,0.0002092316,0.0001273529,0.00002191315,0.1093953,0.00860213,0.005985488,0.5873224,0.2700839,0.0005090747],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8576558,0.000619131,0.002034704,0.01634783,0.0009504979,0.00106929,0.000142637,0.00009417782,0.1210859],"genre_scores_gemma":[0.9929789,0.00001873923,0.006020275,0.000415054,0.00002333814,0.000006020169,0.000003521576,0.000005000513,0.0005291247],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2384505,"threshold_uncertainty_score":0.5671975,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1656389077","doi":"10.14778/2735479.2735485","title":"Rapid sampling for visualizations with ordering guarantees","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":102,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"National Institute of General Medical Sciences","keywords":"Computer science; Bar chart; Visualization; Focus (optics); Sampling (signal processing); Chart; Theoretical computer science; Property (philosophy); Algorithm; Data mining; Mathematics; Statistics; Computer vision","authors":[{"name":"Albert Kim","is_ca":false},{"name":"Eric Blais","is_ca":true},{"name":"Aditya Parameswaran","is_ca":false},{"name":"Piotr Indyk","is_ca":false},{"name":"Samuel Madden","is_ca":false},{"name":"Ronitt Rubinfeld","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07172555247471732,"gpt":0.3140839767866019,"spread":0.2423584243118846,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002622256,0.00009329687,0.0001165568,0.00006731672,0.000106354,0.0001379919,0.000679252,0.00001827532,0.000002296159],"category_scores_gemma":[0.0001283371,0.00005999887,0.00004045055,0.0004271501,0.00003553479,0.0003535777,0.0002212986,0.00003270008,0.000001633603],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003119477,"about_ca_system_score_gemma":0.00005217185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006743267,"about_ca_topic_score_gemma":0.000001771362,"domain_scores_codex":[0.9991853,0.000002819071,0.0001900534,0.0001865415,0.0002775141,0.0001577938],"domain_scores_gemma":[0.9992229,0.00002311272,0.0001618346,0.0001302597,0.0004044468,0.00005749207],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002895241,0.0002120583,0.002403363,0.0001689449,0.00008546365,1.223617e-7,0.003068261,0.0007315007,0.005121602,0.9743031,0.007035243,0.006841437],"study_design_scores_gemma":[0.005441399,0.001120515,0.0006800156,0.000747427,0.0001763775,0.00004539655,0.003868247,0.4542258,0.2367887,0.03517956,0.2607044,0.001022154],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008944848,0.0001202334,0.9858029,0.001512841,0.0002085554,0.0005572779,0.00001114941,0.0001380725,0.002704109],"genre_scores_gemma":[0.826991,0.00004874465,0.1715887,0.0006077579,0.00009691161,0.00008523791,0.00000755836,0.0000261058,0.0005479872],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9391235,"threshold_uncertainty_score":0.2446683,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2119323564","doi":"10.14778/2536206.2536208","title":"A data-adaptive and dynamic segmentation index for whole matching on time series","year":2013,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":99,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Search engine indexing; Series (stratigraphy); Segmentation; Computer science; Matching (statistics); Index (typography); Time series; Similarity (geometry); Tree (set theory); Nearest neighbor search; Data mining; Algorithm; Pattern recognition (psychology); Mathematics; Artificial intelligence; Machine learning; Statistics; Image (mathematics)","authors":[{"name":"Yang Wang","is_ca":false},{"name":"Peng Wang","is_ca":false},{"name":"Jian Pei","is_ca":true},{"name":"Wei Wang","is_ca":false},{"name":"Sheng Huang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0158004004847677,"gpt":0.2299606015603585,"spread":0.2141602010755908,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002121915,0.0001054744,0.0001414858,0.00004910993,0.0001608531,0.0001936496,0.0006167976,0.00002175582,0.000007772007],"category_scores_gemma":[0.00002305831,0.00007066005,0.00004083005,0.0001406382,0.00003832675,0.001028629,0.000574514,0.00005450165,0.000007780195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003358085,"about_ca_system_score_gemma":0.000009106037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004895675,"about_ca_topic_score_gemma":0.000004018458,"domain_scores_codex":[0.9991761,0.000003739391,0.0001898712,0.0002791664,0.0001942232,0.0001569143],"domain_scores_gemma":[0.9994474,0.00003085175,0.0002162026,0.0001697017,0.0001028893,0.00003296685],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002274373,0.0004288633,0.001875951,0.0005058567,0.0007940915,5.257735e-7,0.01574961,0.00154373,0.5255008,0.1021439,0.01257744,0.3386517],"study_design_scores_gemma":[0.000979509,0.0006762427,0.004820655,0.0002244738,0.00009588782,0.00001677316,0.003534931,0.9080855,0.02878493,0.05064853,0.001714072,0.0004184971],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9036361,0.0002207838,0.07598449,0.01167193,0.0002971304,0.003309721,0.0001402411,0.0002004403,0.004539169],"genre_scores_gemma":[0.9465549,0.000007620491,0.05213021,0.0001236315,0.00002430751,0.00007655723,0.000006284109,0.000009898798,0.001066571],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9065418,"threshold_uncertainty_score":0.2881433,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3111141572","doi":"10.14778/3461535.3461552","title":"Are we ready for learned cardinality estimation?","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Cardinality (data modeling); Inference; Focus (optics); Ask price; Domain (mathematical analysis); Workload; Data modeling","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.07254020723674541,"gpt":0.3182425928154698,"spread":0.2457023855787244,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002591104,0.00009846999,0.0001856333,0.00002139974,0.0001427392,0.00004618672,0.0003480255,0.00002453854,0.000002802054],"category_scores_gemma":[0.0002338384,0.00006954681,0.00009262721,0.0002053447,0.0000350757,0.0003859179,0.0003558705,0.00005757762,0.000002549301],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000470658,"about_ca_system_score_gemma":0.00003588518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001513958,"about_ca_topic_score_gemma":0.000003382444,"domain_scores_codex":[0.9990739,0.00000689199,0.0002260823,0.0002768573,0.0002479769,0.0001683179],"domain_scores_gemma":[0.9989714,0.00004187137,0.0003279828,0.0002446446,0.0003742687,0.00003982908],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000165635,0.00008967053,0.001611922,0.0005185461,0.00005855727,0.000001271958,0.000691678,0.0002217164,0.01513472,0.9633622,0.008120652,0.01017254],"study_design_scores_gemma":[0.001145771,0.00009789975,0.003126415,0.0005861234,0.00005536728,0.00006740759,0.001663488,0.01045291,0.6115143,0.05933025,0.3115373,0.0004228036],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03581718,0.001634345,0.9190651,0.03255054,0.001561349,0.001849527,0.0002081821,0.0003165605,0.0069972],"genre_scores_gemma":[0.6461959,0.00009010165,0.3505704,0.0003490755,0.0001376745,0.0002800625,0.000007231757,0.00001838522,0.002351191],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9040319,"threshold_uncertainty_score":0.2836037,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3000259868","doi":"10.14778/3372716.3372728","title":"Evaluating persistent memory range indexes","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Benchmarking; Index (typography); Dram; Range (aeronautics); Tree (set theory); Key (lock); Data structure; Focus (optics); Persistent data structure; Database; Operating system; Computer hardware; Programming language","authors":[{"name":"Lucas Lersch","is_ca":false},{"name":"Xiangpeng Hao","is_ca":true},{"name":"Ismail Oukid","is_ca":false},{"name":"Tianzheng Wang","is_ca":true},{"name":"Thomas Willhalm","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03028429458173998,"gpt":0.2794155407627558,"spread":0.2491312461810158,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006280877,0.0001156522,0.0001554544,0.00007573659,0.00009562964,0.00007921404,0.001151506,0.00003761659,0.00001441975],"category_scores_gemma":[0.0000625481,0.00008094182,0.0001478157,0.0002757289,0.00002906321,0.000220792,0.0005968669,0.0001077152,0.00001571094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006310275,"about_ca_system_score_gemma":0.00002976047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001462899,"about_ca_topic_score_gemma":1.235912e-7,"domain_scores_codex":[0.9988109,0.00001213802,0.0002362846,0.0002743096,0.0004708261,0.0001955009],"domain_scores_gemma":[0.9992614,0.00003457881,0.0002423663,0.0002190664,0.000204892,0.00003768061],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001844472,0.001349701,0.132137,0.00161621,0.0007245926,0.00000162344,0.03164902,0.05395315,0.3542597,0.2404444,0.02866986,0.1550102],"study_design_scores_gemma":[0.002347599,0.0009763126,0.006835184,0.0006564793,0.00007178848,0.00004305108,0.0005988177,0.5122238,0.4644153,0.009403259,0.001630079,0.0007983271],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9432056,0.0004350843,0.009034029,0.002227383,0.0006686972,0.001221099,0.000001129704,0.0005109197,0.04269606],"genre_scores_gemma":[0.9390992,0.00001333533,0.05946341,0.0002220243,0.00002788967,0.00002240793,1.485438e-7,0.000007409551,0.001144204],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4582706,"threshold_uncertainty_score":0.3300712,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2301743601","doi":"10.14778/2904483.2904486","title":"Leopard","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"VLSI and FPGA Design Techniques","field":"Engineering","cited_by":93,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Graph partition; Computer science; Graph; Space partitioning; Vertex (graph theory); Algorithm; Theoretical computer science","authors":[{"name":"Jiewen Huang","is_ca":false},{"name":"Daniel J. Abadi","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.005755987320689607,"gpt":0.165789516692164,"spread":0.1600335293714744,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009377203,0.00008634578,0.00009610636,0.00003430613,0.00002173535,0.000009290191,0.0002488685,0.00003222946,0.00003227071],"category_scores_gemma":[0.00001806988,0.0000435749,0.00005997138,0.00008095094,0.00003220766,0.00009079252,0.00005384014,0.00004150758,0.00001566625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004624658,"about_ca_system_score_gemma":0.000002995871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002279832,"about_ca_topic_score_gemma":2.193135e-7,"domain_scores_codex":[0.9995028,9.398415e-7,0.0001342984,0.00007969975,0.0001360479,0.0001462549],"domain_scores_gemma":[0.9998153,0.00001147158,0.0000324705,0.00007259651,0.00003951891,0.00002858953],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000003392463,0.00001222803,0.001836824,0.000050289,0.00002255357,9.198606e-8,0.00008398108,0.0000019067,0.9541004,0.005848942,0.02010002,0.01793931],"study_design_scores_gemma":[0.0001403723,0.00002390145,0.0008005056,0.00008881865,0.000009032894,0.000003433562,0.00001515884,0.00002841203,0.9833267,0.004602714,0.01088259,0.00007836067],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.789663,0.0006491404,0.002996189,0.0017219,0.0006808917,0.0009463807,0.00001776669,0.001648944,0.2016758],"genre_scores_gemma":[0.9985104,0.0001075808,0.0007772231,0.00002501738,0.00004595014,0.0000392309,4.504066e-8,0.000015685,0.0004789241],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2088473,"threshold_uncertainty_score":0.1776933,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}