{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":867,"total_is_capped":false,"direct_labels_cover":10,"predictions_cover":867,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"98f632c1f71b","filters":{"topic":"Data Quality and Management"}},"results":[{"id":"W2471940872","doi":"10.3163/1536-5050.104.3.014","title":"De-duplication of database search results for systematic reviews in EndNote","year":2016,"lang":"en","type":"article","venue":"Journal of the Medical Library Association JMLA","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1874,"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 Hospital","funders":"","keywords":"Computer science; World Wide Web; Information retrieval; Data science; Library science; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.1603570094009618,"gpt":0.4287371023629208,"spread":0.268380092961959,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04943056,0.00006100885,0.0004351723,0.0001714387,0.00004021694,0.00007131558,0.001340171,0.00007508284,0.0001231607],"category_scores_gemma":[0.1297998,0.00002570955,0.0001965748,0.0004794073,0.00003363213,0.001046447,0.0002371909,0.0001456514,0.0000251573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001075449,"about_ca_system_score_gemma":0.0002258724,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002710707,"about_ca_topic_score_gemma":0.000003709879,"domain_scores_codex":[0.9928336,0.00245526,0.002148626,0.0001289568,0.002284135,0.0001494347],"domain_scores_gemma":[0.9847605,0.01172463,0.002719202,0.0004905218,0.0001741231,0.0001309857],"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":[0.0005142581,0.0004645043,0.01141685,0.002638409,0.0001219698,0.000008298482,0.001151487,0.00002031681,0.0006623063,0.0253601,0.9091059,0.04853562],"study_design_scores_gemma":[0.009985187,0.0004523032,0.04397841,0.03919894,0.0001955396,0.00003185379,0.00122284,0.003369343,0.005215981,0.08551436,0.8104419,0.0003933176],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.07417832,0.001625401,0.1665775,0.7428126,0.002866932,0.005496583,0.001256193,0.00003328519,0.005153174],"genre_scores_gemma":[0.9317532,0.003190311,0.01002476,0.009438374,0.001416275,0.0001162877,0.00004358677,0.00003621234,0.04398097],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8575749,"threshold_uncertainty_score":0.9788113,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2132698877","doi":"10.5596/c13-009","title":"Systematic Approaches to a Successful Literature Review","year":2013,"lang":"fr","type":"article","venue":"Journal of the Canadian Health Libraries Association / Journal de l Association de bilbiothèques de la santé du Canada","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":871,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Systematic review; Epistemology; History; Psychology; Engineering ethics; Political science; Philosophy; MEDLINE; Engineering; Law","retraction":null,"screen_n_in":null,"score":{"opus":0.03310652073829008,"gpt":0.2956478694425366,"spread":0.2625413487042466,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04281271,0.0004530003,0.001533098,0.0006561071,0.00163348,0.009237141,0.002579571,0.0006356114,0.0009161617],"category_scores_gemma":[0.0536176,0.0003470743,0.0006287993,0.002355152,0.0000686936,0.003723175,0.0001999082,0.002267021,0.00003638223],"about_ca_system_candidate":true,"about_ca_system_consensus":true,"about_ca_system_score_codex":0.04852181,"about_ca_system_score_gemma":0.05005241,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.3774697,"about_ca_topic_score_gemma":0.6495816,"domain_scores_codex":[0.9750219,0.0154148,0.003745244,0.0003364936,0.003610084,0.001871497],"domain_scores_gemma":[0.9758449,0.008238387,0.009963109,0.0006060528,0.002189385,0.003158128],"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":[0.00001019078,0.00005395401,0.02030881,0.004763381,0.0005700068,0.0001276044,0.00343886,0.0002489015,5.904487e-7,0.004277109,0.9637952,0.002405341],"study_design_scores_gemma":[0.0005998646,0.0001486173,0.02787434,0.03158946,0.0003864917,0.001417598,0.002640416,0.0004994404,0.000008342927,0.01601362,0.9183198,0.0005020105],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.002842876,0.5370172,0.0005802382,0.4522319,0.004130302,0.001288384,0.0005289915,0.00001350331,0.001366602],"genre_scores_gemma":[0.07753319,0.5000281,0.007590317,0.3731729,0.006142571,0.0001005531,0.00004138495,0.0001419439,0.03524907],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.2721118,"threshold_uncertainty_score":0.9999971,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1977628174","doi":"10.1071/ah080766","title":"A decade of data linkage in Western Australia: strategic design, applications and benefits of the WA data linkage system","year":2008,"lang":"en","type":"article","venue":"Australian Health Review","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":514,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Centre for Global Health Research","funders":"","keywords":"Linkage (software); Population health; Health economics; Record linkage; Data quality; Public health; Population; Data science; Linked data; Medicine; Business; Computer science; Environmental health; Marketing; World Wide Web; Biology; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.7754379927253564,"gpt":0.5261300498695192,"spread":0.2493079428558372,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01119155,0.0002067519,0.0009168574,0.0001305149,0.0001456792,0.00004676117,0.00485499,0.00009259916,0.00004618614],"category_scores_gemma":[0.0003520117,0.0001374255,0.00005480811,0.001333766,0.0002308905,0.0006705398,0.001493021,0.0002810915,0.00007047682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004107284,"about_ca_system_score_gemma":0.000277287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001089047,"about_ca_topic_score_gemma":0.0007821236,"domain_scores_codex":[0.9941986,0.001194782,0.002335086,0.0009144199,0.0009827545,0.0003743734],"domain_scores_gemma":[0.992178,0.0006204227,0.001236784,0.005648484,0.0001216479,0.0001946085],"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":[0.00008091778,0.001852644,0.06181578,0.1509231,0.0003300314,0.00006899494,0.00229816,0.0004183364,0.00004199939,0.07545147,0.3537602,0.3529584],"study_design_scores_gemma":[0.001762597,0.0003901933,0.2138702,0.0371948,0.0003752561,0.000239709,0.002161981,0.0004143405,0.00007773512,0.001767614,0.7407639,0.0009816573],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.1483362,0.5653355,0.02876194,0.1532763,0.001588879,0.05519237,0.04566558,0.0003379705,0.001505257],"genre_scores_gemma":[0.7872013,0.1968265,0.009770202,0.002417563,0.0001339199,0.0001911793,0.001000657,0.00003712253,0.002421503],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6388652,"threshold_uncertainty_score":0.902186,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2171332293","doi":"10.1145/1366102.1366103","title":"Conditional functional dependencies for capturing data inconsistencies","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":458,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Bell (Canada)","funders":"Engineering and Physical Sciences Research Council","keywords":"Computer science; Functional dependency; Data integrity; Consistency (knowledge bases); Relational database; SQL; Data mining; Set (abstract data type); Schema (genetic algorithms); Database; Programming language; Theoretical computer science; Algorithm; Information retrieval; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.5917106512846138,"gpt":0.4156652633131301,"spread":0.1760453879714837,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003093297,0.0002136977,0.0003266986,0.0004035097,0.001083693,0.000231642,0.002135647,0.00007091129,0.0005095956],"category_scores_gemma":[0.001780247,0.0001777547,0.0001249815,0.0004236338,0.0002371596,0.001648846,0.0001434835,0.000182569,0.0006297705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007469964,"about_ca_system_score_gemma":0.0001960979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004541447,"about_ca_topic_score_gemma":0.0005062943,"domain_scores_codex":[0.9959337,0.0002293184,0.0008280448,0.0009323349,0.001756935,0.000319692],"domain_scores_gemma":[0.99266,0.002967176,0.0002184519,0.003711031,0.0002912969,0.0001520473],"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":[0.0007931147,0.001741999,0.0007502174,0.0004755725,0.001046374,0.0001918663,0.001266063,0.03608345,0.001349926,0.0604348,0.8784931,0.0173735],"study_design_scores_gemma":[0.002182904,0.0001645838,0.002556835,0.0001396222,0.0001632143,0.0005551525,0.01051676,0.01397548,0.0006606838,0.005454475,0.9628404,0.0007898973],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002671431,0.0001766919,0.9570127,0.000971684,0.001869707,0.0006627008,0.0357185,0.0001175994,0.0007990051],"genre_scores_gemma":[0.9766784,0.00006541765,0.008499217,0.0005114591,0.0002830176,0.0002859965,0.006512661,0.0000226944,0.007141096],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.974007,"threshold_uncertainty_score":0.8334996,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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","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":"W85648037","doi":"","title":"Proceedings of the 2008 ACM SIGMOD international conference on Management of data","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":423,"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; Dynamism; Session (web analytics); Field (mathematics); Sentence; Data science; Operations research; World Wide Web; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.5943424653324738,"gpt":0.4691355235260268,"spread":0.125206941806447,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001359277,0.00006206545,0.0001211027,0.00008134522,0.0000498558,0.0000372547,0.005721446,0.00001710741,0.001158261],"category_scores_gemma":[0.0003720919,0.00003451123,0.00003565286,0.000296829,0.0001623,0.0004610722,0.00341582,0.00004503171,0.00007995748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008300795,"about_ca_system_score_gemma":0.00001506652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003213449,"about_ca_topic_score_gemma":0.00001018035,"domain_scores_codex":[0.9976973,0.00001596262,0.0004204046,0.0003164647,0.001465929,0.0000839632],"domain_scores_gemma":[0.9982506,0.0001018803,0.0002365317,0.001163518,0.0002245258,0.00002292033],"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":[0.00003034971,0.0001732401,0.00140183,0.00001403051,0.00005170887,0.00000132756,0.0002093602,0.000004941248,0.0001301564,0.6130013,0.368056,0.01692574],"study_design_scores_gemma":[0.001777237,0.0002154056,0.1597244,0.0002457738,0.00006243839,0.00001046515,0.01552581,0.005749364,0.007876202,0.1838002,0.6245964,0.0004164213],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1011551,0.000009802696,0.002362351,0.01158793,0.0004463251,0.0004204701,0.0002623507,0.00002122351,0.8837345],"genre_scores_gemma":[0.9691746,0.0001009503,0.005715843,0.0003726154,0.0000162604,0.000003603451,0.00001303451,0.000002601893,0.02460054],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8680195,"threshold_uncertainty_score":0.9997548,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2775078427","doi":"10.1177/2053951717745678","title":"Challenges in administrative data linkage for research","year":2017,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":356,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Clinical Evaluative Sciences","funders":"Economic and Social Research Council; Wellcome Trust","keywords":"Linkage (software); Record linkage; Computer science; Data quality; Data science; Data collection; Confidentiality; Data mining; Sample (material); Population; Computer security; Engineering; Statistics; Sociology","retraction":null,"screen_n_in":null,"score":{"opus":0.9805021151538041,"gpt":0.681924870153455,"spread":0.2985772450003491,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.04328134,0.0001217356,0.0002611787,0.000056614,0.0008379799,0.001330097,0.01724683,0.0001122376,0.00004209236],"category_scores_gemma":[0.01742786,0.00009554727,0.00005861652,0.0001765882,0.0004806106,0.002232797,0.01498031,0.0002988479,0.0002094819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003457674,"about_ca_system_score_gemma":0.0002224809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002421229,"about_ca_topic_score_gemma":0.007538258,"domain_scores_codex":[0.9956093,0.0003689507,0.0004936482,0.001549033,0.001513541,0.0004654884],"domain_scores_gemma":[0.981907,0.002641019,0.0002371761,0.01489041,0.0002130244,0.0001114057],"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":[0.00001755518,0.000117086,0.0001263642,0.00002794101,0.00002463625,0.000004436773,0.001359644,1.021594e-7,0.000008770851,0.007451819,0.6041026,0.386759],"study_design_scores_gemma":[0.0004770437,0.00005324147,0.01398545,0.00003046324,0.000006787581,4.708933e-7,0.01625402,0.001598255,0.00001628176,0.01735094,0.9500995,0.0001275776],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.02054836,0.01685871,0.05667542,0.4947101,0.008716423,0.0104538,0.1859108,0.0003273233,0.2057991],"genre_scores_gemma":[0.9244187,0.01976064,0.03117278,0.001338234,0.002379258,0.0001834843,0.01221866,0.00004949484,0.008478783],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9038703,"threshold_uncertainty_score":0.9997066,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2044469685","doi":"10.1109/icde.2013.6544847","title":"Holistic data cleaning: Putting violations into context","year":2013,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":319,"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; Hypergraph; Context (archaeology); Pipeline (software); Exploit; Reachability; Quality (philosophy); Functional dependency; Theoretical computer science; Isolation (microbiology); Data mining; Machine learning; Programming language; Relational database; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.5895766416565716,"gpt":0.5011305017614565,"spread":0.08844613989511518,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002758085,0.00007419258,0.0001302318,0.0001138009,0.0002115692,0.0008685137,0.00190413,0.00002547938,0.006099558],"category_scores_gemma":[0.005692525,0.00005210497,0.00002422498,0.00035332,0.00006355769,0.00164673,0.001551356,0.00006790922,0.01238832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001278677,"about_ca_system_score_gemma":0.00001999603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001971473,"about_ca_topic_score_gemma":0.0007005745,"domain_scores_codex":[0.9981281,0.0001248569,0.000472425,0.0004605473,0.0006456053,0.0001684577],"domain_scores_gemma":[0.9967242,0.001097134,0.0001198146,0.001807535,0.0001555115,0.0000958197],"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":[6.514601e-7,0.00002196083,0.0006453118,0.000001839727,0.000006768882,6.563137e-7,0.0002747285,0.000007747453,0.0000272931,0.110112,0.4408453,0.4480558],"study_design_scores_gemma":[0.000169716,0.00001735289,0.01181123,0.000008414145,0.00001014153,9.834822e-7,0.01106392,0.03846326,0.00001726674,0.2345692,0.7037352,0.0001333141],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02425549,0.00006405136,0.7437891,0.01946859,0.0008219974,0.0006123584,0.00007711017,0.0002152282,0.2106961],"genre_scores_gemma":[0.9723129,0.000002697299,0.01464895,0.002547231,0.00006755761,0.000008029888,0.00008594676,0.000004720801,0.01032198],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9480574,"threshold_uncertainty_score":0.994809,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2137775416","doi":"","title":"Improving data quality: consistency and accuracy","year":2007,"lang":"en","type":"article","venue":"Edinburgh Research Explorer (University of Edinburgh)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":312,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Bell (Canada)","funders":"Biotechnology and Biological Sciences Research Council; Engineering and Physical Sciences Research Council; Vlaamse regering; Fonds Wetenschappelijk Onderzoek","keywords":"Consistency (knowledge bases); Computer science; Data consistency; Data integrity; Consistency model; Sequential consistency; Set (abstract data type); Weak consistency; Heuristic; Data mining; Data quality; Quality (philosophy); Strong consistency; Database; Artificial intelligence; Mathematics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.5859534533824458,"gpt":0.5006272625830552,"spread":0.08532619079939052,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05447424,0.0002319622,0.0005974224,0.001473185,0.0009555885,0.0003199072,0.004640433,0.0001760347,0.00505869],"category_scores_gemma":[0.02253627,0.0002299472,0.0001225415,0.002132161,0.001734077,0.003431207,0.007978522,0.0006815409,0.00004847823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001003866,"about_ca_system_score_gemma":0.0002726957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002350342,"about_ca_topic_score_gemma":0.0006030811,"domain_scores_codex":[0.9915153,0.0004853786,0.0008395064,0.001484528,0.004661797,0.001013511],"domain_scores_gemma":[0.9816967,0.01174571,0.0005422751,0.00369432,0.001618496,0.0007024857],"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":[0.0003879935,0.0002372208,0.002631674,0.0000290332,0.00009950793,0.0001642234,0.007009476,0.000001952624,0.001838142,0.007447844,0.628711,0.3514419],"study_design_scores_gemma":[0.001625755,0.0002743789,0.005642102,0.00008165678,0.00004983075,0.000009355788,0.2338953,0.001465369,0.0002630349,0.04320715,0.7129754,0.0005106081],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6877916,0.001788661,0.2007928,0.02557966,0.00316596,0.00243725,0.0008788019,0.000332789,0.07723244],"genre_scores_gemma":[0.9793284,0.0007114592,0.006808088,0.0002164585,0.0005977855,0.000001260331,0.0001498663,0.00002147095,0.01216522],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3509313,"threshold_uncertainty_score":0.9958508,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W760598031","doi":"10.1007/s00778-015-0389-y","title":"Profiling relational data: a survey","year":2015,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":273,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Profiling (computer programming); Metadata; Computer science; Data mining; Data type; Information retrieval; Data science; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.8844173631534311,"gpt":0.5434835487839118,"spread":0.3409338143695193,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05177788,0.0000584324,0.0001057201,0.00008779347,0.0002647905,0.0005620382,0.002124306,0.0000212411,0.0002132176],"category_scores_gemma":[0.01092482,0.00002940482,0.00002786537,0.0003772489,0.00007365708,0.0009252531,0.0007525229,0.0002489306,0.0009997596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002482647,"about_ca_system_score_gemma":0.0001817656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000394526,"about_ca_topic_score_gemma":0.00009459696,"domain_scores_codex":[0.9964501,0.001076383,0.0004557821,0.0001861964,0.001677312,0.0001541984],"domain_scores_gemma":[0.9971984,0.001150703,0.0002507955,0.0009383176,0.0003282107,0.000133551],"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":[0.00008279585,0.00004889921,0.02160096,7.102893e-7,0.00003862204,0.0000145812,0.0004793146,0.0007371026,0.000007779039,0.02283371,0.9319591,0.02219645],"study_design_scores_gemma":[0.0006290396,0.00005144617,0.08757444,0.000009612902,0.00001879511,0.0001690034,0.00230548,0.006690034,0.00001282652,0.1558823,0.7465175,0.0001395253],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.352442,0.001669338,0.5112038,0.05794158,0.009467906,0.0007046077,0.001088508,0.0001032462,0.065379],"genre_scores_gemma":[0.9670879,0.00005673001,0.01336891,0.002534217,0.001571264,0.000002907286,0.0002372622,0.00001702415,0.01512381],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6146459,"threshold_uncertainty_score":0.9997781,"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","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":"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","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":"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","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","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","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":"W2093594738","doi":"10.7152/acro.v24i1.14671","title":"Veracity Roadmap: Is Big Data Objective, Truthful and Credible?","year":2014,"lang":"en","type":"article","venue":"Advances in Classification Research Online","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":227,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Big data; Computer science; Data science; Operationalization; Objectivity (philosophy); Credibility; Data quality; Variety (cybernetics); Quality (philosophy); Data mining; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.68969663109607,"gpt":0.5918893972658551,"spread":0.09780723383021495,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01727999,0.0001327076,0.0002677155,0.0007096014,0.0002574043,0.0003594578,0.002401676,0.0000779112,0.0001542089],"category_scores_gemma":[0.01965881,0.0001066114,0.00002408488,0.00192433,0.000567797,0.001897032,0.001411893,0.0004573232,0.0002020755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006805903,"about_ca_system_score_gemma":0.00009584751,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000120004,"about_ca_topic_score_gemma":0.002273481,"domain_scores_codex":[0.9939373,0.001317344,0.0007311896,0.001232918,0.002357986,0.0004233161],"domain_scores_gemma":[0.99174,0.004552478,0.0001977604,0.002775712,0.000560224,0.0001738427],"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":[0.00007292033,0.0002816042,0.008245844,0.00002506401,0.000006152666,0.000001671836,0.0002109869,0.00001772663,0.0001364671,0.02609894,0.01389879,0.9510038],"study_design_scores_gemma":[0.0004013264,0.00007229761,0.08145236,0.00002375087,0.000002371958,8.204018e-7,0.001656597,0.02780909,0.00006011252,0.1149682,0.7734367,0.0001163615],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3655248,0.01109111,0.2824011,0.2015826,0.00427309,0.004451443,0.007586992,0.0004099977,0.1226788],"genre_scores_gemma":[0.9819894,0.005965859,0.006911457,0.0007853237,0.0003379488,0.0000466795,0.0005709247,0.00001568411,0.003376657],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9508874,"threshold_uncertainty_score":0.988599,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2047745978","doi":"10.1145/1514894.1514901","title":"On approximating optimum repairs for functional dependency violations","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":209,"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","keywords":"Functional dependency; Tuple; Computer science; Set (abstract data type); Dependency theory (database theory); Constant (computer programming); Approximation algorithm; Dependency (UML); Algorithm; Database; Mathematics; Relational database; Discrete mathematics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.2489855454233683,"gpt":0.4310638159039699,"spread":0.1820782704806016,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002627136,0.00007005617,0.0001059041,0.0001380863,0.0002448274,0.000188255,0.0002845711,0.00003010042,0.000939228],"category_scores_gemma":[0.002690885,0.00005007814,0.00009124281,0.000253111,0.00001409768,0.0003528745,0.0000436839,0.00004825124,0.0003581829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001902524,"about_ca_system_score_gemma":0.00001951933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004780912,"about_ca_topic_score_gemma":0.00001442552,"domain_scores_codex":[0.9983321,0.00004998971,0.0004306331,0.0003386959,0.0007012293,0.0001473716],"domain_scores_gemma":[0.9982681,0.001026062,0.0001089553,0.0004266745,0.0001190742,0.000051127],"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":[0.00002623641,0.00009212238,0.00004298326,0.000001345816,0.000005406768,3.672549e-7,0.00005325111,0.001686542,0.00002498355,0.7970377,0.1225505,0.07847858],"study_design_scores_gemma":[0.0003571221,0.0002028427,0.004279559,0.000006464773,0.000007944621,0.000001140795,0.0007401217,0.05237868,0.00006663931,0.8995391,0.04229067,0.0001296859],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003214772,0.000004560587,0.8586867,0.003569468,0.0002376024,0.0002830063,0.00002001688,0.00008978677,0.133894],"genre_scores_gemma":[0.8695891,0.000001252856,0.1011703,0.004783403,0.0001403045,0.00003959616,0.00006795153,0.00000522434,0.02420286],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8663744,"threshold_uncertainty_score":0.9999741,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2284343953","doi":"10.1111/cobi.12706","title":"Emerging problems of data quality in citizen science","year":2016,"lang":"en","type":"editorial","venue":"Conservation Biology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":209,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"Memorial University of Newfoundland; University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Citizen science; Crowdsourcing; Citizen journalism; Open science; Data science; Open data; Resource (disambiguation); World Wide Web; Computer science; Political science; Public relations","retraction":null,"screen_n_in":null,"score":{"opus":0.3374571762887902,"gpt":0.5204741367644338,"spread":0.1830169604756435,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03392427,0.0001760493,0.0006194494,0.0007978627,0.0001000708,0.000109015,0.005622295,0.000361444,0.0002357338],"category_scores_gemma":[0.05627915,0.0001231673,0.00004353419,0.001326021,0.001243302,0.0009043169,0.002795293,0.0002434902,0.0001131935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007504869,"about_ca_system_score_gemma":0.0009809454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001291874,"about_ca_topic_score_gemma":0.001773841,"domain_scores_codex":[0.9940971,0.0008863985,0.001834588,0.001336117,0.001493566,0.0003522169],"domain_scores_gemma":[0.986258,0.007824603,0.0015048,0.003126443,0.001218798,0.00006740783],"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":[0.00002246344,0.00002826774,0.00234826,0.00004019408,0.000008590725,4.710645e-7,0.00008338658,5.52996e-7,0.0005938141,0.01406106,0.9585156,0.02429733],"study_design_scores_gemma":[0.0003588688,0.00003070747,0.001854961,0.00008372658,0.000005126183,7.946777e-8,0.0000933007,0.00006785487,0.00002538256,0.04730366,0.9500223,0.0001540101],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.00236915,0.0002668735,0.01545051,0.00897131,0.9609718,0.0007094137,0.006072109,0.00005096409,0.005137814],"genre_scores_gemma":[0.03865765,0.00238271,0.009695689,0.003657117,0.9068984,0.0002640222,0.02103679,0.0001072511,0.01730039],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.05407348,"threshold_uncertainty_score":0.9997578,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2533963320","doi":"10.1186/s12911-016-0375-3","title":"Describing the linkages of the immigration, refugees and citizenship Canada permanent resident data and vital statistics death registry to Ontario’s administrative health database","year":2016,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":204,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"College of Physicians and Surgeons of Ontario; Ottawa Hospital; Canadian Institute for Health Information; Institute for Clinical Evaluative Sciences","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Health informatics; Refugee; Citizenship; Immigration; Health statistics; Database; Health services research; Official statistics; Nationality; Data science; Medicine; Public health; Political science; Computer science; Nursing; Environmental health; Law; Population","retraction":null,"screen_n_in":null,"score":{"opus":0.2748628273168988,"gpt":0.4274036063539242,"spread":0.1525407790370253,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006436973,0.0001363654,0.0002632047,0.00006754996,0.0004044852,0.0003286037,0.000990583,0.00004338361,0.00005872155],"category_scores_gemma":[0.01062594,0.00005926441,0.00001574423,0.0001542536,0.0002248317,0.0003020389,0.002176706,0.0001508739,0.000001554683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007247046,"about_ca_system_score_gemma":0.001732504,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.03173894,"about_ca_topic_score_gemma":0.7942245,"domain_scores_codex":[0.9958804,0.0002049449,0.001222169,0.0002699288,0.00220954,0.0002130791],"domain_scores_gemma":[0.9909324,0.006924328,0.0005290654,0.001152797,0.0001397234,0.0003216871],"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":[0.0001335754,0.00003186941,0.02600936,0.000196976,0.00005218504,0.0000203111,0.008844078,0.00001900827,0.000004709281,0.05342505,0.3518594,0.5594035],"study_design_scores_gemma":[0.005297608,0.0009601641,0.3463129,0.01407619,0.0002361316,0.0005134228,0.1507431,0.1062634,0.00009785522,0.133792,0.2399453,0.001761949],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3633251,0.0002209082,0.6313368,0.002894763,0.0002134477,0.0003651865,0.001472411,0.000005674804,0.0001656513],"genre_scores_gemma":[0.91771,0.0002260605,0.07770269,0.004081754,0.0000415088,0.00000635456,0.00004477678,0.000006213219,0.0001806653],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7624856,"threshold_uncertainty_score":0.997708,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2037754936","doi":"10.1353/cja.2005.0055","title":"Data Quality in an Information-Rich Environment: Canada as an Example","year":2005,"lang":"en","type":"review","venue":"Canadian Journal on Aging / La Revue canadienne du vieillissement","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":195,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Toronto; University of Manitoba; Health Sciences Centre; Manitoba Health","funders":"","keywords":"Quality (philosophy); Information quality; Data quality; Computer science; Data science; Business; Information system; Political science; Marketing; Epistemology","retraction":null,"screen_n_in":null,"score":{"opus":0.1882385821084955,"gpt":0.3704396366493099,"spread":0.1822010545408144,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01686283,0.0008124957,0.001879552,0.002020986,0.0007810565,0.002297517,0.006939394,0.0002690784,0.003021759],"category_scores_gemma":[0.001905023,0.0007315309,0.0001973247,0.001077658,0.0001311853,0.003316325,0.000367235,0.001338842,0.0003185508],"about_ca_system_candidate":true,"about_ca_system_consensus":true,"about_ca_system_score_codex":0.006449316,"about_ca_system_score_gemma":0.009417726,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9532236,"about_ca_topic_score_gemma":0.9995926,"domain_scores_codex":[0.9898202,0.00243897,0.003597216,0.001383738,0.001163159,0.001596752],"domain_scores_gemma":[0.9881731,0.0009155109,0.001807771,0.004450489,0.0002205483,0.004432593],"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":[0.00000335815,0.00004641155,0.0001034643,0.0003624414,0.00007482643,0.000738115,0.001608482,0.0003500085,8.648719e-9,0.005815016,0.03073278,0.9601651],"study_design_scores_gemma":[0.0002917586,0.00009220463,0.0004203383,0.001497897,0.0001155858,0.0002027091,0.002621338,0.00009061713,2.542905e-8,0.0003440287,0.9934805,0.0008430026],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.005239685,0.9537802,0.0004687307,0.007415234,0.005406608,0.00340063,0.01596426,0.00005747528,0.008267138],"genre_scores_gemma":[0.002216604,0.976966,0.0006304301,0.008181433,0.001450378,0.000122838,0.008630581,0.0001471552,0.0016546],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9627477,"threshold_uncertainty_score":0.9995136,"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","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":"W2135797260","doi":"10.1287/isre.2014.0537","title":"The IQ of the Crowd: Understanding and Improving Information Quality in Structured User-Generated Content","year":2014,"lang":"en","type":"article","venue":"Information Systems Research","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":152,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Information quality; Quality (philosophy); Class (philosophy); Data science; Data mining; Knowledge management; Information retrieval; Information system; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.5163197398913468,"gpt":0.4719992757335768,"spread":0.04432046415777002,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03687475,0.00007746203,0.0001764429,0.0003873585,0.0005621746,0.001693045,0.0007825234,0.00006800729,0.000005629971],"category_scores_gemma":[0.008748434,0.00003939341,0.00003310282,0.001018943,0.0002236131,0.003179783,0.0004604422,0.0002322533,0.00003474048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001806904,"about_ca_system_score_gemma":0.00008854785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002320025,"about_ca_topic_score_gemma":0.0007646969,"domain_scores_codex":[0.9938134,0.001787576,0.001516015,0.00010373,0.002511068,0.0002681953],"domain_scores_gemma":[0.9960116,0.001874529,0.0005778554,0.0006620565,0.0008193257,0.0000546294],"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":[0.0001320623,0.00001068368,0.007926916,0.0002909805,0.00002305062,7.21413e-8,0.01105866,0.001831694,0.000434367,0.9093654,0.006430561,0.06249559],"study_design_scores_gemma":[0.002720098,0.0001400679,0.1659442,0.00019109,0.000006861666,0.000005377116,0.2972694,0.11923,0.00127674,0.01508674,0.3977943,0.0003352058],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.860241,0.0001069971,0.1132712,0.003849464,0.001587866,0.003182992,0.0001602752,0.00004581218,0.01755441],"genre_scores_gemma":[0.9996291,0.00001002564,0.00002150772,0.00008398588,0.00001734401,0.0000281109,0.0000129001,0.000001756481,0.0001952625],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8942786,"threshold_uncertainty_score":0.9996013,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4210862833","doi":"10.1186/s40537-021-00468-0","title":"Big data quality framework: a holistic approach to continuous quality management","year":2021,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":141,"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":"Big data; Computer science; Data quality; Profiling (computer programming); Data science; Data mining; Quality (philosophy); Data management; Exploratory data analysis; Engineering; Operations management","retraction":null,"screen_n_in":null,"score":{"opus":0.7948772270531455,"gpt":0.5341265486844159,"spread":0.2607506783687296,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.04004332,0.0002755397,0.001019818,0.0004144787,0.000206228,0.001400647,0.01257665,0.0001231949,0.0001549446],"category_scores_gemma":[0.02683098,0.0002125618,0.000150117,0.00165884,0.0001337335,0.001328854,0.01508839,0.0005726027,0.0002915296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007502545,"about_ca_system_score_gemma":0.0002600313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001562218,"about_ca_topic_score_gemma":0.0002152151,"domain_scores_codex":[0.988939,0.001935669,0.003011074,0.001415833,0.004177032,0.0005213502],"domain_scores_gemma":[0.9817297,0.002159789,0.00171538,0.01307151,0.0007946881,0.0005289462],"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":[0.0001520835,0.0009380399,0.0004511293,0.0001076099,0.0002987403,0.0002294442,0.0003107419,0.00003254838,0.00002377781,0.02683655,0.3750104,0.5956089],"study_design_scores_gemma":[0.0007654497,0.00005569167,0.01954164,0.0001260307,0.0001702351,0.00006254426,0.007386626,0.0001672225,0.00001589714,0.02900648,0.9423463,0.0003558746],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00518036,0.0006649357,0.9570451,0.008075943,0.004759148,0.0003519765,0.006621786,0.00002873136,0.01727202],"genre_scores_gemma":[0.6252039,0.001131488,0.3299585,0.01897147,0.006124792,0.00001454051,0.005156794,0.00008357462,0.01335492],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6270866,"threshold_uncertainty_score":0.999636,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2156897283","doi":"10.1002/asi.22695","title":"Author name disambiguation: What difference does it make in author‐based citation analysis?","year":2012,"lang":"en","type":"article","venue":"Journal of the American Society for Information Science and Technology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":134,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Workaround; Citation; Computer science; Ambiguity; Ranking (information retrieval); Field (mathematics); Information retrieval; Citation analysis; Journal ranking; Publication; Data science; World Wide Web; Political science; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.09078199573774924,"gpt":0.4091928979380296,"spread":0.3184109022002803,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01218653,0.00009163265,0.000297848,0.001201348,0.0003419147,0.0006052165,0.001148215,0.00004997226,0.000008541886],"category_scores_gemma":[0.00420164,0.00004900637,0.0002171935,0.009250639,0.001419402,0.005489805,0.0002173999,0.0001737817,0.000004899618],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001254322,"about_ca_system_score_gemma":0.0001692373,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001101173,"about_ca_topic_score_gemma":0.00002599965,"domain_scores_codex":[0.997117,0.00006428365,0.0008877515,0.0001273518,0.001525796,0.0002778135],"domain_scores_gemma":[0.9963351,0.0004701557,0.001737698,0.0003898343,0.0009873743,0.00007980366],"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":[0.00005161586,0.0001120362,0.04618249,0.0000191877,0.0001143131,1.293369e-7,0.01156454,0.0004473299,0.0005035694,0.03128979,0.004732374,0.9049826],"study_design_scores_gemma":[0.001077252,0.0003516331,0.3976319,0.00007015421,0.0003020225,0.00001352903,0.3310764,0.04945956,0.001191119,0.03537738,0.183068,0.0003809643],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8012107,0.00005475375,0.10133,0.09650245,0.0005437273,0.0002559965,0.00001742504,0.00001588989,0.00006904471],"genre_scores_gemma":[0.9905065,0.00004233454,0.006253454,0.003064326,0.00002424999,0.0000120378,0.00000227845,0.000001592795,0.00009318952],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9046016,"threshold_uncertainty_score":0.5836117,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gemma","categories":["metaresearch","bibliometrics"],"domain":"methods","study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch","bibliometrics"],"domain":"methods","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4211029301","doi":"10.2200/s00439ed1v01y201207dtm030","title":"Foundations of Data Quality Management","year":2012,"lang":"en","type":"article","venue":"Synthesis lectures on data management","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":131,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Key Research and Development Program of China; Engineering and Physical Sciences Research Council; Universiteit Antwerpen; University of Waterloo; National Natural Science Foundation of China","keywords":"Data quality; Data management; Computer science; Quality (philosophy); Data governance; Data science; Data administration; Database; Database design; Operations management; Engineering; Database model","retraction":null,"screen_n_in":null,"score":{"opus":0.6066300196494542,"gpt":0.5319929733621165,"spread":0.0746370462873377,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.01871854,0.0003581847,0.000573521,0.0007232066,0.0002991184,0.000428702,0.01281669,0.00007258045,0.002019235],"category_scores_gemma":[0.002529032,0.0002789577,0.0001080621,0.001098389,0.0002018146,0.002833464,0.01265596,0.0001583578,0.001552274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007324387,"about_ca_system_score_gemma":0.00001655699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001194065,"about_ca_topic_score_gemma":0.0001386843,"domain_scores_codex":[0.9920037,0.0009916719,0.001505676,0.00162305,0.003175681,0.0007002618],"domain_scores_gemma":[0.9797807,0.002325957,0.000667594,0.01692605,0.00008654097,0.0002131592],"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":[0.00007286094,0.0007017435,0.0003412919,0.0001464184,0.0005127017,0.000005366129,0.00008089448,0.00004543526,0.000006242631,0.2117513,0.2972604,0.4890753],"study_design_scores_gemma":[0.0002921089,0.00002380189,0.02800367,0.00006337895,0.0003219129,8.832457e-7,0.001382352,0.0002606537,0.0001476808,0.0100488,0.9590755,0.0003792356],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.003489257,0.0008780266,0.3307499,0.01269093,0.003013455,0.003780901,0.01387934,0.0004024165,0.6311157],"genre_scores_gemma":[0.937087,0.0005690581,0.04946674,0.002483559,0.0003121108,0.0001366333,0.003593413,0.00005420354,0.006297261],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9335977,"threshold_uncertainty_score":0.9999663,"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","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":"W3146147323","doi":"","title":"Lakehouse: A New Generation of Open Platforms that Unify Data Warehousing and Advanced Analytics.","year":2021,"lang":"en","type":"article","venue":"Conference on Innovative Data Systems Research","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":123,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Analytics; Data warehouse; Data science; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.946872203848267,"gpt":0.6271471361658597,"spread":0.3197250676824073,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.01920787,0.0001846625,0.0005634697,0.0005990985,0.0003330643,0.003047313,0.007935701,0.00009173081,0.000237139],"category_scores_gemma":[0.008996663,0.0001400913,0.00001142573,0.004048625,0.0003438755,0.004107798,0.01728054,0.0004329756,0.00007979927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000617585,"about_ca_system_score_gemma":0.001479583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00130949,"about_ca_topic_score_gemma":0.001838082,"domain_scores_codex":[0.9932848,0.0007882873,0.001013928,0.001601335,0.002890029,0.0004215709],"domain_scores_gemma":[0.9875896,0.001291829,0.0004681597,0.007103241,0.003382313,0.000164864],"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":[0.0001245676,0.0001745498,0.001017623,0.0001318543,0.0001444601,0.00005834777,0.0007685958,0.00007274096,0.003483747,0.4615848,0.3228096,0.2096291],"study_design_scores_gemma":[0.003688337,0.0005489678,0.003738967,0.001484644,0.00003481059,0.00003717185,0.06252182,0.1739665,0.006345469,0.0286581,0.7179775,0.0009976816],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.249746,0.002770397,0.5759263,0.02307307,0.003440607,0.009840389,0.06722741,0.0001945618,0.06778129],"genre_scores_gemma":[0.9801367,0.0003758504,0.002712554,0.0001317854,0.0001367286,0.00001900054,0.01026055,0.00002079907,0.006206062],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7303907,"threshold_uncertainty_score":0.999351,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2131060875","doi":"","title":"Extending dependencies with conditions","year":2007,"lang":"en","type":"article","venue":"Edinburgh Research Explorer (University of Edinburgh)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":108,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Bell (Canada)","funders":"Biotechnology and Biological Sciences Research Council; Engineering and Physical Sciences Research Council","keywords":"Undecidable problem; Computer science; Functional dependency; EXPTIME; Consistency (knowledge bases); Theoretical computer science; Data integrity; Inference; Decidability; Static analysis; Heuristic; Schema (genetic algorithms); Algorithm; Data mining; Computational complexity theory; Programming language; PSPACE; Artificial intelligence; Machine learning; Relational database; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.3687199650519964,"gpt":0.4567409499993181,"spread":0.08802098494732163,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02238943,0.0002102848,0.000440437,0.002176227,0.001124234,0.0002009999,0.002365042,0.0001345878,0.01886809],"category_scores_gemma":[0.002267452,0.0001883843,0.0001720006,0.003275566,0.001544191,0.002002454,0.001222966,0.0006119211,0.0001254095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001772672,"about_ca_system_score_gemma":0.0002005607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004395611,"about_ca_topic_score_gemma":0.0005272553,"domain_scores_codex":[0.991978,0.0002417981,0.0004784186,0.0008684355,0.00541217,0.0010211],"domain_scores_gemma":[0.9924735,0.003788998,0.0002662549,0.001230577,0.001717346,0.0005233702],"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":[0.0005646197,0.0003745437,0.004496933,0.00001141973,0.0001569331,0.0006171765,0.01236598,0.0000872829,0.001929283,0.01978081,0.9367011,0.02291389],"study_design_scores_gemma":[0.001537613,0.0006666294,0.01091262,0.0001356643,0.00004917871,0.00002261789,0.3499449,0.0003583565,0.001132887,0.06766613,0.5670775,0.0004959463],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6753179,0.000253275,0.1735315,0.00680958,0.001276079,0.001181645,0.0001765093,0.0002288648,0.1412247],"genre_scores_gemma":[0.977205,0.0001323944,0.002529804,0.00006859782,0.0002864704,0.000002069535,0.00003764401,0.00001373783,0.0197243],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3696236,"threshold_uncertainty_score":0.9820288,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2104345001","doi":"10.1109/icif.2010.5711858","title":"Measures of effectiveness for high-level fusion","year":2010,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":106,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Robustness (evolution); Sensor fusion; Computer science; Situation awareness; Workload; Data collection; Reliability engineering; Data mining; Engineering; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.3631391937097609,"gpt":0.4469914579324498,"spread":0.08385226422268888,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006593028,0.00005346245,0.0001555521,0.00009814702,0.00005868252,0.00005341764,0.0005019694,0.00003810033,0.0003495922],"category_scores_gemma":[0.00238672,0.00003314935,0.00005630378,0.0001764297,0.000055007,0.000172194,0.0001576954,0.00004161345,0.00007789247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003256079,"about_ca_system_score_gemma":0.00001673837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001817673,"about_ca_topic_score_gemma":0.0005636959,"domain_scores_codex":[0.9986887,0.0001009337,0.0002620165,0.0002209298,0.0006312695,0.00009613366],"domain_scores_gemma":[0.9975103,0.001643542,0.00008774287,0.0004724588,0.0002502942,0.00003565873],"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":[0.00009946861,0.0001068153,0.0007883076,0.00003079171,0.00001365149,2.658056e-7,0.0000713847,0.000006650998,0.05934216,0.5620355,0.01277414,0.3647308],"study_design_scores_gemma":[0.001109168,0.000171198,0.1563661,0.00001526808,0.00001855828,5.580193e-7,0.0003485762,0.0001623429,0.1740354,0.4238023,0.2437992,0.0001712918],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4510157,0.000006546938,0.5376964,0.0005401995,0.001173608,0.00049258,0.0001166068,0.00002718437,0.008931231],"genre_scores_gemma":[0.9893917,0.000001232906,0.008413096,0.0001104004,0.00003278347,0.00001882802,0.00000835831,0.000002974818,0.002020642],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.538376,"threshold_uncertainty_score":0.382779,"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","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":"W2041442195","doi":"10.1109/icde.2013.6544854","title":"On the relative trust between inconsistent data and inaccurate constraints","year":2013,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":103,"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; Semantics (computer science); Consistency (knowledge bases); Data integrity; Data consistency; Data mining; Functional dependency; Data modeling; Theoretical computer science; Database; Programming language; Artificial intelligence; Relational database","retraction":null,"screen_n_in":null,"score":{"opus":0.4110229824573968,"gpt":0.4287673793664585,"spread":0.01774439690906177,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003202428,0.00008457326,0.0001431159,0.00006151466,0.0001686283,0.0004887729,0.001151671,0.00002909471,0.003416055],"category_scores_gemma":[0.003129089,0.0000397813,0.00001892605,0.000194543,0.0004286338,0.0008309379,0.001272702,0.0001070188,0.002696868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008878427,"about_ca_system_score_gemma":0.00001824364,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001505612,"about_ca_topic_score_gemma":0.00004703719,"domain_scores_codex":[0.9982358,0.0002955829,0.0003600768,0.0004068262,0.0005658981,0.0001358039],"domain_scores_gemma":[0.9937946,0.004523485,0.0001268646,0.001402786,0.00007544386,0.00007680563],"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":[0.000003273159,0.00002078833,0.003020291,0.00000144943,0.00004311758,0.000001440405,0.0002877473,3.030352e-7,0.000002815684,0.5115418,0.3085378,0.1765391],"study_design_scores_gemma":[0.000358107,0.00008288413,0.06435929,0.00001689694,0.00002704591,0.000001618766,0.009354157,0.001253522,0.00003238638,0.7332143,0.1911098,0.0001899381],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3703362,0.00003133401,0.02129445,0.0872106,0.0003263291,0.001267986,0.0007086092,0.00006511479,0.5187594],"genre_scores_gemma":[0.9906706,0.000008278439,0.0004928459,0.002841729,0.00002640052,0.000008821187,0.00003224223,0.000002691012,0.005916443],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6203344,"threshold_uncertainty_score":0.9980797,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3155972762","doi":"10.1136/bmjopen-2020-043497","title":"Can synthetic data be a proxy for real clinical trial data? A validation study","year":2021,"lang":"en","type":"article","venue":"BMJ Open","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":103,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; McGill University Health Centre; Children's Hospital of Eastern Ontario; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Univariate; Medicine; Bivariate analysis; Multivariate statistics; Metric (unit); Synthetic data; Statistic; Multivariate analysis; Data mining; Proxy (statistics); Statistics; Internal medicine; Computer science; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.8969700184148548,"gpt":0.6912436001651321,"spread":0.2057264182497227,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.05789609,0.0001104438,0.0004660777,0.00005548149,0.0001875146,0.002118612,0.008854667,0.00004974246,0.00042565],"category_scores_gemma":[0.03995207,0.00008422801,0.00005108284,0.0003814039,0.00005435321,0.001485209,0.01695548,0.00009007742,0.0001253241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001632891,"about_ca_system_score_gemma":0.0006685727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008191967,"about_ca_topic_score_gemma":0.005955818,"domain_scores_codex":[0.993495,0.001932288,0.001469047,0.001570087,0.001320328,0.0002132373],"domain_scores_gemma":[0.9867384,0.002839098,0.0004649841,0.009598044,0.0002439536,0.0001154978],"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":[0.009349477,0.002684507,0.001290391,0.00002179175,0.000168517,0.00005535458,0.0005915348,0.000002797979,0.000002705318,0.004588807,0.8325784,0.1486657],"study_design_scores_gemma":[0.03917745,0.001238234,0.002915755,0.0000483101,0.0002807855,0.000005087345,0.0126572,0.006867401,0.00001899725,0.01211846,0.9242839,0.000388373],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3140984,0.00004039963,0.03406288,0.1971376,0.01688208,0.2959386,0.05875337,0.0003004235,0.0827862],"genre_scores_gemma":[0.7517543,0.00008031743,0.06257853,0.01139222,0.005132528,0.01253687,0.06252386,0.0001461835,0.09385513],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4376559,"threshold_uncertainty_score":0.9989173,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2111589117","doi":"10.1186/1471-2288-14-36","title":"Evaluating bias due to data linkage error in electronic healthcare records","year":2014,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":102,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Hospital for Sick Children; Intensive Care Society; Medical Research Council; National Institute for Health and Care Research; NHS Health Scotland","keywords":"Identifier; Record linkage; Linkage (software); Gold standard (test); Word error rate; Computer science; Imputation (statistics); Statistics; Probabilistic logic; Data mining; Missing data; Data set; Standard error; Medicine; Artificial intelligence; Mathematics; Population","retraction":null,"screen_n_in":null,"score":{"opus":0.9728506852504919,"gpt":0.764426510343351,"spread":0.2084241749071409,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.6394793,0.0001669629,0.0008231283,0.001223558,0.0002291421,0.0001526727,0.006863059,0.0003222363,0.003293406],"category_scores_gemma":[0.8603182,0.0001244588,0.00006607333,0.002723577,0.0004164986,0.0002635641,0.006126467,0.001798008,0.001672955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001880298,"about_ca_system_score_gemma":0.00263265,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004369332,"about_ca_topic_score_gemma":0.09030966,"domain_scores_codex":[0.734938,0.241934,0.002698733,0.003115046,0.01421232,0.003101878],"domain_scores_gemma":[0.4539711,0.5336879,0.0004000413,0.00838872,0.001272805,0.002279496],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002331347,0.00008126542,0.001267249,0.00007418097,0.000009832858,0.00003397545,0.0004587799,0.00002069424,0.00003207957,0.03850866,0.04115869,0.9181215],"study_design_scores_gemma":[0.001343295,0.00187176,0.01666641,0.000199945,0.000008734478,0.00003048684,0.003200525,0.09765793,0.00005937495,0.4002251,0.4784217,0.0003148067],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0874657,0.0004607928,0.8524637,0.0551026,0.0008368647,0.0009685638,0.00004354091,0.00005200067,0.002606248],"genre_scores_gemma":[0.2782663,0.0004027736,0.6975009,0.01615244,0.001625307,0.0003770727,0.0002761832,0.0000640272,0.005335028],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9178067,"threshold_uncertainty_score":0.9991044,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W3106195149","doi":"10.1093/jamia/ocaa225","title":"Assessing the quality of clinical and administrative data extracted from hospitals: the General Medicine Inpatient Initiative (GEMINI) experience","year":2020,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":96,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"Sunnybrook Health Science Centre; Trillium Health Centre; Institute for Clinical Evaluative Sciences; Health Sciences Centre; Mount Sinai Hospital; University of Toronto; University Health Network; Queen's University; St. Michael's Hospital","funders":"University of Toronto","keywords":"Data quality; Data extraction; Computer science; Gold standard (test); Quality (philosophy); Quality management; Data collection; Data mining; Database; Medicine; MEDLINE; Statistics; Operations management; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.540661436719735,"gpt":0.5948575964308802,"spread":0.05419615971114522,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02694858,0.000119626,0.0007019647,0.00003633516,0.0002021425,0.000225763,0.002738889,0.00006304524,0.00007633808],"category_scores_gemma":[0.1491516,0.00004728966,0.0001203662,0.0006692563,0.001335533,0.001258269,0.0010173,0.0007150454,0.000003145027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004691573,"about_ca_system_score_gemma":0.000364506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001493874,"about_ca_topic_score_gemma":0.00002511587,"domain_scores_codex":[0.9884688,0.002604991,0.003922367,0.0001422903,0.004705845,0.0001557224],"domain_scores_gemma":[0.9619874,0.02015221,0.01586803,0.0008826755,0.0008382773,0.0002714251],"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":[0.0002569458,0.0002846608,0.3493963,0.00002616668,0.00085094,0.00000566268,0.1505964,0.00004194603,0.00004271953,0.001629136,0.1403435,0.3565255],"study_design_scores_gemma":[0.0007154464,0.0003637339,0.8092613,0.00008574195,0.0001034789,0.000002012929,0.1616699,0.01556265,0.00003207186,0.002208291,0.009897513,0.0000979286],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9196126,0.00004643229,0.009087991,0.06996868,0.0004803486,0.000164372,0.0001031436,0.000003931286,0.0005325031],"genre_scores_gemma":[0.9816279,0.0002190234,0.001448368,0.01626003,0.0004141408,0.00000180825,0.00001450673,0.000003390338,0.00001081245],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4598649,"threshold_uncertainty_score":0.9339893,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2110848713","doi":"","title":"Linked Movie Data Base","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":93,"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":"RDF; Linked data; Computer science; Metadata; World Wide Web; Database; Cloud computing; Information retrieval; Semantic Web","retraction":null,"screen_n_in":null,"score":{"opus":0.5971839626278773,"gpt":0.5128323344859844,"spread":0.0843516281418929,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004081734,0.00005677115,0.0001072705,0.00008340297,0.00006293753,0.0002953951,0.002328949,0.00002159688,0.00361188],"category_scores_gemma":[0.002020177,0.00003650563,0.00002344835,0.0003326735,0.00002355684,0.0007746493,0.0005982779,0.00004682578,0.004341141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004914388,"about_ca_system_score_gemma":0.00001689507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003533766,"about_ca_topic_score_gemma":0.00006411846,"domain_scores_codex":[0.9982322,0.00008991347,0.0003159349,0.0004301849,0.0007950469,0.0001367267],"domain_scores_gemma":[0.9969358,0.0003017596,0.00005466996,0.002584773,0.00004501234,0.00007791618],"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":[0.000003621497,0.00004258549,0.00002923493,3.335895e-7,0.000001836952,0.000005374014,0.00002314778,0.000003429557,0.00001985641,0.05198266,0.6419196,0.3059683],"study_design_scores_gemma":[0.0001291814,0.00002453065,0.003625872,0.000001463208,0.000003693048,5.330059e-7,0.0002684644,0.002944188,0.00002857787,0.07518294,0.9177235,0.00006710381],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.005022791,0.00009981816,0.2293304,0.07238609,0.0005701613,0.0003043031,0.0002444367,0.0002107698,0.6918312],"genre_scores_gemma":[0.7590675,0.00005268307,0.04554096,0.05871198,0.0002681581,0.000002369818,0.0004039254,0.000006452879,0.135946],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.7540447,"threshold_uncertainty_score":0.997299,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2142472956","doi":"10.1109/icde.2011.5767833","title":"A unified model for data and constraint repair","year":2011,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":92,"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 integrity; Scalability; Constraint (computer-aided design); Data quality; Data modeling; Set (abstract data type); Data mining; Semantics (computer science); Data model (GIS); Quality (philosophy); Database; Artificial intelligence; Programming language; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.7150539177874393,"gpt":0.4688035771737507,"spread":0.2462503406136887,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003680499,0.00004938131,0.00009880316,0.00005216646,0.00005769262,0.00007262633,0.0007420309,0.00002082061,0.0003004346],"category_scores_gemma":[0.000997706,0.00003278205,0.00002262332,0.00007471204,0.0001029326,0.0003787222,0.0007289925,0.00002141316,0.00004522098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002444458,"about_ca_system_score_gemma":0.00002434423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007767727,"about_ca_topic_score_gemma":0.0002344562,"domain_scores_codex":[0.9989598,0.00003245888,0.0002611243,0.0003909208,0.0002483101,0.0001073466],"domain_scores_gemma":[0.9983637,0.000260719,0.00005036132,0.001209556,0.00005598526,0.00005962767],"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":[0.00002801987,0.00004180027,0.0001042755,0.000005516079,0.00001503961,0.000001200463,0.0006771857,0.00000366384,0.000005540262,0.7050052,0.2450929,0.04901963],"study_design_scores_gemma":[0.0002054254,0.00002334487,0.0001540427,0.000001615172,0.000009602936,9.298977e-7,0.001664726,0.6854412,0.00001385843,0.2271969,0.08522347,0.00006482824],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001966916,0.00001240533,0.9197759,0.0005778829,0.00006147511,0.0002342874,0.0002797924,0.00006592048,0.07702541],"genre_scores_gemma":[0.5957312,0.00001462813,0.3735797,0.002613638,0.00001777604,0.00001498701,0.00007094664,0.000005632317,0.02795156],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6854376,"threshold_uncertainty_score":0.3289548,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2770448539","doi":"10.1177/0961000617742465","title":"Data science in data librarianship: Core competencies of a data librarian","year":2017,"lang":"en","type":"article","venue":"Journal of Librarianship and Information Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":92,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Data curation; Computer science; Data management; Metadata; Data science; World Wide Web; Library science; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.6056634588857582,"gpt":0.4724691396796581,"spread":0.1331943192061001,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["metaresearch","scholarly_communication","open_science"],"category_scores_codex":[0.04391963,0.0001901909,0.0005286026,0.002097925,0.001086042,0.01015889,0.05427151,0.00007147681,0.0001104651],"category_scores_gemma":[0.03076707,0.0001366878,0.00002993969,0.002715936,0.004420341,0.4350524,0.02520228,0.0003817633,0.00002671035],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002412741,"about_ca_system_score_gemma":0.003123035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006561949,"about_ca_topic_score_gemma":0.00005110558,"domain_scores_codex":[0.9918983,0.0001417811,0.002477502,0.0007344768,0.004280978,0.0004669627],"domain_scores_gemma":[0.9828526,0.00100006,0.003755411,0.01136076,0.0006028812,0.0004282303],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0003692532,0.0002726261,0.09727208,0.0001616348,0.00003655961,0.00003744724,0.006460982,0.00006164095,0.00072022,0.5059407,0.06204803,0.3266189],"study_design_scores_gemma":[0.001467256,0.0001602205,0.5025309,0.0002826406,0.0000316793,0.00008942857,0.009965533,0.06097112,0.000197108,0.0213159,0.402615,0.0003732372],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4527882,0.001507704,0.1012729,0.1095089,0.01274352,0.002619591,0.02233463,0.0001500903,0.2970744],"genre_scores_gemma":[0.9663391,0.0003892772,0.03175653,0.001065533,0.0001426924,6.584871e-7,0.0001960331,0.000006308987,0.0001038542],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5135509,"threshold_uncertainty_score":0.998289,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2992507139","doi":"10.1177/1833358319887743","title":"Data quality in healthcare: A report of practical experience with the Canadian Primary Care Sentinel Surveillance Network data","year":2019,"lang":"en","type":"article","venue":"Health Information Management Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":91,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Queen's University","funders":"","keywords":"Consistency (knowledge bases); Data quality; Computer science; Context (archaeology); Completeness (order theory); Quality (philosophy); Data consistency; Construct (python library); Health care; Data mining; Risk analysis (engineering); Medicine; Operations management; Database; Engineering; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2813307073526872,"gpt":0.4835402556383956,"spread":0.2022095482857085,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03477419,0.0001470424,0.0003854232,0.0003321031,0.0004840574,0.0006477726,0.002919771,0.00004462036,0.00007761188],"category_scores_gemma":[0.0006251908,0.00009478717,0.00002609166,0.001132153,0.00009423355,0.004726014,0.00151621,0.00044025,0.0000892578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003816988,"about_ca_system_score_gemma":0.00150869,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.02552323,"about_ca_topic_score_gemma":0.2340049,"domain_scores_codex":[0.9929168,0.0009847765,0.002410182,0.000420607,0.002671106,0.0005965381],"domain_scores_gemma":[0.992725,0.0003696184,0.002282076,0.003918269,0.0004076732,0.0002974144],"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":[0.0003273512,0.00009890455,0.3328191,0.001460223,0.00009225894,0.000146528,0.006199261,0.002279626,3.478672e-8,0.04558281,0.5183663,0.09262758],"study_design_scores_gemma":[0.000498081,0.00004308408,0.3210706,0.00007986914,0.000003681741,0.00009789377,0.01071601,0.00146981,2.300488e-8,0.0004422854,0.6654642,0.0001144395],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.03554134,0.001167847,0.1064325,0.7525339,0.004105217,0.007943451,0.00263457,0.0001042275,0.08953694],"genre_scores_gemma":[0.9284338,0.0006665295,0.01952754,0.04495555,0.0002192875,0.00002940834,0.005531436,0.00001733348,0.0006191375],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8928924,"threshold_uncertainty_score":0.9939031,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2795302121","doi":"10.1109/icde.2018.00093","title":"Seeping Semantics: Linking Datasets Using Word Embeddings for Data Discovery","year":2018,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":89,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Schema (genetic algorithms); Knowledge graph; Semantics (computer science); Linked data; Information retrieval; Semantic Web; Word (group theory); RDF; Distributional semantics; Natural language processing; Semantic similarity; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.4932316803399396,"gpt":0.519707133187662,"spread":0.0264754528477224,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00586649,0.0001410183,0.0002499748,0.0001939785,0.0004213437,0.001793432,0.002906196,0.00004840629,0.0002087417],"category_scores_gemma":[0.002537817,0.0001070159,0.00005186133,0.0004483657,0.0001562822,0.004182257,0.003592124,0.0000696452,0.0002593401],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002378588,"about_ca_system_score_gemma":0.00004792117,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001331034,"about_ca_topic_score_gemma":0.0004124949,"domain_scores_codex":[0.9970962,0.00009177249,0.0006427289,0.0009202744,0.0008759178,0.0003731115],"domain_scores_gemma":[0.9957684,0.001003538,0.0002447605,0.002778396,0.000127052,0.00007786896],"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":[0.00009968696,0.000161485,0.002218245,0.0001060045,0.0001459234,0.00001245342,0.0009112635,0.00007543709,0.0009314037,0.07507817,0.7434011,0.1768588],"study_design_scores_gemma":[0.0003101434,0.00003484496,0.000268917,0.00008589038,0.00004894716,0.000003424387,0.001551587,0.1976278,0.0004755246,0.02530724,0.7740192,0.0002665028],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01744589,0.00002235465,0.9766752,0.00102297,0.0008881675,0.0003191295,0.002067088,0.00005565959,0.001503556],"genre_scores_gemma":[0.6047588,0.00002475149,0.3739181,0.008209795,0.001927518,0.00001122734,0.005359818,0.00004993685,0.005740017],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.602757,"threshold_uncertainty_score":0.9992428,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2238711864","doi":"10.1561/9781680830231","title":"Trends in Cleaning Relational Data: Consistency and Deduplication","year":2015,"lang":"en","type":"book","venue":"now publishers, Inc. eBooks","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":84,"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":"Data quality; Computer science; Data deduplication; Data integrity; Relational database; Consistency (knowledge bases); Anomaly detection; Data consistency; Data mining; Data science; Automation; Process (computing); Data warehouse; Database; Quality (philosophy); Artificial intelligence; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.3277735594755778,"gpt":0.4006223382773515,"spread":0.07284877880177365,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.009891309,0.0003277012,0.0005639128,0.001447126,0.000164106,0.002311692,0.002215031,0.0004410967,0.0005017726],"category_scores_gemma":[0.002069721,0.0002990439,0.00006239859,0.000273134,0.0003509328,0.003096117,0.002120657,0.0006385488,0.0002878115],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002816413,"about_ca_system_score_gemma":0.0007819736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001267242,"about_ca_topic_score_gemma":0.002289442,"domain_scores_codex":[0.9944764,0.000291083,0.001278286,0.001438176,0.002177205,0.0003388049],"domain_scores_gemma":[0.9951984,0.0008436409,0.0007438368,0.002504645,0.0004741026,0.0002353605],"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":[0.00001530237,0.00001580691,0.0001243378,0.000009608429,0.00002268146,0.000006855809,0.0002035218,0.000001950162,2.34588e-7,0.06580677,0.7366928,0.1971001],"study_design_scores_gemma":[0.0004483171,0.00002746318,0.001218245,0.00004694225,0.00003622905,0.00000620665,0.0003363875,0.0003578584,1.554054e-7,0.102589,0.8946401,0.0002930168],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00004478248,0.000347872,0.0004044535,0.001565067,0.0006189618,0.0002834307,0.0006484935,0.00006980323,0.9960172],"genre_scores_gemma":[0.0009272893,0.000008588653,0.001944587,0.001139004,0.0003445107,0.00002918406,0.008147668,0.00003770042,0.9874215],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.196807,"threshold_uncertainty_score":0.9999462,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2492590231","doi":"10.14778/2983200.2983203","title":"Distributed data deduplication","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":80,"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":"Data deduplication; Tuple; Computer science; Blocking (statistics); Block (permutation group theory); Relation (database); Backup; Locality; Process (computing); Theoretical computer science; Data mining; Database; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2701566814294362,"gpt":0.4095847037039765,"spread":0.1394280222745403,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002833045,0.00008521082,0.0001396589,0.00006043705,0.00009177444,0.0001074909,0.003610126,0.00002428382,0.0001307707],"category_scores_gemma":[0.002798235,0.00003672095,0.00005029723,0.0004182962,0.0001110266,0.0006597339,0.002338527,0.00003541284,0.0001562509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004289379,"about_ca_system_score_gemma":0.00001607763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002519096,"about_ca_topic_score_gemma":0.000005990526,"domain_scores_codex":[0.9978591,0.00001405707,0.0004675653,0.0004280386,0.001063926,0.0001673008],"domain_scores_gemma":[0.9981716,0.0002162236,0.000400905,0.0009123677,0.0002468247,0.00005205952],"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":[0.00004105053,0.0001785684,0.007698308,0.00002086533,0.00004525364,9.913263e-8,0.0001428125,0.000001038024,0.03373804,0.1816097,0.6230755,0.1534487],"study_design_scores_gemma":[0.0005582732,0.00003815815,0.02255803,0.00006807549,0.0000369814,0.000002175903,0.0005607348,0.0001130602,0.05691171,0.1197099,0.7993017,0.0001411777],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5342019,0.0004479674,0.06260016,0.3123969,0.002539681,0.004448726,0.006065222,0.0003774347,0.07692211],"genre_scores_gemma":[0.9969729,0.00003489666,0.0007136844,0.0003292254,0.00004809302,0.00002346193,0.00001387896,0.000004956632,0.001858892],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4627711,"threshold_uncertainty_score":0.6708572,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2190899134","doi":"10.14778/2850578.2850579","title":"Messing up with BART","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":80,"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":"Scalability; Tuple; Computer science; Benchmarking; Completeness (order theory); Greedy algorithm; Process (computing); Benchmark (surveying); Property (philosophy); Scale (ratio); Control (management); Mathematical optimization; Algorithm; Database; Mathematics; Artificial intelligence; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.2772987549438379,"gpt":0.3926154589624858,"spread":0.1153167040186479,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003346509,0.000110662,0.0001971539,0.00009599598,0.00009975187,0.0002522856,0.001211513,0.0000230524,0.00005341462],"category_scores_gemma":[0.0008722148,0.00005417162,0.00006151065,0.0005217349,0.0001322892,0.0005001387,0.0006481254,0.00007885478,0.0000786362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005142292,"about_ca_system_score_gemma":0.00004377445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000500094,"about_ca_topic_score_gemma":0.000008549571,"domain_scores_codex":[0.997272,0.00001683841,0.0003880643,0.0003015252,0.001818141,0.0002034088],"domain_scores_gemma":[0.998772,0.00007504292,0.0003329346,0.0002754912,0.0004345559,0.0001099547],"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":[0.0003150601,0.0002990874,0.01675562,0.00006978135,0.0001266563,0.00000160258,0.008404786,0.00009016968,0.004001799,0.2104359,0.7078582,0.05164132],"study_design_scores_gemma":[0.002260909,0.0003465919,0.005026209,0.0001844909,0.00009402323,0.00001936978,0.02731994,0.0003347774,0.07325927,0.1365034,0.7542753,0.0003756959],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5979908,0.0002299551,0.001364051,0.02234807,0.001578442,0.001216744,0.00002691926,0.0001204531,0.3751246],"genre_scores_gemma":[0.9887018,0.000004379363,0.001905079,0.0005365335,0.00005012651,0.00001995333,5.894613e-7,0.000007730512,0.008773807],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.390711,"threshold_uncertainty_score":0.2432796,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2070702247","doi":"10.1145/1328964.1328967","title":"Meeting of the MINDS","year":2007,"lang":"en","type":"article","venue":"ACM SIGIR Forum","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":76,"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; Field (mathematics); Key (lock); Space (punctuation); Probabilistic logic; Vector space model; Work (physics); Development (topology); Data science; World Wide Web; Information retrieval; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1208935656852042,"gpt":0.4059370702158174,"spread":0.2850435045306132,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005465372,0.00005424055,0.000104887,0.00007106295,0.0001076588,0.00005077072,0.001858031,0.00002956523,0.0001333796],"category_scores_gemma":[0.005665328,0.00003036047,0.00008591675,0.0004747777,0.00008568238,0.0001509086,0.001140734,0.00005500689,0.0001413788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009407479,"about_ca_system_score_gemma":0.00001141008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005441898,"about_ca_topic_score_gemma":0.0002427386,"domain_scores_codex":[0.9982767,0.00005793049,0.0004129338,0.0001788087,0.0008529299,0.0002207672],"domain_scores_gemma":[0.9974316,0.001043468,0.0001887074,0.001234157,0.00006682317,0.00003524742],"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":[0.00003130706,0.0001217279,0.04894946,0.000009519662,0.00002791656,0.000004367085,0.0009566504,0.00002674349,0.001642829,0.09138636,0.2979901,0.558853],"study_design_scores_gemma":[0.0001704887,0.00002860346,0.0459527,0.00001428455,0.000008359959,0.000001080363,0.004786501,0.00003239023,0.01218813,0.07404162,0.8626972,0.00007862515],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.714979,0.0001446283,0.01020938,0.01652216,0.001229629,0.000303764,0.00003429411,0.00003716202,0.25654],"genre_scores_gemma":[0.9930308,0.000001616167,0.001276759,0.001326773,0.00002467243,0.000001016782,0.000001144532,0.000003186117,0.004334018],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5647071,"threshold_uncertainty_score":0.6782337,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1514828683","doi":"10.1186/1472-6963-6-48","title":"Assessing record linkage between health care and Vital Statistics databases using deterministic methods","year":2006,"lang":"en","type":"article","venue":"BMC Health Services Research","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":73,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"Institute of Health Economics; University of Calgary","funders":"Canadian Institutes of Health Research; Fondation pour la Recherche Médicale; University of Calgary","keywords":"Linkage (software); Record linkage; Medicine; Database; Population; Identifier; Demography; Statistics; Computer science; Genetics; Biology; Environmental health; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.5803401570006748,"gpt":0.6702429424110904,"spread":0.08990278541041563,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.02907761,0.0002228915,0.0006724646,0.0007374022,0.001617174,0.001736957,0.001015928,0.00007112267,0.00006711682],"category_scores_gemma":[0.0007506271,0.0001936543,0.0000447458,0.001319741,0.0002322559,0.001090706,0.001385939,0.0004867791,0.00005849738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003430987,"about_ca_system_score_gemma":0.001459172,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02289781,"about_ca_topic_score_gemma":0.01154931,"domain_scores_codex":[0.9863939,0.007163932,0.001600293,0.001075877,0.002557919,0.001208047],"domain_scores_gemma":[0.9878415,0.009303113,0.0005476414,0.00117424,0.0005837851,0.0005497501],"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":[0.00003159494,0.0000852356,0.06656787,0.004511392,0.00001192867,0.00001795711,0.002707824,0.00003174611,0.00002055118,0.002425792,0.001481027,0.9221071],"study_design_scores_gemma":[0.001469416,0.001162887,0.4932311,0.001459607,0.00003501636,0.00001712886,0.1099322,0.03648302,0.00007450288,0.01958869,0.3356272,0.0009193362],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1539268,0.003238847,0.8375663,0.0005014904,0.0003578262,0.001170358,0.002478803,0.00007523243,0.0006842989],"genre_scores_gemma":[0.1787766,0.0001918061,0.8186132,0.0009779938,0.000448179,0.00001953234,0.0007755491,0.00003600322,0.0001612259],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9211878,"threshold_uncertainty_score":0.9997689,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2146738361","doi":"10.1145/1242572.1242802","title":"BlogScope","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":72,"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":"Blogosphere; Computer science; Ranking (information retrieval); Information retrieval; Relevance (law); Set (abstract data type); World Wide Web; Data mining; The Internet","retraction":null,"screen_n_in":null,"score":{"opus":0.3627863579026169,"gpt":0.5270323869453386,"spread":0.1642460290427217,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007177616,0.00002884656,0.00005402086,0.000087332,0.00003930195,0.0001016395,0.0004354496,0.00001341292,0.004403999],"category_scores_gemma":[0.0007118637,0.00001783163,0.00002386092,0.0002907535,0.00002657817,0.0001648966,0.0001555737,0.00002352361,0.006965039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004785391,"about_ca_system_score_gemma":0.000004712202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003385255,"about_ca_topic_score_gemma":0.0002338902,"domain_scores_codex":[0.9988834,0.00002443773,0.0002312039,0.0001550082,0.0005863011,0.0001196201],"domain_scores_gemma":[0.9990956,0.0003993428,0.00003117715,0.0003836688,0.00003981441,0.00005038887],"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":[0.00000485485,0.00002261809,0.0006233677,3.50033e-7,0.000002334628,0.000006820801,0.00005374524,0.000001244787,0.00005007242,0.4574351,0.286519,0.2552805],"study_design_scores_gemma":[0.00005652782,0.00000984286,0.009888556,3.880161e-7,7.908753e-7,5.058571e-7,0.0006265869,0.00001193526,0.0005547759,0.046389,0.9424286,0.00003248205],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.01128762,0.000009226728,0.1926488,0.001341008,0.0001708221,0.00003830567,0.000001320973,0.00003098926,0.7944719],"genre_scores_gemma":[0.8689656,0.000002033376,0.005496756,0.004621053,0.00003944697,5.320044e-7,0.000001713017,0.000001795107,0.1208711],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.857678,"threshold_uncertainty_score":0.9965061,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1626378195","doi":"10.1145/1938551.1938585","title":"Data cleaning and query answering with matching dependencies and matching functions","year":2011,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":69,"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; Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; International Business Machines Corporation","keywords":"Tuple; Matching (statistics); Computer science; Monotone polygon; Conjunctive query; Dependency (UML); Functional dependency; Semantics (computer science); Dependency theory (database theory); Query optimization; Upper and lower bounds; Theoretical computer science; Mathematics; Information retrieval; Discrete mathematics; Relational database; Artificial intelligence; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.3569999851508519,"gpt":0.3743921688869392,"spread":0.01739218373608725,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002682222,0.0001040017,0.000147724,0.0001287497,0.0003290744,0.0005082656,0.0005340989,0.00002466115,0.0002489441],"category_scores_gemma":[0.0001559216,0.00006900512,0.000009542385,0.0001729763,0.00008762223,0.002071268,0.001372595,0.0001024103,0.00004250402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005568234,"about_ca_system_score_gemma":0.00001416532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001792816,"about_ca_topic_score_gemma":0.005569226,"domain_scores_codex":[0.9984892,0.00007155665,0.0002743815,0.0005203014,0.0004671768,0.0001774018],"domain_scores_gemma":[0.9986876,0.0003148634,0.00008582063,0.0007915698,0.00003369042,0.00008646237],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0003021333,0.0002386019,0.0603885,0.0001728136,0.0003339726,0.0001713046,0.04355098,0.0001608553,0.000948936,0.4015342,0.0258708,0.4663269],"study_design_scores_gemma":[0.001412096,0.000342186,0.1997188,0.0002598643,0.000200762,0.0003177047,0.4543163,0.004884698,0.0002274531,0.2116903,0.1252211,0.001408605],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5379349,0.00007501179,0.4228636,0.0002719466,0.0001229343,0.0001147257,0.00006275924,0.00009173376,0.03846241],"genre_scores_gemma":[0.9638334,0.00002617346,0.03369413,0.0004425959,0.00002422445,0.000002629987,0.00001544147,0.000008539111,0.001952876],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4649183,"threshold_uncertainty_score":0.4901217,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2115215982","doi":"10.14778/1453856.1453883","title":"Hashed samples","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":68,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; York University","funders":"","keywords":"Similarity (geometry); Estimator; A priori and a posteriori; Computer science; Overhead (engineering); Set (abstract data type); Sampling (signal processing); Cosine similarity; Algorithm; Data mining; Pattern recognition (psychology); Mathematics; Artificial intelligence; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.2910039101624485,"gpt":0.3717421828373335,"spread":0.08073827267488504,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001799994,0.0001101546,0.000216988,0.0001112632,0.0002291174,0.00008475884,0.001608782,0.00002763307,0.0002388175],"category_scores_gemma":[0.001475403,0.00006129144,0.0001436007,0.0005140385,0.0002042464,0.0003230026,0.0007911863,0.00007707236,0.0001401256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003216543,"about_ca_system_score_gemma":0.00002115617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008477276,"about_ca_topic_score_gemma":0.000006538192,"domain_scores_codex":[0.9974399,0.00001501746,0.0005259413,0.0003216953,0.001485928,0.0002115138],"domain_scores_gemma":[0.998863,0.0001727117,0.0003394307,0.0003123499,0.0002506686,0.00006179988],"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":[0.00008347817,0.0004162836,0.040989,0.0000521969,0.00009392198,0.000001707678,0.00402312,0.00002868511,0.01871645,0.2555075,0.6621273,0.01796035],"study_design_scores_gemma":[0.0008811202,0.0001198308,0.08030357,0.00004937867,0.00003711039,0.00002502613,0.003397773,0.00008660491,0.1193554,0.1306892,0.6647803,0.0002747251],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9066988,0.0001123909,0.0002972628,0.008024189,0.0005471967,0.0005888966,0.00003887616,0.00006138077,0.08363099],"genre_scores_gemma":[0.9917634,0.00004943211,0.001490486,0.0005860449,0.0000533831,0.00002270144,8.843631e-7,0.000006097551,0.006027601],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1248183,"threshold_uncertainty_score":0.2989544,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2583699183","doi":"","title":"Data Ingestion for the Connected World.","year":2017,"lang":"en","type":"article","venue":"Conference on Innovative Data Systems Research","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":68,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Ingestion; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.9484017230905639,"gpt":0.6713623530691826,"spread":0.2770393700213813,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.06057546,0.0001804614,0.0003630426,0.0006285084,0.002669919,0.007006608,0.02731622,0.00007358223,0.0002100638],"category_scores_gemma":[0.07575348,0.0001063969,0.00001733666,0.001698861,0.001072163,0.002467089,0.01232761,0.000597105,0.0007861222],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000614393,"about_ca_system_score_gemma":0.0004424358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001090417,"about_ca_topic_score_gemma":0.002129748,"domain_scores_codex":[0.9925039,0.001398064,0.0008736888,0.001551561,0.003095837,0.000576882],"domain_scores_gemma":[0.9432418,0.01550063,0.001044693,0.03154089,0.008521804,0.0001501352],"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":[0.0001051304,0.00003857412,0.0001399909,0.00002164601,0.00004079803,0.000002532953,0.00006615131,0.000001733041,0.00003463729,0.4347189,0.4871992,0.07763071],"study_design_scores_gemma":[0.0004705325,0.00009480969,0.004021222,0.0001702697,0.000006161026,0.000001234926,0.003682896,0.06365814,0.00003278553,0.01180344,0.9158978,0.000160641],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005522109,0.0006263262,0.4533053,0.1717604,0.01007029,0.01648564,0.1798762,0.0002678325,0.1620859],"genre_scores_gemma":[0.9747884,0.00006685773,0.0002893289,0.0001664004,0.0004852634,0.0002847146,0.00710516,0.00001804651,0.01679582],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9692663,"threshold_uncertainty_score":0.9999919,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"bench_or_experimental","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2616147950","doi":"10.14778/3115404.3115409","title":"Auto-join","year":2017,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":66,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Joins; Join (topology); Computer science; Transformation (genetics); Domain (mathematical analysis); String (physics); Database; Data mining; Theoretical computer science; Programming language; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1996264917742379,"gpt":0.4134582450415684,"spread":0.2138317532673306,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00326452,0.0001059617,0.0002036543,0.00007488864,0.000509723,0.0006620825,0.003779837,0.00003061836,0.0001923004],"category_scores_gemma":[0.002977339,0.00005891431,0.0001404079,0.0001214365,0.0002163719,0.0006064652,0.002001446,0.00008723116,0.0001954577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003134917,"about_ca_system_score_gemma":0.00001673951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001157699,"about_ca_topic_score_gemma":0.00001310102,"domain_scores_codex":[0.9976644,0.00001054078,0.0004533225,0.0003297332,0.001331779,0.0002102305],"domain_scores_gemma":[0.9981151,0.00008276365,0.0007563882,0.000758498,0.000225204,0.00006204531],"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":[0.00004967026,0.0002360422,0.01742536,0.0000561211,0.00007307003,8.772079e-7,0.001178971,0.000004912488,0.01239709,0.491233,0.384108,0.09323694],"study_design_scores_gemma":[0.000665396,0.00007226803,0.08386739,0.0000710882,0.00003837509,0.00000325142,0.001533925,0.0002289126,0.05437285,0.2421853,0.6167632,0.0001979737],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3593015,0.0000888122,0.0002548805,0.04407267,0.001923103,0.001033821,0.00005741832,0.00007551115,0.5931923],"genre_scores_gemma":[0.9845093,0.00001609309,0.0007370529,0.0004202429,0.00006947974,0.00002097857,3.231767e-7,0.000005812296,0.01422071],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6252078,"threshold_uncertainty_score":0.702394,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2427822648","doi":"10.1109/icde.2016.7498319","title":"DataXFormer: A robust transformation discovery system","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":66,"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; Transformation (genetics); Data transformation; Representation (politics); External Data Representation; Knowledge base; Information retrieval; Base (topology); World Wide Web; Data mining; Theoretical computer science; Artificial intelligence; Data warehouse; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2087469238632512,"gpt":0.3724310305524388,"spread":0.1636841066891875,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002701367,0.00006887154,0.0001215243,0.0001184461,0.00008227745,0.0003717908,0.0006170991,0.00002399604,0.0004849851],"category_scores_gemma":[0.0002369782,0.00003019055,0.00005331533,0.0002305538,0.00003736019,0.004149607,0.0001056094,0.00001958262,0.002968214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000388401,"about_ca_system_score_gemma":0.00001615121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005091473,"about_ca_topic_score_gemma":0.0001250609,"domain_scores_codex":[0.9982138,0.00008922201,0.0004594417,0.0002426479,0.0008402826,0.0001546585],"domain_scores_gemma":[0.9988818,0.0003011689,0.00008642875,0.0006299283,0.0000488276,0.00005191504],"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":[0.00002006219,0.00002274254,0.0001178106,0.00001617523,0.00001035248,0.000001589989,0.0001626216,0.00001353488,0.0001811385,0.783845,0.06957199,0.146037],"study_design_scores_gemma":[0.0007722301,0.00005322631,0.002222907,0.00007301682,0.00001500369,0.000006993277,0.00829381,0.0009839215,0.001177853,0.007760935,0.9784109,0.0002292028],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007657728,0.000005328338,0.8764841,0.003448039,0.0002737723,0.0001468644,0.0001575209,0.00007201974,0.1117546],"genre_scores_gemma":[0.9765282,0.00001162829,0.0007825337,0.0003032623,0.00003952019,0.00001083903,0.00001729176,0.000003279113,0.02230351],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9688704,"threshold_uncertainty_score":0.9978081,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}