{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":17,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":17,"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":"3a6ab8d7bbaf","filters":{"venue":"Journal of Data and Information Quality"}},"results":[{"id":"W2899154813","doi":"10.1145/3239571","title":"Anserini","year":2018,"lang":"en","type":"article","venue":"Journal of Data and Information Quality","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":230,"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; National Science Foundation","keywords":"Computer science; Information retrieval; World Wide Web; Ranking (information retrieval); Context (archaeology); Search engine indexing; Implementation; Data science; Software engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1067568912519719,"gpt":0.3914247076637422,"spread":0.2846678164117703,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001799534,0.00004056701,0.00008620435,0.00009874949,0.00008705493,0.0002323006,0.0007086478,0.0000251479,0.00002811188],"category_scores_gemma":[0.0001646532,0.00002917936,0.00001643538,0.0001605151,0.00004830942,0.02517032,0.0002641701,0.00008664531,0.00005377135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009352794,"about_ca_system_score_gemma":0.00008027624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004730763,"about_ca_topic_score_gemma":5.43782e-7,"domain_scores_codex":[0.9989668,0.00003946371,0.000561218,0.00003411448,0.0003187978,0.00007960243],"domain_scores_gemma":[0.9987403,0.00003476776,0.0003727859,0.000323453,0.000449405,0.00007929713],"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":[0.00006991973,0.00003736054,0.00224117,0.00005612273,0.00001982484,0.000001242331,0.005707963,7.286289e-7,0.0001231654,0.1165566,0.01632141,0.8588645],"study_design_scores_gemma":[0.000881172,0.0004357025,0.09708066,0.0000214165,0.000006304466,0.0001525079,0.0005163454,0.01420645,0.000936305,0.0009835155,0.8846242,0.0001553723],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1500605,0.00002018952,0.8429226,0.001937586,0.0004073869,0.00006370513,0.00005605318,0.00002186618,0.004510132],"genre_scores_gemma":[0.9488256,0.0001039695,0.04834303,0.00246861,0.0001870983,3.315828e-7,0.00003551021,0.000001279739,0.00003455031],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8683028,"threshold_uncertainty_score":0.9884641,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4220991771","doi":"10.1145/3506712","title":"Machine Learning and Data Cleaning: Which Serves the Other?","year":2022,"lang":"en","type":"article","venue":"Journal of Data and Information Quality","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Data quality; Software deployment; Data science; Data integration; Quality (philosophy); Data mining; Software engineering; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.3220743629101961,"gpt":0.472009332225758,"spread":0.1499349693155619,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03712774,0.00006679204,0.0001770647,0.0001204452,0.0005756235,0.0006932159,0.002255425,0.00001533967,0.0003052047],"category_scores_gemma":[0.004194206,0.0000394428,0.00001553522,0.0003377476,0.00005433148,0.01148219,0.004536374,0.0003438487,0.000009422397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001065444,"about_ca_system_score_gemma":0.00004877463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001334627,"about_ca_topic_score_gemma":0.00007638036,"domain_scores_codex":[0.9964837,0.0009377451,0.001119888,0.000140904,0.001221735,0.00009602017],"domain_scores_gemma":[0.9966832,0.0008370957,0.001219966,0.001033531,0.0001637226,0.00006246823],"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":[0.0002824105,0.00008347175,0.01844502,0.00006799703,0.0001217814,0.000001689628,0.008681733,0.000246043,0.0000101267,0.04906906,0.1241074,0.7988833],"study_design_scores_gemma":[0.0003201442,0.00006536437,0.009375265,0.000004142163,0.00001471903,0.00003017954,0.0165838,0.01522554,8.959233e-7,0.001708266,0.9566145,0.00005720624],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4901774,0.006268912,0.2013952,0.2317124,0.003149207,0.001461066,0.03510616,0.0001282592,0.03060134],"genre_scores_gemma":[0.9914062,0.0006906645,0.001637916,0.004695772,0.0001155206,0.000001289817,0.001179164,0.000004722156,0.0002687688],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8325071,"threshold_uncertainty_score":0.9914796,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2883256923","doi":"10.1145/3239570","title":"Evaluation-as-a-Service for the Computational Sciences","year":2018,"lang":"en","type":"article","venue":"Journal of Data and Information Quality","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Data science; Crowdsourcing; Field (mathematics); Executable; Domain (mathematical analysis); Service (business); Confidentiality; Big data; Work (physics); World Wide Web; Data mining; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.2061877675601156,"gpt":0.4578079204475153,"spread":0.2516201528873997,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010552,0.00004053088,0.00006271511,0.00006530986,0.000399626,0.000363438,0.0009756603,0.00001806932,0.00001545962],"category_scores_gemma":[0.00134008,0.0000246838,0.00001346201,0.0002195429,0.00007974594,0.008163187,0.0001553626,0.00006479221,0.00001707799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001219836,"about_ca_system_score_gemma":0.0003050714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002933175,"about_ca_topic_score_gemma":0.000006664369,"domain_scores_codex":[0.9987254,0.0001248028,0.0004169543,0.00006986487,0.0006014598,0.00006148206],"domain_scores_gemma":[0.9973268,0.0005496059,0.0005627371,0.0002953162,0.001233146,0.00003242395],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002100077,0.00001909103,0.0004669597,0.00002228125,0.00002688163,1.628289e-8,0.001999551,0.0005775252,0.000008514745,0.2633557,0.008554601,0.7249479],"study_design_scores_gemma":[0.0003362994,0.0001018782,0.026372,0.000007697025,0.00001453535,0.00001765218,0.0003301192,0.8309835,0.000006493758,0.009466233,0.1323229,0.0000406437],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005839112,0.00007849322,0.9734832,0.01920679,0.0002177447,0.0001150647,0.00004469369,0.000008596578,0.001006279],"genre_scores_gemma":[0.8973797,0.00004238575,0.09706096,0.005113926,0.0002490061,0.000003672358,0.0001436514,0.000001312381,0.000005379151],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8915406,"threshold_uncertainty_score":0.5918114,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3042293458","doi":"10.1145/3328747","title":"Characterizing Disinformation Risk to Open Data in the Post-Truth Era","year":2020,"lang":"en","type":"article","venue":"Journal of Data and Information Quality","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Dalhousie University","funders":"","keywords":"Disinformation; Open data; Computer science; Data science; Data quality; Big data; Analytics; Harm; Transparency (behavior); Quality (philosophy); Business intelligence; Social media; Internet privacy; Computer security; Risk analysis (engineering); Business; Data mining; World Wide Web; Political science; Marketing","retraction":null,"screen_n_in":null,"score":{"opus":0.4065919786832916,"gpt":0.4886072663206588,"spread":0.08201528763736715,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","scholarly_communication"],"category_scores_codex":[0.03093886,0.00008545559,0.0002553613,0.0001640037,0.0001502979,0.002509251,0.006948728,0.00002940476,0.00006600915],"category_scores_gemma":[0.01583162,0.00004949083,0.00002129329,0.0005467085,0.00002810091,0.05792405,0.004427429,0.0002530707,0.0001290751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001312123,"about_ca_system_score_gemma":0.0000835328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001685144,"about_ca_topic_score_gemma":0.00004972967,"domain_scores_codex":[0.9958092,0.0005892538,0.002059575,0.0001559088,0.001262815,0.0001232527],"domain_scores_gemma":[0.9955459,0.0008492147,0.001676866,0.001531337,0.0002618857,0.0001347896],"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":[0.0004791124,0.00006241616,0.003984691,0.00006068265,0.00003286092,0.000001816274,0.04101745,0.00002555692,0.00001319223,0.01245517,0.07857095,0.8632961],"study_design_scores_gemma":[0.0005850638,0.0001121713,0.2279886,0.0000203518,0.00001454624,0.000007177306,0.03070441,0.003427543,0.000004429816,0.000678912,0.736358,0.00009888567],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6037064,0.00005412143,0.1587848,0.2077869,0.0007229007,0.001364874,0.0191085,0.00001909563,0.008452374],"genre_scores_gemma":[0.9459391,0.0002311935,0.00501311,0.04573105,0.0001487081,0.000001804624,0.002927002,0.000002672054,0.000005325878],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8631972,"threshold_uncertainty_score":0.9985262,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2604978321","doi":"10.1145/3148239","title":"Ontological Multidimensional Data Models and Contextual Data Quality","year":2017,"lang":"en","type":"article","venue":"Journal of Data and Information Quality","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University; Carleton University","funders":"","keywords":"Computer science; Datalog; Dimension (graph theory); Context (archaeology); Data model (GIS); Data quality; Representation (politics); Ontology; Data mining; Data modeling; Theoretical computer science; Quality (philosophy); Information retrieval; Artificial intelligence; Database; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.7487698138314796,"gpt":0.5623588758904626,"spread":0.1864109379410169,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","scholarly_communication","open_science"],"category_scores_codex":[0.04532996,0.0001556258,0.0005568557,0.0001305703,0.0006142389,0.001648198,0.007592584,0.0000990979,0.00008860853],"category_scores_gemma":[0.02243092,0.0001019939,0.00003045195,0.00006866532,0.0004314378,0.06763577,0.01360672,0.0002924067,0.00003136159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001386845,"about_ca_system_score_gemma":0.0001339208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003799647,"about_ca_topic_score_gemma":0.0002512015,"domain_scores_codex":[0.9942402,0.0006842088,0.002544707,0.0004558095,0.001877443,0.0001976868],"domain_scores_gemma":[0.9862794,0.001627384,0.003372045,0.007910131,0.0005466595,0.0002643237],"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":[0.0006150565,0.0002105463,0.005029247,0.00007921764,0.0001504444,0.000007444096,0.001091155,0.0000147704,0.00001586194,0.1420344,0.2114191,0.6393327],"study_design_scores_gemma":[0.002368359,0.000100509,0.1741951,0.00004348304,0.0000601109,0.00006109309,0.005304737,0.07036535,0.000003346339,0.01832612,0.7288753,0.0002965089],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3279143,0.0009062098,0.5598378,0.03547599,0.001610404,0.000702173,0.06571767,0.00004392462,0.007791618],"genre_scores_gemma":[0.9670061,0.0008466337,0.02390376,0.002801766,0.0001935651,6.782486e-7,0.0051445,0.000004264868,0.00009868061],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6390919,"threshold_uncertainty_score":0.9993882,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2726342193","doi":"10.1145/3041761","title":"Dependable Data Repairing with Fixing Rules","year":2017,"lang":"en","type":"article","venue":"Journal of Data and Information Quality","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Tuple; Data mining; Set (abstract data type); Data integrity; Class (philosophy); Artificial intelligence; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.4729249625945691,"gpt":0.5056587030425448,"spread":0.03273374044797572,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0224138,0.00007716111,0.0002424564,0.0001301955,0.0005119851,0.002336628,0.004255051,0.0000297141,0.00007370351],"category_scores_gemma":[0.007031674,0.00004731866,0.00001962944,0.00006203949,0.0001017584,0.05900216,0.002837756,0.0001419841,0.0000517918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001093236,"about_ca_system_score_gemma":0.00008152003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001347682,"about_ca_topic_score_gemma":0.00008555132,"domain_scores_codex":[0.997152,0.0001453698,0.001225993,0.000165596,0.001190182,0.0001208469],"domain_scores_gemma":[0.9931403,0.0003544428,0.002416975,0.003678926,0.0003096001,0.00009972096],"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":[0.0003396439,0.00007231635,0.02509123,0.0001297332,0.0001392491,0.00001448056,0.00146423,0.00002544168,0.00001083491,0.01956325,0.1666232,0.7865264],"study_design_scores_gemma":[0.0007154831,0.00005744772,0.08131846,0.00006412008,0.00002873213,0.00004750738,0.00331194,0.003230717,0.00001799727,0.003151797,0.9079359,0.0001199174],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5177891,0.0002965221,0.4129988,0.01693341,0.001126611,0.0004138806,0.007338042,0.00004741095,0.04305623],"genre_scores_gemma":[0.9530135,0.0003379172,0.04388603,0.001262162,0.0002357761,6.395828e-7,0.0009921059,0.000005440054,0.0002664046],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7864065,"threshold_uncertainty_score":0.9986991,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2559039427","doi":"10.1145/3005395","title":"Editorial","year":2016,"lang":"en","type":"editorial","venue":"Journal of Data and Information Quality","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":12,"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":"Citation; Library science; Amazon rainforest; Computer science; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.1552228863963259,"gpt":0.4827182751786968,"spread":0.3274953887823709,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch","scholarly_communication"],"category_scores_codex":[0.03988469,0.0001853865,0.000656428,0.0004277632,0.0001217008,0.001224677,0.00336381,0.0004434359,0.0002146138],"category_scores_gemma":[0.05258418,0.0001067161,0.0001067146,0.0002050875,0.0001167395,0.02607521,0.00151051,0.0005947236,0.0002990428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005422331,"about_ca_system_score_gemma":0.0005145671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002590111,"about_ca_topic_score_gemma":0.000008583929,"domain_scores_codex":[0.9893974,0.0005843971,0.003495985,0.0002233667,0.006117228,0.0001816249],"domain_scores_gemma":[0.9836105,0.005821454,0.005752792,0.001874577,0.002727347,0.0002132904],"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":[0.0001232791,0.00001499579,0.000003763073,0.00004134734,0.00004003839,3.666419e-7,0.0001454716,1.194438e-7,4.106633e-7,0.001055245,0.9067286,0.09184632],"study_design_scores_gemma":[0.0008225002,0.00008446915,0.00003614212,0.00006351248,0.00003563898,0.000001397591,0.0003837147,0.00000584991,8.023886e-7,0.005561367,0.9928522,0.0001524121],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.000007846798,0.00006447607,0.01387044,0.001041563,0.9726511,0.00008462857,0.01002622,0.00000749013,0.002246189],"genre_scores_gemma":[0.00001646157,0.0008656309,0.0004867419,0.0002021593,0.9968705,6.749717e-7,0.001207533,0.000004215344,0.0003460566],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.09169391,"threshold_uncertainty_score":0.9998121,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2797647106","doi":"10.1145/3190577","title":"InfoClean","year":2017,"lang":"en","type":"article","venue":"Journal of Data and Information Quality","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Confidentiality; Information sensitivity; Data mining; Process (computing); Data quality; Set (abstract data type); Information privacy; Information loss; Data set; Database; Data science; Computer security; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1247884661779293,"gpt":0.3855261588859472,"spread":0.2607376927080179,"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":[0.002214273,0.00005036779,0.0001153354,0.00008019911,0.0002130966,0.0008078361,0.02972539,0.00004399081,0.000004408269],"category_scores_gemma":[0.02812174,0.00003932069,0.00001563508,0.00004138452,0.0000776688,0.04651909,0.05689732,0.0001665868,0.00001179596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000127698,"about_ca_system_score_gemma":0.00005348599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001650431,"about_ca_topic_score_gemma":0.000001731292,"domain_scores_codex":[0.9990594,0.00002895773,0.0005021872,0.00006085863,0.0002627324,0.00008582795],"domain_scores_gemma":[0.9907627,0.00006267646,0.00112653,0.007860795,0.0001384678,0.00004887313],"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":[0.00001063374,0.0000140624,0.004101779,0.00003683812,0.00002090883,0.000001939977,0.0001884517,3.248371e-7,0.00001970282,0.02400916,0.2527832,0.7188129],"study_design_scores_gemma":[0.001235881,0.0001370272,0.2327377,0.00008287722,0.00001108801,0.0001586977,0.0002823566,0.04984324,0.0005220816,0.1533345,0.5613782,0.0002764145],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04777244,0.00007527477,0.8783711,0.06789869,0.0005975274,0.00007191343,0.0001685528,0.00008250752,0.004961994],"genre_scores_gemma":[0.6067118,0.0004306412,0.3919497,0.0008021715,0.00006564482,3.219892e-7,0.00003260436,0.000001720799,0.000005415297],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7185366,"threshold_uncertainty_score":0.9800648,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2542250253","doi":"10.1145/3012004","title":"The Challenge of Test Data Quality in Data Processing","year":2017,"lang":"en","type":"article","venue":"Journal of Data and Information Quality","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Vienna Science and Technology Fund","keywords":"Citation; Test (biology); Computer science; Data quality; Library science; Quality (philosophy); World Wide Web; Data science; Engineering; Operations management","retraction":null,"screen_n_in":null,"score":{"opus":0.6182808189797534,"gpt":0.5581897740451959,"spread":0.06009104493455752,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","scholarly_communication","open_science"],"category_scores_codex":[0.07684713,0.00009933436,0.0003788442,0.000132241,0.0004888876,0.001588811,0.01318193,0.00005144603,0.00002323427],"category_scores_gemma":[0.05005168,0.00005754457,0.0000218084,0.0001495291,0.0003019364,0.04817026,0.00825838,0.0002452292,0.00001239321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001384224,"about_ca_system_score_gemma":0.0001956231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002340162,"about_ca_topic_score_gemma":0.0008734395,"domain_scores_codex":[0.9943293,0.000458429,0.003107767,0.0002626484,0.001677534,0.0001642592],"domain_scores_gemma":[0.9806765,0.002355112,0.006202887,0.01011992,0.0005444069,0.0001012007],"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":[0.0001138698,0.0001372191,0.009313148,0.0001532511,0.00002424251,0.000001029494,0.001212401,0.000001661702,0.000003790228,0.008940975,0.03732755,0.9427708],"study_design_scores_gemma":[0.0008729789,0.00004662225,0.2072715,0.00009409866,0.00001942664,0.000004727925,0.007105169,0.006788434,0.000004392203,0.00884197,0.7688248,0.0001258078],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1805124,0.007650509,0.2061564,0.407966,0.004576495,0.002813901,0.1164618,0.00007585327,0.07378659],"genre_scores_gemma":[0.9935477,0.002140949,0.002447961,0.0004336482,0.0001307293,6.512998e-7,0.001232431,0.000003363466,0.00006259493],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9426451,"threshold_uncertainty_score":0.9997627,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2736121570","doi":"10.1145/3058750","title":"An Exploratory Case Study to Understand Primary Care Users and Their Data Quality Tradeoffs","year":2017,"lang":"en","type":"article","venue":"Journal of Data and Information Quality","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Conestoga College","funders":"","keywords":"Completeness (order theory); Computer science; Data quality; Workflow; Quality (philosophy); Data mining; Data science; Database; Business; Mathematics; Marketing","retraction":null,"screen_n_in":null,"score":{"opus":0.5819441096579165,"gpt":0.5200055265519502,"spread":0.06193858310596634,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.02800998,0.0001612598,0.0004645214,0.0002225497,0.0007673483,0.002657176,0.003366498,0.00004599134,0.00001649561],"category_scores_gemma":[0.002455822,0.0001085127,0.00002853026,0.0001231265,0.0001641994,0.04667697,0.002661333,0.0002022967,0.000007572693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004906981,"about_ca_system_score_gemma":0.0001589845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003902924,"about_ca_topic_score_gemma":0.001583568,"domain_scores_codex":[0.9955763,0.0009561778,0.001834873,0.0003435259,0.001123804,0.000165289],"domain_scores_gemma":[0.9923167,0.0004962774,0.001788617,0.004659321,0.0004020772,0.0003369556],"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":[0.0006264931,0.0005843476,0.02512493,0.0003179727,0.0002073394,0.0001012326,0.2656513,0.00001195318,0.00002245608,0.002399811,0.02663383,0.6783183],"study_design_scores_gemma":[0.001289773,0.0003504815,0.08161928,0.00002377041,0.00003580414,0.0001018758,0.8580037,0.0001938912,0.000004864375,0.0006070647,0.05756571,0.0002037512],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9699151,0.00009914848,0.02271079,0.001317441,0.0002657199,0.0003519229,0.004899886,0.00001031295,0.0004297151],"genre_scores_gemma":[0.9971573,0.00008693444,0.001059221,0.001162771,0.00007402505,6.739053e-7,0.0004489303,0.000003719083,0.000006447672],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6781145,"threshold_uncertainty_score":0.9983782,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4366683629","doi":"10.1145/3592534","title":"A Method to Classify Data Quality for Decision Making Under Uncertainty","year":2023,"lang":"en","type":"article","venue":"Journal of Data and Information Quality","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data quality; Quality (philosophy); Context (archaeology); Process (computing); Data mining; Decision support system; Risk analysis (engineering); Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.6503576233917492,"gpt":0.6216140905973337,"spread":0.02874353279441544,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08870495,0.000141448,0.0004960076,0.0005765239,0.0002598975,0.0009816911,0.003528409,0.00008366675,0.00008426142],"category_scores_gemma":[0.02359781,0.00009904963,0.00007733389,0.001041137,0.00004930163,0.0157547,0.003249228,0.0001801006,0.0001360457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005039094,"about_ca_system_score_gemma":0.0001588349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004923259,"about_ca_topic_score_gemma":0.00009392247,"domain_scores_codex":[0.9933423,0.0008287317,0.003119247,0.0003707424,0.002073271,0.0002656634],"domain_scores_gemma":[0.9845453,0.009604562,0.00199241,0.002782747,0.0008491657,0.0002257971],"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":[0.0003490023,0.00002489638,0.0001422521,0.00004898349,0.00003907956,4.401806e-7,0.0006569611,0.0007227823,0.00001046146,0.02417184,0.2809617,0.6928716],"study_design_scores_gemma":[0.0006799682,0.00008421185,0.02437999,0.00007001692,0.00002932078,0.000006514759,0.01079857,0.02816191,0.000003580057,0.05061464,0.8850033,0.0001679391],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008729628,0.00001931649,0.9744458,0.00933944,0.0004082747,0.0003081096,0.006353676,0.0000244693,0.0003712537],"genre_scores_gemma":[0.2065249,0.0002521815,0.7639661,0.02334325,0.0005890628,0.0000147286,0.004972117,0.00002058371,0.0003170806],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6927037,"threshold_uncertainty_score":0.9980114,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2516718098","doi":"10.1145/2883616","title":"Unifying Data and Constraint Repairs","year":2016,"lang":"en","type":"article","venue":"Journal of Data and Information Quality","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data integrity; Data quality; Constraint (computer-aided design); Scalability; Set (abstract data type); Data mining; Semantics (computer science); Data type; Data modeling; Quality (philosophy); Database; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.4241185632103378,"gpt":0.4856853147821305,"spread":0.0615667515717927,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.02414628,0.00007083991,0.0002175969,0.0001666895,0.000105854,0.0004412346,0.00143942,0.00003512104,0.0001236983],"category_scores_gemma":[0.008258068,0.00003786568,0.00001809637,0.0001387017,0.0001789701,0.02498526,0.001700755,0.0000828897,0.00003169769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001193981,"about_ca_system_score_gemma":0.00007275897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001837763,"about_ca_topic_score_gemma":0.00001284292,"domain_scores_codex":[0.9970779,0.0002742521,0.001514367,0.0001594,0.0008687762,0.0001052387],"domain_scores_gemma":[0.9958989,0.001046205,0.001195812,0.001472221,0.0002576878,0.0001291492],"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":[0.00005194274,0.00001664554,0.002216785,0.00002745955,0.00003063586,0.000001500853,0.0005547655,2.561141e-7,0.00002182019,0.02468116,0.08186843,0.8905286],"study_design_scores_gemma":[0.0006963685,0.00004564319,0.01663969,0.00004771412,0.00001677873,0.00004800878,0.005993658,0.0005139337,0.00001027753,0.007119594,0.968779,0.00008927982],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1929626,0.0004199809,0.7375439,0.04379009,0.0009807753,0.0003518716,0.01283271,0.00004186376,0.01107627],"genre_scores_gemma":[0.9825918,0.001437984,0.012566,0.002776641,0.0001310992,4.021833e-7,0.0003476566,0.000003136897,0.0001452829],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8904393,"threshold_uncertainty_score":0.9886518,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4224288101","doi":"10.1145/3524303","title":"Contextual Data Cleaning with Ontology Functional Dependencies","year":2022,"lang":"en","type":"article","venue":"Journal of Data and Information Quality","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Tech University; University of Waterloo; McMaster University","funders":"","keywords":"Ontology; Axiom; Computer science; Functional dependency; Inference; Dependency (UML); Set (abstract data type); Dependency theory (database theory); Relation (database); Data mining; Artificial intelligence; Relational database; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.4677702605003999,"gpt":0.452390842963974,"spread":0.01537941753642585,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01965825,0.00007485142,0.0002399641,0.000215312,0.0003718963,0.0003486891,0.002125288,0.00002035389,0.0007801087],"category_scores_gemma":[0.002353606,0.00005090814,0.00002005252,0.0002561655,0.00009541355,0.01824009,0.00278619,0.0002601177,0.00002295756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000309135,"about_ca_system_score_gemma":0.0001774111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007038731,"about_ca_topic_score_gemma":0.0001273336,"domain_scores_codex":[0.9960566,0.0005074446,0.001294394,0.0001704441,0.001851863,0.0001192398],"domain_scores_gemma":[0.9962589,0.0007830739,0.001380099,0.00118925,0.0003076586,0.00008101842],"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":[0.001447198,0.0001606272,0.008092613,0.00004342758,0.0001939934,0.00001232651,0.003837462,0.0003811502,0.00001173061,0.106944,0.4624178,0.4164577],"study_design_scores_gemma":[0.000935105,0.0002212702,0.02922946,0.000005750696,0.00002535382,0.0002069625,0.04179703,0.002337459,0.000001951253,0.001926091,0.923215,0.00009858714],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1877855,0.000399644,0.7680259,0.01547386,0.00177725,0.0003985738,0.01313973,0.00003932301,0.01296018],"genre_scores_gemma":[0.9888012,0.000051509,0.004055404,0.004526499,0.0001055607,0.000001724062,0.002280913,0.000002927509,0.0001742654],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8010157,"threshold_uncertainty_score":0.9954913,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3195742729","doi":"10.1145/3468063","title":"Benchmark of Bitrate Adaptation in Video Streaming","year":2021,"lang":"en","type":"article","venue":"Journal of Data and Information Quality","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Benchmark (surveying); Upload; Task (project management); Heuristic; Benchmarking; Throughput; Upper and lower bounds; Streaming algorithm; Session (web analytics); Time complexity; Algorithm; Artificial intelligence; Wireless; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.08316224013716889,"gpt":0.3659461388783409,"spread":0.282783898741172,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002150246,0.00004646831,0.0001547465,0.0001093557,0.00002651383,0.0001202994,0.0003238683,0.00002634905,0.000007989182],"category_scores_gemma":[0.0002842769,0.00004080091,0.00002232357,0.0002403565,0.00001524615,0.01398285,0.0001799968,0.0001023237,0.000001002255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001871765,"about_ca_system_score_gemma":0.0002299756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004969941,"about_ca_topic_score_gemma":0.00002235917,"domain_scores_codex":[0.9985076,0.0001662692,0.0009097636,0.00005945903,0.0002872203,0.00006965686],"domain_scores_gemma":[0.9985667,0.0001349139,0.000666096,0.0003044812,0.000291422,0.00003639902],"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":[0.0000666386,0.0002786065,0.007526369,0.0005865784,0.00007520318,0.00001956445,0.02066514,0.0004495515,0.002533752,0.1247654,0.001567192,0.841466],"study_design_scores_gemma":[0.005594988,0.0005283513,0.5445274,0.0008094475,0.00005479005,0.0002611035,0.03061565,0.3375583,0.02104201,0.0139182,0.0444091,0.0006806559],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1754363,0.0001521119,0.8220522,0.001314673,0.0001344012,0.00004200082,0.00004425579,0.000004165604,0.0008197962],"genre_scores_gemma":[0.9441237,0.0002174855,0.05513039,0.0004385943,0.00002060385,2.74979e-7,0.00006431247,8.043946e-7,0.000003795185],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8407853,"threshold_uncertainty_score":0.9998081,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2972308422","doi":"10.1145/3309682","title":"Improving Adaptive Video Streaming through Session Classification","year":2019,"lang":"en","type":"article","venue":"Journal of Data and Information Quality","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Session (web analytics); Popularity; Quality of experience; Throughput; Computer network; The Internet; Multimedia; Quality of service; Real-time computing; World Wide Web; Telecommunications; Wireless","retraction":null,"screen_n_in":null,"score":{"opus":0.09982095728446964,"gpt":0.3748448468625624,"spread":0.2750238895780927,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002006854,0.00007728937,0.000164848,0.00007380303,0.0000850941,0.0003079609,0.0006300884,0.0000454314,0.000009873158],"category_scores_gemma":[0.0001434837,0.00005986482,0.00002968975,0.0001390533,0.00001763391,0.0374161,0.0003422513,0.000169124,0.00002070334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004568599,"about_ca_system_score_gemma":0.0001406418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004773492,"about_ca_topic_score_gemma":0.000001162652,"domain_scores_codex":[0.9984581,0.0001473063,0.0007800504,0.0001062718,0.0004017543,0.0001065269],"domain_scores_gemma":[0.9978963,0.0001447346,0.001105173,0.0005382537,0.0002659622,0.00004957371],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007858734,0.00009341363,0.00285404,0.0002412591,0.00004913811,0.000001242311,0.007486521,0.00002453473,0.003455881,0.1440228,0.002169281,0.8395233],"study_design_scores_gemma":[0.004457525,0.00105497,0.2017867,0.0005081536,0.00006511891,0.0001570245,0.02614356,0.6553015,0.005001083,0.006468399,0.0981733,0.0008827541],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05270239,0.00004403864,0.9447902,0.00095433,0.0002417403,0.00009549213,0.00002406104,0.00001497827,0.001132703],"genre_scores_gemma":[0.9232413,0.00007693333,0.07573932,0.0008309663,0.00005741863,6.053308e-7,0.00003777342,0.000001843144,0.00001391392],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8705388,"threshold_uncertainty_score":0.976047,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4402806881","doi":"10.1145/3696110","title":"Automated anomaly detection for categorical data by repurposing a form filling recommender system","year":2024,"lang":"en","type":"article","venue":"Journal of Data and Information Quality","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"Fonds National de la Recherche Luxembourg; Natural Sciences and Engineering Research Council of Canada; BNP Paribas Cardif; Canada Research Chairs; Science Foundation Ireland","keywords":"Repurposing; Computer science; Categorical variable; Recommender system; Anomaly detection; Data mining; Anomaly (physics); Artificial intelligence; Information retrieval; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.08194400033841359,"gpt":0.3697688114118219,"spread":0.2878248110734083,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002117968,0.00007950013,0.0001452864,0.0001325811,0.0001938142,0.000597074,0.0007927285,0.0000659611,0.000001438209],"category_scores_gemma":[0.00008071769,0.00006465517,0.00003261184,0.0002720591,0.00001384393,0.0131519,0.0003088981,0.0001405456,0.000002657169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007920488,"about_ca_system_score_gemma":0.00006613287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002994589,"about_ca_topic_score_gemma":0.000001940222,"domain_scores_codex":[0.9986984,0.00004213219,0.000817357,0.0001578247,0.0001782967,0.0001060108],"domain_scores_gemma":[0.9985504,0.0001371883,0.0004268601,0.0006579789,0.0001611736,0.00006639721],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003397198,0.00003673903,0.00002104803,0.0006178017,0.00008695166,0.000001057337,0.0006250154,0.000009430137,0.0007996479,0.0299416,0.07652248,0.8913043],"study_design_scores_gemma":[0.0001191445,0.0000619399,0.00004982113,0.0000351631,0.00001558867,0.0001584316,0.000179155,0.7250628,0.0005627057,0.0003236596,0.273357,0.00007456137],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001213028,0.0002333891,0.9966207,0.000775709,0.000218744,0.0001719187,0.0003239151,0.000325828,0.0001167493],"genre_scores_gemma":[0.9201317,0.000182045,0.07889946,0.0002109844,0.0001114307,0.00001176138,0.0004360392,0.000005614565,0.00001098779],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9189187,"threshold_uncertainty_score":0.9534814,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4405575840","doi":"10.1145/3708503","title":"Editorial: Special Issue on Software Engineering and AI for Data Quality","year":2024,"lang":"en","type":"editorial","venue":"Journal of Data and Information Quality","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Quality (philosophy); Data quality; Data science; Software; Software engineering; Software quality; Software development; Engineering; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.089642029191433,"gpt":0.3800565962012896,"spread":0.2904145670098566,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.005113016,0.0003138166,0.0006024451,0.0003689813,0.0001401385,0.001946331,0.001475956,0.0004763953,0.00007270258],"category_scores_gemma":[0.01296599,0.0002551383,0.00005815924,0.0002187049,0.00005731371,0.02365725,0.001499053,0.0008827664,0.00005779833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003718397,"about_ca_system_score_gemma":0.00018182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000165233,"about_ca_topic_score_gemma":0.00002600141,"domain_scores_codex":[0.9967765,0.0000197416,0.001556288,0.0003252304,0.001103653,0.0002185825],"domain_scores_gemma":[0.9955688,0.0007436647,0.001492905,0.001075836,0.001080252,0.00003860755],"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":[0.0002186374,0.00002244567,0.00001842113,0.003382204,0.00006658932,5.369702e-7,0.00004132128,0.000002953263,5.729879e-7,0.001046287,0.9634307,0.03176935],"study_design_scores_gemma":[0.0004495537,0.00002540112,0.00006494261,0.0004520082,0.0001618152,0.000001522865,0.00007432949,0.001261152,0.000001025083,0.0003186086,0.9968774,0.000312254],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.0000380799,0.000181574,0.006553792,0.0007682111,0.9823971,0.000223903,0.009626053,0.00003973872,0.0001715402],"genre_scores_gemma":[0.00001403466,0.0004900568,0.0008793402,0.0004091295,0.9795383,0.00000257549,0.01860843,0.00002067307,0.00003742298],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.03344671,"threshold_uncertainty_score":0.9999901,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}