{"meta":{"query_hash":"3a6ab8d7bbaf","filters":{"venue":"Journal of Data and Information Quality"},"cohort_total":17,"direct_labels_cover":0,"predictions_cover":17,"exported":17,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/3a6ab8d7bbaf","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Data+and+Information+Quality"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.4241185632103378,"score_gpt":0.4856853147821305,"score_spread":0.0615667515717927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2516718098","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19296256,0.00041998093,0.7375439,0.04379009,0.0009807753,0.0003518716,0.012832709,0.00004186376,0.011076272],"genre_scores_gemma":[0.9825918,0.0014379842,0.012566001,0.0027766412,0.00013109918,4.021833e-7,0.0003476566,0.000003136897,0.00014528289],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99707794,0.0002742521,0.0015143673,0.0001594,0.00086877623,0.00010523872],"domain_scores_gemma":[0.9958989,0.0010462049,0.0011958117,0.0014722215,0.00025768782,0.00012914918],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.024146281,0.00007083991,0.00021759687,0.00016668947,0.00010585403,0.0004412346,0.0014394202,0.00003512104,0.0001236983],"category_scores_gemma":[0.008258068,0.000037865677,0.000018096367,0.0001387017,0.00017897015,0.02498526,0.0017007552,0.0000828897,0.00003169769],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051942738,0.000016645536,0.002216785,0.00002745955,0.000030635863,0.0000015008526,0.0005547655,2.5611408e-7,0.000021820195,0.024681162,0.081868425,0.8905286],"study_design_scores_gemma":[0.0006963685,0.000045643188,0.016639687,0.000047714122,0.000016778726,0.00004800878,0.005993658,0.0005139337,0.0000102775275,0.007119594,0.968779,0.00008927982],"about_ca_topic_score_codex":0.000018377626,"about_ca_topic_score_gemma":0.0000128429165,"teacher_disagreement_score":0.89043933,"about_ca_system_score_codex":0.000011939811,"about_ca_system_score_gemma":0.00007275897,"threshold_uncertainty_score":0.98865175},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; 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","score_opus":0.6182808189797534,"score_gpt":0.5581897740451959,"score_spread":0.060091044934557525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2542250253","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18051244,0.007650509,0.20615636,0.40796602,0.0045764954,0.0028139008,0.11646183,0.00007585327,0.07378659],"genre_scores_gemma":[0.9935477,0.0021409488,0.0024479614,0.00043364818,0.00013072934,6.5129984e-7,0.0012324306,0.0000033634656,0.00006259493],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99432933,0.00045842896,0.0031077666,0.00026264836,0.0016775338,0.00016425923],"domain_scores_gemma":[0.9806765,0.002355112,0.0062028873,0.01011992,0.00054440694,0.0001012007],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","scholarly_communication","open_science"],"category_scores_codex":[0.07684713,0.00009933436,0.00037884415,0.000132241,0.0004888876,0.0015888112,0.013181928,0.000051446033,0.000023234266],"category_scores_gemma":[0.05005168,0.000057544567,0.000021808397,0.00014952908,0.00030193635,0.048170265,0.00825838,0.00024522917,0.000012393212],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000113869806,0.0001372191,0.0093131475,0.00015325108,0.000024242509,0.0000010294943,0.0012124007,0.0000016617016,0.0000037902275,0.008940975,0.03732755,0.94277084],"study_design_scores_gemma":[0.00087297894,0.000046622252,0.20727155,0.00009409866,0.000019426641,0.0000047279254,0.0071051694,0.0067884335,0.000004392203,0.00884197,0.7688248,0.00012580781],"about_ca_topic_score_codex":0.0002340162,"about_ca_topic_score_gemma":0.0008734395,"teacher_disagreement_score":0.9426451,"about_ca_system_score_codex":0.000013842239,"about_ca_system_score_gemma":0.00019562313,"threshold_uncertainty_score":0.99976265},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Citation; Library science; Amazon rainforest; Computer science; World Wide Web","score_opus":0.15522288639632592,"score_gpt":0.4827182751786968,"score_spread":0.3274953887823709,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559039427","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007846798,0.00006447607,0.013870438,0.001041563,0.9726511,0.00008462857,0.0100262165,0.0000074901304,0.0022461887],"genre_scores_gemma":[0.00001646157,0.00086563086,0.0004867419,0.00020215931,0.9968705,6.749717e-7,0.0012075328,0.0000042153442,0.00034605656],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9893974,0.0005843971,0.003495985,0.00022336669,0.006117228,0.00018162494],"domain_scores_gemma":[0.9836105,0.0058214543,0.0057527917,0.0018745768,0.0027273472,0.00021329042],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch","scholarly_communication"],"category_scores_codex":[0.039884686,0.00018538645,0.000656428,0.00042776315,0.00012170085,0.0012246774,0.0033638098,0.00044343589,0.00021461376],"category_scores_gemma":[0.05258418,0.000106716114,0.00010671463,0.00020508746,0.0001167395,0.026075209,0.0015105105,0.0005947236,0.00029904282],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012327907,0.000014995789,0.0000037630732,0.000041347335,0.000040038387,3.6664193e-7,0.00014547158,1.1944384e-7,4.1066332e-7,0.0010552453,0.9067286,0.091846325],"study_design_scores_gemma":[0.00082250015,0.000084469146,0.000036142115,0.00006351248,0.000035638983,0.0000013975911,0.00038371474,0.0000058499104,8.0238857e-7,0.0055613667,0.9928522,0.00015241213],"about_ca_topic_score_codex":0.000025901112,"about_ca_topic_score_gemma":0.000008583929,"teacher_disagreement_score":0.09169391,"about_ca_system_score_codex":0.00005422331,"about_ca_system_score_gemma":0.00051456713,"threshold_uncertainty_score":0.9998121},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.7487698138314796,"score_gpt":0.5623588758904626,"score_spread":0.18641093794101693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604978321","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32791427,0.00090620975,0.55983776,0.035475988,0.0016104035,0.000702173,0.065717675,0.00004392462,0.0077916184],"genre_scores_gemma":[0.96700615,0.00084663375,0.023903757,0.0028017664,0.00019356514,6.782486e-7,0.0051444997,0.0000042648685,0.00009868061],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99424016,0.00068420876,0.0025447067,0.00045580947,0.0018774432,0.0001976868],"domain_scores_gemma":[0.9862794,0.0016273839,0.003372045,0.0079101315,0.0005466595,0.0002643237],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","scholarly_communication","open_science"],"category_scores_codex":[0.04532996,0.00015562582,0.0005568557,0.00013057029,0.0006142389,0.0016481981,0.0075925835,0.0000990979,0.00008860853],"category_scores_gemma":[0.02243092,0.000101993915,0.00003045195,0.00006866532,0.0004314378,0.067635775,0.013606718,0.00029240674,0.000031361586],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061505655,0.00021054629,0.0050292467,0.000079217636,0.00015044442,0.0000074440964,0.0010911551,0.000014770402,0.000015861939,0.1420344,0.21141914,0.6393327],"study_design_scores_gemma":[0.0023683594,0.00010050902,0.17419513,0.000043483044,0.0000601109,0.00006109309,0.0053047366,0.07036535,0.0000033463389,0.018326122,0.7288753,0.0002965089],"about_ca_topic_score_codex":0.00037996468,"about_ca_topic_score_gemma":0.00025120153,"teacher_disagreement_score":0.6390919,"about_ca_system_score_codex":0.000013868454,"about_ca_system_score_gemma":0.00013392077,"threshold_uncertainty_score":0.99938816},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.47292496259456906,"score_gpt":0.5056587030425448,"score_spread":0.03273374044797572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2726342193","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5177891,0.00029652208,0.41299877,0.01693341,0.0011266108,0.00041388063,0.007338042,0.00004741095,0.043056235],"genre_scores_gemma":[0.95301354,0.00033791724,0.04388603,0.0012621622,0.00023577614,6.3958277e-7,0.0009921059,0.0000054400543,0.00026640456],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99715203,0.00014536978,0.0012259927,0.00016559596,0.0011901818,0.00012084688],"domain_scores_gemma":[0.99314034,0.00035444277,0.0024169746,0.0036789256,0.0003096001,0.000099720964],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.022413801,0.00007716111,0.0002424564,0.0001301955,0.0005119851,0.0023366276,0.0042550513,0.000029714098,0.00007370351],"category_scores_gemma":[0.007031674,0.000047318656,0.000019629437,0.00006203949,0.00010175842,0.05900216,0.0028377564,0.00014198406,0.000051791798],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033964386,0.000072316354,0.025091225,0.00012973322,0.00013924907,0.000014480564,0.00146423,0.000025441677,0.000010834911,0.019563247,0.16662318,0.78652644],"study_design_scores_gemma":[0.0007154831,0.000057447716,0.08131846,0.00006412008,0.000028732129,0.000047507383,0.0033119398,0.0032307166,0.000017997269,0.0031517968,0.90793586,0.00011991741],"about_ca_topic_score_codex":0.0001347682,"about_ca_topic_score_gemma":0.00008555132,"teacher_disagreement_score":0.7864065,"about_ca_system_score_codex":0.00001093236,"about_ca_system_score_gemma":0.00008152003,"threshold_uncertainty_score":0.99869907},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.5819441096579165,"score_gpt":0.5200055265519502,"score_spread":0.06193858310596634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736121570","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9699151,0.000099148485,0.022710785,0.0013174415,0.00026571992,0.00035192288,0.004899886,0.000010312953,0.00042971515],"genre_scores_gemma":[0.9971573,0.000086934444,0.0010592215,0.0011627714,0.00007402505,6.7390533e-7,0.0004489303,0.0000037190825,0.000006447672],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9955763,0.00095617777,0.0018348726,0.00034352587,0.0011238036,0.00016528899],"domain_scores_gemma":[0.9923167,0.0004962774,0.0017886165,0.0046593207,0.0004020772,0.00033695562],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.028009975,0.00016125984,0.00046452138,0.00022254973,0.00076734833,0.0026571758,0.0033664976,0.000045991335,0.000016495615],"category_scores_gemma":[0.0024558217,0.00010851273,0.000028530258,0.0001231265,0.00016419943,0.046676967,0.0026613327,0.0002022967,0.000007572693],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062649307,0.00058434764,0.025124928,0.00031797268,0.00020733944,0.00010123257,0.26565135,0.000011953179,0.00002245608,0.002399811,0.026633825,0.6783183],"study_design_scores_gemma":[0.0012897727,0.0003504815,0.08161928,0.000023770412,0.000035804136,0.000101875776,0.85800374,0.00019389117,0.000004864375,0.0006070647,0.05756571,0.00020375122],"about_ca_topic_score_codex":0.00039029244,"about_ca_topic_score_gemma":0.0015835679,"teacher_disagreement_score":0.67811453,"about_ca_system_score_codex":0.000049069815,"about_ca_system_score_gemma":0.00015898448,"threshold_uncertainty_score":0.99837816},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.12478846617792934,"score_gpt":0.3855261588859472,"score_spread":0.2607376927080179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797647106","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047772445,0.00007527477,0.8783711,0.06789869,0.00059752737,0.000071913426,0.00016855281,0.00008250752,0.0049619945],"genre_scores_gemma":[0.6067118,0.00043064117,0.39194968,0.0008021715,0.000065644825,3.219892e-7,0.00003260436,0.000001720799,0.0000054152974],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99905944,0.000028957731,0.00050218723,0.000060858627,0.0002627324,0.00008582795],"domain_scores_gemma":[0.99076265,0.00006267646,0.0011265296,0.007860795,0.00013846785,0.000048873135],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0022142727,0.000050367787,0.000115335366,0.00008019911,0.00021309665,0.0008078361,0.02972539,0.000043990807,0.0000044082685],"category_scores_gemma":[0.028121738,0.000039320686,0.000015635083,0.00004138452,0.000077668796,0.04651909,0.05689732,0.00016658679,0.000011795956],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010633739,0.0000140624,0.004101779,0.000036838115,0.000020908832,0.0000019399768,0.00018845173,3.2483715e-7,0.000019702822,0.024009155,0.25278324,0.71881294],"study_design_scores_gemma":[0.0012358808,0.00013702724,0.23273769,0.00008287722,0.000011088013,0.00015869772,0.00028235657,0.049843237,0.00052208157,0.15333447,0.5613782,0.0002764145],"about_ca_topic_score_codex":0.000016504315,"about_ca_topic_score_gemma":0.0000017312922,"teacher_disagreement_score":0.71853656,"about_ca_system_score_codex":0.0000127698,"about_ca_system_score_gemma":0.00005348599,"threshold_uncertainty_score":0.9800648},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Data science; Crowdsourcing; Field (mathematics); Executable; Domain (mathematical analysis); Service (business); Confidentiality; Big data; Work (physics); World Wide Web; Data mining; Computer security","score_opus":0.2061877675601156,"score_gpt":0.4578079204475153,"score_spread":0.2516201528873997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2883256923","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058391117,0.00007849322,0.9734832,0.019206787,0.0002177447,0.00011506471,0.00004469369,0.0000085965785,0.0010062787],"genre_scores_gemma":[0.8973797,0.000042385753,0.09706096,0.0051139263,0.00024900606,0.000003672358,0.00014365141,0.0000013123814,0.000005379151],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987254,0.00012480281,0.00041695428,0.000069864866,0.00060145976,0.00006148206],"domain_scores_gemma":[0.9973268,0.00054960593,0.0005627371,0.00029531625,0.0012331458,0.000032423948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010551997,0.000040530882,0.00006271511,0.00006530986,0.00039962598,0.000363438,0.00097566034,0.00001806932,0.000015459624],"category_scores_gemma":[0.0013400802,0.000024683803,0.000013462014,0.0002195429,0.00007974594,0.008163187,0.0001553626,0.000064792206,0.000017077993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021000766,0.000019091029,0.00046695967,0.000022281247,0.000026881635,1.6282891e-8,0.001999551,0.0005775252,0.000008514745,0.2633557,0.008554601,0.72494787],"study_design_scores_gemma":[0.00033629942,0.00010187821,0.026371997,0.0000076970255,0.000014535349,0.000017652175,0.00033011916,0.8309835,0.000006493758,0.009466233,0.13232292,0.000040643696],"about_ca_topic_score_codex":0.000029331752,"about_ca_topic_score_gemma":0.000006664369,"teacher_disagreement_score":0.8915406,"about_ca_system_score_codex":0.000012198363,"about_ca_system_score_gemma":0.00030507141,"threshold_uncertainty_score":0.59181136},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Computer science; Information retrieval; World Wide Web; Ranking (information retrieval); Context (archaeology); Search engine indexing; Implementation; Data science; Software engineering","score_opus":0.1067568912519719,"score_gpt":0.3914247076637422,"score_spread":0.2846678164117703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899154813","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15006047,0.000020189516,0.8429226,0.0019375865,0.00040738692,0.00006370513,0.000056053177,0.000021866179,0.0045101317],"genre_scores_gemma":[0.9488256,0.00010396949,0.04834303,0.0024686097,0.00018709833,3.315828e-7,0.000035510213,0.0000012797386,0.00003455031],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989668,0.000039463706,0.000561218,0.000034114477,0.00031879783,0.000079602425],"domain_scores_gemma":[0.9987403,0.00003476776,0.00037278587,0.00032345304,0.00044940496,0.00007929713],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0017995344,0.00004056701,0.000086204345,0.000098749486,0.000087054934,0.00023230056,0.0007086478,0.0000251479,0.000028111885],"category_scores_gemma":[0.00016465325,0.000029179357,0.000016435377,0.00016051509,0.00004830942,0.025170324,0.00026417006,0.00008664531,0.000053771346],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000069919726,0.00003736054,0.0022411705,0.00005612273,0.000019824844,0.0000012423307,0.0057079634,7.286289e-7,0.00012316545,0.11655656,0.016321408,0.85886455],"study_design_scores_gemma":[0.000881172,0.0004357025,0.09708066,0.000021416505,0.0000063044663,0.00015250791,0.0005163454,0.0142064495,0.00093630503,0.0009835155,0.88462424,0.00015537231],"about_ca_topic_score_codex":0.0000047307626,"about_ca_topic_score_gemma":5.43782e-7,"teacher_disagreement_score":0.8683028,"about_ca_system_score_codex":0.000009352794,"about_ca_system_score_gemma":0.000080276244,"threshold_uncertainty_score":0.9884641},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09982095728446964,"score_gpt":0.37484484686256236,"score_spread":0.2750238895780927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972308422","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052702386,0.000044038636,0.94479024,0.00095432997,0.00024174032,0.000095492134,0.000024061044,0.000014978274,0.0011327029],"genre_scores_gemma":[0.92324126,0.000076933335,0.07573932,0.00083096634,0.00005741863,6.053308e-7,0.000037773425,0.0000018431441,0.000013913917],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984581,0.00014730632,0.0007800504,0.00010627179,0.00040175434,0.00010652692],"domain_scores_gemma":[0.9978963,0.00014473459,0.001105173,0.0005382537,0.00026596218,0.00004957371],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002006854,0.00007728937,0.000164848,0.00007380303,0.0000850941,0.0003079609,0.00063008844,0.000045431403,0.000009873158],"category_scores_gemma":[0.00014348375,0.000059864822,0.000029689754,0.0001390533,0.000017633913,0.037416097,0.00034225127,0.00016912405,0.000020703337],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007858734,0.000093413626,0.0028540401,0.00024125908,0.00004913811,0.0000012423109,0.007486521,0.000024534731,0.0034558806,0.14402281,0.0021692812,0.8395233],"study_design_scores_gemma":[0.0044575245,0.0010549698,0.20178667,0.00050815364,0.00006511891,0.00015702452,0.026143558,0.65530145,0.0050010835,0.006468399,0.0981733,0.0008827541],"about_ca_topic_score_codex":0.000047734917,"about_ca_topic_score_gemma":0.0000011626522,"teacher_disagreement_score":0.87053883,"about_ca_system_score_codex":0.000045685985,"about_ca_system_score_gemma":0.00014064185,"threshold_uncertainty_score":0.97604704},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.4065919786832916,"score_gpt":0.48860726632065876,"score_spread":0.08201528763736715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3042293458","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60370636,0.00005412143,0.15878484,0.20778693,0.00072290073,0.0013648736,0.019108497,0.000019095629,0.008452374],"genre_scores_gemma":[0.9459391,0.0002311935,0.00501311,0.045731045,0.00014870807,0.0000018046242,0.0029270023,0.0000026720538,0.000005325878],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958092,0.0005892538,0.0020595752,0.00015590881,0.0012628152,0.00012325274],"domain_scores_gemma":[0.9955459,0.0008492147,0.0016768657,0.001531337,0.0002618857,0.00013478962],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","scholarly_communication"],"category_scores_codex":[0.030938858,0.00008545559,0.00025536134,0.00016400368,0.00015029788,0.002509251,0.006948728,0.000029404759,0.00006600915],"category_scores_gemma":[0.01583162,0.000049490827,0.000021293288,0.0005467085,0.000028100914,0.05792405,0.0044274293,0.0002530707,0.00012907505],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047911244,0.00006241616,0.003984691,0.000060682647,0.000032860924,0.0000018162739,0.041017447,0.000025556925,0.000013192233,0.012455174,0.07857095,0.8632961],"study_design_scores_gemma":[0.00058506377,0.000112171285,0.22798856,0.000020351796,0.000014546242,0.000007177306,0.030704413,0.0034275425,0.000004429816,0.00067891204,0.736358,0.00009888567],"about_ca_topic_score_codex":0.00016851442,"about_ca_topic_score_gemma":0.00004972967,"teacher_disagreement_score":0.8631972,"about_ca_system_score_codex":0.000013121229,"about_ca_system_score_gemma":0.000083532796,"threshold_uncertainty_score":0.9985262},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.08316224013716889,"score_gpt":0.36594613887834093,"score_spread":0.28278389874117205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3195742729","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17543635,0.00015211193,0.82205224,0.0013146731,0.0001344012,0.000042000822,0.000044255794,0.0000041656044,0.0008197962],"genre_scores_gemma":[0.94412374,0.00021748546,0.055130392,0.00043859435,0.000020603848,2.7497902e-7,0.00006431247,8.043946e-7,0.0000037951845],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9985076,0.00016626921,0.0009097636,0.000059459027,0.0002872203,0.00006965686],"domain_scores_gemma":[0.9985667,0.00013491395,0.000666096,0.00030448125,0.00029142195,0.000036399022],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0021502457,0.00004646831,0.00015474652,0.00010935574,0.00002651383,0.00012029939,0.0003238683,0.000026349051,0.000007989182],"category_scores_gemma":[0.00028427693,0.000040800907,0.00002232357,0.00024035649,0.000015246151,0.013982853,0.00017999683,0.0001023237,0.0000010022549],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000066638604,0.0002786065,0.007526369,0.00058657845,0.00007520318,0.000019564453,0.020665137,0.00044955153,0.0025337522,0.12476544,0.0015671917,0.84146595],"study_design_scores_gemma":[0.0055949884,0.0005283513,0.54452735,0.0008094475,0.000054790045,0.00026110347,0.030615654,0.33755833,0.02104201,0.0139182005,0.044409104,0.0006806559],"about_ca_topic_score_codex":0.00004969941,"about_ca_topic_score_gemma":0.000022359174,"teacher_disagreement_score":0.8407853,"about_ca_system_score_codex":0.000018717648,"about_ca_system_score_gemma":0.00022997557,"threshold_uncertainty_score":0.9998081},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Data quality; Software deployment; Data science; Data integration; Quality (philosophy); Data mining; Software engineering; Engineering","score_opus":0.32207436291019614,"score_gpt":0.472009332225758,"score_spread":0.14993496931556188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220991771","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4901774,0.006268912,0.20139523,0.23171243,0.0031492065,0.0014610664,0.035106163,0.0001282592,0.03060134],"genre_scores_gemma":[0.9914062,0.0006906645,0.0016379164,0.0046957717,0.00011552061,0.0000012898166,0.0011791636,0.0000047221556,0.00026876878],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964837,0.00093774515,0.0011198876,0.00014090401,0.0012217353,0.000096020165],"domain_scores_gemma":[0.99668324,0.0008370957,0.0012199655,0.0010335309,0.0001637226,0.00006246823],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.037127737,0.00006679204,0.00017706468,0.00012044524,0.0005756235,0.00069321593,0.0022554253,0.000015339672,0.00030520474],"category_scores_gemma":[0.0041942056,0.0000394428,0.000015535223,0.0003377476,0.000054331478,0.011482188,0.0045363735,0.0003438487,0.000009422397],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028241047,0.00008347175,0.018445017,0.000067997025,0.00012178139,0.0000016896282,0.008681733,0.00024604303,0.000010126701,0.04906906,0.12410737,0.7988833],"study_design_scores_gemma":[0.0003201442,0.00006536437,0.009375265,0.0000041421627,0.00001471903,0.000030179543,0.0165838,0.015225545,8.959233e-7,0.0017082655,0.9566145,0.000057206238],"about_ca_topic_score_codex":0.00013346274,"about_ca_topic_score_gemma":0.00007638036,"teacher_disagreement_score":0.83250713,"about_ca_system_score_codex":0.000010654441,"about_ca_system_score_gemma":0.00004877463,"threshold_uncertainty_score":0.99147964},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.4677702605003999,"score_gpt":0.452390842963974,"score_spread":0.015379417536425855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224288101","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18778548,0.000399644,0.76802593,0.015473858,0.0017772497,0.0003985738,0.01313973,0.000039323015,0.012960178],"genre_scores_gemma":[0.9888012,0.000051509,0.0040554036,0.0045264987,0.00010556073,0.0000017240621,0.0022809133,0.0000029275086,0.00017426544],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960566,0.00050744455,0.0012943941,0.00017044407,0.001851863,0.0001192398],"domain_scores_gemma":[0.9962589,0.0007830739,0.0013800985,0.0011892498,0.0003076586,0.00008101842],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.019658245,0.00007485142,0.00023996407,0.000215312,0.00037189628,0.00034868906,0.0021252884,0.000020353888,0.00078010873],"category_scores_gemma":[0.002353606,0.000050908136,0.000020052516,0.00025616545,0.000095413554,0.018240092,0.00278619,0.00026011773,0.000022957563],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014471976,0.00016062718,0.008092613,0.00004342758,0.0001939934,0.000012326508,0.0038374618,0.00038115022,0.000011730611,0.106944,0.4624178,0.41645765],"study_design_scores_gemma":[0.000935105,0.00022127017,0.029229457,0.0000057506963,0.000025353818,0.0002069625,0.041797027,0.0023374595,0.0000019512531,0.0019260907,0.923215,0.000098587145],"about_ca_topic_score_codex":0.00007038731,"about_ca_topic_score_gemma":0.00012733357,"teacher_disagreement_score":0.80101573,"about_ca_system_score_codex":0.000030913496,"about_ca_system_score_gemma":0.0001774111,"threshold_uncertainty_score":0.99549127},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.6503576233917492,"score_gpt":0.6216140905973337,"score_spread":0.02874353279441544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366683629","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008729628,0.00001931649,0.9744458,0.00933944,0.00040827467,0.00030810962,0.0063536763,0.000024469304,0.00037125367],"genre_scores_gemma":[0.20652492,0.0002521815,0.7639661,0.02334325,0.00058906275,0.0000147285955,0.0049721166,0.000020583713,0.0003170806],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99334234,0.0008287317,0.0031192475,0.0003707424,0.002073271,0.00026566337],"domain_scores_gemma":[0.9845453,0.009604562,0.0019924103,0.0027827474,0.00084916566,0.00022579709],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08870495,0.00014144804,0.00049600756,0.00057652395,0.0002598975,0.0009816911,0.0035284092,0.000083666746,0.000084261424],"category_scores_gemma":[0.023597807,0.000099049634,0.00007733389,0.0010411366,0.00004930163,0.015754698,0.0032492282,0.00018010056,0.0001360457],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003490023,0.000024896384,0.00014225209,0.000048983493,0.00003907956,4.4018057e-7,0.0006569611,0.00072278234,0.000010461464,0.024171844,0.28096166,0.69287163],"study_design_scores_gemma":[0.00067996816,0.000084211846,0.024379995,0.00007001692,0.00002932078,0.000006514759,0.010798568,0.028161906,0.000003580057,0.05061464,0.8850033,0.00016793906],"about_ca_topic_score_codex":0.000049232593,"about_ca_topic_score_gemma":0.00009392247,"teacher_disagreement_score":0.6927037,"about_ca_system_score_codex":0.000050390943,"about_ca_system_score_gemma":0.00015883494,"threshold_uncertainty_score":0.9980114},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.08194400033841359,"score_gpt":0.3697688114118219,"score_spread":0.2878248110734083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402806881","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012130277,0.00023338906,0.9966207,0.000775709,0.00021874401,0.0001719187,0.00032391513,0.00032582798,0.00011674934],"genre_scores_gemma":[0.9201317,0.00018204504,0.07889946,0.00021098444,0.00011143066,0.000011761376,0.00043603918,0.000005614565,0.000010987786],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869835,0.000042132186,0.00081735704,0.00015782466,0.00017829669,0.000106010826],"domain_scores_gemma":[0.9985504,0.00013718833,0.00042686006,0.0006579789,0.00016117361,0.00006639721],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002117968,0.000079500125,0.00014528641,0.00013258107,0.0001938142,0.000597074,0.0007927285,0.000065961096,0.0000014382089],"category_scores_gemma":[0.00008071769,0.00006465517,0.000032611835,0.00027205906,0.00001384393,0.013151905,0.0003088981,0.00014054556,0.0000026571686],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003397198,0.00003673903,0.000021048028,0.00061780174,0.00008695166,0.0000010573366,0.00062501535,0.000009430137,0.0007996479,0.029941596,0.076522484,0.89130425],"study_design_scores_gemma":[0.00011914455,0.0000619399,0.000049821127,0.000035163095,0.000015588672,0.00015843163,0.00017915499,0.72506285,0.0005627057,0.00032365962,0.27335697,0.000074561365],"about_ca_topic_score_codex":0.000029945893,"about_ca_topic_score_gemma":0.000001940222,"teacher_disagreement_score":0.91891867,"about_ca_system_score_codex":0.00007920488,"about_ca_system_score_gemma":0.000066132874,"threshold_uncertainty_score":0.9534814},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.089642029191433,"score_gpt":0.38005659620128956,"score_spread":0.2904145670098566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405575840","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000038079903,0.00018157397,0.006553792,0.0007682111,0.9823971,0.00022390296,0.009626053,0.000039738723,0.00017154017],"genre_scores_gemma":[0.000014034663,0.0004900568,0.00087934016,0.00040912945,0.9795383,0.00000257549,0.01860843,0.000020673071,0.00003742298],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967765,0.000019741596,0.0015562883,0.00032523045,0.0011036526,0.00021858249],"domain_scores_gemma":[0.99556875,0.0007436647,0.0014929053,0.0010758361,0.0010802519,0.00003860755],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0051130163,0.00031381662,0.0006024451,0.00036898133,0.00014013851,0.0019463309,0.0014759557,0.00047639533,0.000072702576],"category_scores_gemma":[0.012965993,0.00025513832,0.00005815924,0.00021870492,0.00005731371,0.02365725,0.0014990534,0.00088276644,0.000057798334],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021863742,0.000022445665,0.000018421135,0.003382204,0.00006658932,5.369702e-7,0.000041321277,0.000002953263,5.7298786e-7,0.0010462874,0.9634307,0.031769354],"study_design_scores_gemma":[0.00044955369,0.000025401117,0.00006494261,0.0004520082,0.00016181523,0.0000015228645,0.00007432949,0.0012611515,0.0000010250826,0.00031860857,0.9968774,0.00031225404],"about_ca_topic_score_codex":0.00016523304,"about_ca_topic_score_gemma":0.000026001411,"teacher_disagreement_score":0.033446714,"about_ca_system_score_codex":0.000037183967,"about_ca_system_score_gemma":0.00018181995,"threshold_uncertainty_score":0.9999901},"labels":[],"label_agreement":null}]}